mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 09:25:19 +07:00
bf0dea23a9
Because of chicken and egg problem, initialization of SLAB is really complicated. We need to allocate cpu cache through SLAB to make the kmem_cache work, but before initialization of kmem_cache, allocation through SLAB is impossible. On the other hand, SLUB does initialization in a more simple way. It uses percpu allocator to allocate cpu cache so there is no chicken and egg problem. So, this patch try to use percpu allocator in SLAB. This simplifies the initialization step in SLAB so that we could maintain SLAB code more easily. In my testing there is no performance difference. This implementation relies on percpu allocator. Because percpu allocator uses vmalloc address space, vmalloc address space could be exhausted by this change on many cpu system with *32 bit* kernel. This implementation can cover 1024 cpus in worst case by following calculation. Worst: 1024 cpus * 4 bytes for pointer * 300 kmem_caches * 120 objects per cpu_cache = 140 MB Normal: 1024 cpus * 4 bytes for pointer * 150 kmem_caches(slab merge) * 80 objects per cpu_cache = 46 MB Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Jeremiah Mahler <jmmahler@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
80 lines
1.9 KiB
C
80 lines
1.9 KiB
C
#ifndef _LINUX_SLAB_DEF_H
|
|
#define _LINUX_SLAB_DEF_H
|
|
|
|
#include <linux/reciprocal_div.h>
|
|
|
|
/*
|
|
* Definitions unique to the original Linux SLAB allocator.
|
|
*/
|
|
|
|
struct kmem_cache {
|
|
struct array_cache __percpu *cpu_cache;
|
|
|
|
/* 1) Cache tunables. Protected by slab_mutex */
|
|
unsigned int batchcount;
|
|
unsigned int limit;
|
|
unsigned int shared;
|
|
|
|
unsigned int size;
|
|
struct reciprocal_value reciprocal_buffer_size;
|
|
/* 2) touched by every alloc & free from the backend */
|
|
|
|
unsigned int flags; /* constant flags */
|
|
unsigned int num; /* # of objs per slab */
|
|
|
|
/* 3) cache_grow/shrink */
|
|
/* order of pgs per slab (2^n) */
|
|
unsigned int gfporder;
|
|
|
|
/* force GFP flags, e.g. GFP_DMA */
|
|
gfp_t allocflags;
|
|
|
|
size_t colour; /* cache colouring range */
|
|
unsigned int colour_off; /* colour offset */
|
|
struct kmem_cache *freelist_cache;
|
|
unsigned int freelist_size;
|
|
|
|
/* constructor func */
|
|
void (*ctor)(void *obj);
|
|
|
|
/* 4) cache creation/removal */
|
|
const char *name;
|
|
struct list_head list;
|
|
int refcount;
|
|
int object_size;
|
|
int align;
|
|
|
|
/* 5) statistics */
|
|
#ifdef CONFIG_DEBUG_SLAB
|
|
unsigned long num_active;
|
|
unsigned long num_allocations;
|
|
unsigned long high_mark;
|
|
unsigned long grown;
|
|
unsigned long reaped;
|
|
unsigned long errors;
|
|
unsigned long max_freeable;
|
|
unsigned long node_allocs;
|
|
unsigned long node_frees;
|
|
unsigned long node_overflow;
|
|
atomic_t allochit;
|
|
atomic_t allocmiss;
|
|
atomic_t freehit;
|
|
atomic_t freemiss;
|
|
|
|
/*
|
|
* If debugging is enabled, then the allocator can add additional
|
|
* fields and/or padding to every object. size contains the total
|
|
* object size including these internal fields, the following two
|
|
* variables contain the offset to the user object and its size.
|
|
*/
|
|
int obj_offset;
|
|
#endif /* CONFIG_DEBUG_SLAB */
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
struct memcg_cache_params *memcg_params;
|
|
#endif
|
|
|
|
struct kmem_cache_node *node[MAX_NUMNODES];
|
|
};
|
|
|
|
#endif /* _LINUX_SLAB_DEF_H */
|