alistair23-linux/include/linux/memblock.h
Michal Hocko 864b9a393d mm: consider memblock reservations for deferred memory initialization sizing
We have seen an early OOM killer invocation on ppc64 systems with
crashkernel=4096M:

	kthreadd invoked oom-killer: gfp_mask=0x16040c0(GFP_KERNEL|__GFP_COMP|__GFP_NOTRACK), nodemask=7, order=0, oom_score_adj=0
	kthreadd cpuset=/ mems_allowed=7
	CPU: 0 PID: 2 Comm: kthreadd Not tainted 4.4.68-1.gd7fe927-default #1
	Call Trace:
	  dump_stack+0xb0/0xf0 (unreliable)
	  dump_header+0xb0/0x258
	  out_of_memory+0x5f0/0x640
	  __alloc_pages_nodemask+0xa8c/0xc80
	  kmem_getpages+0x84/0x1a0
	  fallback_alloc+0x2a4/0x320
	  kmem_cache_alloc_node+0xc0/0x2e0
	  copy_process.isra.25+0x260/0x1b30
	  _do_fork+0x94/0x470
	  kernel_thread+0x48/0x60
	  kthreadd+0x264/0x330
	  ret_from_kernel_thread+0x5c/0xa4

	Mem-Info:
	active_anon:0 inactive_anon:0 isolated_anon:0
	 active_file:0 inactive_file:0 isolated_file:0
	 unevictable:0 dirty:0 writeback:0 unstable:0
	 slab_reclaimable:5 slab_unreclaimable:73
	 mapped:0 shmem:0 pagetables:0 bounce:0
	 free:0 free_pcp:0 free_cma:0
	Node 7 DMA free:0kB min:0kB low:0kB high:0kB active_anon:0kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:52428800kB managed:110016kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB shmem:0kB slab_reclaimable:320kB slab_unreclaimable:4672kB kernel_stack:1152kB pagetables:0kB unstable:0kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? yes
	lowmem_reserve[]: 0 0 0 0
	Node 7 DMA: 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB 0*8192kB 0*16384kB = 0kB
	0 total pagecache pages
	0 pages in swap cache
	Swap cache stats: add 0, delete 0, find 0/0
	Free swap  = 0kB
	Total swap = 0kB
	819200 pages RAM
	0 pages HighMem/MovableOnly
	817481 pages reserved
	0 pages cma reserved
	0 pages hwpoisoned

the reason is that the managed memory is too low (only 110MB) while the
rest of the the 50GB is still waiting for the deferred intialization to
be done.  update_defer_init estimates the initial memoty to initialize
to 2GB at least but it doesn't consider any memory allocated in that
range.  In this particular case we've had

	Reserving 4096MB of memory at 128MB for crashkernel (System RAM: 51200MB)

so the low 2GB is mostly depleted.

Fix this by considering memblock allocations in the initial static
initialization estimation.  Move the max_initialise to
reset_deferred_meminit and implement a simple memblock_reserved_memory
helper which iterates all reserved blocks and sums the size of all that
start below the given address.  The cumulative size is than added on top
of the initial estimation.  This is still not ideal because
reset_deferred_meminit doesn't consider holes and so reservation might
be above the initial estimation whihch we ignore but let's make the
logic simpler until we really need to handle more complicated cases.

Fixes: 3a80a7fa79 ("mm: meminit: initialise a subset of struct pages if CONFIG_DEFERRED_STRUCT_PAGE_INIT is set")
Link: http://lkml.kernel.org/r/20170531104010.GI27783@dhcp22.suse.cz
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Tested-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: <stable@vger.kernel.org>	[4.2+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-06-02 15:07:38 -07:00

447 lines
14 KiB
C

#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
#define INIT_PHYSMEM_REGIONS 4
/* Definition of memblock flags. */
enum {
MEMBLOCK_NONE = 0x0, /* No special request */
MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */
MEMBLOCK_MIRROR = 0x2, /* mirrored region */
MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */
};
struct memblock_region {
phys_addr_t base;
phys_addr_t size;
unsigned long flags;
#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;
char *name;
};
struct memblock {
bool bottom_up; /* is bottom up direction? */
phys_addr_t current_limit;
struct memblock_type memory;
struct memblock_type reserved;
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
struct memblock_type physmem;
#endif
};
extern struct memblock memblock;
extern int memblock_debug;
#ifdef CONFIG_MOVABLE_NODE
/* If movable_node boot option specified */
extern bool movable_node_enabled;
#endif /* CONFIG_MOVABLE_NODE */
#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
#define __init_memblock __meminit
#define __initdata_memblock __meminitdata
#else
#define __init_memblock
#define __initdata_memblock
#endif
#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 size, phys_addr_t align,
phys_addr_t start, phys_addr_t end,
int nid, ulong flags);
phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
phys_addr_t size, phys_addr_t align);
phys_addr_t get_allocated_memblock_reserved_regions_info(phys_addr_t *addr);
phys_addr_t get_allocated_memblock_memory_regions_info(phys_addr_t *addr);
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);
bool memblock_overlaps_region(struct memblock_type *type,
phys_addr_t base, phys_addr_t size);
int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size);
int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
int memblock_clear_nomap(phys_addr_t base, phys_addr_t size);
ulong choose_memblock_flags(void);
/* Low level functions */
int memblock_add_range(struct memblock_type *type,
phys_addr_t base, phys_addr_t size,
int nid, unsigned long flags);
void __next_mem_range(u64 *idx, int nid, ulong flags,
struct memblock_type *type_a,
struct memblock_type *type_b, phys_addr_t *out_start,
phys_addr_t *out_end, int *out_nid);
void __next_mem_range_rev(u64 *idx, int nid, ulong flags,
struct memblock_type *type_a,
struct memblock_type *type_b, phys_addr_t *out_start,
phys_addr_t *out_end, int *out_nid);
void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start,
phys_addr_t *out_end);
/**
* for_each_mem_range - iterate through memblock areas from type_a and not
* included in type_b. Or just type_a if type_b is NULL.
* @i: u64 used as loop variable
* @type_a: ptr to memblock_type to iterate
* @type_b: ptr to memblock_type which excludes from the iteration
* @nid: node selector, %NUMA_NO_NODE for all nodes
* @flags: pick from blocks based on memory attributes
* @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
*/
#define for_each_mem_range(i, type_a, type_b, nid, flags, \
p_start, p_end, p_nid) \
for (i = 0, __next_mem_range(&i, nid, flags, type_a, type_b, \
p_start, p_end, p_nid); \
i != (u64)ULLONG_MAX; \
__next_mem_range(&i, nid, flags, type_a, type_b, \
p_start, p_end, p_nid))
/**
* for_each_mem_range_rev - reverse iterate through memblock areas from
* type_a and not included in type_b. Or just type_a if type_b is NULL.
* @i: u64 used as loop variable
* @type_a: ptr to memblock_type to iterate
* @type_b: ptr to memblock_type which excludes from the iteration
* @nid: node selector, %NUMA_NO_NODE for all nodes
* @flags: pick from blocks based on memory attributes
* @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
*/
#define for_each_mem_range_rev(i, type_a, type_b, nid, flags, \
p_start, p_end, p_nid) \
for (i = (u64)ULLONG_MAX, \
__next_mem_range_rev(&i, nid, flags, type_a, type_b,\
p_start, p_end, p_nid); \
i != (u64)ULLONG_MAX; \
__next_mem_range_rev(&i, nid, flags, type_a, type_b, \
p_start, p_end, p_nid))
/**
* for_each_reserved_mem_region - iterate over all reserved memblock areas
* @i: u64 used as loop variable
* @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
*
* Walks over reserved areas of memblock. Available as soon as memblock
* is initialized.
*/
#define for_each_reserved_mem_region(i, p_start, p_end) \
for (i = 0UL, __next_reserved_mem_region(&i, p_start, p_end); \
i != (u64)ULLONG_MAX; \
__next_reserved_mem_region(&i, p_start, p_end))
#ifdef CONFIG_MOVABLE_NODE
static inline bool memblock_is_hotpluggable(struct memblock_region *m)
{
return m->flags & MEMBLOCK_HOTPLUG;
}
static inline bool __init_memblock movable_node_is_enabled(void)
{
return movable_node_enabled;
}
#else
static inline bool memblock_is_hotpluggable(struct memblock_region *m)
{
return false;
}
static inline bool movable_node_is_enabled(void)
{
return false;
}
#endif
static inline bool memblock_is_mirror(struct memblock_region *m)
{
return m->flags & MEMBLOCK_MIRROR;
}
static inline bool memblock_is_nomap(struct memblock_region *m)
{
return m->flags & MEMBLOCK_NOMAP;
}
#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);
unsigned long memblock_next_valid_pfn(unsigned long pfn, unsigned long max_pfn);
/**
* 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 */
/**
* for_each_free_mem_range - iterate through free memblock areas
* @i: u64 used as loop variable
* @nid: node selector, %NUMA_NO_NODE for all nodes
* @flags: pick from blocks based on memory attributes
* @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, flags, p_start, p_end, p_nid) \
for_each_mem_range(i, &memblock.memory, &memblock.reserved, \
nid, flags, p_start, p_end, p_nid)
/**
* for_each_free_mem_range_reverse - rev-iterate through free memblock areas
* @i: u64 used as loop variable
* @nid: node selector, %NUMA_NO_NODE for all nodes
* @flags: pick from blocks based on memory attributes
* @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, flags, p_start, p_end, \
p_nid) \
for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \
nid, flags, p_start, p_end, p_nid)
static inline void memblock_set_region_flags(struct memblock_region *r,
unsigned long flags)
{
r->flags |= flags;
}
static inline void memblock_clear_region_flags(struct memblock_region *r,
unsigned long flags)
{
r->flags &= ~flags;
}
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
int memblock_set_node(phys_addr_t base, phys_addr_t size,
struct memblock_type *type, 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);
#ifdef CONFIG_MOVABLE_NODE
/*
* Set the allocation direction to bottom-up or top-down.
*/
static inline void __init 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 __init 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 __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
phys_addr_t start, phys_addr_t end,
ulong flags);
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_reserved_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);
void memblock_cap_memory_range(phys_addr_t base, phys_addr_t size);
void memblock_mem_limit_remove_map(phys_addr_t limit);
bool memblock_is_memory(phys_addr_t addr);
int memblock_is_map_memory(phys_addr_t addr);
int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
bool memblock_is_reserved(phys_addr_t addr);
bool 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);
phys_addr_t memblock_get_current_limit(void);
/*
* 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++)
#define for_each_memblock_type(memblock_type, rgn) \
for (idx = 0, rgn = &memblock_type->regions[0]; \
idx < memblock_type->cnt; \
idx++, rgn = &memblock_type->regions[idx])
#ifdef CONFIG_MEMTEST
extern void early_memtest(phys_addr_t start, phys_addr_t end);
#else
static inline void early_memtest(phys_addr_t start, phys_addr_t end)
{
}
#endif
extern unsigned long memblock_reserved_memory_within(phys_addr_t start_addr,
phys_addr_t end_addr);
#else
static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align)
{
return 0;
}
static inline unsigned long memblock_reserved_memory_within(phys_addr_t start_addr,
phys_addr_t end_addr)
{
return 0;
}
#endif /* CONFIG_HAVE_MEMBLOCK */
#endif /* __KERNEL__ */
#endif /* _LINUX_MEMBLOCK_H */