linux-stable/include/linux/memblock.h
Daniel Vacek f59f1caf72 Revert "mm: page_alloc: skip over regions of invalid pfns where possible"
This reverts commit b92df1de5d ("mm: page_alloc: skip over regions of
invalid pfns where possible").  The commit is meant to be a boot init
speed up skipping the loop in memmap_init_zone() for invalid pfns.

But given some specific memory mapping on x86_64 (or more generally
theoretically anywhere but on arm with CONFIG_HAVE_ARCH_PFN_VALID) the
implementation also skips valid pfns which is plain wrong and causes
'kernel BUG at mm/page_alloc.c:1389!'

  crash> log | grep -e BUG -e RIP -e Call.Trace -e move_freepages_block -e rmqueue -e freelist -A1
  kernel BUG at mm/page_alloc.c:1389!
  invalid opcode: 0000 [#1] SMP
  --
  RIP: 0010: move_freepages+0x15e/0x160
  --
  Call Trace:
    move_freepages_block+0x73/0x80
    __rmqueue+0x263/0x460
    get_page_from_freelist+0x7e1/0x9e0
    __alloc_pages_nodemask+0x176/0x420
  --

  crash> page_init_bug -v | grep RAM
  <struct resource 0xffff88067fffd2f8>          1000 -        9bfff       System RAM (620.00 KiB)
  <struct resource 0xffff88067fffd3a0>        100000 -     430bffff       System RAM (  1.05 GiB = 1071.75 MiB = 1097472.00 KiB)
  <struct resource 0xffff88067fffd410>      4b0c8000 -     4bf9cfff       System RAM ( 14.83 MiB = 15188.00 KiB)
  <struct resource 0xffff88067fffd480>      4bfac000 -     646b1fff       System RAM (391.02 MiB = 400408.00 KiB)
  <struct resource 0xffff88067fffd560>      7b788000 -     7b7fffff       System RAM (480.00 KiB)
  <struct resource 0xffff88067fffd640>     100000000 -    67fffffff       System RAM ( 22.00 GiB)

  crash> page_init_bug | head -6
  <struct resource 0xffff88067fffd560>      7b788000 -     7b7fffff       System RAM (480.00 KiB)
  <struct page 0xffffea0001ede200>   1fffff00000000  0 <struct pglist_data 0xffff88047ffd9000> 1 <struct zone 0xffff88047ffd9800> DMA32          4096    1048575
  <struct page 0xffffea0001ede200>       505736 505344 <struct page 0xffffea0001ed8000> 505855 <struct page 0xffffea0001edffc0>
  <struct page 0xffffea0001ed8000>                0  0 <struct pglist_data 0xffff88047ffd9000> 0 <struct zone 0xffff88047ffd9000> DMA               1       4095
  <struct page 0xffffea0001edffc0>   1fffff00000400  0 <struct pglist_data 0xffff88047ffd9000> 1 <struct zone 0xffff88047ffd9800> DMA32          4096    1048575
  BUG, zones differ!

  crash> kmem -p 77fff000 78000000 7b5ff000 7b600000 7b787000 7b788000
        PAGE        PHYSICAL      MAPPING       INDEX CNT FLAGS
  ffffea0001e00000  78000000                0        0  0 0
  ffffea0001ed7fc0  7b5ff000                0        0  0 0
  ffffea0001ed8000  7b600000                0        0  0 0       <<<<
  ffffea0001ede1c0  7b787000                0        0  0 0
  ffffea0001ede200  7b788000                0        0  1 1fffff00000000

Link: http://lkml.kernel.org/r/20180316143855.29838-1-neelx@redhat.com
Fixes: b92df1de5d ("mm: page_alloc: skip over regions of invalid pfns where possible")
Signed-off-by: Daniel Vacek <neelx@redhat.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Pavel Tatashin <pasha.tatashin@oracle.com>
Cc: Paul Burton <paul.burton@imgtec.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-03-22 17:07:01 -07:00

438 lines
15 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_ARCH_DISCARD_MEMBLOCK
#define __init_memblock __meminit
#define __initdata_memblock __meminitdata
void memblock_discard(void);
#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);
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);
void __memblock_free_early(phys_addr_t base, phys_addr_t size);
void __memblock_free_late(phys_addr_t base, phys_addr_t size);
/**
* 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))
static inline bool memblock_is_hotpluggable(struct memblock_region *m)
{
return m->flags & MEMBLOCK_HOTPLUG;
}
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);
/**
* 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)
/**
* for_each_resv_unavail_range - iterate through reserved and unavailable memory
* @i: u64 used as loop variable
* @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
*
* Walks over unavailable but reserved (reserved && !memory) areas of memblock.
* Available as soon as memblock is initialized.
* Note: because this memory does not belong to any physical node, flags and
* nid arguments do not make sense and thus not exported as arguments.
*/
#define for_each_resv_unavail_range(i, p_start, p_end) \
for_each_mem_range(i, &memblock.reserved, &memblock.memory, \
NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL)
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);
/*
* 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;
}
/* 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);
bool memblock_is_map_memory(phys_addr_t addr);
bool 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(i, memblock_type, rgn) \
for (i = 0, rgn = &memblock_type->regions[0]; \
i < memblock_type->cnt; \
i++, rgn = &memblock_type->regions[i])
#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 */