summaryrefslogtreecommitdiffstats
path: root/block/qcow2-cache.c
blob: 86dd7f2bd9e2ce4a99d764c2d8bbd3c98d04ea69 (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
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
/*
 * L2/refcount table cache for the QCOW2 format
 *
 * Copyright (c) 2010 Kevin Wolf <kwolf@redhat.com>
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

/* Needed for CONFIG_MADVISE */
#include "config-host.h"

#if defined(CONFIG_MADVISE) || defined(CONFIG_POSIX_MADVISE)
#include <sys/mman.h>
#endif

#include "block/block_int.h"
#include "qemu-common.h"
#include "qemu/osdep.h"
#include "qcow2.h"
#include "trace.h"

typedef struct Qcow2CachedTable {
    int64_t  offset;
    uint64_t lru_counter;
    int      ref;
    bool     dirty;
} Qcow2CachedTable;

struct Qcow2Cache {
    Qcow2CachedTable       *entries;
    struct Qcow2Cache      *depends;
    int                     size;
    bool                    depends_on_flush;
    void                   *table_array;
    uint64_t                lru_counter;
    uint64_t                cache_clean_lru_counter;
};

static inline void *qcow2_cache_get_table_addr(BlockDriverState *bs,
                    Qcow2Cache *c, int table)
{
    BDRVQcow2State *s = bs->opaque;
    return (uint8_t *) c->table_array + (size_t) table * s->cluster_size;
}

static inline int qcow2_cache_get_table_idx(BlockDriverState *bs,
                  Qcow2Cache *c, void *table)
{
    BDRVQcow2State *s = bs->opaque;
    ptrdiff_t table_offset = (uint8_t *) table - (uint8_t *) c->table_array;
    int idx = table_offset / s->cluster_size;
    assert(idx >= 0 && idx < c->size && table_offset % s->cluster_size == 0);
    return idx;
}

static void qcow2_cache_table_release(BlockDriverState *bs, Qcow2Cache *c,
                                      int i, int num_tables)
{
#if QEMU_MADV_DONTNEED != QEMU_MADV_INVALID
    BDRVQcow2State *s = bs->opaque;
    void *t = qcow2_cache_get_table_addr(bs, c, i);
    int align = getpagesize();
    size_t mem_size = (size_t) s->cluster_size * num_tables;
    size_t offset = QEMU_ALIGN_UP((uintptr_t) t, align) - (uintptr_t) t;
    size_t length = QEMU_ALIGN_DOWN(mem_size - offset, align);
    if (length > 0) {
        qemu_madvise((uint8_t *) t + offset, length, QEMU_MADV_DONTNEED);
    }
#endif
}

static inline bool can_clean_entry(Qcow2Cache *c, int i)
{
    Qcow2CachedTable *t = &c->entries[i];
    return t->ref == 0 && !t->dirty && t->offset != 0 &&
        t->lru_counter <= c->cache_clean_lru_counter;
}

void qcow2_cache_clean_unused(BlockDriverState *bs, Qcow2Cache *c)
{
    int i = 0;
    while (i < c->size) {
        int to_clean = 0;

        /* Skip the entries that we don't need to clean */
        while (i < c->size && !can_clean_entry(c, i)) {
            i++;
        }

        /* And count how many we can clean in a row */
        while (i < c->size && can_clean_entry(c, i)) {
            c->entries[i].offset = 0;
            c->entries[i].lru_counter = 0;
            i++;
            to_clean++;
        }

        if (to_clean > 0) {
            qcow2_cache_table_release(bs, c, i - to_clean, to_clean);
        }
    }

    c->cache_clean_lru_counter = c->lru_counter;
}

Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables)
{
    BDRVQcow2State *s = bs->opaque;
    Qcow2Cache *c;

    c = g_new0(Qcow2Cache, 1);
    c->size = num_tables;
    c->entries = g_try_new0(Qcow2CachedTable, num_tables);
    c->table_array = qemu_try_blockalign(bs->file->bs,
                                         (size_t) num_tables * s->cluster_size);

    if (!c->entries || !c->table_array) {
        qemu_vfree(c->table_array);
        g_free(c->entries);
        g_free(c);
        c = NULL;
    }

    return c;
}

int qcow2_cache_destroy(BlockDriverState *bs, Qcow2Cache *c)
{
    int i;

    for (i = 0; i < c->size; i++) {
        assert(c->entries[i].ref == 0);
    }

    qemu_vfree(c->table_array);
    g_free(c->entries);
    g_free(c);

    return 0;
}

static int qcow2_cache_flush_dependency(BlockDriverState *bs, Qcow2Cache *c)
{
    int ret;

    ret = qcow2_cache_flush(bs, c->depends);
    if (ret < 0) {
        return ret;
    }

    c->depends = NULL;
    c->depends_on_flush = false;

    return 0;
}

static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
{
    BDRVQcow2State *s = bs->opaque;
    int ret = 0;

    if (!c->entries[i].dirty || !c->entries[i].offset) {
        return 0;
    }

    trace_qcow2_cache_entry_flush(qemu_coroutine_self(),
                                  c == s->l2_table_cache, i);

    if (c->depends) {
        ret = qcow2_cache_flush_dependency(bs, c);
    } else if (c->depends_on_flush) {
        ret = bdrv_flush(bs->file->bs);
        if (ret >= 0) {
            c->depends_on_flush = false;
        }
    }

    if (ret < 0) {
        return ret;
    }

    if (c == s->refcount_block_cache) {
        ret = qcow2_pre_write_overlap_check(bs, QCOW2_OL_REFCOUNT_BLOCK,
                c->entries[i].offset, s->cluster_size);
    } else if (c == s->l2_table_cache) {
        ret = qcow2_pre_write_overlap_check(bs, QCOW2_OL_ACTIVE_L2,
                c->entries[i].offset, s->cluster_size);
    } else {
        ret = qcow2_pre_write_overlap_check(bs, 0,
                c->entries[i].offset, s->cluster_size);
    }

    if (ret < 0) {
        return ret;
    }

    if (c == s->refcount_block_cache) {
        BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_UPDATE_PART);
    } else if (c == s->l2_table_cache) {
        BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE);
    }

    ret = bdrv_pwrite(bs->file->bs, c->entries[i].offset,
                      qcow2_cache_get_table_addr(bs, c, i), s->cluster_size);
    if (ret < 0) {
        return ret;
    }

    c->entries[i].dirty = false;

    return 0;
}

int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c)
{
    BDRVQcow2State *s = bs->opaque;
    int result = 0;
    int ret;
    int i;

    trace_qcow2_cache_flush(qemu_coroutine_self(), c == s->l2_table_cache);

    for (i = 0; i < c->size; i++) {
        ret = qcow2_cache_entry_flush(bs, c, i);
        if (ret < 0 && result != -ENOSPC) {
            result = ret;
        }
    }

    if (result == 0) {
        ret = bdrv_flush(bs->file->bs);
        if (ret < 0) {
            result = ret;
        }
    }

    return result;
}

int qcow2_cache_set_dependency(BlockDriverState *bs, Qcow2Cache *c,
    Qcow2Cache *dependency)
{
    int ret;

    if (dependency->depends) {
        ret = qcow2_cache_flush_dependency(bs, dependency);
        if (ret < 0) {
            return ret;
        }
    }

    if (c->depends && (c->depends != dependency)) {
        ret = qcow2_cache_flush_dependency(bs, c);
        if (ret < 0) {
            return ret;
        }
    }

    c->depends = dependency;
    return 0;
}

void qcow2_cache_depends_on_flush(Qcow2Cache *c)
{
    c->depends_on_flush = true;
}

int qcow2_cache_empty(BlockDriverState *bs, Qcow2Cache *c)
{
    int ret, i;

    ret = qcow2_cache_flush(bs, c);
    if (ret < 0) {
        return ret;
    }

    for (i = 0; i < c->size; i++) {
        assert(c->entries[i].ref == 0);
        c->entries[i].offset = 0;
        c->entries[i].lru_counter = 0;
    }

    qcow2_cache_table_release(bs, c, 0, c->size);

    c->lru_counter = 0;

    return 0;
}

static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c,
    uint64_t offset, void **table, bool read_from_disk)
{
    BDRVQcow2State *s = bs->opaque;
    int i;
    int ret;
    int lookup_index;
    uint64_t min_lru_counter = UINT64_MAX;
    int min_lru_index = -1;

    trace_qcow2_cache_get(qemu_coroutine_self(), c == s->l2_table_cache,
                          offset, read_from_disk);

    /* Check if the table is already cached */
    i = lookup_index = (offset / s->cluster_size * 4) % c->size;
    do {
        const Qcow2CachedTable *t = &c->entries[i];
        if (t->offset == offset) {
            goto found;
        }
        if (t->ref == 0 && t->lru_counter < min_lru_counter) {
            min_lru_counter = t->lru_counter;
            min_lru_index = i;
        }
        if (++i == c->size) {
            i = 0;
        }
    } while (i != lookup_index);

    if (min_lru_index == -1) {
        /* This can't happen in current synchronous code, but leave the check
         * here as a reminder for whoever starts using AIO with the cache */
        abort();
    }

    /* Cache miss: write a table back and replace it */
    i = min_lru_index;
    trace_qcow2_cache_get_replace_entry(qemu_coroutine_self(),
                                        c == s->l2_table_cache, i);

    ret = qcow2_cache_entry_flush(bs, c, i);
    if (ret < 0) {
        return ret;
    }

    trace_qcow2_cache_get_read(qemu_coroutine_self(),
                               c == s->l2_table_cache, i);
    c->entries[i].offset = 0;
    if (read_from_disk) {
        if (c == s->l2_table_cache) {
            BLKDBG_EVENT(bs->file, BLKDBG_L2_LOAD);
        }

        ret = bdrv_pread(bs->file->bs, offset,
                         qcow2_cache_get_table_addr(bs, c, i),
                         s->cluster_size);
        if (ret < 0) {
            return ret;
        }
    }

    c->entries[i].offset = offset;

    /* And return the right table */
found:
    c->entries[i].ref++;
    *table = qcow2_cache_get_table_addr(bs, c, i);

    trace_qcow2_cache_get_done(qemu_coroutine_self(),
                               c == s->l2_table_cache, i);

    return 0;
}

int qcow2_cache_get(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
    void **table)
{
    return qcow2_cache_do_get(bs, c, offset, table, true);
}

int qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
    void **table)
{
    return qcow2_cache_do_get(bs, c, offset, table, false);
}

void qcow2_cache_put(BlockDriverState *bs, Qcow2Cache *c, void **table)
{
    int i = qcow2_cache_get_table_idx(bs, c, *table);

    c->entries[i].ref--;
    *table = NULL;

    if (c->entries[i].ref == 0) {
        c->entries[i].lru_counter = ++c->lru_counter;
    }

    assert(c->entries[i].ref >= 0);
}

void qcow2_cache_entry_mark_dirty(BlockDriverState *bs, Qcow2Cache *c,
     void *table)
{
    int i = qcow2_cache_get_table_idx(bs, c, table);
    assert(c->entries[i].offset != 0);
    c->entries[i].dirty = true;
}
OpenPOWER on IntegriCloud