The SLAB functionality has been supplanted by SLUB. Benefits of SLUB

- More compact data store. Less cache footprint
- Reporting function and tools
- Higher speed
- Eliminate SLAB bitrot

Signed-off-by: Christoph Lameter <clameter@sgi.com>

---
 fs/proc/proc_misc.c  |   47 
 include/linux/slab.h |   18 
 init/Kconfig         |   26 
 lib/Kconfig.debug    |   17 
 mm/Makefile          |    4 
 mm/slab.c            | 4448 ---------------------------------------------------
 6 files changed, 2 insertions(+), 4558 deletions(-)

Index: linux-2.6.22-rc6-mm1/include/linux/slab.h
===================================================================
--- linux-2.6.22-rc6-mm1.orig/include/linux/slab.h	2007-07-05 23:28:12.000000000 -0700
+++ linux-2.6.22-rc6-mm1/include/linux/slab.h	2007-07-05 23:36:12.000000000 -0700
@@ -16,7 +16,6 @@
 
 /*
  * Flags to pass to kmem_cache_create().
- * The ones marked DEBUG are only valid if CONFIG_SLAB_DEBUG is set.
  */
 #define SLAB_DEBUG_FREE		0x00000100UL	/* DEBUG: Perform (expensive) checks on free */
 #define SLAB_RED_ZONE		0x00000400UL	/* DEBUG: Red zone objs in a cache */
@@ -154,11 +153,7 @@ size_t ksize(const void *);
  * See each allocator definition file for additional comments and
  * implementation notes.
  */
-#ifdef CONFIG_SLUB
 #include <linux/slub_def.h>
-#else
-#include <linux/slab_def.h>
-#endif
 
 /**
  * kcalloc - allocate memory for an array. The memory is set to zero.
@@ -256,14 +251,9 @@ static inline void *kmem_cache_alloc_nod
  * allocator where we care about the real place the memory allocation
  * request comes from.
  */
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB)
 extern void *__kmalloc_track_caller(size_t, gfp_t, void*);
 #define kmalloc_track_caller(size, flags) \
 	__kmalloc_track_caller(size, flags, __builtin_return_address(0))
-#else
-#define kmalloc_track_caller(size, flags) \
-	__kmalloc(size, flags)
-#endif /* DEBUG_SLAB */
 
 #ifdef CONFIG_NUMA
 /*
@@ -274,22 +264,16 @@ extern void *__kmalloc_track_caller(size
  * standard allocator where we care about the real place the memory
  * allocation request comes from.
  */
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB)
 extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, void *);
 #define kmalloc_node_track_caller(size, flags, node) \
 	__kmalloc_node_track_caller(size, flags, node, \
 			__builtin_return_address(0))
-#else
-#define kmalloc_node_track_caller(size, flags, node) \
-	__kmalloc_node(size, flags, node)
-#endif
-
 #else /* CONFIG_NUMA */
 
 #define kmalloc_node_track_caller(size, flags, node) \
 	kmalloc_track_caller(size, flags)
 
-#endif /* DEBUG_SLAB */
+#endif /* CONFIG_NUMA */
 
 /*
  * Shortcuts
Index: linux-2.6.22-rc6-mm1/init/Kconfig
===================================================================
--- linux-2.6.22-rc6-mm1.orig/init/Kconfig	2007-07-05 23:30:11.000000000 -0700
+++ linux-2.6.22-rc6-mm1/init/Kconfig	2007-07-06 09:14:48.000000000 -0700
@@ -594,38 +594,12 @@ config VM_EVENT_COUNTERS
 config SLUB_DEBUG
 	default y
 	bool "Enable SLUB debugging support" if EMBEDDED
-	depends on SLUB
 	help
 	  SLUB has extensive debug support features. Disabling these can
 	  result in significant savings in code size. This also disables
 	  SLUB sysfs support. /sys/slab will not exist and there will be
 	  no support for cache validation etc.
 
-choice
-	prompt "Choose SLAB allocator"
-	default SLUB
-	help
-	   This option allows to select a slab allocator.
-
-config SLAB
-	bool "SLAB"
-	help
-	  The regular slab allocator that is established and known to work
-	  well in all environments. It organizes cache hot objects in
-	  per cpu and per node queues. SLAB is the default choice for
-	  a slab allocator.
-
-config SLUB
-	bool "SLUB (Unqueued Allocator)"
-	help
-	   SLUB is a slab allocator that minimizes cache line usage
-	   instead of managing queues of cached objects (SLAB approach).
-	   Per cpu caching is realized using slabs of objects instead
-	   of queues of objects. SLUB can use memory efficiently
-	   and has enhanced diagnostics.
-
-endchoice
-
 config PROC_SMAPS
 	default y
 	bool "Enable /proc/pid/smaps support" if EMBEDDED && PROC_FS && MMU
Index: linux-2.6.22-rc6-mm1/mm/Makefile
===================================================================
--- linux-2.6.22-rc6-mm1.orig/mm/Makefile	2007-07-05 23:29:47.000000000 -0700
+++ linux-2.6.22-rc6-mm1/mm/Makefile	2007-07-05 23:30:07.000000000 -0700
@@ -11,7 +11,7 @@ obj-y			:= bootmem.o filemap.o mempool.o
 			   page_alloc.o page-writeback.o pdflush.o \
 			   readahead.o swap.o truncate.o vmscan.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
-			   $(mmu-y)
+			   slub.o $(mmu-y)
 
 obj-$(CONFIG_BOUNCE)	+= bounce.o
 obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o thrash.o
@@ -22,8 +22,6 @@ obj-$(CONFIG_SPARSEMEM)	+= sparse.o
 obj-$(CONFIG_SHMEM) += shmem.o
 obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o
 obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o
-obj-$(CONFIG_SLAB) += slab.o
-obj-$(CONFIG_SLUB) += slub.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
Index: linux-2.6.22-rc6-mm1/mm/slab.c
===================================================================
--- linux-2.6.22-rc6-mm1.orig/mm/slab.c	2007-07-05 23:30:53.000000000 -0700
+++ /dev/null	1970-01-01 00:00:00.000000000 +0000
@@ -1,4448 +0,0 @@
-/*
- * 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 intializations 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 'cache_chain_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/poison.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/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/string.h>
-#include	<linux/uaccess.h>
-#include	<linux/nodemask.h>
-#include	<linux/mempolicy.h>
-#include	<linux/mutex.h>
-#include	<linux/fault-inject.h>
-#include	<linux/rtmutex.h>
-#include	<linux/reciprocal_div.h>
-
-#include	<asm/cacheflush.h>
-#include	<asm/tlbflush.h>
-#include	<asm/page.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 *)
-
-#ifndef cache_line_size
-#define cache_line_size()	L1_CACHE_BYTES
-#endif
-
-#ifndef ARCH_KMALLOC_MINALIGN
-/*
- * Enforce a minimum alignment for the kmalloc caches.
- * Usually, the kmalloc caches are cache_line_size() aligned, except when
- * DEBUG and FORCED_DEBUG are enabled, then they are BYTES_PER_WORD aligned.
- * Some archs want to perform DMA into kmalloc caches and need a guaranteed
- * alignment larger than the alignment of a 64-bit integer.
- * ARCH_KMALLOC_MINALIGN allows that.
- * Note that increasing this value may disable some debug features.
- */
-#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
-#endif
-
-#ifndef ARCH_SLAB_MINALIGN
-/*
- * Enforce a minimum alignment for all caches.
- * Intended for archs that get misalignment faults even for BYTES_PER_WORD
- * aligned buffers. Includes ARCH_KMALLOC_MINALIGN.
- * If possible: Do not enable this flag for CONFIG_DEBUG_SLAB, it disables
- * some debug features.
- */
-#define ARCH_SLAB_MINALIGN 0
-#endif
-
-#ifndef ARCH_KMALLOC_FLAGS
-#define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN
-#endif
-
-/* Legal flag mask for kmem_cache_create(). */
-#if DEBUG
-# define CREATE_MASK	(SLAB_RED_ZONE | \
-			 SLAB_POISON | SLAB_HWCACHE_ALIGN | \
-			 SLAB_CACHE_DMA | \
-			 SLAB_STORE_USER | \
-			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
-			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD)
-#else
-# define CREATE_MASK	(SLAB_HWCACHE_ALIGN | \
-			 SLAB_CACHE_DMA | \
-			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
-			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD)
-#endif
-
-/*
- * kmem_bufctl_t:
- *
- * Bufctl's are used for linking objs within a slab
- * linked offsets.
- *
- * This implementation relies on "struct page" for locating the cache &
- * slab an object belongs to.
- * This allows the bufctl structure to be small (one int), but limits
- * the number of objects a slab (not a cache) can contain when off-slab
- * bufctls are used. The limit is the size of the largest general cache
- * that does not use off-slab slabs.
- * For 32bit archs with 4 kB pages, is this 56.
- * This is not serious, as it is only for large objects, when it is unwise
- * to have too many per slab.
- * Note: This limit can be raised by introducing a general cache whose size
- * is less than 512 (PAGE_SIZE<<3), but greater than 256.
- */
-
-typedef unsigned int kmem_bufctl_t;
-#define BUFCTL_END	(((kmem_bufctl_t)(~0U))-0)
-#define BUFCTL_FREE	(((kmem_bufctl_t)(~0U))-1)
-#define	BUFCTL_ACTIVE	(((kmem_bufctl_t)(~0U))-2)
-#define	SLAB_LIMIT	(((kmem_bufctl_t)(~0U))-3)
-
-/*
- * struct slab
- *
- * Manages the objs in a slab. Placed either at the beginning of mem allocated
- * for a slab, or allocated from an general cache.
- * Slabs are chained into three list: fully used, partial, fully free slabs.
- */
-struct slab {
-	struct list_head list;
-	unsigned long colouroff;
-	void *s_mem;		/* including colour offset */
-	unsigned int inuse;	/* num of objs active in slab */
-	kmem_bufctl_t free;
-	unsigned short nodeid;
-};
-
-/*
- * struct slab_rcu
- *
- * slab_destroy on a SLAB_DESTROY_BY_RCU cache uses this structure to
- * arrange for kmem_freepages to be called via RCU.  This is useful if
- * we need to approach a kernel structure obliquely, from its address
- * obtained without the usual locking.  We can lock the structure to
- * stabilize it and check it's still at the given address, only if we
- * can be sure that the memory has not been meanwhile reused for some
- * other kind of object (which our subsystem's lock might corrupt).
- *
- * rcu_read_lock before reading the address, then rcu_read_unlock after
- * taking the spinlock within the structure expected at that address.
- *
- * We assume struct slab_rcu can overlay struct slab when destroying.
- */
-struct slab_rcu {
-	struct rcu_head head;
-	struct kmem_cache *cachep;
-	void *addr;
-};
-
-/*
- * 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;
-	spinlock_t lock;
-	void *entry[0];	/*
-			 * Must have this definition in here for the proper
-			 * alignment of array_cache. Also simplifies accessing
-			 * the entries.
-			 * [0] is for gcc 2.95. It should really be [].
-			 */
-};
-
-/*
- * bootstrap: The caches do not work without cpuarrays anymore, but the
- * cpuarrays are allocated from the generic caches...
- */
-#define BOOT_CPUCACHE_ENTRIES	1
-struct arraycache_init {
-	struct array_cache cache;
-	void *entries[BOOT_CPUCACHE_ENTRIES];
-};
-
-/*
- * The slab lists for all objects.
- */
-struct kmem_list3 {
-	struct list_head slabs_partial;	/* partial list first, better asm code */
-	struct list_head slabs_full;
-	struct list_head slabs_free;
-	unsigned long free_objects;
-	unsigned int free_limit;
-	unsigned int colour_next;	/* Per-node cache coloring */
-	spinlock_t list_lock;
-	struct array_cache *shared;	/* shared per node */
-	struct array_cache **alien;	/* on other nodes */
-	unsigned long next_reap;	/* updated without locking */
-	int free_touched;		/* updated without locking */
-};
-
-/*
- * Need this for bootstrapping a per node allocator.
- */
-#define NUM_INIT_LISTS (2 * MAX_NUMNODES + 1)
-struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS];
-#define	CACHE_CACHE 0
-#define	SIZE_AC 1
-#define	SIZE_L3 (1 + MAX_NUMNODES)
-
-static int drain_freelist(struct kmem_cache *cache,
-			struct kmem_list3 *l3, int tofree);
-static void free_block(struct kmem_cache *cachep, void **objpp, int len,
-			int node);
-static int enable_cpucache(struct kmem_cache *cachep);
-static void cache_reap(struct work_struct *unused);
-
-/*
- * This function must be completely optimized away if a constant is passed to
- * it.  Mostly the same as what is in linux/slab.h except it returns an index.
- */
-static __always_inline int index_of(const size_t size)
-{
-	extern void __bad_size(void);
-
-	if (__builtin_constant_p(size)) {
-		int i = 0;
-
-#define CACHE(x) \
-	if (size <=x) \
-		return i; \
-	else \
-		i++;
-#include "linux/kmalloc_sizes.h"
-#undef CACHE
-		__bad_size();
-	} else
-		__bad_size();
-	return 0;
-}
-
-static int slab_early_init = 1;
-
-#define INDEX_AC index_of(sizeof(struct arraycache_init))
-#define INDEX_L3 index_of(sizeof(struct kmem_list3))
-
-static void kmem_list3_init(struct kmem_list3 *parent)
-{
-	INIT_LIST_HEAD(&parent->slabs_full);
-	INIT_LIST_HEAD(&parent->slabs_partial);
-	INIT_LIST_HEAD(&parent->slabs_free);
-	parent->shared = NULL;
-	parent->alien = NULL;
-	parent->colour_next = 0;
-	spin_lock_init(&parent->list_lock);
-	parent->free_objects = 0;
-	parent->free_touched = 0;
-}
-
-#define MAKE_LIST(cachep, listp, slab, nodeid)				\
-	do {								\
-		INIT_LIST_HEAD(listp);					\
-		list_splice(&(cachep->nodelists[nodeid]->slab), listp);	\
-	} while (0)
-
-#define	MAKE_ALL_LISTS(cachep, ptr, nodeid)				\
-	do {								\
-	MAKE_LIST((cachep), (&(ptr)->slabs_full), slabs_full, nodeid);	\
-	MAKE_LIST((cachep), (&(ptr)->slabs_partial), slabs_partial, nodeid); \
-	MAKE_LIST((cachep), (&(ptr)->slabs_free), slabs_free, nodeid);	\
-	} while (0)
-
-/*
- * struct kmem_cache
- *
- * manages a cache.
- */
-
-struct kmem_cache {
-/* 1) per-cpu data, touched during every alloc/free */
-	struct array_cache *array[NR_CPUS];
-/* 2) Cache tunables. Protected by cache_chain_mutex */
-	unsigned int batchcount;
-	unsigned int limit;
-	unsigned int shared;
-
-	unsigned int buffer_size;
-	u32 reciprocal_buffer_size;
-/* 3) touched by every alloc & free from the backend */
-
-	unsigned int flags;		/* constant flags */
-	unsigned int num;		/* # of objs per slab */
-
-/* 4) cache_grow/shrink */
-	/* order of pgs per slab (2^n) */
-	unsigned int gfporder;
-
-	/* force GFP flags, e.g. GFP_DMA */
-	gfp_t gfpflags;
-
-	size_t colour;			/* cache colouring range */
-	unsigned int colour_off;	/* colour offset */
-	struct kmem_cache *slabp_cache;
-	unsigned int slab_size;
-	unsigned int dflags;		/* dynamic flags */
-
-	/* constructor func */
-	void (*ctor) (void *, struct kmem_cache *, unsigned long);
-
-/* 5) cache creation/removal */
-	const char *name;
-	struct list_head next;
-
-/* 6) statistics */
-#if STATS
-	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;
-#endif
-#if DEBUG
-	/*
-	 * If debugging is enabled, then the allocator can add additional
-	 * fields and/or padding to every object. buffer_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;
-	int obj_size;
-#endif
-	/*
-	 * We put nodelists[] at the end of kmem_cache, because we want to size
-	 * this array to nr_node_ids slots instead of MAX_NUMNODES
-	 * (see kmem_cache_init())
-	 * We still use [MAX_NUMNODES] and not [1] or [0] because cache_cache
-	 * is statically defined, so we reserve the max number of nodes.
-	 */
-	struct kmem_list3 *nodelists[MAX_NUMNODES];
-	/*
-	 * Do not add fields after nodelists[]
-	 */
-};
-
-#define CFLGS_OFF_SLAB		(0x80000000UL)
-#define	OFF_SLAB(x)	((x)->flags & CFLGS_OFF_SLAB)
-
-#define BATCHREFILL_LIMIT	16
-/*
- * Optimization question: fewer reaps means less probability for unnessary
- * cpucache drain/refill cycles.
- *
- * OTOH the cpuarrays can contain lots of objects,
- * which could lock up otherwise freeable slabs.
- */
-#define REAPTIMEOUT_CPUC	(2*HZ)
-#define REAPTIMEOUT_LIST3	(4*HZ)
-
-#if STATS
-#define	STATS_INC_ACTIVE(x)	((x)->num_active++)
-#define	STATS_DEC_ACTIVE(x)	((x)->num_active--)
-#define	STATS_INC_ALLOCED(x)	((x)->num_allocations++)
-#define	STATS_INC_GROWN(x)	((x)->grown++)
-#define	STATS_ADD_REAPED(x,y)	((x)->reaped += (y))
-#define	STATS_SET_HIGH(x)						\
-	do {								\
-		if ((x)->num_active > (x)->high_mark)			\
-			(x)->high_mark = (x)->num_active;		\
-	} while (0)
-#define	STATS_INC_ERR(x)	((x)->errors++)
-#define	STATS_INC_NODEALLOCS(x)	((x)->node_allocs++)
-#define	STATS_INC_NODEFREES(x)	((x)->node_frees++)
-#define STATS_INC_ACOVERFLOW(x)   ((x)->node_overflow++)
-#define	STATS_SET_FREEABLE(x, i)					\
-	do {								\
-		if ((x)->max_freeable < i)				\
-			(x)->max_freeable = i;				\
-	} while (0)
-#define STATS_INC_ALLOCHIT(x)	atomic_inc(&(x)->allochit)
-#define STATS_INC_ALLOCMISS(x)	atomic_inc(&(x)->allocmiss)
-#define STATS_INC_FREEHIT(x)	atomic_inc(&(x)->freehit)
-#define STATS_INC_FREEMISS(x)	atomic_inc(&(x)->freemiss)
-#else
-#define	STATS_INC_ACTIVE(x)	do { } while (0)
-#define	STATS_DEC_ACTIVE(x)	do { } while (0)
-#define	STATS_INC_ALLOCED(x)	do { } while (0)
-#define	STATS_INC_GROWN(x)	do { } while (0)
-#define	STATS_ADD_REAPED(x,y)	do { } while (0)
-#define	STATS_SET_HIGH(x)	do { } while (0)
-#define	STATS_INC_ERR(x)	do { } while (0)
-#define	STATS_INC_NODEALLOCS(x)	do { } while (0)
-#define	STATS_INC_NODEFREES(x)	do { } while (0)
-#define STATS_INC_ACOVERFLOW(x)   do { } while (0)
-#define	STATS_SET_FREEABLE(x, i) do { } while (0)
-#define STATS_INC_ALLOCHIT(x)	do { } while (0)
-#define STATS_INC_ALLOCMISS(x)	do { } while (0)
-#define STATS_INC_FREEHIT(x)	do { } while (0)
-#define STATS_INC_FREEMISS(x)	do { } while (0)
-#endif
-
-#if DEBUG
-
-/*
- * memory layout of objects:
- * 0		: objp
- * 0 .. cachep->obj_offset - BYTES_PER_WORD - 1: padding. This ensures that
- * 		the end of an object is aligned with the end of the real
- * 		allocation. Catches writes behind the end of the allocation.
- * cachep->obj_offset - BYTES_PER_WORD .. cachep->obj_offset - 1:
- * 		redzone word.
- * cachep->obj_offset: The real object.
- * cachep->buffer_size - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long]
- * cachep->buffer_size - 1* BYTES_PER_WORD: last caller address
- *					[BYTES_PER_WORD long]
- */
-static int obj_offset(struct kmem_cache *cachep)
-{
-	return cachep->obj_offset;
-}
-
-static int obj_size(struct kmem_cache *cachep)
-{
-	return cachep->obj_size;
-}
-
-static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp)
-{
-	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
-	return (unsigned long long*) (objp + obj_offset(cachep) -
-				      sizeof(unsigned long long));
-}
-
-static unsigned long long *dbg_redzone2(struct kmem_cache *cachep, void *objp)
-{
-	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
-	if (cachep->flags & SLAB_STORE_USER)
-		return (unsigned long long *)(objp + cachep->buffer_size -
-					      sizeof(unsigned long long) -
-					      BYTES_PER_WORD);
-	return (unsigned long long *) (objp + cachep->buffer_size -
-				       sizeof(unsigned long long));
-}
-
-static void **dbg_userword(struct kmem_cache *cachep, void *objp)
-{
-	BUG_ON(!(cachep->flags & SLAB_STORE_USER));
-	return (void **)(objp + cachep->buffer_size - BYTES_PER_WORD);
-}
-
-#else
-
-#define obj_offset(x)			0
-#define obj_size(cachep)		(cachep->buffer_size)
-#define dbg_redzone1(cachep, objp)	({BUG(); (unsigned long long *)NULL;})
-#define dbg_redzone2(cachep, objp)	({BUG(); (unsigned long long *)NULL;})
-#define dbg_userword(cachep, objp)	({BUG(); (void **)NULL;})
-
-#endif
-
-/*
- * Do not go above this order unless 0 objects fit into the slab.
- */
-#define	BREAK_GFP_ORDER_HI	1
-#define	BREAK_GFP_ORDER_LO	0
-static int slab_break_gfp_order = BREAK_GFP_ORDER_LO;
-
-/*
- * Functions for storing/retrieving the cachep and or slab from the page
- * allocator.  These are used to find the slab an obj belongs to.  With kfree(),
- * these are used to find the cache which an obj belongs to.
- */
-static inline void page_set_cache(struct page *page, struct kmem_cache *cache)
-{
-	page->lru.next = (struct list_head *)cache;
-}
-
-static inline struct kmem_cache *page_get_cache(struct page *page)
-{
-	page = compound_head(page);
-	BUG_ON(!PageSlab(page));
-	return (struct kmem_cache *)page->lru.next;
-}
-
-static inline void page_set_slab(struct page *page, struct slab *slab)
-{
-	page->lru.prev = (struct list_head *)slab;
-}
-
-static inline struct slab *page_get_slab(struct page *page)
-{
-	BUG_ON(!PageSlab(page));
-	return (struct slab *)page->lru.prev;
-}
-
-static inline struct kmem_cache *virt_to_cache(const void *obj)
-{
-	struct page *page = virt_to_head_page(obj);
-	return page_get_cache(page);
-}
-
-static inline struct slab *virt_to_slab(const void *obj)
-{
-	struct page *page = virt_to_head_page(obj);
-	return page_get_slab(page);
-}
-
-static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab,
-				 unsigned int idx)
-{
-	return slab->s_mem + cache->buffer_size * idx;
-}
-
-/*
- * We want to avoid an expensive divide : (offset / cache->buffer_size)
- *   Using the fact that buffer_size is a constant for a particular cache,
- *   we can replace (offset / cache->buffer_size) by
- *   reciprocal_divide(offset, cache->reciprocal_buffer_size)
- */
-static inline unsigned int obj_to_index(const struct kmem_cache *cache,
-					const struct slab *slab, void *obj)
-{
-	u32 offset = (obj - slab->s_mem);
-	return reciprocal_divide(offset, cache->reciprocal_buffer_size);
-}
-
-/*
- * These are the default caches for kmalloc. Custom caches can have other sizes.
- */
-struct cache_sizes malloc_sizes[] = {
-#define CACHE(x) { .cs_size = (x) },
-#include <linux/kmalloc_sizes.h>
-	CACHE(ULONG_MAX)
-#undef CACHE
-};
-EXPORT_SYMBOL(malloc_sizes);
-
-/* Must match cache_sizes above. Out of line to keep cache footprint low. */
-struct cache_names {
-	char *name;
-	char *name_dma;
-};
-
-static struct cache_names __initdata cache_names[] = {
-#define CACHE(x) { .name = "size-" #x, .name_dma = "size-" #x "(DMA)" },
-#include <linux/kmalloc_sizes.h>
-	{NULL,}
-#undef CACHE
-};
-
-static struct arraycache_init initarray_cache __initdata =
-    { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} };
-static struct arraycache_init initarray_generic =
-    { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} };
-
-/* internal cache of cache description objs */
-static struct kmem_cache cache_cache = {
-	.batchcount = 1,
-	.limit = BOOT_CPUCACHE_ENTRIES,
-	.shared = 1,
-	.buffer_size = sizeof(struct kmem_cache),
-	.name = "kmem_cache",
-};
-
-#define BAD_ALIEN_MAGIC 0x01020304ul
-
-#ifdef CONFIG_LOCKDEP
-
-/*
- * Slab sometimes uses the kmalloc slabs to store the slab headers
- * for other slabs "off slab".
- * The locking for this is tricky in that it nests within the locks
- * of all other slabs in a few places; to deal with this special
- * locking we put on-slab caches into a separate lock-class.
- *
- * We set lock class for alien array caches which are up during init.
- * The lock annotation will be lost if all cpus of a node goes down and
- * then comes back up during hotplug
- */
-static struct lock_class_key on_slab_l3_key;
-static struct lock_class_key on_slab_alc_key;
-
-static inline void init_lock_keys(void)
-
-{
-	int q;
-	struct cache_sizes *s = malloc_sizes;
-
-	while (s->cs_size != ULONG_MAX) {
-		for_each_node(q) {
-			struct array_cache **alc;
-			int r;
-			struct kmem_list3 *l3 = s->cs_cachep->nodelists[q];
-			if (!l3 || OFF_SLAB(s->cs_cachep))
-				continue;
-			lockdep_set_class(&l3->list_lock, &on_slab_l3_key);
-			alc = l3->alien;
-			/*
-			 * FIXME: This check for BAD_ALIEN_MAGIC
-			 * should go away when common slab code is taught to
-			 * work even without alien caches.
-			 * Currently, non NUMA code returns BAD_ALIEN_MAGIC
-			 * for alloc_alien_cache,
-			 */
-			if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC)
-				continue;
-			for_each_node(r) {
-				if (alc[r])
-					lockdep_set_class(&alc[r]->lock,
-					     &on_slab_alc_key);
-			}
-		}
-		s++;
-	}
-}
-#else
-static inline void init_lock_keys(void)
-{
-}
-#endif
-
-/*
- * 1. Guard access to the cache-chain.
- * 2. Protect sanity of cpu_online_map against cpu hotplug events
- */
-static DEFINE_MUTEX(cache_chain_mutex);
-static struct list_head cache_chain;
-
-/*
- * chicken and egg problem: delay the per-cpu array allocation
- * until the general caches are up.
- */
-static enum {
-	NONE,
-	PARTIAL_AC,
-	PARTIAL_L3,
-	FULL
-} g_cpucache_up;
-
-/*
- * used by boot code to determine if it can use slab based allocator
- */
-int slab_is_available(void)
-{
-	return g_cpucache_up == FULL;
-}
-
-static DEFINE_PER_CPU(struct delayed_work, reap_work);
-
-static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
-{
-	return cachep->array[smp_processor_id()];
-}
-
-static inline struct kmem_cache *__find_general_cachep(size_t size,
-							gfp_t gfpflags)
-{
-	struct cache_sizes *csizep = malloc_sizes;
-
-#if DEBUG
-	/* This happens if someone tries to call
-	 * kmem_cache_create(), or __kmalloc(), before
-	 * the generic caches are initialized.
-	 */
-	BUG_ON(malloc_sizes[INDEX_AC].cs_cachep == NULL);
-#endif
-	if (!size)
-		return ZERO_SIZE_PTR;
-
-	while (size > csizep->cs_size)
-		csizep++;
-
-	/*
-	 * Really subtle: The last entry with cs->cs_size==ULONG_MAX
-	 * has cs_{dma,}cachep==NULL. Thus no special case
-	 * for large kmalloc calls required.
-	 */
-#ifdef CONFIG_ZONE_DMA
-	if (unlikely(gfpflags & GFP_DMA))
-		return csizep->cs_dmacachep;
-#endif
-	return csizep->cs_cachep;
-}
-
-static struct kmem_cache *kmem_find_general_cachep(size_t size, gfp_t gfpflags)
-{
-	return __find_general_cachep(size, gfpflags);
-}
-
-static size_t slab_mgmt_size(size_t nr_objs, size_t align)
-{
-	return ALIGN(sizeof(struct slab)+nr_objs*sizeof(kmem_bufctl_t), align);
-}
-
-/*
- * Calculate the number of objects and left-over bytes for a given buffer size.
- */
-static void cache_estimate(unsigned long gfporder, size_t buffer_size,
-			   size_t align, int flags, size_t *left_over,
-			   unsigned int *num)
-{
-	int nr_objs;
-	size_t mgmt_size;
-	size_t slab_size = PAGE_SIZE << gfporder;
-
-	/*
-	 * The slab management structure can be either off the slab or
-	 * on it. For the latter case, the memory allocated for a
-	 * slab is used for:
-	 *
-	 * - The struct slab
-	 * - One kmem_bufctl_t for each object
-	 * - Padding to respect alignment of @align
-	 * - @buffer_size bytes for each object
-	 *
-	 * If the slab management structure is off the slab, then the
-	 * alignment will already be calculated into the size. Because
-	 * the slabs are all pages aligned, the objects will be at the
-	 * correct alignment when allocated.
-	 */
-	if (flags & CFLGS_OFF_SLAB) {
-		mgmt_size = 0;
-		nr_objs = slab_size / buffer_size;
-
-		if (nr_objs > SLAB_LIMIT)
-			nr_objs = SLAB_LIMIT;
-	} else {
-		/*
-		 * Ignore padding for the initial guess. The padding
-		 * is at most @align-1 bytes, and @buffer_size is at
-		 * least @align. In the worst case, this result will
-		 * be one greater than the number of objects that fit
-		 * into the memory allocation when taking the padding
-		 * into account.
-		 */
-		nr_objs = (slab_size - sizeof(struct slab)) /
-			  (buffer_size + sizeof(kmem_bufctl_t));
-
-		/*
-		 * This calculated number will be either the right
-		 * amount, or one greater than what we want.
-		 */
-		if (slab_mgmt_size(nr_objs, align) + nr_objs*buffer_size
-		       > slab_size)
-			nr_objs--;
-
-		if (nr_objs > SLAB_LIMIT)
-			nr_objs = SLAB_LIMIT;
-
-		mgmt_size = slab_mgmt_size(nr_objs, align);
-	}
-	*num = nr_objs;
-	*left_over = slab_size - nr_objs*buffer_size - mgmt_size;
-}
-
-#define slab_error(cachep, msg) __slab_error(__FUNCTION__, cachep, msg)
-
-static void __slab_error(const char *function, struct kmem_cache *cachep,
-			char *msg)
-{
-	printk(KERN_ERR "slab error in %s(): cache `%s': %s\n",
-	       function, cachep->name, msg);
-	dump_stack();
-}
-
-/*
- * By default on NUMA we use alien caches to stage the freeing of
- * objects allocated from other nodes. This causes massive memory
- * inefficiencies when using fake NUMA setup to split memory into a
- * large number of small nodes, so it can be disabled on the command
- * line
-  */
-
-static int use_alien_caches __read_mostly = 1;
-static int __init noaliencache_setup(char *s)
-{
-	use_alien_caches = 0;
-	return 1;
-}
-__setup("noaliencache", noaliencache_setup);
-
-#ifdef CONFIG_NUMA
-/*
- * Special reaping functions for NUMA systems called from cache_reap().
- * These take care of doing round robin flushing of alien caches (containing
- * objects freed on different nodes from which they were allocated) and the
- * flushing of remote pcps by calling drain_node_pages.
- */
-static DEFINE_PER_CPU(unsigned long, reap_node);
-
-static void init_reap_node(int cpu)
-{
-	int node;
-
-	node = next_node(cpu_to_node(cpu), node_online_map);
-	if (node == MAX_NUMNODES)
-		node = first_node(node_online_map);
-
-	per_cpu(reap_node, cpu) = node;
-}
-
-static void next_reap_node(void)
-{
-	int node = __get_cpu_var(reap_node);
-
-	node = next_node(node, node_online_map);
-	if (unlikely(node >= MAX_NUMNODES))
-		node = first_node(node_online_map);
-	__get_cpu_var(reap_node) = node;
-}
-
-#else
-#define init_reap_node(cpu) do { } while (0)
-#define next_reap_node(void) do { } while (0)
-#endif
-
-/*
- * Initiate the reap timer running on the target CPU.  We run at around 1 to 2Hz
- * via the workqueue/eventd.
- * Add the CPU number into the expiration time to minimize the possibility of
- * the CPUs getting into lockstep and contending for the global cache chain
- * lock.
- */
-static void __cpuinit start_cpu_timer(int cpu)
-{
-	struct delayed_work *reap_work = &per_cpu(reap_work, cpu);
-
-	/*
-	 * When this gets called from do_initcalls via cpucache_init(),
-	 * init_workqueues() has already run, so keventd will be setup
-	 * at that time.
-	 */
-	if (keventd_up() && reap_work->work.func == NULL) {
-		init_reap_node(cpu);
-		INIT_DELAYED_WORK(reap_work, cache_reap);
-		schedule_delayed_work_on(cpu, reap_work,
-					__round_jiffies_relative(HZ, cpu));
-	}
-}
-
-static struct array_cache *alloc_arraycache(int node, int entries,
-					    int batchcount)
-{
-	int memsize = sizeof(void *) * entries + sizeof(struct array_cache);
-	struct array_cache *nc = NULL;
-
-	nc = kmalloc_node(memsize, GFP_KERNEL, node);
-	if (nc) {
-		nc->avail = 0;
-		nc->limit = entries;
-		nc->batchcount = batchcount;
-		nc->touched = 0;
-		spin_lock_init(&nc->lock);
-	}
-	return nc;
-}
-
-/*
- * Transfer objects in one arraycache to another.
- * Locking must be handled by the caller.
- *
- * Return the number of entries transferred.
- */
-static int transfer_objects(struct array_cache *to,
-		struct array_cache *from, unsigned int max)
-{
-	/* Figure out how many entries to transfer */
-	int nr = min(min(from->avail, max), to->limit - to->avail);
-
-	if (!nr)
-		return 0;
-
-	memcpy(to->entry + to->avail, from->entry + from->avail -nr,
-			sizeof(void *) *nr);
-
-	from->avail -= nr;
-	to->avail += nr;
-	to->touched = 1;
-	return nr;
-}
-
-#ifndef CONFIG_NUMA
-
-#define drain_alien_cache(cachep, alien) do { } while (0)
-#define reap_alien(cachep, l3) do { } while (0)
-
-static inline struct array_cache **alloc_alien_cache(int node, int limit)
-{
-	return (struct array_cache **)BAD_ALIEN_MAGIC;
-}
-
-static inline void free_alien_cache(struct array_cache **ac_ptr)
-{
-}
-
-static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
-{
-	return 0;
-}
-
-static inline void *alternate_node_alloc(struct kmem_cache *cachep,
-		gfp_t flags)
-{
-	return NULL;
-}
-
-static inline void *____cache_alloc_node(struct kmem_cache *cachep,
-		 gfp_t flags, int nodeid)
-{
-	return NULL;
-}
-
-#else	/* CONFIG_NUMA */
-
-static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int);
-static void *alternate_node_alloc(struct kmem_cache *, gfp_t);
-
-static struct array_cache **alloc_alien_cache(int node, int limit)
-{
-	struct array_cache **ac_ptr;
-	int memsize = sizeof(void *) * nr_node_ids;
-	int i;
-
-	if (limit > 1)
-		limit = 12;
-	ac_ptr = kmalloc_node(memsize, GFP_KERNEL, node);
-	if (ac_ptr) {
-		for_each_node(i) {
-			if (i == node || !node_online(i)) {
-				ac_ptr[i] = NULL;
-				continue;
-			}
-			ac_ptr[i] = alloc_arraycache(node, limit, 0xbaadf00d);
-			if (!ac_ptr[i]) {
-				for (i--; i <= 0; i--)
-					kfree(ac_ptr[i]);
-				kfree(ac_ptr);
-				return NULL;
-			}
-		}
-	}
-	return ac_ptr;
-}
-
-static void free_alien_cache(struct array_cache **ac_ptr)
-{
-	int i;
-
-	if (!ac_ptr)
-		return;
-	for_each_node(i)
-	    kfree(ac_ptr[i]);
-	kfree(ac_ptr);
-}
-
-static void __drain_alien_cache(struct kmem_cache *cachep,
-				struct array_cache *ac, int node)
-{
-	struct kmem_list3 *rl3 = cachep->nodelists[node];
-
-	if (ac->avail) {
-		spin_lock(&rl3->list_lock);
-		/*
-		 * Stuff objects into the remote nodes shared array first.
-		 * That way we could avoid the overhead of putting the objects
-		 * into the free lists and getting them back later.
-		 */
-		if (rl3->shared)
-			transfer_objects(rl3->shared, ac, ac->limit);
-
-		free_block(cachep, ac->entry, ac->avail, node);
-		ac->avail = 0;
-		spin_unlock(&rl3->list_lock);
-	}
-}
-
-/*
- * Called from cache_reap() to regularly drain alien caches round robin.
- */
-static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
-{
-	int node = __get_cpu_var(reap_node);
-
-	if (l3->alien) {
-		struct array_cache *ac = l3->alien[node];
-
-		if (ac && ac->avail && spin_trylock_irq(&ac->lock)) {
-			__drain_alien_cache(cachep, ac, node);
-			spin_unlock_irq(&ac->lock);
-		}
-	}
-}
-
-static void drain_alien_cache(struct kmem_cache *cachep,
-				struct array_cache **alien)
-{
-	int i = 0;
-	struct array_cache *ac;
-	unsigned long flags;
-
-	for_each_online_node(i) {
-		ac = alien[i];
-		if (ac) {
-			spin_lock_irqsave(&ac->lock, flags);
-			__drain_alien_cache(cachep, ac, i);
-			spin_unlock_irqrestore(&ac->lock, flags);
-		}
-	}
-}
-
-static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
-{
-	struct slab *slabp = virt_to_slab(objp);
-	int nodeid = slabp->nodeid;
-	struct kmem_list3 *l3;
-	struct array_cache *alien = NULL;
-	int node;
-
-	node = numa_node_id();
-
-	/*
-	 * Make sure we are not freeing a object from another node to the array
-	 * cache on this cpu.
-	 */
-	if (likely(slabp->nodeid == node))
-		return 0;
-
-	l3 = cachep->nodelists[node];
-	STATS_INC_NODEFREES(cachep);
-	if (l3->alien && l3->alien[nodeid]) {
-		alien = l3->alien[nodeid];
-		spin_lock(&alien->lock);
-		if (unlikely(alien->avail == alien->limit)) {
-			STATS_INC_ACOVERFLOW(cachep);
-			__drain_alien_cache(cachep, alien, nodeid);
-		}
-		alien->entry[alien->avail++] = objp;
-		spin_unlock(&alien->lock);
-	} else {
-		spin_lock(&(cachep->nodelists[nodeid])->list_lock);
-		free_block(cachep, &objp, 1, nodeid);
-		spin_unlock(&(cachep->nodelists[nodeid])->list_lock);
-	}
-	return 1;
-}
-#endif
-
-static int __cpuinit cpuup_callback(struct notifier_block *nfb,
-				    unsigned long action, void *hcpu)
-{
-	long cpu = (long)hcpu;
-	struct kmem_cache *cachep;
-	struct kmem_list3 *l3 = NULL;
-	int node = cpu_to_node(cpu);
-	int memsize = sizeof(struct kmem_list3);
-
-	switch (action) {
-	case CPU_LOCK_ACQUIRE:
-		mutex_lock(&cache_chain_mutex);
-		break;
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		/*
-		 * We need to do this right in the beginning since
-		 * alloc_arraycache's are going to use this list.
-		 * kmalloc_node allows us to add the slab to the right
-		 * kmem_list3 and not this cpu's kmem_list3
-		 */
-
-		list_for_each_entry(cachep, &cache_chain, next) {
-			/*
-			 * Set up the size64 kmemlist for cpu before we can
-			 * begin anything. Make sure some other cpu on this
-			 * node has not already allocated this
-			 */
-			if (!cachep->nodelists[node]) {
-				l3 = kmalloc_node(memsize, GFP_KERNEL, node);
-				if (!l3)
-					goto bad;
-				kmem_list3_init(l3);
-				l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
-				    ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
-
-				/*
-				 * The l3s don't come and go as CPUs come and
-				 * go.  cache_chain_mutex is sufficient
-				 * protection here.
-				 */
-				cachep->nodelists[node] = l3;
-			}
-
-			spin_lock_irq(&cachep->nodelists[node]->list_lock);
-			cachep->nodelists[node]->free_limit =
-				(1 + nr_cpus_node(node)) *
-				cachep->batchcount + cachep->num;
-			spin_unlock_irq(&cachep->nodelists[node]->list_lock);
-		}
-
-		/*
-		 * Now we can go ahead with allocating the shared arrays and
-		 * array caches
-		 */
-		list_for_each_entry(cachep, &cache_chain, next) {
-			struct array_cache *nc;
-			struct array_cache *shared = NULL;
-			struct array_cache **alien = NULL;
-
-			nc = alloc_arraycache(node, cachep->limit,
-						cachep->batchcount);
-			if (!nc)
-				goto bad;
-			if (cachep->shared) {
-				shared = alloc_arraycache(node,
-					cachep->shared * cachep->batchcount,
-					0xbaadf00d);
-				if (!shared)
-					goto bad;
-			}
-			if (use_alien_caches) {
-                                alien = alloc_alien_cache(node, cachep->limit);
-                                if (!alien)
-                                        goto bad;
-                        }
-			cachep->array[cpu] = nc;
-			l3 = cachep->nodelists[node];
-			BUG_ON(!l3);
-
-			spin_lock_irq(&l3->list_lock);
-			if (!l3->shared) {
-				/*
-				 * We are serialised from CPU_DEAD or
-				 * CPU_UP_CANCELLED by the cpucontrol lock
-				 */
-				l3->shared = shared;
-				shared = NULL;
-			}
-#ifdef CONFIG_NUMA
-			if (!l3->alien) {
-				l3->alien = alien;
-				alien = NULL;
-			}
-#endif
-			spin_unlock_irq(&l3->list_lock);
-			kfree(shared);
-			free_alien_cache(alien);
-		}
-		break;
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		start_cpu_timer(cpu);
-		break;
-#ifdef CONFIG_HOTPLUG_CPU
-  	case CPU_DOWN_PREPARE:
-  	case CPU_DOWN_PREPARE_FROZEN:
-		/*
-		 * Shutdown cache reaper. Note that the cache_chain_mutex is
-		 * held so that if cache_reap() is invoked it cannot do
-		 * anything expensive but will only modify reap_work
-		 * and reschedule the timer.
-		*/
-		cancel_rearming_delayed_work(&per_cpu(reap_work, cpu));
-		/* Now the cache_reaper is guaranteed to be not running. */
-		per_cpu(reap_work, cpu).work.func = NULL;
-  		break;
-  	case CPU_DOWN_FAILED:
-  	case CPU_DOWN_FAILED_FROZEN:
-		start_cpu_timer(cpu);
-  		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		/*
-		 * Even if all the cpus of a node are down, we don't free the
-		 * kmem_list3 of any cache. This to avoid a race between
-		 * cpu_down, and a kmalloc allocation from another cpu for
-		 * memory from the node of the cpu going down.  The list3
-		 * structure is usually allocated from kmem_cache_create() and
-		 * gets destroyed at kmem_cache_destroy().
-		 */
-		/* fall thru */
-#endif
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		list_for_each_entry(cachep, &cache_chain, next) {
-			struct array_cache *nc;
-			struct array_cache *shared;
-			struct array_cache **alien;
-			cpumask_t mask;
-
-			mask = node_to_cpumask(node);
-			/* cpu is dead; no one can alloc from it. */
-			nc = cachep->array[cpu];
-			cachep->array[cpu] = NULL;
-			l3 = cachep->nodelists[node];
-
-			if (!l3)
-				goto free_array_cache;
-
-			spin_lock_irq(&l3->list_lock);
-
-			/* Free limit for this kmem_list3 */
-			l3->free_limit -= cachep->batchcount;
-			if (nc)
-				free_block(cachep, nc->entry, nc->avail, node);
-
-			if (!cpus_empty(mask)) {
-				spin_unlock_irq(&l3->list_lock);
-				goto free_array_cache;
-			}
-
-			shared = l3->shared;
-			if (shared) {
-				free_block(cachep, shared->entry,
-					   shared->avail, node);
-				l3->shared = NULL;
-			}
-
-			alien = l3->alien;
-			l3->alien = NULL;
-
-			spin_unlock_irq(&l3->list_lock);
-
-			kfree(shared);
-			if (alien) {
-				drain_alien_cache(cachep, alien);
-				free_alien_cache(alien);
-			}
-free_array_cache:
-			kfree(nc);
-		}
-		/*
-		 * In the previous loop, all the objects were freed to
-		 * the respective cache's slabs,  now we can go ahead and
-		 * shrink each nodelist to its limit.
-		 */
-		list_for_each_entry(cachep, &cache_chain, next) {
-			l3 = cachep->nodelists[node];
-			if (!l3)
-				continue;
-			drain_freelist(cachep, l3, l3->free_objects);
-		}
-		break;
-	case CPU_LOCK_RELEASE:
-		mutex_unlock(&cache_chain_mutex);
-		break;
-	}
-	return NOTIFY_OK;
-bad:
-	return NOTIFY_BAD;
-}
-
-static struct notifier_block __cpuinitdata cpucache_notifier = {
-	&cpuup_callback, NULL, 0
-};
-
-/*
- * swap the static kmem_list3 with kmalloced memory
- */
-static void init_list(struct kmem_cache *cachep, struct kmem_list3 *list,
-			int nodeid)
-{
-	struct kmem_list3 *ptr;
-
-	ptr = kmalloc_node(sizeof(struct kmem_list3), GFP_KERNEL, nodeid);
-	BUG_ON(!ptr);
-
-	local_irq_disable();
-	memcpy(ptr, list, sizeof(struct kmem_list3));
-	/*
-	 * Do not assume that spinlocks can be initialized via memcpy:
-	 */
-	spin_lock_init(&ptr->list_lock);
-
-	MAKE_ALL_LISTS(cachep, ptr, nodeid);
-	cachep->nodelists[nodeid] = ptr;
-	local_irq_enable();
-}
-
-/*
- * Initialisation.  Called after the page allocator have been initialised and
- * before smp_init().
- */
-void __init kmem_cache_init(void)
-{
-	size_t left_over;
-	struct cache_sizes *sizes;
-	struct cache_names *names;
-	int i;
-	int order;
-	int node;
-
-	if (num_possible_nodes() == 1)
-		use_alien_caches = 0;
-
-	for (i = 0; i < NUM_INIT_LISTS; i++) {
-		kmem_list3_init(&initkmem_list3[i]);
-		if (i < MAX_NUMNODES)
-			cache_cache.nodelists[i] = NULL;
-	}
-
-	/*
-	 * Fragmentation resistance on low memory - only use bigger
-	 * page orders on machines with more than 32MB of memory.
-	 */
-	if (num_physpages > (32 << 20) >> PAGE_SHIFT)
-		slab_break_gfp_order = BREAK_GFP_ORDER_HI;
-
-	/* Bootstrap is tricky, because several objects are allocated
-	 * from caches that do not exist yet:
-	 * 1) initialize the cache_cache cache: it contains the struct
-	 *    kmem_cache structures of all caches, except cache_cache itself:
-	 *    cache_cache is statically allocated.
-	 *    Initially an __init data area is used for the head array and the
-	 *    kmem_list3 structures, it's replaced with a kmalloc allocated
-	 *    array at the end of the bootstrap.
-	 * 2) Create the first kmalloc cache.
-	 *    The struct kmem_cache for the new cache is allocated normally.
-	 *    An __init data area is used for the head array.
-	 * 3) Create the remaining kmalloc caches, with minimally sized
-	 *    head arrays.
-	 * 4) Replace the __init data head arrays for cache_cache and the first
-	 *    kmalloc cache with kmalloc allocated arrays.
-	 * 5) Replace the __init data for kmem_list3 for cache_cache and
-	 *    the other cache's with kmalloc allocated memory.
-	 * 6) Resize the head arrays of the kmalloc caches to their final sizes.
-	 */
-
-	node = numa_node_id();
-
-	/* 1) create the cache_cache */
-	INIT_LIST_HEAD(&cache_chain);
-	list_add(&cache_cache.next, &cache_chain);
-	cache_cache.colour_off = cache_line_size();
-	cache_cache.array[smp_processor_id()] = &initarray_cache.cache;
-	cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE];
-
-	/*
-	 * struct kmem_cache size depends on nr_node_ids, which
-	 * can be less than MAX_NUMNODES.
-	 */
-	cache_cache.buffer_size = offsetof(struct kmem_cache, nodelists) +
-				 nr_node_ids * sizeof(struct kmem_list3 *);
-#if DEBUG
-	cache_cache.obj_size = cache_cache.buffer_size;
-#endif
-	cache_cache.buffer_size = ALIGN(cache_cache.buffer_size,
-					cache_line_size());
-	cache_cache.reciprocal_buffer_size =
-		reciprocal_value(cache_cache.buffer_size);
-
-	for (order = 0; order < MAX_ORDER; order++) {
-		cache_estimate(order, cache_cache.buffer_size,
-			cache_line_size(), 0, &left_over, &cache_cache.num);
-		if (cache_cache.num)
-			break;
-	}
-	BUG_ON(!cache_cache.num);
-	cache_cache.gfporder = order;
-	cache_cache.colour = left_over / cache_cache.colour_off;
-	cache_cache.slab_size = ALIGN(cache_cache.num * sizeof(kmem_bufctl_t) +
-				      sizeof(struct slab), cache_line_size());
-
-	/* 2+3) create the kmalloc caches */
-	sizes = malloc_sizes;
-	names = cache_names;
-
-	/*
-	 * Initialize the caches that provide memory for the array cache and the
-	 * kmem_list3 structures first.  Without this, further allocations will
-	 * bug.
-	 */
-
-	sizes[INDEX_AC].cs_cachep = kmem_cache_create(names[INDEX_AC].name,
-					sizes[INDEX_AC].cs_size,
-					ARCH_KMALLOC_MINALIGN,
-					ARCH_KMALLOC_FLAGS|SLAB_PANIC,
-					NULL, NULL);
-
-	if (INDEX_AC != INDEX_L3) {
-		sizes[INDEX_L3].cs_cachep =
-			kmem_cache_create(names[INDEX_L3].name,
-				sizes[INDEX_L3].cs_size,
-				ARCH_KMALLOC_MINALIGN,
-				ARCH_KMALLOC_FLAGS|SLAB_PANIC,
-				NULL, NULL);
-	}
-
-	slab_early_init = 0;
-
-	while (sizes->cs_size != ULONG_MAX) {
-		/*
-		 * For performance, all the general caches are L1 aligned.
-		 * This should be particularly beneficial on SMP boxes, as it
-		 * eliminates "false sharing".
-		 * Note for systems short on memory removing the alignment will
-		 * allow tighter packing of the smaller caches.
-		 */
-		if (!sizes->cs_cachep) {
-			sizes->cs_cachep = kmem_cache_create(names->name,
-					sizes->cs_size,
-					ARCH_KMALLOC_MINALIGN,
-					ARCH_KMALLOC_FLAGS|SLAB_PANIC,
-					NULL, NULL);
-		}
-#ifdef CONFIG_ZONE_DMA
-		sizes->cs_dmacachep = kmem_cache_create(
-					names->name_dma,
-					sizes->cs_size,
-					ARCH_KMALLOC_MINALIGN,
-					ARCH_KMALLOC_FLAGS|SLAB_CACHE_DMA|
-						SLAB_PANIC,
-					NULL, NULL);
-#endif
-		sizes++;
-		names++;
-	}
-	/* 4) Replace the bootstrap head arrays */
-	{
-		struct array_cache *ptr;
-
-		ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);
-
-		local_irq_disable();
-		BUG_ON(cpu_cache_get(&cache_cache) != &initarray_cache.cache);
-		memcpy(ptr, cpu_cache_get(&cache_cache),
-		       sizeof(struct arraycache_init));
-		/*
-		 * Do not assume that spinlocks can be initialized via memcpy:
-		 */
-		spin_lock_init(&ptr->lock);
-
-		cache_cache.array[smp_processor_id()] = ptr;
-		local_irq_enable();
-
-		ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);
-
-		local_irq_disable();
-		BUG_ON(cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep)
-		       != &initarray_generic.cache);
-		memcpy(ptr, cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep),
-		       sizeof(struct arraycache_init));
-		/*
-		 * Do not assume that spinlocks can be initialized via memcpy:
-		 */
-		spin_lock_init(&ptr->lock);
-
-		malloc_sizes[INDEX_AC].cs_cachep->array[smp_processor_id()] =
-		    ptr;
-		local_irq_enable();
-	}
-	/* 5) Replace the bootstrap kmem_list3's */
-	{
-		int nid;
-
-		/* Replace the static kmem_list3 structures for the boot cpu */
-		init_list(&cache_cache, &initkmem_list3[CACHE_CACHE], node);
-
-		for_each_online_node(nid) {
-			init_list(malloc_sizes[INDEX_AC].cs_cachep,
-				  &initkmem_list3[SIZE_AC + nid], nid);
-
-			if (INDEX_AC != INDEX_L3) {
-				init_list(malloc_sizes[INDEX_L3].cs_cachep,
-					  &initkmem_list3[SIZE_L3 + nid], nid);
-			}
-		}
-	}
-
-	/* 6) resize the head arrays to their final sizes */
-	{
-		struct kmem_cache *cachep;
-		mutex_lock(&cache_chain_mutex);
-		list_for_each_entry(cachep, &cache_chain, next)
-			if (enable_cpucache(cachep))
-				BUG();
-		mutex_unlock(&cache_chain_mutex);
-	}
-
-	/* Annotate slab for lockdep -- annotate the malloc caches */
-	init_lock_keys();
-
-
-	/* Done! */
-	g_cpucache_up = FULL;
-
-	/*
-	 * Register a cpu startup notifier callback that initializes
-	 * cpu_cache_get for all new cpus
-	 */
-	register_cpu_notifier(&cpucache_notifier);
-
-	/*
-	 * The reap timers are started later, with a module init call: That part
-	 * of the kernel is not yet operational.
-	 */
-}
-
-static int __init cpucache_init(void)
-{
-	int cpu;
-
-	/*
-	 * Register the timers that return unneeded pages to the page allocator
-	 */
-	for_each_online_cpu(cpu)
-		start_cpu_timer(cpu);
-	return 0;
-}
-__initcall(cpucache_init);
-
-/*
- * Interface to system's page allocator. No need to hold the cache-lock.
- *
- * If we requested dmaable memory, we will get it. Even if we
- * did not request dmaable memory, we might get it, but that
- * would be relatively rare and ignorable.
- */
-static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
-{
-	struct page *page;
-	int nr_pages;
-	int i;
-
-#ifndef CONFIG_MMU
-	/*
-	 * Nommu uses slab's for process anonymous memory allocations, and thus
-	 * requires __GFP_COMP to properly refcount higher order allocations
-	 */
-	flags |= __GFP_COMP;
-#endif
-
-	flags |= cachep->gfpflags;
-	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
-		flags |= __GFP_RECLAIMABLE;
-
-	page = alloc_pages_node(nodeid, flags, cachep->gfporder);
-	if (!page)
-		return NULL;
-
-	nr_pages = (1 << cachep->gfporder);
-	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
-		add_zone_page_state(page_zone(page),
-			NR_SLAB_RECLAIMABLE, nr_pages);
-	else
-		add_zone_page_state(page_zone(page),
-			NR_SLAB_UNRECLAIMABLE, nr_pages);
-	for (i = 0; i < nr_pages; i++)
-		__SetPageSlab(page + i);
-	return page_address(page);
-}
-
-/*
- * Interface to system's page release.
- */
-static void kmem_freepages(struct kmem_cache *cachep, void *addr)
-{
-	unsigned long i = (1 << cachep->gfporder);
-	struct page *page = virt_to_page(addr);
-	const unsigned long nr_freed = i;
-
-	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
-		sub_zone_page_state(page_zone(page),
-				NR_SLAB_RECLAIMABLE, nr_freed);
-	else
-		sub_zone_page_state(page_zone(page),
-				NR_SLAB_UNRECLAIMABLE, nr_freed);
-	while (i--) {
-		BUG_ON(!PageSlab(page));
-		__ClearPageSlab(page);
-		page++;
-	}
-	if (current->reclaim_state)
-		current->reclaim_state->reclaimed_slab += nr_freed;
-	free_pages((unsigned long)addr, cachep->gfporder);
-}
-
-static void kmem_rcu_free(struct rcu_head *head)
-{
-	struct slab_rcu *slab_rcu = (struct slab_rcu *)head;
-	struct kmem_cache *cachep = slab_rcu->cachep;
-
-	kmem_freepages(cachep, slab_rcu->addr);
-	if (OFF_SLAB(cachep))
-		kmem_cache_free(cachep->slabp_cache, slab_rcu);
-}
-
-#if DEBUG
-
-#ifdef CONFIG_DEBUG_PAGEALLOC
-static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
-			    unsigned long caller)
-{
-	int size = obj_size(cachep);
-
-	addr = (unsigned long *)&((char *)addr)[obj_offset(cachep)];
-
-	if (size < 5 * sizeof(unsigned long))
-		return;
-
-	*addr++ = 0x12345678;
-	*addr++ = caller;
-	*addr++ = smp_processor_id();
-	size -= 3 * sizeof(unsigned long);
-	{
-		unsigned long *sptr = &caller;
-		unsigned long svalue;
-
-		while (!kstack_end(sptr)) {
-			svalue = *sptr++;
-			if (kernel_text_address(svalue)) {
-				*addr++ = svalue;
-				size -= sizeof(unsigned long);
-				if (size <= sizeof(unsigned long))
-					break;
-			}
-		}
-
-	}
-	*addr++ = 0x87654321;
-}
-#endif
-
-static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val)
-{
-	int size = obj_size(cachep);
-	addr = &((char *)addr)[obj_offset(cachep)];
-
-	memset(addr, val, size);
-	*(unsigned char *)(addr + size - 1) = POISON_END;
-}
-
-static void dump_line(char *data, int offset, int limit)
-{
-	int i;
-	unsigned char error = 0;
-	int bad_count = 0;
-
-	printk(KERN_ERR "%03x:", offset);
-	for (i = 0; i < limit; i++) {
-		if (data[offset + i] != POISON_FREE) {
-			error = data[offset + i];
-			bad_count++;
-		}
-		printk(" %02x", (unsigned char)data[offset + i]);
-	}
-	printk("\n");
-
-	if (bad_count == 1) {
-		error ^= POISON_FREE;
-		if (!(error & (error - 1))) {
-			printk(KERN_ERR "Single bit error detected. Probably "
-					"bad RAM.\n");
-#ifdef CONFIG_X86
-			printk(KERN_ERR "Run memtest86+ or a similar memory "
-					"test tool.\n");
-#else
-			printk(KERN_ERR "Run a memory test tool.\n");
-#endif
-		}
-	}
-}
-#endif
-
-#if DEBUG
-
-static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines)
-{
-	int i, size;
-	char *realobj;
-
-	if (cachep->flags & SLAB_RED_ZONE) {
-		printk(KERN_ERR "Redzone: 0x%llx/0x%llx.\n",
-			*dbg_redzone1(cachep, objp),
-			*dbg_redzone2(cachep, objp));
-	}
-
-	if (cachep->flags & SLAB_STORE_USER) {
-		printk(KERN_ERR "Last user: [<%p>]",
-			*dbg_userword(cachep, objp));
-		print_symbol("(%s)",
-				(unsigned long)*dbg_userword(cachep, objp));
-		printk("\n");
-	}
-	realobj = (char *)objp + obj_offset(cachep);
-	size = obj_size(cachep);
-	for (i = 0; i < size && lines; i += 16, lines--) {
-		int limit;
-		limit = 16;
-		if (i + limit > size)
-			limit = size - i;
-		dump_line(realobj, i, limit);
-	}
-}
-
-static void check_poison_obj(struct kmem_cache *cachep, void *objp)
-{
-	char *realobj;
-	int size, i;
-	int lines = 0;
-
-	realobj = (char *)objp + obj_offset(cachep);
-	size = obj_size(cachep);
-
-	for (i = 0; i < size; i++) {
-		char exp = POISON_FREE;
-		if (i == size - 1)
-			exp = POISON_END;
-		if (realobj[i] != exp) {
-			int limit;
-			/* Mismatch ! */
-			/* Print header */
-			if (lines == 0) {
-				printk(KERN_ERR
-					"Slab corruption: %s start=%p, len=%d\n",
-					cachep->name, realobj, size);
-				print_objinfo(cachep, objp, 0);
-			}
-			/* Hexdump the affected line */
-			i = (i / 16) * 16;
-			limit = 16;
-			if (i + limit > size)
-				limit = size - i;
-			dump_line(realobj, i, limit);
-			i += 16;
-			lines++;
-			/* Limit to 5 lines */
-			if (lines > 5)
-				break;
-		}
-	}
-	if (lines != 0) {
-		/* Print some data about the neighboring objects, if they
-		 * exist:
-		 */
-		struct slab *slabp = virt_to_slab(objp);
-		unsigned int objnr;
-
-		objnr = obj_to_index(cachep, slabp, objp);
-		if (objnr) {
-			objp = index_to_obj(cachep, slabp, objnr - 1);
-			realobj = (char *)objp + obj_offset(cachep);
-			printk(KERN_ERR "Prev obj: start=%p, len=%d\n",
-			       realobj, size);
-			print_objinfo(cachep, objp, 2);
-		}
-		if (objnr + 1 < cachep->num) {
-			objp = index_to_obj(cachep, slabp, objnr + 1);
-			realobj = (char *)objp + obj_offset(cachep);
-			printk(KERN_ERR "Next obj: start=%p, len=%d\n",
-			       realobj, size);
-			print_objinfo(cachep, objp, 2);
-		}
-	}
-}
-#endif
-
-#if DEBUG
-/**
- * slab_destroy_objs - destroy a slab and its objects
- * @cachep: cache pointer being destroyed
- * @slabp: slab pointer being destroyed
- *
- * Call the registered destructor for each object in a slab that is being
- * destroyed.
- */
-static void slab_destroy_objs(struct kmem_cache *cachep, struct slab *slabp)
-{
-	int i;
-	for (i = 0; i < cachep->num; i++) {
-		void *objp = index_to_obj(cachep, slabp, i);
-
-		if (cachep->flags & SLAB_POISON) {
-#ifdef CONFIG_DEBUG_PAGEALLOC
-			if (cachep->buffer_size % PAGE_SIZE == 0 &&
-					OFF_SLAB(cachep))
-				kernel_map_pages(virt_to_page(objp),
-					cachep->buffer_size / PAGE_SIZE, 1);
-			else
-				check_poison_obj(cachep, objp);
-#else
-			check_poison_obj(cachep, objp);
-#endif
-		}
-		if (cachep->flags & SLAB_RED_ZONE) {
-			if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
-				slab_error(cachep, "start of a freed object "
-					   "was overwritten");
-			if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
-				slab_error(cachep, "end of a freed object "
-					   "was overwritten");
-		}
-	}
-}
-#else
-static void slab_destroy_objs(struct kmem_cache *cachep, struct slab *slabp)
-{
-}
-#endif
-
-/**
- * slab_destroy - destroy and release all objects in a slab
- * @cachep: cache pointer being destroyed
- * @slabp: slab pointer being destroyed
- *
- * Destroy all the objs in a slab, and release the mem back to the system.
- * Before calling the slab must have been unlinked from the cache.  The
- * cache-lock is not held/needed.
- */
-static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp)
-{
-	void *addr = slabp->s_mem - slabp->colouroff;
-
-	slab_destroy_objs(cachep, slabp);
-	if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) {
-		struct slab_rcu *slab_rcu;
-
-		slab_rcu = (struct slab_rcu *)slabp;
-		slab_rcu->cachep = cachep;
-		slab_rcu->addr = addr;
-		call_rcu(&slab_rcu->head, kmem_rcu_free);
-	} else {
-		kmem_freepages(cachep, addr);
-		if (OFF_SLAB(cachep))
-			kmem_cache_free(cachep->slabp_cache, slabp);
-	}
-}
-
-/*
- * For setting up all the kmem_list3s for cache whose buffer_size is same as
- * size of kmem_list3.
- */
-static void __init set_up_list3s(struct kmem_cache *cachep, int index)
-{
-	int node;
-
-	for_each_online_node(node) {
-		cachep->nodelists[node] = &initkmem_list3[index + node];
-		cachep->nodelists[node]->next_reap = jiffies +
-		    REAPTIMEOUT_LIST3 +
-		    ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
-	}
-}
-
-static void __kmem_cache_destroy(struct kmem_cache *cachep)
-{
-	int i;
-	struct kmem_list3 *l3;
-
-	for_each_online_cpu(i)
-	    kfree(cachep->array[i]);
-
-	/* NUMA: free the list3 structures */
-	for_each_online_node(i) {
-		l3 = cachep->nodelists[i];
-		if (l3) {
-			kfree(l3->shared);
-			free_alien_cache(l3->alien);
-			kfree(l3);
-		}
-	}
-	kmem_cache_free(&cache_cache, cachep);
-}
-
-
-/**
- * calculate_slab_order - calculate size (page order) of slabs
- * @cachep: pointer to the cache that is being created
- * @size: size of objects to be created in this cache.
- * @align: required alignment for the objects.
- * @flags: slab allocation flags
- *
- * Also calculates the number of objects per slab.
- *
- * This could be made much more intelligent.  For now, try to avoid using
- * high order pages for slabs.  When the gfp() functions are more friendly
- * towards high-order requests, this should be changed.
- */
-static size_t calculate_slab_order(struct kmem_cache *cachep,
-			size_t size, size_t align, unsigned long flags)
-{
-	unsigned long offslab_limit;
-	size_t left_over = 0;
-	int gfporder;
-
-	for (gfporder = 0; gfporder <= KMALLOC_MAX_ORDER; gfporder++) {
-		unsigned int num;
-		size_t remainder;
-
-		cache_estimate(gfporder, size, align, flags, &remainder, &num);
-		if (!num)
-			continue;
-
-		if (flags & CFLGS_OFF_SLAB) {
-			/*
-			 * Max number of objs-per-slab for caches which
-			 * use off-slab slabs. Needed to avoid a possible
-			 * looping condition in cache_grow().
-			 */
-			offslab_limit = size - sizeof(struct slab);
-			offslab_limit /= sizeof(kmem_bufctl_t);
-
- 			if (num > offslab_limit)
-				break;
-		}
-
-		/* Found something acceptable - save it away */
-		cachep->num = num;
-		cachep->gfporder = gfporder;
-		left_over = remainder;
-
-		/*
-		 * A VFS-reclaimable slab tends to have most allocations
-		 * as GFP_NOFS and we really don't want to have to be allocating
-		 * higher-order pages when we are unable to shrink dcache.
-		 */
-		if (flags & SLAB_RECLAIM_ACCOUNT)
-			break;
-
-		/*
-		 * Large number of objects is good, but very large slabs are
-		 * currently bad for the gfp()s.
-		 */
-		if (gfporder >= slab_break_gfp_order)
-			break;
-
-		/*
-		 * Acceptable internal fragmentation?
-		 */
-		if (left_o