qcow2-cluster.c 23.0 KB
Newer Older
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
/*
 * Block driver for the QCOW version 2 format
 *
 * Copyright (c) 2004-2006 Fabrice Bellard
 *
 * 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.
 */

#include <zlib.h>

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

K
Kevin Wolf 已提交
31
int qcow2_grow_l1_table(BlockDriverState *bs, int min_size)
32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49
{
    BDRVQcowState *s = bs->opaque;
    int new_l1_size, new_l1_size2, ret, i;
    uint64_t *new_l1_table;
    uint64_t new_l1_table_offset;
    uint8_t data[12];

    new_l1_size = s->l1_size;
    if (min_size <= new_l1_size)
        return 0;
    while (min_size > new_l1_size) {
        new_l1_size = (new_l1_size * 3 + 1) / 2;
    }
#ifdef DEBUG_ALLOC2
    printf("grow l1_table from %d to %d\n", s->l1_size, new_l1_size);
#endif

    new_l1_size2 = sizeof(uint64_t) * new_l1_size;
50
    new_l1_table = qemu_mallocz(align_offset(new_l1_size2, 512));
51 52 53
    memcpy(new_l1_table, s->l1_table, s->l1_size * sizeof(uint64_t));

    /* write new table (align to cluster) */
K
Kevin Wolf 已提交
54
    new_l1_table_offset = qcow2_alloc_clusters(bs, new_l1_size2);
55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70

    for(i = 0; i < s->l1_size; i++)
        new_l1_table[i] = cpu_to_be64(new_l1_table[i]);
    ret = bdrv_pwrite(s->hd, new_l1_table_offset, new_l1_table, new_l1_size2);
    if (ret != new_l1_size2)
        goto fail;
    for(i = 0; i < s->l1_size; i++)
        new_l1_table[i] = be64_to_cpu(new_l1_table[i]);

    /* set new table */
    cpu_to_be32w((uint32_t*)data, new_l1_size);
    cpu_to_be64w((uint64_t*)(data + 4), new_l1_table_offset);
    if (bdrv_pwrite(s->hd, offsetof(QCowHeader, l1_size), data,
                sizeof(data)) != sizeof(data))
        goto fail;
    qemu_free(s->l1_table);
K
Kevin Wolf 已提交
71
    qcow2_free_clusters(bs, s->l1_table_offset, s->l1_size * sizeof(uint64_t));
72 73 74 75 76 77 78 79 80
    s->l1_table_offset = new_l1_table_offset;
    s->l1_table = new_l1_table;
    s->l1_size = new_l1_size;
    return 0;
 fail:
    qemu_free(s->l1_table);
    return -EIO;
}

K
Kevin Wolf 已提交
81
void qcow2_l2_cache_reset(BlockDriverState *bs)
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
{
    BDRVQcowState *s = bs->opaque;

    memset(s->l2_cache, 0, s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
    memset(s->l2_cache_offsets, 0, L2_CACHE_SIZE * sizeof(uint64_t));
    memset(s->l2_cache_counts, 0, L2_CACHE_SIZE * sizeof(uint32_t));
}

static inline int l2_cache_new_entry(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    uint32_t min_count;
    int min_index, i;

    /* find a new entry in the least used one */
    min_index = 0;
    min_count = 0xffffffff;
    for(i = 0; i < L2_CACHE_SIZE; i++) {
        if (s->l2_cache_counts[i] < min_count) {
            min_count = s->l2_cache_counts[i];
            min_index = i;
        }
    }
    return min_index;
}

/*
 * seek_l2_table
 *
 * seek l2_offset in the l2_cache table
 * if not found, return NULL,
 * if found,
 *   increments the l2 cache hit count of the entry,
 *   if counter overflow, divide by two all counters
 *   return the pointer to the l2 cache entry
 *
 */

static uint64_t *seek_l2_table(BDRVQcowState *s, uint64_t l2_offset)
{
    int i, j;

    for(i = 0; i < L2_CACHE_SIZE; i++) {
        if (l2_offset == s->l2_cache_offsets[i]) {
            /* increment the hit count */
            if (++s->l2_cache_counts[i] == 0xffffffff) {
                for(j = 0; j < L2_CACHE_SIZE; j++) {
                    s->l2_cache_counts[j] >>= 1;
                }
            }
            return s->l2_cache + (i << s->l2_bits);
        }
    }
    return NULL;
}

/*
 * l2_load
 *
 * Loads a L2 table into memory. If the table is in the cache, the cache
 * is used; otherwise the L2 table is loaded from the image file.
 *
 * Returns a pointer to the L2 table on success, or NULL if the read from
 * the image file failed.
 */

static uint64_t *l2_load(BlockDriverState *bs, uint64_t l2_offset)
{
    BDRVQcowState *s = bs->opaque;
    int min_index;
    uint64_t *l2_table;

    /* seek if the table for the given offset is in the cache */

    l2_table = seek_l2_table(s, l2_offset);
    if (l2_table != NULL)
        return l2_table;

    /* not found: load a new entry in the least used one */

    min_index = l2_cache_new_entry(bs);
    l2_table = s->l2_cache + (min_index << s->l2_bits);
    if (bdrv_pread(s->hd, l2_offset, l2_table, s->l2_size * sizeof(uint64_t)) !=
        s->l2_size * sizeof(uint64_t))
        return NULL;
    s->l2_cache_offsets[min_index] = l2_offset;
    s->l2_cache_counts[min_index] = 1;

    return l2_table;
}

K
Kevin Wolf 已提交
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
/*
 * Writes one sector of the L1 table to the disk (can't update single entries
 * and we really don't want bdrv_pread to perform a read-modify-write)
 */
#define L1_ENTRIES_PER_SECTOR (512 / 8)
static int write_l1_entry(BDRVQcowState *s, int l1_index)
{
    uint64_t buf[L1_ENTRIES_PER_SECTOR];
    int l1_start_index;
    int i;

    l1_start_index = l1_index & ~(L1_ENTRIES_PER_SECTOR - 1);
    for (i = 0; i < L1_ENTRIES_PER_SECTOR; i++) {
        buf[i] = cpu_to_be64(s->l1_table[l1_start_index + i]);
    }

    if (bdrv_pwrite(s->hd, s->l1_table_offset + 8 * l1_start_index,
        buf, sizeof(buf)) != sizeof(buf))
    {
        return -1;
    }

    return 0;
}

198 199 200 201 202 203 204 205 206 207 208 209 210 211
/*
 * l2_allocate
 *
 * Allocate a new l2 entry in the file. If l1_index points to an already
 * used entry in the L2 table (i.e. we are doing a copy on write for the L2
 * table) copy the contents of the old L2 table into the newly allocated one.
 * Otherwise the new table is initialized with zeros.
 *
 */

static uint64_t *l2_allocate(BlockDriverState *bs, int l1_index)
{
    BDRVQcowState *s = bs->opaque;
    int min_index;
K
Kevin Wolf 已提交
212
    uint64_t old_l2_offset;
213 214 215 216 217 218
    uint64_t *l2_table, l2_offset;

    old_l2_offset = s->l1_table[l1_index];

    /* allocate a new l2 entry */

K
Kevin Wolf 已提交
219
    l2_offset = qcow2_alloc_clusters(bs, s->l2_size * sizeof(uint64_t));
220 221 222 223

    /* update the L1 entry */

    s->l1_table[l1_index] = l2_offset | QCOW_OFLAG_COPIED;
K
Kevin Wolf 已提交
224
    if (write_l1_entry(s, l1_index) < 0) {
225
        return NULL;
K
Kevin Wolf 已提交
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

    /* allocate a new entry in the l2 cache */

    min_index = l2_cache_new_entry(bs);
    l2_table = s->l2_cache + (min_index << s->l2_bits);

    if (old_l2_offset == 0) {
        /* if there was no old l2 table, clear the new table */
        memset(l2_table, 0, s->l2_size * sizeof(uint64_t));
    } else {
        /* if there was an old l2 table, read it from the disk */
        if (bdrv_pread(s->hd, old_l2_offset,
                       l2_table, s->l2_size * sizeof(uint64_t)) !=
            s->l2_size * sizeof(uint64_t))
            return NULL;
    }
    /* write the l2 table to the file */
    if (bdrv_pwrite(s->hd, l2_offset,
                    l2_table, s->l2_size * sizeof(uint64_t)) !=
        s->l2_size * sizeof(uint64_t))
        return NULL;

    /* update the l2 cache entry */

    s->l2_cache_offsets[min_index] = l2_offset;
    s->l2_cache_counts[min_index] = 1;

    return l2_table;
}

static int count_contiguous_clusters(uint64_t nb_clusters, int cluster_size,
        uint64_t *l2_table, uint64_t start, uint64_t mask)
{
    int i;
    uint64_t offset = be64_to_cpu(l2_table[0]) & ~mask;

    if (!offset)
        return 0;

    for (i = start; i < start + nb_clusters; i++)
        if (offset + i * cluster_size != (be64_to_cpu(l2_table[i]) & ~mask))
            break;

	return (i - start);
}

static int count_contiguous_free_clusters(uint64_t nb_clusters, uint64_t *l2_table)
{
    int i = 0;

    while(nb_clusters-- && l2_table[i] == 0)
        i++;

    return i;
}

/* The crypt function is compatible with the linux cryptoloop
   algorithm for < 4 GB images. NOTE: out_buf == in_buf is
   supported */
K
Kevin Wolf 已提交
286 287 288 289
void qcow2_encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
                           uint8_t *out_buf, const uint8_t *in_buf,
                           int nb_sectors, int enc,
                           const AES_KEY *key)
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
{
    union {
        uint64_t ll[2];
        uint8_t b[16];
    } ivec;
    int i;

    for(i = 0; i < nb_sectors; i++) {
        ivec.ll[0] = cpu_to_le64(sector_num);
        ivec.ll[1] = 0;
        AES_cbc_encrypt(in_buf, out_buf, 512, key,
                        ivec.b, enc);
        sector_num++;
        in_buf += 512;
        out_buf += 512;
    }
}


static int qcow_read(BlockDriverState *bs, int64_t sector_num,
                     uint8_t *buf, int nb_sectors)
{
    BDRVQcowState *s = bs->opaque;
    int ret, index_in_cluster, n, n1;
    uint64_t cluster_offset;

    while (nb_sectors > 0) {
        n = nb_sectors;
K
Kevin Wolf 已提交
318
        cluster_offset = qcow2_get_cluster_offset(bs, sector_num << 9, &n);
319 320 321 322
        index_in_cluster = sector_num & (s->cluster_sectors - 1);
        if (!cluster_offset) {
            if (bs->backing_hd) {
                /* read from the base image */
K
Kevin Wolf 已提交
323
                n1 = qcow2_backing_read1(bs->backing_hd, sector_num, buf, n);
324 325 326 327 328 329 330 331 332
                if (n1 > 0) {
                    ret = bdrv_read(bs->backing_hd, sector_num, buf, n1);
                    if (ret < 0)
                        return -1;
                }
            } else {
                memset(buf, 0, 512 * n);
            }
        } else if (cluster_offset & QCOW_OFLAG_COMPRESSED) {
K
Kevin Wolf 已提交
333
            if (qcow2_decompress_cluster(s, cluster_offset) < 0)
334 335 336 337 338 339 340
                return -1;
            memcpy(buf, s->cluster_cache + index_in_cluster * 512, 512 * n);
        } else {
            ret = bdrv_pread(s->hd, cluster_offset + index_in_cluster * 512, buf, n * 512);
            if (ret != n * 512)
                return -1;
            if (s->crypt_method) {
K
Kevin Wolf 已提交
341
                qcow2_encrypt_sectors(s, sector_num, buf, buf, n, 0,
342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364
                                &s->aes_decrypt_key);
            }
        }
        nb_sectors -= n;
        sector_num += n;
        buf += n * 512;
    }
    return 0;
}

static int copy_sectors(BlockDriverState *bs, uint64_t start_sect,
                        uint64_t cluster_offset, int n_start, int n_end)
{
    BDRVQcowState *s = bs->opaque;
    int n, ret;

    n = n_end - n_start;
    if (n <= 0)
        return 0;
    ret = qcow_read(bs, start_sect + n_start, s->cluster_data, n);
    if (ret < 0)
        return ret;
    if (s->crypt_method) {
K
Kevin Wolf 已提交
365
        qcow2_encrypt_sectors(s, start_sect + n_start,
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
                        s->cluster_data,
                        s->cluster_data, n, 1,
                        &s->aes_encrypt_key);
    }
    ret = bdrv_write(s->hd, (cluster_offset >> 9) + n_start,
                     s->cluster_data, n);
    if (ret < 0)
        return ret;
    return 0;
}


/*
 * get_cluster_offset
 *
 * For a given offset of the disk image, return cluster offset in
 * qcow2 file.
 *
 * on entry, *num is the number of contiguous clusters we'd like to
 * access following offset.
 *
 * on exit, *num is the number of contiguous clusters we can read.
 *
 * Return 1, if the offset is found
 * Return 0, otherwise.
 *
 */

K
Kevin Wolf 已提交
394 395
uint64_t qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
    int *num)
396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492
{
    BDRVQcowState *s = bs->opaque;
    int l1_index, l2_index;
    uint64_t l2_offset, *l2_table, cluster_offset;
    int l1_bits, c;
    int index_in_cluster, nb_available, nb_needed, nb_clusters;

    index_in_cluster = (offset >> 9) & (s->cluster_sectors - 1);
    nb_needed = *num + index_in_cluster;

    l1_bits = s->l2_bits + s->cluster_bits;

    /* compute how many bytes there are between the offset and
     * the end of the l1 entry
     */

    nb_available = (1 << l1_bits) - (offset & ((1 << l1_bits) - 1));

    /* compute the number of available sectors */

    nb_available = (nb_available >> 9) + index_in_cluster;

    if (nb_needed > nb_available) {
        nb_needed = nb_available;
    }

    cluster_offset = 0;

    /* seek the the l2 offset in the l1 table */

    l1_index = offset >> l1_bits;
    if (l1_index >= s->l1_size)
        goto out;

    l2_offset = s->l1_table[l1_index];

    /* seek the l2 table of the given l2 offset */

    if (!l2_offset)
        goto out;

    /* load the l2 table in memory */

    l2_offset &= ~QCOW_OFLAG_COPIED;
    l2_table = l2_load(bs, l2_offset);
    if (l2_table == NULL)
        return 0;

    /* find the cluster offset for the given disk offset */

    l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1);
    cluster_offset = be64_to_cpu(l2_table[l2_index]);
    nb_clusters = size_to_clusters(s, nb_needed << 9);

    if (!cluster_offset) {
        /* how many empty clusters ? */
        c = count_contiguous_free_clusters(nb_clusters, &l2_table[l2_index]);
    } else {
        /* how many allocated clusters ? */
        c = count_contiguous_clusters(nb_clusters, s->cluster_size,
                &l2_table[l2_index], 0, QCOW_OFLAG_COPIED);
    }

   nb_available = (c * s->cluster_sectors);
out:
    if (nb_available > nb_needed)
        nb_available = nb_needed;

    *num = nb_available - index_in_cluster;

    return cluster_offset & ~QCOW_OFLAG_COPIED;
}

/*
 * get_cluster_table
 *
 * for a given disk offset, load (and allocate if needed)
 * the l2 table.
 *
 * the l2 table offset in the qcow2 file and the cluster index
 * in the l2 table are given to the caller.
 *
 */

static int get_cluster_table(BlockDriverState *bs, uint64_t offset,
                             uint64_t **new_l2_table,
                             uint64_t *new_l2_offset,
                             int *new_l2_index)
{
    BDRVQcowState *s = bs->opaque;
    int l1_index, l2_index, ret;
    uint64_t l2_offset, *l2_table;

    /* seek the the l2 offset in the l1 table */

    l1_index = offset >> (s->l2_bits + s->cluster_bits);
    if (l1_index >= s->l1_size) {
K
Kevin Wolf 已提交
493
        ret = qcow2_grow_l1_table(bs, l1_index + 1);
494 495 496 497 498 499 500 501 502 503 504 505 506 507 508
        if (ret < 0)
            return 0;
    }
    l2_offset = s->l1_table[l1_index];

    /* seek the l2 table of the given l2 offset */

    if (l2_offset & QCOW_OFLAG_COPIED) {
        /* load the l2 table in memory */
        l2_offset &= ~QCOW_OFLAG_COPIED;
        l2_table = l2_load(bs, l2_offset);
        if (l2_table == NULL)
            return 0;
    } else {
        if (l2_offset)
K
Kevin Wolf 已提交
509
            qcow2_free_clusters(bs, l2_offset, s->l2_size * sizeof(uint64_t));
510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539
        l2_table = l2_allocate(bs, l1_index);
        if (l2_table == NULL)
            return 0;
        l2_offset = s->l1_table[l1_index] & ~QCOW_OFLAG_COPIED;
    }

    /* find the cluster offset for the given disk offset */

    l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1);

    *new_l2_table = l2_table;
    *new_l2_offset = l2_offset;
    *new_l2_index = l2_index;

    return 1;
}

/*
 * alloc_compressed_cluster_offset
 *
 * For a given offset of the disk image, return cluster offset in
 * qcow2 file.
 *
 * If the offset is not found, allocate a new compressed cluster.
 *
 * Return the cluster offset if successful,
 * Return 0, otherwise.
 *
 */

K
Kevin Wolf 已提交
540 541 542
uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
                                               uint64_t offset,
                                               int compressed_size)
543 544 545 546 547 548 549 550 551 552 553 554 555 556 557
{
    BDRVQcowState *s = bs->opaque;
    int l2_index, ret;
    uint64_t l2_offset, *l2_table, cluster_offset;
    int nb_csectors;

    ret = get_cluster_table(bs, offset, &l2_table, &l2_offset, &l2_index);
    if (ret == 0)
        return 0;

    cluster_offset = be64_to_cpu(l2_table[l2_index]);
    if (cluster_offset & QCOW_OFLAG_COPIED)
        return cluster_offset & ~QCOW_OFLAG_COPIED;

    if (cluster_offset)
K
Kevin Wolf 已提交
558
        qcow2_free_any_clusters(bs, cluster_offset, 1);
559

K
Kevin Wolf 已提交
560
    cluster_offset = qcow2_alloc_bytes(bs, compressed_size);
561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580
    nb_csectors = ((cluster_offset + compressed_size - 1) >> 9) -
                  (cluster_offset >> 9);

    cluster_offset |= QCOW_OFLAG_COMPRESSED |
                      ((uint64_t)nb_csectors << s->csize_shift);

    /* update L2 table */

    /* compressed clusters never have the copied flag */

    l2_table[l2_index] = cpu_to_be64(cluster_offset);
    if (bdrv_pwrite(s->hd,
                    l2_offset + l2_index * sizeof(uint64_t),
                    l2_table + l2_index,
                    sizeof(uint64_t)) != sizeof(uint64_t))
        return 0;

    return cluster_offset;
}

581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602
/*
 * Write L2 table updates to disk, writing whole sectors to avoid a
 * read-modify-write in bdrv_pwrite
 */
#define L2_ENTRIES_PER_SECTOR (512 / 8)
static int write_l2_entries(BDRVQcowState *s, uint64_t *l2_table,
    uint64_t l2_offset, int l2_index, int num)
{
    int l2_start_index = l2_index & ~(L1_ENTRIES_PER_SECTOR - 1);
    int start_offset = (8 * l2_index) & ~511;
    int end_offset = (8 * (l2_index + num) + 511) & ~511;
    size_t len = end_offset - start_offset;

    if (bdrv_pwrite(s->hd, l2_offset + start_offset, &l2_table[l2_start_index],
        len) != len)
    {
        return -1;
    }

    return 0;
}

K
Kevin Wolf 已提交
603
int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, uint64_t cluster_offset,
604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649
    QCowL2Meta *m)
{
    BDRVQcowState *s = bs->opaque;
    int i, j = 0, l2_index, ret;
    uint64_t *old_cluster, start_sect, l2_offset, *l2_table;

    if (m->nb_clusters == 0)
        return 0;

    old_cluster = qemu_malloc(m->nb_clusters * sizeof(uint64_t));

    /* copy content of unmodified sectors */
    start_sect = (m->offset & ~(s->cluster_size - 1)) >> 9;
    if (m->n_start) {
        ret = copy_sectors(bs, start_sect, cluster_offset, 0, m->n_start);
        if (ret < 0)
            goto err;
    }

    if (m->nb_available & (s->cluster_sectors - 1)) {
        uint64_t end = m->nb_available & ~(uint64_t)(s->cluster_sectors - 1);
        ret = copy_sectors(bs, start_sect + end, cluster_offset + (end << 9),
                m->nb_available - end, s->cluster_sectors);
        if (ret < 0)
            goto err;
    }

    ret = -EIO;
    /* update L2 table */
    if (!get_cluster_table(bs, m->offset, &l2_table, &l2_offset, &l2_index))
        goto err;

    for (i = 0; i < m->nb_clusters; i++) {
        /* if two concurrent writes happen to the same unallocated cluster
	 * each write allocates separate cluster and writes data concurrently.
	 * The first one to complete updates l2 table with pointer to its
	 * cluster the second one has to do RMW (which is done above by
	 * copy_sectors()), update l2 table with its cluster pointer and free
	 * old cluster. This is what this loop does */
        if(l2_table[l2_index + i] != 0)
            old_cluster[j++] = l2_table[l2_index + i];

        l2_table[l2_index + i] = cpu_to_be64((cluster_offset +
                    (i << s->cluster_bits)) | QCOW_OFLAG_COPIED);
     }

650 651
    if (write_l2_entries(s, l2_table, l2_offset, l2_index, m->nb_clusters) < 0) {
        ret = -1;
652
        goto err;
653
    }
654 655

    for (i = 0; i < j; i++)
K
Kevin Wolf 已提交
656 657
        qcow2_free_any_clusters(bs,
            be64_to_cpu(old_cluster[i]) & ~QCOW_OFLAG_COPIED, 1);
658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677

    ret = 0;
err:
    qemu_free(old_cluster);
    return ret;
 }

/*
 * alloc_cluster_offset
 *
 * For a given offset of the disk image, return cluster offset in
 * qcow2 file.
 *
 * If the offset is not found, allocate a new cluster.
 *
 * Return the cluster offset if successful,
 * Return 0, otherwise.
 *
 */

K
Kevin Wolf 已提交
678 679 680 681
uint64_t qcow2_alloc_cluster_offset(BlockDriverState *bs,
                                    uint64_t offset,
                                    int n_start, int n_end,
                                    int *num, QCowL2Meta *m)
682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736
{
    BDRVQcowState *s = bs->opaque;
    int l2_index, ret;
    uint64_t l2_offset, *l2_table, cluster_offset;
    int nb_clusters, i = 0;

    ret = get_cluster_table(bs, offset, &l2_table, &l2_offset, &l2_index);
    if (ret == 0)
        return 0;

    nb_clusters = size_to_clusters(s, n_end << 9);

    nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);

    cluster_offset = be64_to_cpu(l2_table[l2_index]);

    /* We keep all QCOW_OFLAG_COPIED clusters */

    if (cluster_offset & QCOW_OFLAG_COPIED) {
        nb_clusters = count_contiguous_clusters(nb_clusters, s->cluster_size,
                &l2_table[l2_index], 0, 0);

        cluster_offset &= ~QCOW_OFLAG_COPIED;
        m->nb_clusters = 0;

        goto out;
    }

    /* for the moment, multiple compressed clusters are not managed */

    if (cluster_offset & QCOW_OFLAG_COMPRESSED)
        nb_clusters = 1;

    /* how many available clusters ? */

    while (i < nb_clusters) {
        i += count_contiguous_clusters(nb_clusters - i, s->cluster_size,
                &l2_table[l2_index], i, 0);

        if(be64_to_cpu(l2_table[l2_index + i]))
            break;

        i += count_contiguous_free_clusters(nb_clusters - i,
                &l2_table[l2_index + i]);

        cluster_offset = be64_to_cpu(l2_table[l2_index + i]);

        if ((cluster_offset & QCOW_OFLAG_COPIED) ||
                (cluster_offset & QCOW_OFLAG_COMPRESSED))
            break;
    }
    nb_clusters = i;

    /* allocate a new cluster */

K
Kevin Wolf 已提交
737
    cluster_offset = qcow2_alloc_clusters(bs, nb_clusters * s->cluster_size);
738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778

    /* save info needed for meta data update */
    m->offset = offset;
    m->n_start = n_start;
    m->nb_clusters = nb_clusters;

out:
    m->nb_available = MIN(nb_clusters << (s->cluster_bits - 9), n_end);

    *num = m->nb_available - n_start;

    return cluster_offset;
}

static int decompress_buffer(uint8_t *out_buf, int out_buf_size,
                             const uint8_t *buf, int buf_size)
{
    z_stream strm1, *strm = &strm1;
    int ret, out_len;

    memset(strm, 0, sizeof(*strm));

    strm->next_in = (uint8_t *)buf;
    strm->avail_in = buf_size;
    strm->next_out = out_buf;
    strm->avail_out = out_buf_size;

    ret = inflateInit2(strm, -12);
    if (ret != Z_OK)
        return -1;
    ret = inflate(strm, Z_FINISH);
    out_len = strm->next_out - out_buf;
    if ((ret != Z_STREAM_END && ret != Z_BUF_ERROR) ||
        out_len != out_buf_size) {
        inflateEnd(strm);
        return -1;
    }
    inflateEnd(strm);
    return 0;
}

K
Kevin Wolf 已提交
779
int qcow2_decompress_cluster(BDRVQcowState *s, uint64_t cluster_offset)
780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800
{
    int ret, csize, nb_csectors, sector_offset;
    uint64_t coffset;

    coffset = cluster_offset & s->cluster_offset_mask;
    if (s->cluster_cache_offset != coffset) {
        nb_csectors = ((cluster_offset >> s->csize_shift) & s->csize_mask) + 1;
        sector_offset = coffset & 511;
        csize = nb_csectors * 512 - sector_offset;
        ret = bdrv_read(s->hd, coffset >> 9, s->cluster_data, nb_csectors);
        if (ret < 0) {
            return -1;
        }
        if (decompress_buffer(s->cluster_cache, s->cluster_size,
                              s->cluster_data + sector_offset, csize) < 0) {
            return -1;
        }
        s->cluster_cache_offset = coffset;
    }
    return 0;
}