/*
* 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 */
+ ALLOC_SLOWPATH, /* Allocation by getting a new cpu slab */
+ FREE_FASTPATH, /* Free to cpu slub */
+ FREE_SLOWPATH, /* Freeing not to cpu slab */
+ FREE_FROZEN, /* Freeing to frozen slab */
+ FREE_ADD_PARTIAL, /* Freeing moves slab to partial list */
+ FREE_REMOVE_PARTIAL, /* Freeing removes last object */
+ ALLOC_FROM_PARTIAL, /* Cpu slab acquired from partial list */
+ ALLOC_SLAB, /* Cpu slab acquired from page allocator */
+ ALLOC_REFILL, /* Refill cpu slab from slab freelist */
+ FREE_SLAB, /* Slab freed to the page allocator */
+ CPUSLAB_FLUSH, /* Abandoning of the cpu slab */
+ DEACTIVATE_FULL, /* Cpu slab was full when deactivated */
+ DEACTIVATE_EMPTY, /* Cpu slab was empty when deactivated */
+ 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 {
+ void **freelist; /* Pointer to first free per cpu object */
+ struct page *page; /* The slab from which we are allocating */
+ int node; /* The node of the page (or -1 for debug) */
+#ifdef CONFIG_SLUB_STATS
+ unsigned stat[NR_SLUB_STAT_ITEMS];
+#endif
+};
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 {
+ struct kmem_cache_cpu *cpu_slab;
/* 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. */
- unsigned 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)(void *, struct kmem_cache *, unsigned long);
- void (*dtor)(void *, struct kmem_cache *, unsigned long);
+ 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
struct kobject kobj; /* For sysfs */
+#endif
#ifdef CONFIG_NUMA
- int defrag_ratio;
+ /*
+ * Defragmentation by allocating from a remote node.
+ */
+ int remote_node_defrag_ratio;
struct kmem_cache_node *node[MAX_NUMNODES];
#endif
- struct page *cpu_slab[NR_CPUS];
};
/*
* Kmalloc subsystem.
*/
-#define KMALLOC_SHIFT_LOW 3
-
-#ifdef CONFIG_LARGE_ALLOCS
-#define KMALLOC_SHIFT_HIGH 25
+#if defined(ARCH_KMALLOC_MINALIGN) && ARCH_KMALLOC_MINALIGN > 8
+#define KMALLOC_MIN_SIZE ARCH_KMALLOC_MINALIGN
#else
-#if !defined(CONFIG_MMU) || NR_CPUS > 512 || MAX_NUMNODES > 256
-#define KMALLOC_SHIFT_HIGH 20
-#else
-#define KMALLOC_SHIFT_HIGH 18
+#define KMALLOC_MIN_SIZE 8
#endif
+
+#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)
+
+#ifdef CONFIG_ZONE_DMA
+#define SLUB_DMA __GFP_DMA
+/* Reserve extra caches for potential DMA use */
+#define KMALLOC_CACHES (2 * SLUB_PAGE_SHIFT - 6)
+#else
+/* Disable DMA functionality */
+#define SLUB_DMA (__force gfp_t)0
+#define KMALLOC_CACHES SLUB_PAGE_SHIFT
#endif
/*
* 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[KMALLOC_SHIFT_HIGH + 1];
+extern struct kmem_cache kmalloc_caches[KMALLOC_CACHES];
/*
* Sorry that the following has to be that ugly but some versions of GCC
* have trouble with constant propagation and loops.
*/
-static inline int kmalloc_index(int size)
+static __always_inline int kmalloc_index(size_t size)
{
- /*
- * We should return 0 if size == 0 but we use the smallest object
- * here for SLAB legacy reasons.
- */
- WARN_ON_ONCE(size == 0);
+ if (!size)
+ return 0;
- if (size > 64 && size <= 96)
+ if (size <= KMALLOC_MIN_SIZE)
+ return KMALLOC_SHIFT_LOW;
+
+ 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 <= 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 <= 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 KMALLOC_SHIFT_HIGH > 18
- if (size <= 512 * 1024) return 19;
+ if (size <= 512 * 1024) return 19;
if (size <= 1024 * 1024) return 20;
-#endif
-#if KMALLOC_SHIFT_HIGH > 20
if (size <= 2 * 1024 * 1024) return 21;
- if (size <= 4 * 1024 * 1024) return 22;
- if (size <= 8 * 1024 * 1024) return 23;
- if (size <= 16 * 1024 * 1024) return 24;
- if (size <= 32 * 1024 * 1024) return 25;
-#endif
return -1;
/*
* This ought to end up with a global pointer to the right cache
* in kmalloc_caches.
*/
-static inline struct kmem_cache *kmalloc_slab(size_t size)
+static __always_inline struct kmem_cache *kmalloc_slab(size_t size)
{
int index = kmalloc_index(size);
if (index == 0)
return NULL;
- if (index < 0) {
- /*
- * Generate a link failure. Would be great if we could
- * do something to stop the compile here.
- */
- extern void __kmalloc_size_too_large(void);
- __kmalloc_size_too_large();
- }
return &kmalloc_caches[index];
}
-#ifdef CONFIG_ZONE_DMA
-#define SLUB_DMA __GFP_DMA
+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
-/* Disable DMA functionality */
-#define SLUB_DMA 0
+static __always_inline void *
+kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags)
+{
+ return kmem_cache_alloc(s, gfpflags);
+}
#endif
-static inline void *kmalloc(size_t size, gfp_t flags)
+static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
{
- if (__builtin_constant_p(size) && !(flags & SLUB_DMA)) {
- struct kmem_cache *s = kmalloc_slab(size);
+ unsigned int order = get_order(size);
+ void *ret = (void *) __get_free_pages(flags | __GFP_COMP, order);
- if (!s)
- return NULL;
+ kmemleak_alloc(ret, size, 1, flags);
+ trace_kmalloc(_THIS_IP_, ret, size, PAGE_SIZE << order, flags);
- return kmem_cache_alloc(s, flags);
- } else
- return __kmalloc(size, flags);
+ return ret;
}
-static inline void *kzalloc(size_t size, gfp_t flags)
+static __always_inline void *kmalloc(size_t size, gfp_t flags)
{
- if (__builtin_constant_p(size) && !(flags & SLUB_DMA)) {
- struct kmem_cache *s = kmalloc_slab(size);
+ void *ret;
- if (!s)
- return NULL;
+ if (__builtin_constant_p(size)) {
+ if (size > SLUB_MAX_SIZE)
+ return kmalloc_large(size, flags);
- return kmem_cache_zalloc(s, flags);
- } else
- return __kzalloc(size, flags);
+ if (!(flags & SLUB_DMA)) {
+ struct kmem_cache *s = kmalloc_slab(size);
+
+ if (!s)
+ return ZERO_SIZE_PTR;
+
+ ret = kmem_cache_alloc_notrace(s, flags);
+
+ trace_kmalloc(_THIS_IP_, ret, size, s->size, flags);
+
+ return ret;
+ }
+ }
+ return __kmalloc(size, flags);
}
#ifdef CONFIG_NUMA
-extern void *__kmalloc_node(size_t size, gfp_t flags, int node);
+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 inline void *kmalloc_node(size_t size, gfp_t flags, int node)
+static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
{
- if (__builtin_constant_p(size) && !(flags & SLUB_DMA)) {
- struct kmem_cache *s = kmalloc_slab(size);
+ void *ret;
+
+ if (__builtin_constant_p(size) &&
+ size <= SLUB_MAX_SIZE && !(flags & SLUB_DMA)) {
+ struct kmem_cache *s = kmalloc_slab(size);
if (!s)
- return NULL;
+ return ZERO_SIZE_PTR;
- return kmem_cache_alloc_node(s, flags, node);
- } else
- return __kmalloc_node(size, 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);
}
#endif
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff