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
|
// SPDX-License-Identifier: GPL-2.0
#include <stdlib.h>
#include <string.h>
#include <malloc.h>
#include <pthread.h>
#include <unistd.h>
#include <assert.h>
#include <linux/gfp.h>
#include <linux/poison.h>
#include <linux/slab.h>
#include <linux/radix-tree.h>
#include <urcu/uatomic.h>
int nr_allocated;
int preempt_count;
int test_verbose;
struct kmem_cache {
pthread_mutex_t lock;
unsigned int size;
unsigned int align;
int nr_objs;
void *objs;
void (*ctor)(void *);
unsigned int non_kernel;
unsigned long nr_allocated;
unsigned long nr_tallocated;
};
void kmem_cache_set_non_kernel(struct kmem_cache *cachep, unsigned int val)
{
cachep->non_kernel = val;
}
unsigned long kmem_cache_get_alloc(struct kmem_cache *cachep)
{
return cachep->size * cachep->nr_allocated;
}
unsigned long kmem_cache_nr_allocated(struct kmem_cache *cachep)
{
return cachep->nr_allocated;
}
unsigned long kmem_cache_nr_tallocated(struct kmem_cache *cachep)
{
return cachep->nr_tallocated;
}
void kmem_cache_zero_nr_tallocated(struct kmem_cache *cachep)
{
cachep->nr_tallocated = 0;
}
void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
int gfp)
{
void *p;
if (!(gfp & __GFP_DIRECT_RECLAIM)) {
if (!cachep->non_kernel)
return NULL;
cachep->non_kernel--;
}
pthread_mutex_lock(&cachep->lock);
if (cachep->nr_objs) {
struct radix_tree_node *node = cachep->objs;
cachep->nr_objs--;
cachep->objs = node->parent;
pthread_mutex_unlock(&cachep->lock);
node->parent = NULL;
p = node;
} else {
pthread_mutex_unlock(&cachep->lock);
if (cachep->align)
posix_memalign(&p, cachep->align, cachep->size);
else
p = malloc(cachep->size);
if (cachep->ctor)
cachep->ctor(p);
else if (gfp & __GFP_ZERO)
memset(p, 0, cachep->size);
}
uatomic_inc(&cachep->nr_allocated);
uatomic_inc(&nr_allocated);
uatomic_inc(&cachep->nr_tallocated);
if (kmalloc_verbose)
printf("Allocating %p from slab\n", p);
return p;
}
void __kmem_cache_free_locked(struct kmem_cache *cachep, void *objp)
{
assert(objp);
if (cachep->nr_objs > 10 || cachep->align) {
memset(objp, POISON_FREE, cachep->size);
free(objp);
} else {
struct radix_tree_node *node = objp;
cachep->nr_objs++;
node->parent = cachep->objs;
cachep->objs = node;
}
}
void kmem_cache_free_locked(struct kmem_cache *cachep, void *objp)
{
uatomic_dec(&nr_allocated);
uatomic_dec(&cachep->nr_allocated);
if (kmalloc_verbose)
printf("Freeing %p to slab\n", objp);
__kmem_cache_free_locked(cachep, objp);
}
void kmem_cache_free(struct kmem_cache *cachep, void *objp)
{
pthread_mutex_lock(&cachep->lock);
kmem_cache_free_locked(cachep, objp);
pthread_mutex_unlock(&cachep->lock);
}
void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list)
{
if (kmalloc_verbose)
pr_debug("Bulk free %p[0-%lu]\n", list, size - 1);
pthread_mutex_lock(&cachep->lock);
for (int i = 0; i < size; i++)
kmem_cache_free_locked(cachep, list[i]);
pthread_mutex_unlock(&cachep->lock);
}
void kmem_cache_shrink(struct kmem_cache *cachep)
{
}
int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
void **p)
{
size_t i;
if (kmalloc_verbose)
pr_debug("Bulk alloc %lu\n", size);
pthread_mutex_lock(&cachep->lock);
if (cachep->nr_objs >= size) {
struct radix_tree_node *node;
for (i = 0; i < size; i++) {
if (!(gfp & __GFP_DIRECT_RECLAIM)) {
if (!cachep->non_kernel)
break;
cachep->non_kernel--;
}
node = cachep->objs;
cachep->nr_objs--;
cachep->objs = node->parent;
p[i] = node;
node->parent = NULL;
}
pthread_mutex_unlock(&cachep->lock);
} else {
pthread_mutex_unlock(&cachep->lock);
for (i = 0; i < size; i++) {
if (!(gfp & __GFP_DIRECT_RECLAIM)) {
if (!cachep->non_kernel)
break;
cachep->non_kernel--;
}
if (cachep->align) {
posix_memalign(&p[i], cachep->align,
cachep->size);
} else {
p[i] = malloc(cachep->size);
if (!p[i])
break;
}
if (cachep->ctor)
cachep->ctor(p[i]);
else if (gfp & __GFP_ZERO)
memset(p[i], 0, cachep->size);
}
}
if (i < size) {
size = i;
pthread_mutex_lock(&cachep->lock);
for (i = 0; i < size; i++)
__kmem_cache_free_locked(cachep, p[i]);
pthread_mutex_unlock(&cachep->lock);
return 0;
}
for (i = 0; i < size; i++) {
uatomic_inc(&nr_allocated);
uatomic_inc(&cachep->nr_allocated);
uatomic_inc(&cachep->nr_tallocated);
if (kmalloc_verbose)
printf("Allocating %p from slab\n", p[i]);
}
return size;
}
struct kmem_cache *
kmem_cache_create(const char *name, unsigned int size, unsigned int align,
unsigned int flags, void (*ctor)(void *))
{
struct kmem_cache *ret = malloc(sizeof(*ret));
pthread_mutex_init(&ret->lock, NULL);
ret->size = size;
ret->align = align;
ret->nr_objs = 0;
ret->nr_allocated = 0;
ret->nr_tallocated = 0;
ret->objs = NULL;
ret->ctor = ctor;
ret->non_kernel = 0;
return ret;
}
/*
* Test the test infrastructure for kem_cache_alloc/free and bulk counterparts.
*/
void test_kmem_cache_bulk(void)
{
int i;
void *list[12];
static struct kmem_cache *test_cache, *test_cache2;
/*
* Testing the bulk allocators without aligned kmem_cache to force the
* bulk alloc/free to reuse
*/
test_cache = kmem_cache_create("test_cache", 256, 0, SLAB_PANIC, NULL);
for (i = 0; i < 5; i++)
list[i] = kmem_cache_alloc(test_cache, __GFP_DIRECT_RECLAIM);
for (i = 0; i < 5; i++)
kmem_cache_free(test_cache, list[i]);
assert(test_cache->nr_objs == 5);
kmem_cache_alloc_bulk(test_cache, __GFP_DIRECT_RECLAIM, 5, list);
kmem_cache_free_bulk(test_cache, 5, list);
for (i = 0; i < 12 ; i++)
list[i] = kmem_cache_alloc(test_cache, __GFP_DIRECT_RECLAIM);
for (i = 0; i < 12; i++)
kmem_cache_free(test_cache, list[i]);
/* The last free will not be kept around */
assert(test_cache->nr_objs == 11);
/* Aligned caches will immediately free */
test_cache2 = kmem_cache_create("test_cache2", 128, 128, SLAB_PANIC, NULL);
kmem_cache_alloc_bulk(test_cache2, __GFP_DIRECT_RECLAIM, 10, list);
kmem_cache_free_bulk(test_cache2, 10, list);
assert(!test_cache2->nr_objs);
}
|