Newer
Older
/*
* linux/mm/slab.c
* Written by Mark Hemment, 1996/97.
* (markhe@nextd.demon.co.uk)
*
* kmem_cache_destroy() + some cleanup - 1999 Andrea Arcangeli
*
* Major cleanup, different bufctl logic, per-cpu arrays
* (c) 2000 Manfred Spraul
*
* Cleanup, make the head arrays unconditional, preparation for NUMA
* (c) 2002 Manfred Spraul
*
* An implementation of the Slab Allocator as described in outline in;
* UNIX Internals: The New Frontiers by Uresh Vahalia
* Pub: Prentice Hall ISBN 0-13-101908-2
* or with a little more detail in;
* The Slab Allocator: An Object-Caching Kernel Memory Allocator
* Jeff Bonwick (Sun Microsystems).
* Presented at: USENIX Summer 1994 Technical Conference
*
* The memory is organized in caches, one cache for each object type.
* (e.g. inode_cache, dentry_cache, buffer_head, vm_area_struct)
* Each cache consists out of many slabs (they are small (usually one
* page long) and always contiguous), and each slab contains multiple
* initialized objects.
*
* This means, that your constructor is used only for newly allocated
* slabs and you must pass objects with the same initializations to
* kmem_cache_free.
*
* Each cache can only support one memory type (GFP_DMA, GFP_HIGHMEM,
* normal). If you need a special memory type, then must create a new
* cache for that memory type.
*
* In order to reduce fragmentation, the slabs are sorted in 3 groups:
* full slabs with 0 free objects
* partial slabs
* empty slabs with no allocated objects
*
* If partial slabs exist, then new allocations come from these slabs,
* otherwise from empty slabs or new slabs are allocated.
*
* kmem_cache_destroy() CAN CRASH if you try to allocate from the cache
* during kmem_cache_destroy(). The caller must prevent concurrent allocs.
*
* Each cache has a short per-cpu head array, most allocs
* and frees go into that array, and if that array overflows, then 1/2
* of the entries in the array are given back into the global cache.
* The head array is strictly LIFO and should improve the cache hit rates.
* On SMP, it additionally reduces the spinlock operations.
*
* The c_cpuarray may not be read with enabled local interrupts -
* it's changed with a smp_call_function().
*
* SMP synchronization:
* constructors and destructors are called without any locking.
* Several members in struct kmem_cache and struct slab never change, they
* are accessed without any locking.
* The per-cpu arrays are never accessed from the wrong cpu, no locking,
* and local interrupts are disabled so slab code is preempt-safe.
* The non-constant members are protected with a per-cache irq spinlock.
*
* Many thanks to Mark Hemment, who wrote another per-cpu slab patch
* in 2000 - many ideas in the current implementation are derived from
* his patch.
*
* Further notes from the original documentation:
*
* 11 April '97. Started multi-threading - markhe
* The global cache-chain is protected by the mutex 'slab_mutex'.
* The sem is only needed when accessing/extending the cache-chain, which
* can never happen inside an interrupt (kmem_cache_create(),
* kmem_cache_shrink() and kmem_cache_reap()).
*
* At present, each engine can be growing a cache. This should be blocked.
*
* 15 March 2005. NUMA slab allocator.
* Shai Fultheim <shai@scalex86.org>.
* Shobhit Dayal <shobhit@calsoftinc.com>
* Alok N Kataria <alokk@calsoftinc.com>
* Christoph Lameter <christoph@lameter.com>
*
* Modified the slab allocator to be node aware on NUMA systems.
* Each node has its own list of partial, free and full slabs.
* All object allocations for a node occur from node specific slab lists.
*/
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/cache.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/cpuset.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/notifier.h>
#include <linux/kallsyms.h>
#include <linux/cpu.h>
#include <linux/sysctl.h>
#include <linux/module.h>
#include <linux/rcupdate.h>
#include <linux/kmemleak.h>
#include <linux/mempolicy.h>
#include <linux/fault-inject.h>
#include <linux/reciprocal_div.h>
#include <linux/debugobjects.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
#include <trace/events/kmem.h>
#include "internal.h"
#include "slab.h"
* DEBUG - 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON.
* 0 for faster, smaller code (especially in the critical paths).
*
* STATS - 1 to collect stats for /proc/slabinfo.
* 0 for faster, smaller code (especially in the critical paths).
*
* FORCED_DEBUG - 1 enables SLAB_RED_ZONE and SLAB_POISON (if possible)
*/
#ifdef CONFIG_DEBUG_SLAB
#define DEBUG 1
#define STATS 1
#define FORCED_DEBUG 1
#else
#define DEBUG 0
#define STATS 0
#define FORCED_DEBUG 0
#endif
/* Shouldn't this be in a header file somewhere? */
#define BYTES_PER_WORD sizeof(void *)
#define REDZONE_ALIGN max(BYTES_PER_WORD, __alignof__(unsigned long long))
#ifndef ARCH_KMALLOC_FLAGS
#define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN
#endif
/*
* true if a page was allocated from pfmemalloc reserves for network-based
* swap
*/
static bool pfmemalloc_active __read_mostly;
/*
* struct array_cache
*
* Purpose:
* - LIFO ordering, to hand out cache-warm objects from _alloc
* - reduce the number of linked list operations
* - reduce spinlock operations
*
* The limit is stored in the per-cpu structure to reduce the data cache
* footprint.
*
*/
struct array_cache {
unsigned int avail;
unsigned int limit;
unsigned int batchcount;
unsigned int touched;
* Must have this definition in here for the proper
* alignment of array_cache. Also simplifies accessing
* the entries.
*
* Entries should not be directly dereferenced as
* entries belonging to slabs marked pfmemalloc will
* have the lower bits set SLAB_OBJ_PFMEMALLOC
#define SLAB_OBJ_PFMEMALLOC 1
static inline bool is_obj_pfmemalloc(void *objp)
{
return (unsigned long)objp & SLAB_OBJ_PFMEMALLOC;
}
Loading
Loading full blame...