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
|
// SPDX-License-Identifier: GPL-2.0-or-later
#include <linux/blkdev.h>
#include <linux/dax.h>
#include <linux/vmalloc.h>
#include <linux/parser.h>
#include "cache_dev.h"
#include "backing_dev.h"
#include "cache.h"
#include "dm_pcache.h"
static void cache_dev_dax_exit(struct pcache_cache_dev *cache_dev)
{
if (cache_dev->use_vmap)
vunmap(cache_dev->mapping);
}
static int build_vmap(struct dax_device *dax_dev, long total_pages, void **vaddr)
{
struct page **pages;
long i = 0, chunk;
unsigned long pfn;
int ret;
pages = vmalloc_array(total_pages, sizeof(struct page *));
if (!pages)
return -ENOMEM;
do {
chunk = dax_direct_access(dax_dev, i, total_pages - i,
DAX_ACCESS, NULL, &pfn);
if (chunk <= 0) {
ret = chunk ? chunk : -EINVAL;
goto out_free;
}
if (!pfn_valid(pfn)) {
ret = -EOPNOTSUPP;
goto out_free;
}
while (chunk-- && i < total_pages) {
pages[i++] = pfn_to_page(pfn);
pfn++;
if (!(i & 15))
cond_resched();
}
} while (i < total_pages);
*vaddr = vmap(pages, total_pages, VM_MAP, PAGE_KERNEL);
if (!*vaddr) {
ret = -ENOMEM;
goto out_free;
}
ret = 0;
out_free:
vfree(pages);
return ret;
}
static int cache_dev_dax_init(struct pcache_cache_dev *cache_dev)
{
struct dm_pcache *pcache = CACHE_DEV_TO_PCACHE(cache_dev);
struct dax_device *dax_dev;
long total_pages, mapped_pages;
u64 bdev_size;
void *vaddr;
int ret;
int id;
unsigned long pfn;
dax_dev = cache_dev->dm_dev->dax_dev;
/* total size check */
bdev_size = bdev_nr_bytes(cache_dev->dm_dev->bdev);
if (bdev_size < PCACHE_CACHE_DEV_SIZE_MIN) {
pcache_dev_err(pcache, "dax device is too small, required at least %llu",
PCACHE_CACHE_DEV_SIZE_MIN);
ret = -ENOSPC;
goto out;
}
total_pages = bdev_size >> PAGE_SHIFT;
/* attempt: direct-map the whole range */
id = dax_read_lock();
mapped_pages = dax_direct_access(dax_dev, 0, total_pages,
DAX_ACCESS, &vaddr, &pfn);
if (mapped_pages < 0) {
pcache_dev_err(pcache, "dax_direct_access failed: %ld\n", mapped_pages);
ret = mapped_pages;
goto unlock;
}
if (!pfn_valid(pfn)) {
ret = -EOPNOTSUPP;
goto unlock;
}
if (mapped_pages == total_pages) {
/* success: contiguous direct mapping */
cache_dev->mapping = vaddr;
} else {
/* need vmap fallback */
ret = build_vmap(dax_dev, total_pages, &vaddr);
if (ret) {
pcache_dev_err(pcache, "vmap fallback failed: %d\n", ret);
goto unlock;
}
cache_dev->mapping = vaddr;
cache_dev->use_vmap = true;
}
dax_read_unlock(id);
return 0;
unlock:
dax_read_unlock(id);
out:
return ret;
}
void cache_dev_zero_range(struct pcache_cache_dev *cache_dev, void *pos, u32 size)
{
memset(pos, 0, size);
dax_flush(cache_dev->dm_dev->dax_dev, pos, size);
}
static int sb_read(struct pcache_cache_dev *cache_dev, struct pcache_sb *sb)
{
struct pcache_sb *sb_addr = CACHE_DEV_SB(cache_dev);
if (copy_mc_to_kernel(sb, sb_addr, sizeof(struct pcache_sb)))
return -EIO;
return 0;
}
static void sb_write(struct pcache_cache_dev *cache_dev, struct pcache_sb *sb)
{
struct pcache_sb *sb_addr = CACHE_DEV_SB(cache_dev);
memcpy_flushcache(sb_addr, sb, sizeof(struct pcache_sb));
pmem_wmb();
}
static int sb_init(struct pcache_cache_dev *cache_dev, struct pcache_sb *sb)
{
struct dm_pcache *pcache = CACHE_DEV_TO_PCACHE(cache_dev);
u64 nr_segs;
u64 cache_dev_size;
u64 magic;
u32 flags = 0;
magic = le64_to_cpu(sb->magic);
if (magic)
return -EEXIST;
cache_dev_size = bdev_nr_bytes(file_bdev(cache_dev->dm_dev->bdev_file));
if (cache_dev_size < PCACHE_CACHE_DEV_SIZE_MIN) {
pcache_dev_err(pcache, "dax device is too small, required at least %llu",
PCACHE_CACHE_DEV_SIZE_MIN);
return -ENOSPC;
}
nr_segs = (cache_dev_size - PCACHE_SEGMENTS_OFF) / ((PCACHE_SEG_SIZE));
#if defined(__BYTE_ORDER) ? (__BIG_ENDIAN == __BYTE_ORDER) : defined(__BIG_ENDIAN)
flags |= PCACHE_SB_F_BIGENDIAN;
#endif
sb->flags = cpu_to_le32(flags);
sb->magic = cpu_to_le64(PCACHE_MAGIC);
sb->seg_num = cpu_to_le32(nr_segs);
sb->crc = cpu_to_le32(crc32c(PCACHE_CRC_SEED, (void *)(sb) + 4, sizeof(struct pcache_sb) - 4));
cache_dev_zero_range(cache_dev, CACHE_DEV_CACHE_INFO(cache_dev),
PCACHE_CACHE_INFO_SIZE * PCACHE_META_INDEX_MAX +
PCACHE_CACHE_CTRL_SIZE);
return 0;
}
static int sb_validate(struct pcache_cache_dev *cache_dev, struct pcache_sb *sb)
{
struct dm_pcache *pcache = CACHE_DEV_TO_PCACHE(cache_dev);
u32 flags;
u32 crc;
if (le64_to_cpu(sb->magic) != PCACHE_MAGIC) {
pcache_dev_err(pcache, "unexpected magic: %llx\n",
le64_to_cpu(sb->magic));
return -EINVAL;
}
crc = crc32c(PCACHE_CRC_SEED, (void *)(sb) + 4, sizeof(struct pcache_sb) - 4);
if (crc != le32_to_cpu(sb->crc)) {
pcache_dev_err(pcache, "corrupted sb: %u, expected: %u\n", crc, le32_to_cpu(sb->crc));
return -EINVAL;
}
flags = le32_to_cpu(sb->flags);
#if defined(__BYTE_ORDER) ? (__BIG_ENDIAN == __BYTE_ORDER) : defined(__BIG_ENDIAN)
if (!(flags & PCACHE_SB_F_BIGENDIAN)) {
pcache_dev_err(pcache, "cache_dev is not big endian\n");
return -EINVAL;
}
#else
if (flags & PCACHE_SB_F_BIGENDIAN) {
pcache_dev_err(pcache, "cache_dev is big endian\n");
return -EINVAL;
}
#endif
return 0;
}
static int cache_dev_init(struct pcache_cache_dev *cache_dev, u32 seg_num)
{
cache_dev->seg_num = seg_num;
cache_dev->seg_bitmap = kvcalloc(BITS_TO_LONGS(cache_dev->seg_num), sizeof(unsigned long), GFP_KERNEL);
if (!cache_dev->seg_bitmap)
return -ENOMEM;
return 0;
}
static void cache_dev_exit(struct pcache_cache_dev *cache_dev)
{
kvfree(cache_dev->seg_bitmap);
}
void cache_dev_stop(struct dm_pcache *pcache)
{
struct pcache_cache_dev *cache_dev = &pcache->cache_dev;
cache_dev_exit(cache_dev);
cache_dev_dax_exit(cache_dev);
}
int cache_dev_start(struct dm_pcache *pcache)
{
struct pcache_cache_dev *cache_dev = &pcache->cache_dev;
struct pcache_sb sb;
bool format = false;
int ret;
mutex_init(&cache_dev->seg_lock);
ret = cache_dev_dax_init(cache_dev);
if (ret) {
pcache_dev_err(pcache, "failed to init cache_dev %s via dax way: %d.",
cache_dev->dm_dev->name, ret);
goto err;
}
ret = sb_read(cache_dev, &sb);
if (ret)
goto dax_release;
if (le64_to_cpu(sb.magic) == 0) {
format = true;
ret = sb_init(cache_dev, &sb);
if (ret < 0)
goto dax_release;
}
ret = sb_validate(cache_dev, &sb);
if (ret)
goto dax_release;
cache_dev->sb_flags = le32_to_cpu(sb.flags);
ret = cache_dev_init(cache_dev, le32_to_cpu(sb.seg_num));
if (ret)
goto dax_release;
if (format)
sb_write(cache_dev, &sb);
return 0;
dax_release:
cache_dev_dax_exit(cache_dev);
err:
return ret;
}
int cache_dev_get_empty_segment_id(struct pcache_cache_dev *cache_dev, u32 *seg_id)
{
int ret;
mutex_lock(&cache_dev->seg_lock);
*seg_id = find_next_zero_bit(cache_dev->seg_bitmap, cache_dev->seg_num, 0);
if (*seg_id == cache_dev->seg_num) {
ret = -ENOSPC;
goto unlock;
}
__set_bit(*seg_id, cache_dev->seg_bitmap);
ret = 0;
unlock:
mutex_unlock(&cache_dev->seg_lock);
return ret;
}
|
