int len, i, shift, ret;
QCowHeader header;
+ /* Performance is terrible right now with cache=writethrough due mainly
+ * to reference count updates. If the user does not explicitly specify
+ * a caching type, force to writeback caching.
+ */
+ if ((flags & BDRV_O_CACHE_DEF)) {
+ flags |= BDRV_O_CACHE_WB;
+ flags &= ~BDRV_O_CACHE_DEF;
+ }
ret = bdrv_file_open(&s->hd, filename, flags);
if (ret < 0)
return ret;
goto fail;
s->l1_table_offset = header.l1_table_offset;
s->l1_table = qemu_malloc(s->l1_size * sizeof(uint64_t));
- if (!s->l1_table)
- goto fail;
if (bdrv_pread(s->hd, s->l1_table_offset, s->l1_table, s->l1_size * sizeof(uint64_t)) !=
s->l1_size * sizeof(uint64_t))
goto fail;
}
/* alloc L2 cache */
s->l2_cache = qemu_malloc(s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
- if (!s->l2_cache)
- goto fail;
s->cluster_cache = qemu_malloc(s->cluster_size);
- if (!s->cluster_cache)
- goto fail;
/* one more sector for decompressed data alignment */
s->cluster_data = qemu_malloc(QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size
+ 512);
- if (!s->cluster_data)
- goto fail;
s->cluster_cache_offset = -1;
if (refcount_init(bs) < 0)
new_l1_size2 = sizeof(uint64_t) * new_l1_size;
new_l1_table = qemu_mallocz(new_l1_size2);
- if (!new_l1_table)
- return -ENOMEM;
memcpy(new_l1_table, s->l1_table, s->l1_size * sizeof(uint64_t));
/* write new table (align to cluster) */
return l2_table;
}
+static int size_to_clusters(BDRVQcowState *s, int64_t size)
+{
+ return (size + (s->cluster_size - 1)) >> s->cluster_bits;
+}
+
+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;
+}
+
/*
* get_cluster_offset
*
{
BDRVQcowState *s = bs->opaque;
int l1_index, l2_index;
- uint64_t l2_offset, *l2_table, cluster_offset, next;
- int l1_bits;
- int index_in_cluster, nb_available, nb_needed;
+ 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
- * and the end of the l1 entry
+ * the end of the l1 entry
*/
nb_available = (1 << l1_bits) - (offset & ((1 << l1_bits) - 1));
l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1);
cluster_offset = be64_to_cpu(l2_table[l2_index]);
- nb_available = s->cluster_sectors;
- l2_index++;
+ nb_clusters = size_to_clusters(s, nb_needed << 9);
if (!cluster_offset) {
-
- /* how many empty clusters ? */
-
- while (nb_available < nb_needed && !l2_table[l2_index]) {
- l2_index++;
- nb_available += s->cluster_sectors;
- }
+ /* 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);
+ }
- /* how many allocated clusters ? */
-
- cluster_offset &= ~QCOW_OFLAG_COPIED;
- while (nb_available < nb_needed) {
- next = be64_to_cpu(l2_table[l2_index]) & ~QCOW_OFLAG_COPIED;
- if (next != cluster_offset + (nb_available << 9))
- break;
- l2_index++;
- nb_available += s->cluster_sectors;
- }
- }
-
+ 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;
+ return cluster_offset & ~QCOW_OFLAG_COPIED;
}
/*
return cluster_offset;
}
+typedef struct QCowL2Meta
+{
+ uint64_t offset;
+ int n_start;
+ int nb_available;
+ int nb_clusters;
+} QCowL2Meta;
+
+static int alloc_cluster_link_l2(BlockDriverState *bs, uint64_t cluster_offset,
+ 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(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);
+ }
+
+ if (bdrv_pwrite(s->hd, l2_offset + l2_index * sizeof(uint64_t),
+ l2_table + l2_index, m->nb_clusters * sizeof(uint64_t)) !=
+ m->nb_clusters * sizeof(uint64_t))
+ goto err;
+
+ for (i = 0; i < j; i++)
+ free_any_clusters(bs, old_cluster[i], 1);
+
+ ret = 0;
+err:
+ qemu_free(old_cluster);
+ return ret;
+ }
+
/*
* alloc_cluster_offset
*
static uint64_t alloc_cluster_offset(BlockDriverState *bs,
uint64_t offset,
int n_start, int n_end,
- int *num)
+ int *num, QCowL2Meta *m)
{
BDRVQcowState *s = bs->opaque;
int l2_index, ret;
uint64_t l2_offset, *l2_table, cluster_offset;
- int nb_available, nb_clusters, i, j;
- uint64_t start_sect, current;
+ int nb_clusters, i = 0;
ret = get_cluster_table(bs, offset, &l2_table, &l2_offset, &l2_index);
if (ret == 0)
return 0;
- nb_clusters = ((n_end << 9) + s->cluster_size - 1) >>
- s->cluster_bits;
- if (nb_clusters > s->l2_size - l2_index)
- nb_clusters = s->l2_size - l2_index;
+ 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) {
-
- for (i = 1; i < nb_clusters; i++) {
- current = be64_to_cpu(l2_table[l2_index + i]);
- if (cluster_offset + (i << s->cluster_bits) != current)
- break;
- }
- nb_clusters = i;
-
- nb_available = nb_clusters << (s->cluster_bits - 9);
- if (nb_available > n_end)
- nb_available = n_end;
+ 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;
}
/* how many available clusters ? */
- i = 0;
while (i < nb_clusters) {
+ i += count_contiguous_clusters(nb_clusters - i, s->cluster_size,
+ &l2_table[l2_index], i, 0);
- i++;
-
- if (!cluster_offset) {
+ if(be64_to_cpu(l2_table[l2_index + i]))
+ break;
- /* how many free clusters ? */
+ i += count_contiguous_free_clusters(nb_clusters - i,
+ &l2_table[l2_index + i]);
- while (i < nb_clusters) {
- cluster_offset = be64_to_cpu(l2_table[l2_index + i]);
- if (cluster_offset != 0)
- break;
- i++;
- }
+ cluster_offset = be64_to_cpu(l2_table[l2_index + i]);
- if ((cluster_offset & QCOW_OFLAG_COPIED) ||
+ if ((cluster_offset & QCOW_OFLAG_COPIED) ||
(cluster_offset & QCOW_OFLAG_COMPRESSED))
- break;
-
- } else {
-
- /* how many contiguous clusters ? */
-
- j = 1;
- current = 0;
- while (i < nb_clusters) {
- current = be64_to_cpu(l2_table[l2_index + i]);
- if (cluster_offset + (j << s->cluster_bits) != current)
- break;
-
- i++;
- j++;
- }
-
- free_any_clusters(bs, cluster_offset, j);
- if (current)
- break;
- cluster_offset = current;
- }
+ break;
}
nb_clusters = i;
cluster_offset = alloc_clusters(bs, nb_clusters * s->cluster_size);
- /* we must initialize the cluster content which won't be
- written */
-
- nb_available = nb_clusters << (s->cluster_bits - 9);
- if (nb_available > n_end)
- nb_available = n_end;
-
- /* copy content of unmodified sectors */
-
- start_sect = (offset & ~(s->cluster_size - 1)) >> 9;
- if (n_start) {
- ret = copy_sectors(bs, start_sect, cluster_offset, 0, n_start);
- if (ret < 0)
- return 0;
- }
-
- if (nb_available & (s->cluster_sectors - 1)) {
- uint64_t end = nb_available & ~(uint64_t)(s->cluster_sectors - 1);
- ret = copy_sectors(bs, start_sect + end,
- cluster_offset + (end << 9),
- nb_available - end,
- s->cluster_sectors);
- if (ret < 0)
- return 0;
- }
-
- /* update L2 table */
-
- for (i = 0; i < nb_clusters; i++)
- l2_table[l2_index + i] = cpu_to_be64((cluster_offset +
- (i << s->cluster_bits)) |
- QCOW_OFLAG_COPIED);
-
- if (bdrv_pwrite(s->hd,
- l2_offset + l2_index * sizeof(uint64_t),
- l2_table + l2_index,
- nb_clusters * sizeof(uint64_t)) !=
- nb_clusters * sizeof(uint64_t))
- return 0;
+ /* save info needed for meta data update */
+ m->offset = offset;
+ m->n_start = n_start;
+ m->nb_clusters = nb_clusters;
out:
- *num = nb_available - n_start;
+ m->nb_available = MIN(nb_clusters << (s->cluster_bits - 9), n_end);
+
+ *num = m->nb_available - n_start;
return cluster_offset;
}
int ret, index_in_cluster, n;
uint64_t cluster_offset;
int n_end;
+ QCowL2Meta l2meta;
while (nb_sectors > 0) {
index_in_cluster = sector_num & (s->cluster_sectors - 1);
n_end = QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors;
cluster_offset = alloc_cluster_offset(bs, sector_num << 9,
index_in_cluster,
- n_end, &n);
+ n_end, &n, &l2meta);
if (!cluster_offset)
return -1;
if (s->crypt_method) {
} else {
ret = bdrv_pwrite(s->hd, cluster_offset + index_in_cluster * 512, buf, n * 512);
}
- if (ret != n * 512)
+ if (ret != n * 512 || alloc_cluster_link_l2(bs, cluster_offset, &l2meta) < 0) {
+ free_any_clusters(bs, cluster_offset, l2meta.nb_clusters);
return -1;
+ }
nb_sectors -= n;
sector_num += n;
buf += n * 512;
uint8_t *cluster_data;
BlockDriverAIOCB *hd_aiocb;
QEMUBH *bh;
+ QCowL2Meta l2meta;
} QCowAIOCB;
static void qcow_aio_read_cb(void *opaque, int ret);
acb->nb_sectors = nb_sectors;
acb->n = 0;
acb->cluster_offset = 0;
+ acb->l2meta.nb_clusters = 0;
return acb;
}
BlockDriverState *bs = acb->common.bs;
BDRVQcowState *s = bs->opaque;
int index_in_cluster;
- uint64_t cluster_offset;
const uint8_t *src_buf;
int n_end;
return;
}
+ if (alloc_cluster_link_l2(bs, acb->cluster_offset, &acb->l2meta) < 0) {
+ free_any_clusters(bs, acb->cluster_offset, acb->l2meta.nb_clusters);
+ goto fail;
+ }
+
acb->nb_sectors -= acb->n;
acb->sector_num += acb->n;
acb->buf += acb->n * 512;
n_end > QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors)
n_end = QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors;
- cluster_offset = alloc_cluster_offset(bs, acb->sector_num << 9,
+ acb->cluster_offset = alloc_cluster_offset(bs, acb->sector_num << 9,
index_in_cluster,
- n_end, &acb->n);
- if (!cluster_offset || (cluster_offset & 511) != 0) {
+ n_end, &acb->n, &acb->l2meta);
+ if (!acb->cluster_offset || (acb->cluster_offset & 511) != 0) {
ret = -EIO;
goto fail;
}
if (!acb->cluster_data) {
acb->cluster_data = qemu_mallocz(QCOW_MAX_CRYPT_CLUSTERS *
s->cluster_size);
- if (!acb->cluster_data) {
- ret = -ENOMEM;
- goto fail;
- }
}
encrypt_sectors(s, acb->sector_num, acb->cluster_data, acb->buf,
acb->n, 1, &s->aes_encrypt_key);
src_buf = acb->buf;
}
acb->hd_aiocb = bdrv_aio_write(s->hd,
- (cluster_offset >> 9) + index_in_cluster,
+ (acb->cluster_offset >> 9) + index_in_cluster,
src_buf, acb->n,
qcow_aio_write_cb, acb);
if (acb->hd_aiocb == NULL)
offset += align_offset(l1_size * sizeof(uint64_t), s->cluster_size);
s->refcount_table = qemu_mallocz(s->cluster_size);
- if (!s->refcount_table)
- goto fail;
s->refcount_block = qemu_mallocz(s->cluster_size);
- if (!s->refcount_block)
- goto fail;
s->refcount_table_offset = offset;
header.refcount_table_offset = cpu_to_be64(offset);
qemu_free(s->refcount_block);
close(fd);
return 0;
- fail:
- qemu_free(s->refcount_table);
- qemu_free(s->refcount_block);
- close(fd);
- return -ENOMEM;
}
static int qcow_make_empty(BlockDriverState *bs)
return -EINVAL;
out_buf = qemu_malloc(s->cluster_size + (s->cluster_size / 1000) + 128);
- if (!out_buf)
- return -ENOMEM;
/* best compression, small window, no zlib header */
memset(&strm, 0, sizeof(strm));
l1_allocated = 0;
if (l1_table_offset != s->l1_table_offset) {
l1_table = qemu_malloc(l1_size2);
- if (!l1_table)
- goto fail;
l1_allocated = 1;
if (bdrv_pread(s->hd, l1_table_offset,
l1_table, l1_size2) != l1_size2)
l2_size = s->l2_size * sizeof(uint64_t);
l2_table = qemu_malloc(l2_size);
- if (!l2_table)
- goto fail;
l1_modified = 0;
for(i = 0; i < l1_size; i++) {
l2_offset = l1_table[i];
int64_t offset;
uint32_t extra_data_size;
+ if (!s->nb_snapshots) {
+ s->snapshots = NULL;
+ s->snapshots_size = 0;
+ return 0;
+ }
+
offset = s->snapshots_offset;
s->snapshots = qemu_mallocz(s->nb_snapshots * sizeof(QCowSnapshot));
- if (!s->snapshots)
- goto fail;
for(i = 0; i < s->nb_snapshots; i++) {
offset = align_offset(offset, 8);
if (bdrv_pread(s->hd, offset, &h, sizeof(h)) != sizeof(h))
offset += extra_data_size;
sn->id_str = qemu_malloc(id_str_size + 1);
- if (!sn->id_str)
- goto fail;
if (bdrv_pread(s->hd, offset, sn->id_str, id_str_size) != id_str_size)
goto fail;
offset += id_str_size;
sn->id_str[id_str_size] = '\0';
sn->name = qemu_malloc(name_size + 1);
- if (!sn->name)
- goto fail;
if (bdrv_pread(s->hd, offset, sn->name, name_size) != name_size)
goto fail;
offset += name_size;
sn->l1_size = s->l1_size;
l1_table = qemu_malloc(s->l1_size * sizeof(uint64_t));
- if (!l1_table)
- goto fail;
for(i = 0; i < s->l1_size; i++) {
l1_table[i] = cpu_to_be64(s->l1_table[i]);
}
l1_table = NULL;
snapshots1 = qemu_malloc((s->nb_snapshots + 1) * sizeof(QCowSnapshot));
- if (!snapshots1)
- goto fail;
- memcpy(snapshots1, s->snapshots, s->nb_snapshots * sizeof(QCowSnapshot));
+ if (s->snapshots) {
+ memcpy(snapshots1, s->snapshots, s->nb_snapshots * sizeof(QCowSnapshot));
+ qemu_free(s->snapshots);
+ }
s->snapshots = snapshots1;
s->snapshots[s->nb_snapshots++] = *sn;
int i;
sn_tab = qemu_mallocz(s->nb_snapshots * sizeof(QEMUSnapshotInfo));
- if (!sn_tab)
- goto fail;
for(i = 0; i < s->nb_snapshots; i++) {
sn_info = sn_tab + i;
sn = s->snapshots + i;
}
*psn_tab = sn_tab;
return s->nb_snapshots;
- fail:
- qemu_free(sn_tab);
- *psn_tab = NULL;
- return -ENOMEM;
}
/*********************************************************/
int ret, refcount_table_size2, i;
s->refcount_block_cache = qemu_malloc(s->cluster_size);
- if (!s->refcount_block_cache)
- goto fail;
refcount_table_size2 = s->refcount_table_size * sizeof(uint64_t);
s->refcount_table = qemu_malloc(refcount_table_size2);
- if (!s->refcount_table)
- goto fail;
if (s->refcount_table_size > 0) {
ret = bdrv_pread(s->hd, s->refcount_table_offset,
s->refcount_table, refcount_table_size2);
BDRVQcowState *s = bs->opaque;
int i, nb_clusters;
- nb_clusters = (size + s->cluster_size - 1) >> s->cluster_bits;
- for(;;) {
- if (get_refcount(bs, s->free_cluster_index) == 0) {
- s->free_cluster_index++;
- for(i = 1; i < nb_clusters; i++) {
- if (get_refcount(bs, s->free_cluster_index) != 0)
- goto not_found;
- s->free_cluster_index++;
- }
+ nb_clusters = size_to_clusters(s, size);
+retry:
+ for(i = 0; i < nb_clusters; i++) {
+ int64_t i = s->free_cluster_index++;
+ if (get_refcount(bs, i) != 0)
+ goto retry;
+ }
#ifdef DEBUG_ALLOC2
- printf("alloc_clusters: size=%lld -> %lld\n",
- size,
- (s->free_cluster_index - nb_clusters) << s->cluster_bits);
+ printf("alloc_clusters: size=%lld -> %lld\n",
+ size,
+ (s->free_cluster_index - nb_clusters) << s->cluster_bits);
#endif
- return (s->free_cluster_index - nb_clusters) << s->cluster_bits;
- } else {
- not_found:
- s->free_cluster_index++;
- }
- }
+ return (s->free_cluster_index - nb_clusters) << s->cluster_bits;
}
static int64_t alloc_clusters(BlockDriverState *bs, int64_t size)
#endif
new_table_size2 = new_table_size * sizeof(uint64_t);
new_table = qemu_mallocz(new_table_size2);
- if (!new_table)
- return -ENOMEM;
memcpy(new_table, s->refcount_table,
s->refcount_table_size * sizeof(uint64_t));
for(i = 0; i < s->refcount_table_size; i++)
l1_table_offset, l1_size2);
l1_table = qemu_malloc(l1_size2);
- if (!l1_table)
- goto fail;
if (bdrv_pread(s->hd, l1_table_offset,
l1_table, l1_size2) != l1_size2)
goto fail;
l2_size = s->l2_size * sizeof(uint64_t);
l2_table = qemu_malloc(l2_size);
- if (!l2_table)
- goto fail;
for(i = 0; i < l1_size; i++) {
l2_offset = l1_table[i];
if (l2_offset) {
uint16_t *refcount_table;
size = bdrv_getlength(s->hd);
- nb_clusters = (size + s->cluster_size - 1) >> s->cluster_bits;
+ nb_clusters = size_to_clusters(s, size);
refcount_table = qemu_mallocz(nb_clusters * sizeof(uint16_t));
/* header */
int refcount;
size = bdrv_getlength(s->hd);
- nb_clusters = (size + s->cluster_size - 1) >> s->cluster_bits;
+ nb_clusters = size_to_clusters(s, size);
for(k = 0; k < nb_clusters;) {
k1 = k;
refcount = get_refcount(bs, k);
#endif
BlockDriver bdrv_qcow2 = {
- "qcow2",
- sizeof(BDRVQcowState),
- qcow_probe,
- qcow_open,
- NULL,
- NULL,
- qcow_close,
- qcow_create,
- qcow_flush,
- qcow_is_allocated,
- qcow_set_key,
- qcow_make_empty,
-
- .bdrv_aio_read = qcow_aio_read,
- .bdrv_aio_write = qcow_aio_write,
- .bdrv_aio_cancel = qcow_aio_cancel,
- .aiocb_size = sizeof(QCowAIOCB),
+ .format_name = "qcow2",
+ .instance_size = sizeof(BDRVQcowState),
+ .bdrv_probe = qcow_probe,
+ .bdrv_open = qcow_open,
+ .bdrv_close = qcow_close,
+ .bdrv_create = qcow_create,
+ .bdrv_flush = qcow_flush,
+ .bdrv_is_allocated = qcow_is_allocated,
+ .bdrv_set_key = qcow_set_key,
+ .bdrv_make_empty = qcow_make_empty,
+
+ .bdrv_aio_read = qcow_aio_read,
+ .bdrv_aio_write = qcow_aio_write,
+ .bdrv_aio_cancel = qcow_aio_cancel,
+ .aiocb_size = sizeof(QCowAIOCB),
.bdrv_write_compressed = qcow_write_compressed,
.bdrv_snapshot_create = qcow_snapshot_create,
- .bdrv_snapshot_goto = qcow_snapshot_goto,
+ .bdrv_snapshot_goto = qcow_snapshot_goto,
.bdrv_snapshot_delete = qcow_snapshot_delete,
- .bdrv_snapshot_list = qcow_snapshot_list,
- .bdrv_get_info = qcow_get_info,
+ .bdrv_snapshot_list = qcow_snapshot_list,
+ .bdrv_get_info = qcow_get_info,
};
projects / qemu / blobdiff