kernel-ark/include/linux/slub_def.h
Christoph Lameter b3fba8da65 SLUB: Move page->offset to kmem_cache_cpu->offset
We need the offset from the page struct during slab_alloc and slab_free. In
both cases we also reference the cacheline of the kmem_cache_cpu structure.
We can therefore move the offset field into the kmem_cache_cpu structure
freeing up 16 bits in the page struct.

Moving the offset allows an allocation from slab_alloc() without touching the
page struct in the hot path.

The only thing left in slab_free() that touches the page struct cacheline for
per cpu freeing is the checking of SlabDebug(page). The next patch deals with
that.

Use the available 16 bits to broaden page->inuse. More than 64k objects per
slab become possible and we can get rid of the checks for that limitation.

No need anymore to shrink the order of slabs if we boot with 2M sized slabs
(slub_min_order=9).

No need anymore to switch off the offset calculation for very large slabs
since the field in the kmem_cache_cpu structure is 32 bits and so the offset
field can now handle slab sizes of up to 8GB.

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 09:43:01 -07:00

200 lines
4.8 KiB
C

#ifndef _LINUX_SLUB_DEF_H
#define _LINUX_SLUB_DEF_H
/*
* SLUB : A Slab allocator without object queues.
*
* (C) 2007 SGI, Christoph Lameter <clameter@sgi.com>
*/
#include <linux/types.h>
#include <linux/gfp.h>
#include <linux/workqueue.h>
#include <linux/kobject.h>
struct kmem_cache_cpu {
void **freelist;
struct page *page;
int node;
unsigned int offset;
/* Lots of wasted space */
} ____cacheline_aligned_in_smp;
struct kmem_cache_node {
spinlock_t list_lock; /* Protect partial list and nr_partial */
unsigned long nr_partial;
atomic_long_t nr_slabs;
struct list_head partial;
#ifdef CONFIG_SLUB_DEBUG
struct list_head full;
#endif
};
/*
* Slab cache management.
*/
struct kmem_cache {
/* Used for retriving partial slabs etc */
unsigned long flags;
int size; /* The size of an object including meta data */
int objsize; /* The size of an object without meta data */
int offset; /* Free pointer offset. */
int order;
/*
* Avoid an extra cache line for UP, SMP and for the node local to
* struct kmem_cache.
*/
struct kmem_cache_node local_node;
/* Allocation and freeing of slabs */
int objects; /* Number of objects in slab */
int refcount; /* Refcount for slab cache destroy */
void (*ctor)(void *, struct kmem_cache *, unsigned long);
int inuse; /* Offset to metadata */
int align; /* Alignment */
const char *name; /* Name (only for display!) */
struct list_head list; /* List of slab caches */
#ifdef CONFIG_SLUB_DEBUG
struct kobject kobj; /* For sysfs */
#endif
#ifdef CONFIG_NUMA
int defrag_ratio;
struct kmem_cache_node *node[MAX_NUMNODES];
#endif
struct kmem_cache_cpu cpu_slab[NR_CPUS];
};
/*
* Kmalloc subsystem.
*/
#if defined(ARCH_KMALLOC_MINALIGN) && ARCH_KMALLOC_MINALIGN > 8
#define KMALLOC_MIN_SIZE ARCH_KMALLOC_MINALIGN
#else
#define KMALLOC_MIN_SIZE 8
#endif
#define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE)
/*
* We keep the general caches in an array of slab caches that are used for
* 2^x bytes of allocations.
*/
extern struct kmem_cache kmalloc_caches[PAGE_SHIFT];
/*
* Sorry that the following has to be that ugly but some versions of GCC
* have trouble with constant propagation and loops.
*/
static __always_inline int kmalloc_index(size_t size)
{
if (!size)
return 0;
if (size <= KMALLOC_MIN_SIZE)
return KMALLOC_SHIFT_LOW;
if (size > 64 && size <= 96)
return 1;
if (size > 128 && size <= 192)
return 2;
if (size <= 8) return 3;
if (size <= 16) return 4;
if (size <= 32) return 5;
if (size <= 64) return 6;
if (size <= 128) return 7;
if (size <= 256) return 8;
if (size <= 512) return 9;
if (size <= 1024) return 10;
if (size <= 2 * 1024) return 11;
/*
* The following is only needed to support architectures with a larger page
* size than 4k.
*/
if (size <= 4 * 1024) return 12;
if (size <= 8 * 1024) return 13;
if (size <= 16 * 1024) return 14;
if (size <= 32 * 1024) return 15;
if (size <= 64 * 1024) return 16;
if (size <= 128 * 1024) return 17;
if (size <= 256 * 1024) return 18;
if (size <= 512 * 1024) return 19;
if (size <= 1024 * 1024) return 20;
if (size <= 2 * 1024 * 1024) return 21;
return -1;
/*
* What we really wanted to do and cannot do because of compiler issues is:
* int i;
* for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++)
* if (size <= (1 << i))
* return i;
*/
}
/*
* Find the slab cache for a given combination of allocation flags and size.
*
* This ought to end up with a global pointer to the right cache
* in kmalloc_caches.
*/
static __always_inline struct kmem_cache *kmalloc_slab(size_t size)
{
int index = kmalloc_index(size);
if (index == 0)
return NULL;
return &kmalloc_caches[index];
}
#ifdef CONFIG_ZONE_DMA
#define SLUB_DMA __GFP_DMA
#else
/* Disable DMA functionality */
#define SLUB_DMA (__force gfp_t)0
#endif
void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
void *__kmalloc(size_t size, gfp_t flags);
static __always_inline void *kmalloc(size_t size, gfp_t flags)
{
if (__builtin_constant_p(size)) {
if (size > PAGE_SIZE / 2)
return (void *)__get_free_pages(flags | __GFP_COMP,
get_order(size));
if (!(flags & SLUB_DMA)) {
struct kmem_cache *s = kmalloc_slab(size);
if (!s)
return ZERO_SIZE_PTR;
return kmem_cache_alloc(s, flags);
}
}
return __kmalloc(size, flags);
}
#ifdef CONFIG_NUMA
void *__kmalloc_node(size_t size, gfp_t flags, int node);
void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
{
if (__builtin_constant_p(size) &&
size <= PAGE_SIZE / 2 && !(flags & SLUB_DMA)) {
struct kmem_cache *s = kmalloc_slab(size);
if (!s)
return ZERO_SIZE_PTR;
return kmem_cache_alloc_node(s, flags, node);
}
return __kmalloc_node(size, flags, node);
}
#endif
#endif /* _LINUX_SLUB_DEF_H */