99ab7b1944
After commitf5bf18fa22("bootmem/sparsemem: remove limit constraint in alloc_bootmem_section"), usemap allocations may easily be placed outside the optimal section that holds the node descriptor, even if there is space available in that section. This results in unnecessary hotplug dependencies that need to have the node unplugged before the section holding the usemap. The reason is that the bootmem allocator doesn't guarantee a linear search starting from the passed allocation goal but may start out at a much higher address absent an upper limit. Fix this by trying the allocation with the limit at the section end, then retry without if that fails. This keeps the fix fromf5bf18fa22of not panicking if the allocation does not fit in the section, but still makes sure to try to stay within the section at first. Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Cc: <stable@vger.kernel.org> [3.3.x, 3.4.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
177 lines
5.4 KiB
C
177 lines
5.4 KiB
C
/*
|
|
* Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
|
|
*/
|
|
#ifndef _LINUX_BOOTMEM_H
|
|
#define _LINUX_BOOTMEM_H
|
|
|
|
#include <linux/mmzone.h>
|
|
#include <asm/dma.h>
|
|
|
|
/*
|
|
* simple boot-time physical memory area allocator.
|
|
*/
|
|
|
|
extern unsigned long max_low_pfn;
|
|
extern unsigned long min_low_pfn;
|
|
|
|
/*
|
|
* highest page
|
|
*/
|
|
extern unsigned long max_pfn;
|
|
|
|
#ifndef CONFIG_NO_BOOTMEM
|
|
/*
|
|
* node_bootmem_map is a map pointer - the bits represent all physical
|
|
* memory pages (including holes) on the node.
|
|
*/
|
|
typedef struct bootmem_data {
|
|
unsigned long node_min_pfn;
|
|
unsigned long node_low_pfn;
|
|
void *node_bootmem_map;
|
|
unsigned long last_end_off;
|
|
unsigned long hint_idx;
|
|
struct list_head list;
|
|
} bootmem_data_t;
|
|
|
|
extern bootmem_data_t bootmem_node_data[];
|
|
#endif
|
|
|
|
extern unsigned long bootmem_bootmap_pages(unsigned long);
|
|
|
|
extern unsigned long init_bootmem_node(pg_data_t *pgdat,
|
|
unsigned long freepfn,
|
|
unsigned long startpfn,
|
|
unsigned long endpfn);
|
|
extern unsigned long init_bootmem(unsigned long addr, unsigned long memend);
|
|
|
|
extern unsigned long free_low_memory_core_early(int nodeid);
|
|
extern unsigned long free_all_bootmem_node(pg_data_t *pgdat);
|
|
extern unsigned long free_all_bootmem(void);
|
|
|
|
extern void free_bootmem_node(pg_data_t *pgdat,
|
|
unsigned long addr,
|
|
unsigned long size);
|
|
extern void free_bootmem(unsigned long addr, unsigned long size);
|
|
extern void free_bootmem_late(unsigned long addr, unsigned long size);
|
|
|
|
/*
|
|
* Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE,
|
|
* the architecture-specific code should honor this).
|
|
*
|
|
* If flags is 0, then the return value is always 0 (success). If
|
|
* flags contains BOOTMEM_EXCLUSIVE, then -EBUSY is returned if the
|
|
* memory already was reserved.
|
|
*/
|
|
#define BOOTMEM_DEFAULT 0
|
|
#define BOOTMEM_EXCLUSIVE (1<<0)
|
|
|
|
extern int reserve_bootmem(unsigned long addr,
|
|
unsigned long size,
|
|
int flags);
|
|
extern int reserve_bootmem_node(pg_data_t *pgdat,
|
|
unsigned long physaddr,
|
|
unsigned long size,
|
|
int flags);
|
|
|
|
extern void *__alloc_bootmem(unsigned long size,
|
|
unsigned long align,
|
|
unsigned long goal);
|
|
extern void *__alloc_bootmem_nopanic(unsigned long size,
|
|
unsigned long align,
|
|
unsigned long goal);
|
|
extern void *__alloc_bootmem_node(pg_data_t *pgdat,
|
|
unsigned long size,
|
|
unsigned long align,
|
|
unsigned long goal);
|
|
void *__alloc_bootmem_node_high(pg_data_t *pgdat,
|
|
unsigned long size,
|
|
unsigned long align,
|
|
unsigned long goal);
|
|
extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat,
|
|
unsigned long size,
|
|
unsigned long align,
|
|
unsigned long goal);
|
|
void *___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
|
|
unsigned long size,
|
|
unsigned long align,
|
|
unsigned long goal,
|
|
unsigned long limit);
|
|
extern void *__alloc_bootmem_low(unsigned long size,
|
|
unsigned long align,
|
|
unsigned long goal);
|
|
extern void *__alloc_bootmem_low_node(pg_data_t *pgdat,
|
|
unsigned long size,
|
|
unsigned long align,
|
|
unsigned long goal);
|
|
|
|
#ifdef CONFIG_NO_BOOTMEM
|
|
/* We are using top down, so it is safe to use 0 here */
|
|
#define BOOTMEM_LOW_LIMIT 0
|
|
#else
|
|
#define BOOTMEM_LOW_LIMIT __pa(MAX_DMA_ADDRESS)
|
|
#endif
|
|
|
|
#define alloc_bootmem(x) \
|
|
__alloc_bootmem(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT)
|
|
#define alloc_bootmem_align(x, align) \
|
|
__alloc_bootmem(x, align, BOOTMEM_LOW_LIMIT)
|
|
#define alloc_bootmem_nopanic(x) \
|
|
__alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT)
|
|
#define alloc_bootmem_pages(x) \
|
|
__alloc_bootmem(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT)
|
|
#define alloc_bootmem_pages_nopanic(x) \
|
|
__alloc_bootmem_nopanic(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT)
|
|
#define alloc_bootmem_node(pgdat, x) \
|
|
__alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT)
|
|
#define alloc_bootmem_node_nopanic(pgdat, x) \
|
|
__alloc_bootmem_node_nopanic(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT)
|
|
#define alloc_bootmem_pages_node(pgdat, x) \
|
|
__alloc_bootmem_node(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT)
|
|
#define alloc_bootmem_pages_node_nopanic(pgdat, x) \
|
|
__alloc_bootmem_node_nopanic(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT)
|
|
|
|
#define alloc_bootmem_low(x) \
|
|
__alloc_bootmem_low(x, SMP_CACHE_BYTES, 0)
|
|
#define alloc_bootmem_low_pages(x) \
|
|
__alloc_bootmem_low(x, PAGE_SIZE, 0)
|
|
#define alloc_bootmem_low_pages_node(pgdat, x) \
|
|
__alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0)
|
|
|
|
extern int reserve_bootmem_generic(unsigned long addr, unsigned long size,
|
|
int flags);
|
|
|
|
#ifdef CONFIG_HAVE_ARCH_ALLOC_REMAP
|
|
extern void *alloc_remap(int nid, unsigned long size);
|
|
#else
|
|
static inline void *alloc_remap(int nid, unsigned long size)
|
|
{
|
|
return NULL;
|
|
}
|
|
#endif /* CONFIG_HAVE_ARCH_ALLOC_REMAP */
|
|
|
|
extern void *alloc_large_system_hash(const char *tablename,
|
|
unsigned long bucketsize,
|
|
unsigned long numentries,
|
|
int scale,
|
|
int flags,
|
|
unsigned int *_hash_shift,
|
|
unsigned int *_hash_mask,
|
|
unsigned long low_limit,
|
|
unsigned long high_limit);
|
|
|
|
#define HASH_EARLY 0x00000001 /* Allocating during early boot? */
|
|
#define HASH_SMALL 0x00000002 /* sub-page allocation allowed, min
|
|
* shift passed via *_hash_shift */
|
|
|
|
/* Only NUMA needs hash distribution. 64bit NUMA architectures have
|
|
* sufficient vmalloc space.
|
|
*/
|
|
#if defined(CONFIG_NUMA) && defined(CONFIG_64BIT)
|
|
#define HASHDIST_DEFAULT 1
|
|
#else
|
|
#define HASHDIST_DEFAULT 0
|
|
#endif
|
|
extern int hashdist; /* Distribute hashes across NUMA nodes? */
|
|
|
|
|
|
#endif /* _LINUX_BOOTMEM_H */
|