* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
-#include "vl.h"
+#include "qemu-common.h"
#include "block_int.h"
#include <zlib.h>
#include "aes.h"
- Size of compressed clusters is stored in sectors to reduce bit usage
in the cluster offsets.
- Support for storing additional data (such as the VM state) in the
- snapshots.
+ snapshots.
- If a backing store is used, the cluster size is not constrained
(could be backported to QCOW).
- L2 tables have always a size of one cluster.
#define QCOW_CRYPT_NONE 0
#define QCOW_CRYPT_AES 1
+#define QCOW_MAX_CRYPT_CLUSTERS 32
+
/* indicate that the refcount of the referenced cluster is exactly one. */
#define QCOW_OFLAG_COPIED (1LL << 63)
/* indicate that the cluster is compressed (they never have the copied flag) */
#define REFCOUNT_SHIFT 1 /* refcount size is 2 bytes */
-#ifndef offsetof
-#define offsetof(type, field) ((size_t) &((type *)0)->field)
-#endif
-
typedef struct QCowHeader {
uint32_t magic;
uint32_t version;
static int qcow_probe(const uint8_t *buf, int buf_size, const char *filename)
{
const QCowHeader *cow_header = (const void *)buf;
-
+
if (buf_size >= sizeof(QCowHeader) &&
be32_to_cpu(cow_header->magic) == QCOW_MAGIC &&
be32_to_cpu(cow_header->version) == QCOW_VERSION)
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;
be32_to_cpus(&header.refcount_table_clusters);
be64_to_cpus(&header.snapshots_offset);
be32_to_cpus(&header.nb_snapshots);
-
+
if (header.magic != QCOW_MAGIC || header.version != QCOW_VERSION)
goto fail;
if (header.size <= 1 ||
if (!s->cluster_cache)
goto fail;
/* one more sector for decompressed data alignment */
- s->cluster_data = qemu_malloc(s->cluster_size + 512);
+ 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)
goto fail;
BDRVQcowState *s = bs->opaque;
uint8_t keybuf[16];
int len, i;
-
+
memset(keybuf, 0, 16);
len = strlen(key);
if (len > 16)
int new_l1_size, new_l1_size2, ret, i;
uint64_t *new_l1_table;
uint64_t new_l1_table_offset;
- uint64_t data64;
- uint32_t data32;
+ uint8_t data[12];
new_l1_size = s->l1_size;
if (min_size <= new_l1_size)
/* write new table (align to cluster) */
new_l1_table_offset = alloc_clusters(bs, new_l1_size2);
-
+
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);
goto fail;
for(i = 0; i < s->l1_size; i++)
new_l1_table[i] = be64_to_cpu(new_l1_table[i]);
-
+
/* set new table */
- data64 = cpu_to_be64(new_l1_table_offset);
- if (bdrv_pwrite(s->hd, offsetof(QCowHeader, l1_table_offset),
- &data64, sizeof(data64)) != sizeof(data64))
- goto fail;
- data32 = cpu_to_be32(new_l1_size);
- if (bdrv_pwrite(s->hd, offsetof(QCowHeader, l1_size),
- &data32, sizeof(data32)) != sizeof(data32))
+ 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);
free_clusters(bs, s->l1_table_offset, s->l1_size * sizeof(uint64_t));
return -EIO;
}
-/* 'allocate' is:
+/*
+ * 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
*
- * 0 not to allocate.
+ * 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.
*
- * 1 to allocate a normal cluster (for sector indexes 'n_start' to
- * 'n_end')
+ * 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;
+}
+
+/*
+ * l2_allocate
*
- * 2 to allocate a compressed cluster of size
- * 'compressed_size'. 'compressed_size' must be > 0 and <
- * cluster_size
+ * 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.
*
- * return 0 if not allocated.
*/
+
+static uint64_t *l2_allocate(BlockDriverState *bs, int l1_index)
+{
+ BDRVQcowState *s = bs->opaque;
+ int min_index;
+ uint64_t old_l2_offset, tmp;
+ uint64_t *l2_table, l2_offset;
+
+ old_l2_offset = s->l1_table[l1_index];
+
+ /* allocate a new l2 entry */
+
+ l2_offset = alloc_clusters(bs, s->l2_size * sizeof(uint64_t));
+
+ /* update the L1 entry */
+
+ s->l1_table[l1_index] = l2_offset | QCOW_OFLAG_COPIED;
+
+ tmp = cpu_to_be64(l2_offset | QCOW_OFLAG_COPIED);
+ if (bdrv_pwrite(s->hd, s->l1_table_offset + l1_index * sizeof(tmp),
+ &tmp, sizeof(tmp)) != sizeof(tmp))
+ return NULL;
+
+ /* 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 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 mask)
+{
+ int i;
+ uint64_t offset = be64_to_cpu(l2_table[0]) & ~mask;
+
+ for (i = 0; i < nb_clusters; i++)
+ if (offset + i * cluster_size != (be64_to_cpu(l2_table[i]) & ~mask))
+ break;
+
+ return i;
+}
+
+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
+ *
+ * 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.
+ *
+ */
+
static uint64_t get_cluster_offset(BlockDriverState *bs,
- uint64_t offset, int allocate,
- int compressed_size,
- int n_start, int n_end)
+ uint64_t offset, int *num)
{
BDRVQcowState *s = bs->opaque;
- int min_index, i, j, l1_index, l2_index, ret;
- uint64_t l2_offset, *l2_table, cluster_offset, tmp, old_l2_offset;
-
+ 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;
+
+ 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], 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;
+}
+
+/*
+ * free_any_clusters
+ *
+ * free clusters according to its type: compressed or not
+ *
+ */
+
+static void free_any_clusters(BlockDriverState *bs,
+ uint64_t cluster_offset, int nb_clusters)
+{
+ BDRVQcowState *s = bs->opaque;
+
+ /* free the cluster */
+
+ if (cluster_offset & QCOW_OFLAG_COMPRESSED) {
+ int nb_csectors;
+ nb_csectors = ((cluster_offset >> s->csize_shift) &
+ s->csize_mask) + 1;
+ free_clusters(bs, (cluster_offset & s->cluster_offset_mask) & ~511,
+ nb_csectors * 512);
+ return;
+ }
+
+ free_clusters(bs, cluster_offset, nb_clusters << s->cluster_bits);
+
+ return;
+}
+
+/*
+ * 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) {
- /* outside l1 table is allowed: we grow the table if needed */
- if (!allocate)
- return 0;
- if (grow_l1_table(bs, l1_index + 1) < 0)
+ ret = grow_l1_table(bs, l1_index + 1);
+ if (ret < 0)
return 0;
}
l2_offset = s->l1_table[l1_index];
- if (!l2_offset) {
- if (!allocate)
- return 0;
- l2_allocate:
- old_l2_offset = l2_offset;
- /* allocate a new l2 entry */
- l2_offset = alloc_clusters(bs, s->l2_size * sizeof(uint64_t));
- /* update the L1 entry */
- s->l1_table[l1_index] = l2_offset | QCOW_OFLAG_COPIED;
- tmp = cpu_to_be64(l2_offset | QCOW_OFLAG_COPIED);
- if (bdrv_pwrite(s->hd, s->l1_table_offset + l1_index * sizeof(tmp),
- &tmp, sizeof(tmp)) != sizeof(tmp))
- return 0;
- min_index = l2_cache_new_entry(bs);
- l2_table = s->l2_cache + (min_index << s->l2_bits);
- if (old_l2_offset == 0) {
- memset(l2_table, 0, s->l2_size * sizeof(uint64_t));
- } else {
- if (bdrv_pread(s->hd, old_l2_offset,
- l2_table, s->l2_size * sizeof(uint64_t)) !=
- s->l2_size * sizeof(uint64_t))
- return 0;
- }
- if (bdrv_pwrite(s->hd, l2_offset,
- l2_table, s->l2_size * sizeof(uint64_t)) !=
- s->l2_size * sizeof(uint64_t))
+ /* 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 & QCOW_OFLAG_COPIED)) {
- if (allocate) {
- free_clusters(bs, l2_offset, s->l2_size * sizeof(uint64_t));
- goto l2_allocate;
- }
- } else {
- l2_offset &= ~QCOW_OFLAG_COPIED;
- }
- 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;
- }
- }
- l2_table = s->l2_cache + (i << s->l2_bits);
- goto found;
- }
- }
- /* 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))
+ if (l2_offset)
+ free_clusters(bs, l2_offset, s->l2_size * sizeof(uint64_t));
+ l2_table = l2_allocate(bs, l1_index);
+ if (l2_table == NULL)
return 0;
+ l2_offset = s->l1_table[l1_index] & ~QCOW_OFLAG_COPIED;
}
- s->l2_cache_offsets[min_index] = l2_offset;
- s->l2_cache_counts[min_index] = 1;
- found:
+
+ /* 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.
+ *
+ */
+
+static uint64_t alloc_compressed_cluster_offset(BlockDriverState *bs,
+ uint64_t offset,
+ int compressed_size)
+{
+ 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) {
- if (!allocate)
- return cluster_offset;
- } else if (!(cluster_offset & QCOW_OFLAG_COPIED)) {
- if (!allocate)
- return cluster_offset;
- /* free the cluster */
- if (cluster_offset & QCOW_OFLAG_COMPRESSED) {
- int nb_csectors;
- nb_csectors = ((cluster_offset >> s->csize_shift) &
- s->csize_mask) + 1;
- free_clusters(bs, (cluster_offset & s->cluster_offset_mask) & ~511,
- nb_csectors * 512);
- } else {
- free_clusters(bs, cluster_offset, s->cluster_size);
- }
- } else {
- cluster_offset &= ~QCOW_OFLAG_COPIED;
- return cluster_offset;
- }
- if (allocate == 1) {
- /* allocate a new cluster */
- cluster_offset = alloc_clusters(bs, s->cluster_size);
-
- /* we must initialize the cluster content which won't be
- written */
- if ((n_end - n_start) < s->cluster_sectors) {
- uint64_t start_sect;
-
- start_sect = (offset & ~(s->cluster_size - 1)) >> 9;
- ret = copy_sectors(bs, start_sect,
- cluster_offset, 0, n_start);
- if (ret < 0)
- return 0;
- ret = copy_sectors(bs, start_sect,
- cluster_offset, n_end, s->cluster_sectors);
- if (ret < 0)
- return 0;
- }
- tmp = cpu_to_be64(cluster_offset | QCOW_OFLAG_COPIED);
- } else {
- int nb_csectors;
- cluster_offset = alloc_bytes(bs, compressed_size);
- nb_csectors = ((cluster_offset + compressed_size - 1) >> 9) -
- (cluster_offset >> 9);
- cluster_offset |= QCOW_OFLAG_COMPRESSED |
- ((uint64_t)nb_csectors << s->csize_shift);
- /* compressed clusters never have the copied flag */
- tmp = cpu_to_be64(cluster_offset);
- }
+ if (cluster_offset & QCOW_OFLAG_COPIED)
+ return cluster_offset & ~QCOW_OFLAG_COPIED;
+
+ if (cluster_offset)
+ free_any_clusters(bs, cluster_offset, 1);
+
+ cluster_offset = alloc_bytes(bs, compressed_size);
+ 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 */
- l2_table[l2_index] = tmp;
+
+ /* 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(tmp), &tmp, sizeof(tmp)) != sizeof(tmp))
+ l2_offset + l2_index * sizeof(uint64_t),
+ l2_table + l2_index,
+ sizeof(uint64_t)) != sizeof(uint64_t))
return 0;
+
+ 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;
+
+ if (!(old_cluster = qemu_malloc(m->nb_clusters * sizeof(uint64_t))))
+ return -ENOMEM;
+
+ /* 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
+ *
+ * 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.
+ *
+ */
+
+static uint64_t alloc_cluster_offset(BlockDriverState *bs,
+ uint64_t offset,
+ int n_start, int n_end,
+ int *num, QCowL2Meta *m)
+{
+ 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);
+
+ 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_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;
+
+ 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;
+ }
+ nb_clusters = i;
+
+ /* allocate a new cluster */
+
+ cluster_offset = alloc_clusters(bs, nb_clusters * s->cluster_size);
+
+ /* 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 qcow_is_allocated(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, int *pnum)
{
- BDRVQcowState *s = bs->opaque;
- int index_in_cluster, n;
uint64_t cluster_offset;
- cluster_offset = get_cluster_offset(bs, sector_num << 9, 0, 0, 0, 0);
- index_in_cluster = sector_num & (s->cluster_sectors - 1);
- n = s->cluster_sectors - index_in_cluster;
- if (n > nb_sectors)
- n = nb_sectors;
- *pnum = n;
+ *pnum = nb_sectors;
+ cluster_offset = get_cluster_offset(bs, sector_num << 9, pnum);
+
return (cluster_offset != 0);
}
inflateEnd(strm);
return 0;
}
-
+
static int decompress_cluster(BDRVQcowState *s, uint64_t cluster_offset)
{
int ret, csize, nb_csectors, sector_offset;
BDRVQcowState *s = bs->opaque;
int ret, index_in_cluster, n, n1;
uint64_t cluster_offset;
-
+
while (nb_sectors > 0) {
- cluster_offset = get_cluster_offset(bs, sector_num << 9, 0, 0, 0, 0);
+ n = nb_sectors;
+ cluster_offset = get_cluster_offset(bs, sector_num << 9, &n);
index_in_cluster = sector_num & (s->cluster_sectors - 1);
- n = s->cluster_sectors - index_in_cluster;
- if (n > nb_sectors)
- n = nb_sectors;
if (!cluster_offset) {
if (bs->backing_hd) {
/* read from the base image */
BDRVQcowState *s = bs->opaque;
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 = s->cluster_sectors - index_in_cluster;
- if (n > nb_sectors)
- n = nb_sectors;
- cluster_offset = get_cluster_offset(bs, sector_num << 9, 1, 0,
- index_in_cluster,
- index_in_cluster + n);
+ n_end = index_in_cluster + nb_sectors;
+ if (s->crypt_method &&
+ n_end > QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors)
+ n_end = QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors;
+ cluster_offset = alloc_cluster_offset(bs, sector_num << 9,
+ index_in_cluster,
+ 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;
uint64_t cluster_offset;
uint8_t *cluster_data;
BlockDriverAIOCB *hd_aiocb;
+ QEMUBH *bh;
+ QCowL2Meta l2meta;
} QCowAIOCB;
+static void qcow_aio_read_cb(void *opaque, int ret);
+static void qcow_aio_read_bh(void *opaque)
+{
+ QCowAIOCB *acb = opaque;
+ qemu_bh_delete(acb->bh);
+ acb->bh = NULL;
+ qcow_aio_read_cb(opaque, 0);
+}
+
+static int qcow_schedule_bh(QEMUBHFunc *cb, QCowAIOCB *acb)
+{
+ if (acb->bh)
+ return -EIO;
+
+ acb->bh = qemu_bh_new(cb, acb);
+ if (!acb->bh)
+ return -EIO;
+
+ qemu_bh_schedule(acb->bh);
+
+ return 0;
+}
+
static void qcow_aio_read_cb(void *opaque, int ret)
{
QCowAIOCB *acb = opaque;
acb->hd_aiocb = NULL;
if (ret < 0) {
- fail:
+fail:
acb->common.cb(acb->common.opaque, ret);
qemu_aio_release(acb);
return;
}
- redo:
/* post process the read buffer */
if (!acb->cluster_offset) {
/* nothing to do */
qemu_aio_release(acb);
return;
}
-
+
/* prepare next AIO request */
- acb->cluster_offset = get_cluster_offset(bs, acb->sector_num << 9,
- 0, 0, 0, 0);
+ acb->n = acb->nb_sectors;
+ acb->cluster_offset = get_cluster_offset(bs, acb->sector_num << 9, &acb->n);
index_in_cluster = acb->sector_num & (s->cluster_sectors - 1);
- acb->n = s->cluster_sectors - index_in_cluster;
- if (acb->n > acb->nb_sectors)
- acb->n = acb->nb_sectors;
if (!acb->cluster_offset) {
if (bs->backing_hd) {
if (acb->hd_aiocb == NULL)
goto fail;
} else {
- goto redo;
+ ret = qcow_schedule_bh(qcow_aio_read_bh, acb);
+ if (ret < 0)
+ goto fail;
}
} else {
/* Note: in this case, no need to wait */
memset(acb->buf, 0, 512 * acb->n);
- goto redo;
+ ret = qcow_schedule_bh(qcow_aio_read_bh, acb);
+ if (ret < 0)
+ goto fail;
}
} else if (acb->cluster_offset & QCOW_OFLAG_COMPRESSED) {
/* add AIO support for compressed blocks ? */
goto fail;
memcpy(acb->buf,
s->cluster_cache + index_in_cluster * 512, 512 * acb->n);
- goto redo;
+ ret = qcow_schedule_bh(qcow_aio_read_bh, acb);
+ if (ret < 0)
+ goto fail;
} else {
if ((acb->cluster_offset & 511) != 0) {
ret = -EIO;
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;
acb->hd_aiocb = NULL;
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;
qemu_aio_release(acb);
return;
}
-
+
index_in_cluster = acb->sector_num & (s->cluster_sectors - 1);
- acb->n = s->cluster_sectors - index_in_cluster;
- if (acb->n > acb->nb_sectors)
- acb->n = acb->nb_sectors;
- cluster_offset = get_cluster_offset(bs, acb->sector_num << 9, 1, 0,
- index_in_cluster,
- index_in_cluster + acb->n);
- if (!cluster_offset || (cluster_offset & 511) != 0) {
+ n_end = index_in_cluster + acb->nb_sectors;
+ if (s->crypt_method &&
+ n_end > QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors)
+ n_end = QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors;
+
+ acb->cluster_offset = alloc_cluster_offset(bs, acb->sector_num << 9,
+ index_in_cluster,
+ n_end, &acb->n, &acb->l2meta);
+ if (!acb->cluster_offset || (acb->cluster_offset & 511) != 0) {
ret = -EIO;
goto fail;
}
if (s->crypt_method) {
if (!acb->cluster_data) {
- acb->cluster_data = qemu_mallocz(s->cluster_size);
+ acb->cluster_data = qemu_mallocz(QCOW_MAX_CRYPT_CLUSTERS *
+ s->cluster_size);
if (!acb->cluster_data) {
ret = -ENOMEM;
goto fail;
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)
{
BDRVQcowState *s = bs->opaque;
QCowAIOCB *acb;
-
+
s->cluster_cache_offset = -1; /* disable compressed cache */
acb = qcow_aio_setup(bs, sector_num, (uint8_t*)buf, nb_sectors, cb, opaque);
if (!acb)
return NULL;
-
+
qcow_aio_write_cb(acb, 0);
return &acb->common;
}
QCowHeader header;
uint64_t tmp, offset;
QCowCreateState s1, *s = &s1;
-
+
memset(s, 0, sizeof(*s));
fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644);
s->cluster_size = 1 << s->cluster_bits;
header.cluster_bits = cpu_to_be32(s->cluster_bits);
header_size = (header_size + 7) & ~7;
- if (flags) {
+ if (flags & BLOCK_FLAG_ENCRYPT) {
header.crypt_method = cpu_to_be32(QCOW_CRYPT_AES);
} else {
header.crypt_method = cpu_to_be32(QCOW_CRYPT_NONE);
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);
header.refcount_table_clusters = cpu_to_be32(1);
create_refcount_update(s, s->l1_table_offset, l1_size * sizeof(uint64_t));
create_refcount_update(s, s->refcount_table_offset, s->cluster_size);
create_refcount_update(s, s->refcount_block_offset, s->cluster_size);
-
+
/* write all the data */
write(fd, &header, sizeof(header));
if (backing_file) {
}
lseek(fd, s->refcount_table_offset, SEEK_SET);
write(fd, s->refcount_table, s->cluster_size);
-
+
lseek(fd, s->refcount_block_offset, SEEK_SET);
write(fd, s->refcount_block, s->cluster_size);
memset(s->l1_table, 0, l1_length);
if (bdrv_pwrite(s->hd, s->l1_table_offset, s->l1_table, l1_length) < 0)
- return -1;
+ return -1;
ret = bdrv_truncate(s->hd, s->l1_table_offset + l1_length);
if (ret < 0)
return ret;
-
+
l2_cache_reset(bs);
#endif
return 0;
/* could not compress: write normal cluster */
qcow_write(bs, sector_num, buf, s->cluster_sectors);
} else {
- cluster_offset = get_cluster_offset(bs, sector_num << 9, 2,
- out_len, 0, 0);
+ cluster_offset = alloc_compressed_cluster_offset(bs, sector_num << 9,
+ out_len);
+ if (!cluster_offset)
+ return -1;
cluster_offset &= s->cluster_offset_mask;
if (bdrv_pwrite(s->hd, cluster_offset, out_buf, out_len) != out_len) {
qemu_free(out_buf);
return -1;
}
}
-
+
qemu_free(out_buf);
return 0;
}
uint64_t *l1_table, *l2_table, l2_offset, offset, l1_size2, l1_allocated;
int64_t old_offset, old_l2_offset;
int l2_size, i, j, l1_modified, l2_modified, nb_csectors, refcount;
-
+
l2_cache_reset(bs);
l2_table = NULL;
l1_table = s->l1_table;
l1_allocated = 0;
}
-
+
l2_size = s->l2_size * sizeof(uint64_t);
l2_table = qemu_malloc(l2_size);
if (!l2_table)
snapshots_offset = alloc_clusters(bs, snapshots_size);
offset = snapshots_offset;
-
+
for(i = 0; i < s->nb_snapshots; i++) {
sn = s->snapshots + i;
memset(&h, 0, sizeof(h));
h.date_sec = cpu_to_be32(sn->date_sec);
h.date_nsec = cpu_to_be32(sn->date_nsec);
h.vm_clock_nsec = cpu_to_be64(sn->vm_clock_nsec);
-
+
id_str_size = strlen(sn->id_str);
name_size = strlen(sn->name);
h.id_str_size = cpu_to_be16(id_str_size);
{
BDRVQcowState *s = bs->opaque;
int i, ret;
-
+
ret = find_snapshot_by_id(bs, name);
if (ret >= 0)
return ret;
QCowSnapshot *snapshots1, sn1, *sn = &sn1;
int i, ret;
uint64_t *l1_table = NULL;
-
+
memset(sn, 0, sizeof(*sn));
if (sn_info->id_str[0] == '\0') {
BDRVQcowState *s = bs->opaque;
QCowSnapshot *sn;
int snapshot_index, ret;
-
+
snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_id);
if (snapshot_index < 0)
return -ENOENT;
{
BDRVQcowState *s = bs->opaque;
int ret, refcount_table_size2, i;
-
+
s->refcount_block_cache = qemu_malloc(s->cluster_size);
if (!s->refcount_block_cache)
goto fail;
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)
BDRVQcowState *s = bs->opaque;
int64_t offset, cluster_offset;
int free_in_cluster;
-
+
assert(size > 0 && size <= s->cluster_size);
if (s->free_byte_offset == 0) {
s->free_byte_offset = alloc_clusters(bs, s->cluster_size);
int new_table_size, new_table_size2, refcount_table_clusters, i, ret;
uint64_t *new_table;
int64_t table_offset;
- uint64_t data64;
- uint32_t data32;
+ uint8_t data[12];
int old_table_size;
int64_t old_table_offset;
for(i = 0; i < s->refcount_table_size; i++)
be64_to_cpus(&new_table[i]);
- data64 = cpu_to_be64(table_offset);
+ cpu_to_be64w((uint64_t*)data, table_offset);
+ cpu_to_be32w((uint32_t*)(data + 8), refcount_table_clusters);
if (bdrv_pwrite(s->hd, offsetof(QCowHeader, refcount_table_offset),
- &data64, sizeof(data64)) != sizeof(data64))
- goto fail;
- data32 = cpu_to_be32(refcount_table_clusters);
- if (bdrv_pwrite(s->hd, offsetof(QCowHeader, refcount_table_clusters),
- &data32, sizeof(data32)) != sizeof(data32))
+ data, sizeof(data)) != sizeof(data))
goto fail;
qemu_free(s->refcount_table);
old_table_offset = s->refcount_table_offset;
BDRVQcowState *s = bs->opaque;
int64_t start, last, cluster_offset;
int k;
-
+
if (size <= 0)
return;
goto fail;
for(i = 0;i < l1_size; i++)
be64_to_cpus(&l1_table[i]);
-
+
l2_size = s->l2_size * sizeof(uint64_t);
l2_table = qemu_malloc(l2_size);
if (!l2_table)
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 */
inc_refcounts(bs, refcount_table, nb_clusters,
0, s->cluster_size);
-
+
check_refcounts_l1(bs, refcount_table, nb_clusters,
s->l1_table_offset, s->l1_size, 1);
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);
projects / qemu.git / blobdiff