summaryrefslogtreecommitdiffstats
path: root/include/linux/slub_def.h
blob: 4b35c06dfbc5448b46b85422659f5552af817c37 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
#ifndef _LINUX_SLUB_DEF_H
#define _LINUX_SLUB_DEF_H

/*
 * SLUB : A Slab allocator without object queues.
 *
 * (C) 2007 SGI, Christoph Lameter
 */
#include <linux/types.h>
#include <linux/gfp.h>
#include <linux/workqueue.h>
#include <linux/kobject.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 */
	CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */
	NR_SLUB_STAT_ITEMS };

struct kmem_cache_cpu {
	void **freelist;	/* Pointer to next available object */
	unsigned long tid;	/* Globally unique transaction id */
	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;
	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 __percpu *cpu_slab;
	/* Used for retriving partial slabs etc */
	unsigned long flags;
	unsigned long min_partial;
	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. */
	struct kmem_cache_order_objects oo;

	/* Allocation and freeing of slabs */
	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 *);
	int inuse;		/* Offset to metadata */
	int align;		/* Alignment */
	int reserved;		/* Reserved bytes at the end of slabs */
	const char *name;	/* Name (only for display!) */
	struct list_head list;	/* List of slab caches */
#ifdef CONFIG_SYSFS
	struct kobject kobj;	/* For sysfs */
#endif

#ifdef CONFIG_NUMA
	/*
	 * Defragmentation by allocating from a remote node.
	 */
	int remote_node_defrag_ratio;
#endif
	struct kmem_cache_node *node[MAX_NUMNODES];
};

/*
 * Kmalloc subsystem.
 */
#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8
#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN
#else
#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
#else
/* Disable DMA functionality */
#define SLUB_DMA (__force gfp_t)0
#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[SLUB_PAGE_SHIFT];

/*
 * Sorry that the following has to be that ugly but some versions of GCC
 * have trouble with constant propagation and loops.
 */
static __always_inline int kmalloc_index(size_t size)
{
	if (!size)
		return 0;

	if (size <= KMALLOC_MIN_SIZE)
		return KMALLOC_SHIFT_LOW;

	if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96)
		return 1;
	if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192)
		return 2;
	if (size <=          8) return 3;
	if (size <=         16) return 4;
	if (size <=         32) return 5;
	if (size <=         64) return 6;
	if (size <=        128) return 7;
	if (size <=        256) return 8;
	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. We need to support 2 * PAGE_SIZE here. So for a 64k page
 * size we would have to go up to 128k.
 */
	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 (size <= 512 * 1024) return 19;
	if (size <= 1024 * 1024) return 20;
	if (size <=  2 * 1024 * 1024) return 21;
	BUG();
	return -1; /* Will never be reached */

/*
 * What we really wanted to do and cannot do because of compiler issues is:
 *	int i;
 *	for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++)
 *		if (size <= (1 << i))
 *			return i;
 */
}

/*
 * Find the slab cache for a given combination of allocation flags and size.
 *
 * This ought to end up with a global pointer to the right cache
 * in kmalloc_caches.
 */
static __always_inline struct kmem_cache *kmalloc_slab(size_t size)
{
	int index = kmalloc_index(size);

	if (index == 0)
		return NULL;

	return kmalloc_caches[index];
}

void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
void *__kmalloc(size_t size, gfp_t flags);

static __always_inline void *
kmalloc_order(size_t size, gfp_t flags, unsigned int order)
{
	void *ret = (void *) __get_free_pages(flags | __GFP_COMP, order);
	kmemleak_alloc(ret, size, 1, flags);
	return ret;
}

/**
 * Calling this on allocated memory will check that the memory
 * is expected to be in use, and print warnings if not.
 */
#ifdef CONFIG_SLUB_DEBUG
extern bool verify_mem_not_deleted(const void *x);
#else
static inline bool verify_mem_not_deleted(const void *x)
{
	return true;
}
#endif

#ifdef CONFIG_TRACING
extern void *
kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size);
extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order);
#else
static __always_inline void *
kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
{
	return kmem_cache_alloc(s, gfpflags);
}

static __always_inline void *
kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order)
{
	return kmalloc_order(size, flags, order);
}
#endif

static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
{
	unsigned int order = get_order(size);
	return kmalloc_order_trace(size, flags, order);
}

static __always_inline void *kmalloc(size_t size, gfp_t flags)
{
	if (__builtin_constant_p(size)) {
		if (size > SLUB_MAX_SIZE)
			return kmalloc_large(size, flags);

		if (!(flags & SLUB_DMA)) {
			struct kmem_cache *s = kmalloc_slab(size);

			if (!s)
				return ZERO_SIZE_PTR;

			return kmem_cache_alloc_trace(s, flags, size);
		}
	}
	return __kmalloc(size, flags);
}

#ifdef CONFIG_NUMA
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_trace(struct kmem_cache *s,
					   gfp_t gfpflags,
					   int node, size_t size);
#else
static __always_inline void *
kmem_cache_alloc_node_trace(struct kmem_cache *s,
			      gfp_t gfpflags,
			      int node, size_t size)
{
	return kmem_cache_alloc_node(s, gfpflags, node);
}
#endif

static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
{
	if (__builtin_constant_p(size) &&
		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_trace(s, flags, node, size);
	}
	return __kmalloc_node(size, flags, node);
}
#endif

#endif /* _LINUX_SLUB_DEF_H */