/*
* SLUB : A Slab allocator without object queues.
*
- * (C) 2007 SGI, Christoph Lameter <clameter@sgi.com>
+ * (C) 2007 SGI, Christoph Lameter
*/
#include <linux/types.h>
#include <linux/gfp.h>
#include <linux/workqueue.h>
#include <linux/kobject.h>
+#include <linux/kmemtrace.h>
+#include <linux/kmemleak.h>
enum stat_item {
ALLOC_FASTPATH, /* Allocation from cpu slab */
DEACTIVATE_TO_HEAD, /* Cpu slab was moved to the head of partials */
DEACTIVATE_TO_TAIL, /* Cpu slab was moved to the tail of partials */
DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */
+ ORDER_FALLBACK, /* Number of times fallback was necessary */
NR_SLUB_STAT_ITEMS };
struct kmem_cache_cpu {
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
+ atomic_long_t nr_slabs;
+ atomic_long_t total_objects;
struct list_head full;
#endif
};
/*
+ * Word size structure that can be atomically updated or read and that
+ * contains both the order and the number of objects that a slab of the
+ * given order would contain.
+ */
+struct kmem_cache_order_objects {
+ unsigned long x;
+};
+
+/*
* Slab cache management.
*/
struct kmem_cache {
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;
+ struct kmem_cache_order_objects oo;
/*
* Avoid an extra cache line for UP, SMP and for the node local to
struct kmem_cache_node local_node;
/* Allocation and freeing of slabs */
- int objects; /* Number of objects in slab */
+ struct kmem_cache_order_objects max;
+ struct kmem_cache_order_objects min;
gfp_t allocflags; /* gfp flags to use on each alloc */
int refcount; /* Refcount for slab cache destroy */
- void (*ctor)(struct kmem_cache *, void *);
+ void (*ctor)(void *);
int inuse; /* Offset to metadata */
int align; /* Alignment */
+ unsigned long min_partial;
const char *name; /* Name (only for display!) */
struct list_head list; /* List of slab caches */
#ifdef CONFIG_SLUB_DEBUG
#define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE)
/*
+ * Maximum kmalloc object size handled by SLUB. Larger object allocations
+ * are passed through to the page allocator. The page allocator "fastpath"
+ * is relatively slow so we need this value sufficiently high so that
+ * performance critical objects are allocated through the SLUB fastpath.
+ *
+ * This should be dropped to PAGE_SIZE / 2 once the page allocator
+ * "fastpath" becomes competitive with the slab allocator fastpaths.
+ */
+#define SLUB_MAX_SIZE (2 * PAGE_SIZE)
+
+#define SLUB_PAGE_SHIFT (PAGE_SHIFT + 2)
+
+/*
* 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 + 1];
+extern struct kmem_cache kmalloc_caches[SLUB_PAGE_SHIFT];
/*
* Sorry that the following has to be that ugly but some versions of GCC
if (size <= KMALLOC_MIN_SIZE)
return KMALLOC_SHIFT_LOW;
- if (size > 64 && size <= 96)
+ if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96)
return 1;
- if (size > 128 && size <= 192)
+ if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192)
return 2;
if (size <= 8) return 3;
if (size <= 16) return 4;
if (size <= 512) return 9;
if (size <= 1024) return 10;
if (size <= 2 * 1024) return 11;
+ if (size <= 4 * 1024) return 12;
/*
* 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;
void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
void *__kmalloc(size_t size, gfp_t flags);
+#ifdef CONFIG_TRACING
+extern void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags);
+#else
+static __always_inline void *
+kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags)
+{
+ return kmem_cache_alloc(s, gfpflags);
+}
+#endif
+
static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
{
- return (void *)__get_free_pages(flags | __GFP_COMP, get_order(size));
+ unsigned int order = get_order(size);
+ void *ret = (void *) __get_free_pages(flags | __GFP_COMP, order);
+
+ kmemleak_alloc(ret, size, 1, flags);
+ trace_kmalloc(_THIS_IP_, ret, size, PAGE_SIZE << order, flags);
+
+ return ret;
}
static __always_inline void *kmalloc(size_t size, gfp_t flags)
{
+ void *ret;
+
if (__builtin_constant_p(size)) {
- if (size > PAGE_SIZE)
+ if (size > SLUB_MAX_SIZE)
return kmalloc_large(size, flags);
if (!(flags & SLUB_DMA)) {
if (!s)
return ZERO_SIZE_PTR;
- return kmem_cache_alloc(s, flags);
+ ret = kmem_cache_alloc_notrace(s, flags);
+
+ trace_kmalloc(_THIS_IP_, ret, size, s->size, flags);
+
+ return ret;
}
}
return __kmalloc(size, flags);
void *__kmalloc_node(size_t size, gfp_t flags, int node);
void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
+#ifdef CONFIG_TRACING
+extern void *kmem_cache_alloc_node_notrace(struct kmem_cache *s,
+ gfp_t gfpflags,
+ int node);
+#else
+static __always_inline void *
+kmem_cache_alloc_node_notrace(struct kmem_cache *s,
+ gfp_t gfpflags,
+ int node)
+{
+ return kmem_cache_alloc_node(s, gfpflags, node);
+}
+#endif
+
static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
{
+ void *ret;
+
if (__builtin_constant_p(size) &&
- size <= PAGE_SIZE && !(flags & SLUB_DMA)) {
+ size <= SLUB_MAX_SIZE && !(flags & SLUB_DMA)) {
struct kmem_cache *s = kmalloc_slab(size);
if (!s)
return ZERO_SIZE_PTR;
- return kmem_cache_alloc_node(s, flags, node);
+ ret = kmem_cache_alloc_node_notrace(s, flags, node);
+
+ trace_kmalloc_node(_THIS_IP_, ret,
+ size, s->size, flags, node);
+
+ return ret;
}
return __kmalloc_node(size, flags, node);
}