* THE SOFTWARE.
*/
+#include "qemu/osdep.h"
+#include "qapi/error.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "block/qcow2.h"
#include "qemu/range.h"
+#include "qemu/bswap.h"
static int64_t alloc_clusters_noref(BlockDriverState *bs, uint64_t size);
static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
- int64_t offset, int64_t length, uint16_t addend,
+ int64_t offset, int64_t length, uint64_t addend,
bool decrease, enum qcow2_discard_type type);
+static uint64_t get_refcount_ro0(const void *refcount_array, uint64_t index);
+static uint64_t get_refcount_ro1(const void *refcount_array, uint64_t index);
+static uint64_t get_refcount_ro2(const void *refcount_array, uint64_t index);
+static uint64_t get_refcount_ro3(const void *refcount_array, uint64_t index);
+static uint64_t get_refcount_ro4(const void *refcount_array, uint64_t index);
+static uint64_t get_refcount_ro5(const void *refcount_array, uint64_t index);
+static uint64_t get_refcount_ro6(const void *refcount_array, uint64_t index);
+
+static void set_refcount_ro0(void *refcount_array, uint64_t index,
+ uint64_t value);
+static void set_refcount_ro1(void *refcount_array, uint64_t index,
+ uint64_t value);
+static void set_refcount_ro2(void *refcount_array, uint64_t index,
+ uint64_t value);
+static void set_refcount_ro3(void *refcount_array, uint64_t index,
+ uint64_t value);
+static void set_refcount_ro4(void *refcount_array, uint64_t index,
+ uint64_t value);
+static void set_refcount_ro5(void *refcount_array, uint64_t index,
+ uint64_t value);
+static void set_refcount_ro6(void *refcount_array, uint64_t index,
+ uint64_t value);
+
+
+static Qcow2GetRefcountFunc *const get_refcount_funcs[] = {
+ &get_refcount_ro0,
+ &get_refcount_ro1,
+ &get_refcount_ro2,
+ &get_refcount_ro3,
+ &get_refcount_ro4,
+ &get_refcount_ro5,
+ &get_refcount_ro6
+};
+
+static Qcow2SetRefcountFunc *const set_refcount_funcs[] = {
+ &set_refcount_ro0,
+ &set_refcount_ro1,
+ &set_refcount_ro2,
+ &set_refcount_ro3,
+ &set_refcount_ro4,
+ &set_refcount_ro5,
+ &set_refcount_ro6
+};
+
/*********************************************************/
/* refcount handling */
int qcow2_refcount_init(BlockDriverState *bs)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
unsigned int refcount_table_size2, i;
int ret;
+ assert(s->refcount_order >= 0 && s->refcount_order <= 6);
+
+ s->get_refcount = get_refcount_funcs[s->refcount_order];
+ s->set_refcount = set_refcount_funcs[s->refcount_order];
+
assert(s->refcount_table_size <= INT_MAX / sizeof(uint64_t));
refcount_table_size2 = s->refcount_table_size * sizeof(uint64_t);
s->refcount_table = g_try_malloc(refcount_table_size2);
goto fail;
}
BLKDBG_EVENT(bs->file, BLKDBG_REFTABLE_LOAD);
- ret = bdrv_pread(bs->file, s->refcount_table_offset,
+ ret = bdrv_pread(bs->file->bs, s->refcount_table_offset,
s->refcount_table, refcount_table_size2);
if (ret < 0) {
goto fail;
void qcow2_refcount_close(BlockDriverState *bs)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
g_free(s->refcount_table);
}
+static uint64_t get_refcount_ro0(const void *refcount_array, uint64_t index)
+{
+ return (((const uint8_t *)refcount_array)[index / 8] >> (index % 8)) & 0x1;
+}
+
+static void set_refcount_ro0(void *refcount_array, uint64_t index,
+ uint64_t value)
+{
+ assert(!(value >> 1));
+ ((uint8_t *)refcount_array)[index / 8] &= ~(0x1 << (index % 8));
+ ((uint8_t *)refcount_array)[index / 8] |= value << (index % 8);
+}
+
+static uint64_t get_refcount_ro1(const void *refcount_array, uint64_t index)
+{
+ return (((const uint8_t *)refcount_array)[index / 4] >> (2 * (index % 4)))
+ & 0x3;
+}
+
+static void set_refcount_ro1(void *refcount_array, uint64_t index,
+ uint64_t value)
+{
+ assert(!(value >> 2));
+ ((uint8_t *)refcount_array)[index / 4] &= ~(0x3 << (2 * (index % 4)));
+ ((uint8_t *)refcount_array)[index / 4] |= value << (2 * (index % 4));
+}
+
+static uint64_t get_refcount_ro2(const void *refcount_array, uint64_t index)
+{
+ return (((const uint8_t *)refcount_array)[index / 2] >> (4 * (index % 2)))
+ & 0xf;
+}
+
+static void set_refcount_ro2(void *refcount_array, uint64_t index,
+ uint64_t value)
+{
+ assert(!(value >> 4));
+ ((uint8_t *)refcount_array)[index / 2] &= ~(0xf << (4 * (index % 2)));
+ ((uint8_t *)refcount_array)[index / 2] |= value << (4 * (index % 2));
+}
+
+static uint64_t get_refcount_ro3(const void *refcount_array, uint64_t index)
+{
+ return ((const uint8_t *)refcount_array)[index];
+}
+
+static void set_refcount_ro3(void *refcount_array, uint64_t index,
+ uint64_t value)
+{
+ assert(!(value >> 8));
+ ((uint8_t *)refcount_array)[index] = value;
+}
+
+static uint64_t get_refcount_ro4(const void *refcount_array, uint64_t index)
+{
+ return be16_to_cpu(((const uint16_t *)refcount_array)[index]);
+}
+
+static void set_refcount_ro4(void *refcount_array, uint64_t index,
+ uint64_t value)
+{
+ assert(!(value >> 16));
+ ((uint16_t *)refcount_array)[index] = cpu_to_be16(value);
+}
+
+static uint64_t get_refcount_ro5(const void *refcount_array, uint64_t index)
+{
+ return be32_to_cpu(((const uint32_t *)refcount_array)[index]);
+}
+
+static void set_refcount_ro5(void *refcount_array, uint64_t index,
+ uint64_t value)
+{
+ assert(!(value >> 32));
+ ((uint32_t *)refcount_array)[index] = cpu_to_be32(value);
+}
+
+static uint64_t get_refcount_ro6(const void *refcount_array, uint64_t index)
+{
+ return be64_to_cpu(((const uint64_t *)refcount_array)[index]);
+}
+
+static void set_refcount_ro6(void *refcount_array, uint64_t index,
+ uint64_t value)
+{
+ ((uint64_t *)refcount_array)[index] = cpu_to_be64(value);
+}
+
+
static int load_refcount_block(BlockDriverState *bs,
int64_t refcount_block_offset,
void **refcount_block)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
int ret;
BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_LOAD);
* *refcount. Returns 0 on success and -errno on failure.
*/
int qcow2_get_refcount(BlockDriverState *bs, int64_t cluster_index,
- uint16_t *refcount)
+ uint64_t *refcount)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
uint64_t refcount_table_index, block_index;
int64_t refcount_block_offset;
int ret;
- uint16_t *refcount_block;
+ void *refcount_block;
refcount_table_index = cluster_index >> s->refcount_block_bits;
if (refcount_table_index >= s->refcount_table_size) {
}
ret = qcow2_cache_get(bs, s->refcount_block_cache, refcount_block_offset,
- (void**) &refcount_block);
+ &refcount_block);
if (ret < 0) {
return ret;
}
block_index = cluster_index & (s->refcount_block_size - 1);
- *refcount = be16_to_cpu(refcount_block[block_index]);
+ *refcount = s->get_refcount(refcount_block, block_index);
- ret = qcow2_cache_put(bs, s->refcount_block_cache,
- (void**) &refcount_block);
- if (ret < 0) {
- return ret;
- }
+ qcow2_cache_put(bs, s->refcount_block_cache, &refcount_block);
return 0;
}
* Rounds the refcount table size up to avoid growing the table for each single
* refcount block that is allocated.
*/
-static unsigned int next_refcount_table_size(BDRVQcowState *s,
+static unsigned int next_refcount_table_size(BDRVQcow2State *s,
unsigned int min_size)
{
unsigned int min_clusters = (min_size >> (s->cluster_bits - 3)) + 1;
/* Checks if two offsets are described by the same refcount block */
-static int in_same_refcount_block(BDRVQcowState *s, uint64_t offset_a,
+static int in_same_refcount_block(BDRVQcow2State *s, uint64_t offset_a,
uint64_t offset_b)
{
uint64_t block_a = offset_a >> (s->cluster_bits + s->refcount_block_bits);
* Returns 0 on success or -errno in error case
*/
static int alloc_refcount_block(BlockDriverState *bs,
- int64_t cluster_index, uint16_t **refcount_block)
+ int64_t cluster_index, void **refcount_block)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
unsigned int refcount_table_index;
int ret;
}
return load_refcount_block(bs, refcount_block_offset,
- (void**) refcount_block);
+ refcount_block);
}
}
if (in_same_refcount_block(s, new_block, cluster_index << s->cluster_bits)) {
/* Zero the new refcount block before updating it */
ret = qcow2_cache_get_empty(bs, s->refcount_block_cache, new_block,
- (void**) refcount_block);
+ refcount_block);
if (ret < 0) {
goto fail_block;
}
/* The block describes itself, need to update the cache */
int block_index = (new_block >> s->cluster_bits) &
(s->refcount_block_size - 1);
- (*refcount_block)[block_index] = cpu_to_be16(1);
+ s->set_refcount(*refcount_block, block_index, 1);
} else {
/* Described somewhere else. This can recurse at most twice before we
* arrive at a block that describes itself. */
/* Initialize the new refcount block only after updating its refcount,
* update_refcount uses the refcount cache itself */
ret = qcow2_cache_get_empty(bs, s->refcount_block_cache, new_block,
- (void**) refcount_block);
+ refcount_block);
if (ret < 0) {
goto fail_block;
}
/* Now the new refcount block needs to be written to disk */
BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE);
- qcow2_cache_entry_mark_dirty(s->refcount_block_cache, *refcount_block);
+ qcow2_cache_entry_mark_dirty(bs, s->refcount_block_cache, *refcount_block);
ret = qcow2_cache_flush(bs, s->refcount_block_cache);
if (ret < 0) {
goto fail_block;
if (refcount_table_index < s->refcount_table_size) {
uint64_t data64 = cpu_to_be64(new_block);
BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_HOOKUP);
- ret = bdrv_pwrite_sync(bs->file,
+ ret = bdrv_pwrite_sync(bs->file->bs,
s->refcount_table_offset + refcount_table_index * sizeof(uint64_t),
&data64, sizeof(data64));
if (ret < 0) {
return -EAGAIN;
}
- ret = qcow2_cache_put(bs, s->refcount_block_cache, (void**) refcount_block);
- if (ret < 0) {
- goto fail_block;
- }
+ qcow2_cache_put(bs, s->refcount_block_cache, refcount_block);
/*
* If we come here, we need to grow the refcount table. Again, a new
*/
BLKDBG_EVENT(bs->file, BLKDBG_REFTABLE_GROW);
- /* Calculate the number of refcount blocks needed so far */
- uint64_t blocks_used = DIV_ROUND_UP(cluster_index, s->refcount_block_size);
+ /* Calculate the number of refcount blocks needed so far; this will be the
+ * basis for calculating the index of the first cluster used for the
+ * self-describing refcount structures which we are about to create.
+ *
+ * Because we reached this point, there cannot be any refcount entries for
+ * cluster_index or higher indices yet. However, because new_block has been
+ * allocated to describe that cluster (and it will assume this role later
+ * on), we cannot use that index; also, new_block may actually have a higher
+ * cluster index than cluster_index, so it needs to be taken into account
+ * here (and 1 needs to be added to its value because that cluster is used).
+ */
+ uint64_t blocks_used = DIV_ROUND_UP(MAX(cluster_index + 1,
+ (new_block >> s->cluster_bits) + 1),
+ s->refcount_block_size);
if (blocks_used > QCOW_MAX_REFTABLE_SIZE / sizeof(uint64_t)) {
return -EFBIG;
s->cluster_size;
uint64_t table_offset = meta_offset + blocks_clusters * s->cluster_size;
uint64_t *new_table = g_try_new0(uint64_t, table_size);
- uint16_t *new_blocks = g_try_malloc0(blocks_clusters * s->cluster_size);
+ void *new_blocks = g_try_malloc0(blocks_clusters * s->cluster_size);
assert(table_size > 0 && blocks_clusters > 0);
if (new_table == NULL || new_blocks == NULL) {
uint64_t table_clusters = size_to_clusters(s, table_size * sizeof(uint64_t));
int block = 0;
for (i = 0; i < table_clusters + blocks_clusters; i++) {
- new_blocks[block++] = cpu_to_be16(1);
+ s->set_refcount(new_blocks, block++, 1);
}
/* Write refcount blocks to disk */
BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE_BLOCKS);
- ret = bdrv_pwrite_sync(bs->file, meta_offset, new_blocks,
+ ret = bdrv_pwrite_sync(bs->file->bs, meta_offset, new_blocks,
blocks_clusters * s->cluster_size);
g_free(new_blocks);
new_blocks = NULL;
}
BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE_TABLE);
- ret = bdrv_pwrite_sync(bs->file, table_offset, new_table,
+ ret = bdrv_pwrite_sync(bs->file->bs, table_offset, new_table,
table_size * sizeof(uint64_t));
if (ret < 0) {
goto fail_table;
}
/* Hook up the new refcount table in the qcow2 header */
- uint8_t data[12];
- cpu_to_be64w((uint64_t*)data, table_offset);
- cpu_to_be32w((uint32_t*)(data + 8), table_clusters);
+ struct QEMU_PACKED {
+ uint64_t d64;
+ uint32_t d32;
+ } data;
+ cpu_to_be64w(&data.d64, table_offset);
+ cpu_to_be32w(&data.d32, table_clusters);
BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_SWITCH_TABLE);
- ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, refcount_table_offset),
- data, sizeof(data));
+ ret = bdrv_pwrite_sync(bs->file->bs,
+ offsetof(QCowHeader, refcount_table_offset),
+ &data, sizeof(data));
if (ret < 0) {
goto fail_table;
}
qcow2_free_clusters(bs, old_table_offset, old_table_size * sizeof(uint64_t),
QCOW2_DISCARD_OTHER);
- ret = load_refcount_block(bs, new_block, (void**) refcount_block);
+ ret = load_refcount_block(bs, new_block, refcount_block);
if (ret < 0) {
return ret;
}
g_free(new_table);
fail_block:
if (*refcount_block != NULL) {
- qcow2_cache_put(bs, s->refcount_block_cache, (void**) refcount_block);
+ qcow2_cache_put(bs, s->refcount_block_cache, refcount_block);
}
return ret;
}
void qcow2_process_discards(BlockDriverState *bs, int ret)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
Qcow2DiscardRegion *d, *next;
QTAILQ_FOREACH_SAFE(d, &s->discards, next, next) {
/* Discard is optional, ignore the return value */
if (ret >= 0) {
- bdrv_discard(bs->file,
+ bdrv_discard(bs->file->bs,
d->offset >> BDRV_SECTOR_BITS,
d->bytes >> BDRV_SECTOR_BITS);
}
static void update_refcount_discard(BlockDriverState *bs,
uint64_t offset, uint64_t length)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
Qcow2DiscardRegion *d, *p, *next;
QTAILQ_FOREACH(d, &s->discards, next) {
static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
int64_t offset,
int64_t length,
- uint16_t addend,
+ uint64_t addend,
bool decrease,
enum qcow2_discard_type type)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
int64_t start, last, cluster_offset;
- uint16_t *refcount_block = NULL;
+ void *refcount_block = NULL;
int64_t old_table_index = -1;
int ret;
#ifdef DEBUG_ALLOC2
fprintf(stderr, "update_refcount: offset=%" PRId64 " size=%" PRId64
- " addend=%s%" PRIu16 "\n", offset, length, decrease ? "-" : "",
+ " addend=%s%" PRIu64 "\n", offset, length, decrease ? "-" : "",
addend);
#endif
if (length < 0) {
cluster_offset += s->cluster_size)
{
int block_index;
- uint16_t refcount;
+ uint64_t refcount;
int64_t cluster_index = cluster_offset >> s->cluster_bits;
int64_t table_index = cluster_index >> s->refcount_block_bits;
/* Load the refcount block and allocate it if needed */
if (table_index != old_table_index) {
if (refcount_block) {
- ret = qcow2_cache_put(bs, s->refcount_block_cache,
- (void**) &refcount_block);
- if (ret < 0) {
- goto fail;
- }
+ qcow2_cache_put(bs, s->refcount_block_cache, &refcount_block);
}
-
ret = alloc_refcount_block(bs, cluster_index, &refcount_block);
if (ret < 0) {
goto fail;
}
old_table_index = table_index;
- qcow2_cache_entry_mark_dirty(s->refcount_block_cache, refcount_block);
+ qcow2_cache_entry_mark_dirty(bs, s->refcount_block_cache,
+ refcount_block);
/* we can update the count and save it */
block_index = cluster_index & (s->refcount_block_size - 1);
- refcount = be16_to_cpu(refcount_block[block_index]);
- if (decrease ? ((uint16_t)(refcount - addend) > refcount)
- : ((uint16_t)(refcount + addend) < refcount ||
- (uint16_t)(refcount + addend) > s->refcount_max))
+ refcount = s->get_refcount(refcount_block, block_index);
+ if (decrease ? (refcount - addend > refcount)
+ : (refcount + addend < refcount ||
+ refcount + addend > s->refcount_max))
{
ret = -EINVAL;
goto fail;
if (refcount == 0 && cluster_index < s->free_cluster_index) {
s->free_cluster_index = cluster_index;
}
- refcount_block[block_index] = cpu_to_be16(refcount);
+ s->set_refcount(refcount_block, block_index, refcount);
if (refcount == 0 && s->discard_passthrough[type]) {
update_refcount_discard(bs, cluster_offset, s->cluster_size);
/* Write last changed block to disk */
if (refcount_block) {
- int wret;
- wret = qcow2_cache_put(bs, s->refcount_block_cache,
- (void**) &refcount_block);
- if (wret < 0) {
- return ret < 0 ? ret : wret;
- }
+ qcow2_cache_put(bs, s->refcount_block_cache, &refcount_block);
}
/*
*/
int qcow2_update_cluster_refcount(BlockDriverState *bs,
int64_t cluster_index,
- uint16_t addend, bool decrease,
+ uint64_t addend, bool decrease,
enum qcow2_discard_type type)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
int ret;
ret = update_refcount(bs, cluster_index << s->cluster_bits, 1, addend,
/* return < 0 if error */
static int64_t alloc_clusters_noref(BlockDriverState *bs, uint64_t size)
{
- BDRVQcowState *s = bs->opaque;
- uint64_t i, nb_clusters;
- uint16_t refcount;
+ BDRVQcow2State *s = bs->opaque;
+ uint64_t i, nb_clusters, refcount;
int ret;
+ /* We can't allocate clusters if they may still be queued for discard. */
+ if (s->cache_discards) {
+ qcow2_process_discards(bs, 0);
+ }
+
nb_clusters = size_to_clusters(s, size);
retry:
for(i = 0; i < nb_clusters; i++) {
return offset;
}
-int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
- int nb_clusters)
+int64_t qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
+ int64_t nb_clusters)
{
- BDRVQcowState *s = bs->opaque;
- uint64_t cluster_index;
+ BDRVQcow2State *s = bs->opaque;
+ uint64_t cluster_index, refcount;
uint64_t i;
- uint16_t refcount;
int ret;
assert(nb_clusters >= 0);
contiguous sectors. size must be <= cluster_size */
int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
int64_t offset;
size_t free_in_cluster;
int ret;
offset = s->free_byte_offset;
if (offset) {
- uint16_t refcount;
+ uint64_t refcount;
ret = qcow2_get_refcount(bs, offset >> s->cluster_bits, &refcount);
if (ret < 0) {
return ret;
}
free_in_cluster = s->cluster_size - offset_into_cluster(s, offset);
- if (!offset || free_in_cluster < size) {
- int64_t new_cluster = alloc_clusters_noref(bs, s->cluster_size);
- if (new_cluster < 0) {
- return new_cluster;
- }
+ do {
+ if (!offset || free_in_cluster < size) {
+ int64_t new_cluster = alloc_clusters_noref(bs, s->cluster_size);
+ if (new_cluster < 0) {
+ return new_cluster;
+ }
- if (!offset || ROUND_UP(offset, s->cluster_size) != new_cluster) {
- offset = new_cluster;
+ if (!offset || ROUND_UP(offset, s->cluster_size) != new_cluster) {
+ offset = new_cluster;
+ free_in_cluster = s->cluster_size;
+ } else {
+ free_in_cluster += s->cluster_size;
+ }
}
- }
- assert(offset);
- ret = update_refcount(bs, offset, size, 1, false, QCOW2_DISCARD_NEVER);
+ assert(offset);
+ ret = update_refcount(bs, offset, size, 1, false, QCOW2_DISCARD_NEVER);
+ if (ret < 0) {
+ offset = 0;
+ }
+ } while (ret == -EAGAIN);
if (ret < 0) {
return ret;
}
void qcow2_free_any_clusters(BlockDriverState *bs, uint64_t l2_entry,
int nb_clusters, enum qcow2_discard_type type)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
switch (qcow2_get_cluster_type(l2_entry)) {
case QCOW2_CLUSTER_COMPRESSED:
int qcow2_update_snapshot_refcount(BlockDriverState *bs,
int64_t l1_table_offset, int l1_size, int addend)
{
- BDRVQcowState *s = bs->opaque;
- uint64_t *l1_table, *l2_table, l2_offset, offset, l1_size2;
+ BDRVQcow2State *s = bs->opaque;
+ uint64_t *l1_table, *l2_table, l2_offset, offset, l1_size2, refcount;
bool l1_allocated = false;
int64_t old_offset, old_l2_offset;
int i, j, l1_modified = 0, nb_csectors;
- uint16_t refcount;
int ret;
assert(addend >= -1 && addend <= 1);
}
l1_allocated = true;
- ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size2);
+ ret = bdrv_pread(bs->file->bs, l1_table_offset, l1_table, l1_size2);
if (ret < 0) {
goto fail;
}
s->refcount_block_cache);
}
l2_table[j] = cpu_to_be64(offset);
- qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
+ qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache,
+ l2_table);
}
}
- ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
- if (ret < 0) {
- goto fail;
- }
-
+ qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table);
if (addend != 0) {
ret = qcow2_update_cluster_refcount(bs, l2_offset >>
cpu_to_be64s(&l1_table[i]);
}
- ret = bdrv_pwrite_sync(bs->file, l1_table_offset, l1_table, l1_size2);
+ ret = bdrv_pwrite_sync(bs->file->bs, l1_table_offset,
+ l1_table, l1_size2);
for (i = 0; i < l1_size; i++) {
be64_to_cpus(&l1_table[i]);
/* refcount checking functions */
+static uint64_t refcount_array_byte_size(BDRVQcow2State *s, uint64_t entries)
+{
+ /* This assertion holds because there is no way we can address more than
+ * 2^(64 - 9) clusters at once (with cluster size 512 = 2^9, and because
+ * offsets have to be representable in bytes); due to every cluster
+ * corresponding to one refcount entry, we are well below that limit */
+ assert(entries < (UINT64_C(1) << (64 - 9)));
+
+ /* Thanks to the assertion this will not overflow, because
+ * s->refcount_order < 7.
+ * (note: x << s->refcount_order == x * s->refcount_bits) */
+ return DIV_ROUND_UP(entries << s->refcount_order, 8);
+}
+
+/**
+ * Reallocates *array so that it can hold new_size entries. *size must contain
+ * the current number of entries in *array. If the reallocation fails, *array
+ * and *size will not be modified and -errno will be returned. If the
+ * reallocation is successful, *array will be set to the new buffer, *size
+ * will be set to new_size and 0 will be returned. The size of the reallocated
+ * refcount array buffer will be aligned to a cluster boundary, and the newly
+ * allocated area will be zeroed.
+ */
+static int realloc_refcount_array(BDRVQcow2State *s, void **array,
+ int64_t *size, int64_t new_size)
+{
+ int64_t old_byte_size, new_byte_size;
+ void *new_ptr;
+
+ /* Round to clusters so the array can be directly written to disk */
+ old_byte_size = size_to_clusters(s, refcount_array_byte_size(s, *size))
+ * s->cluster_size;
+ new_byte_size = size_to_clusters(s, refcount_array_byte_size(s, new_size))
+ * s->cluster_size;
+
+ if (new_byte_size == old_byte_size) {
+ *size = new_size;
+ return 0;
+ }
+
+ assert(new_byte_size > 0);
+
+ if (new_byte_size > SIZE_MAX) {
+ return -ENOMEM;
+ }
+
+ new_ptr = g_try_realloc(*array, new_byte_size);
+ if (!new_ptr) {
+ return -ENOMEM;
+ }
+
+ if (new_byte_size > old_byte_size) {
+ memset((char *)new_ptr + old_byte_size, 0,
+ new_byte_size - old_byte_size);
+ }
+
+ *array = new_ptr;
+ *size = new_size;
+
+ return 0;
+}
/*
* Increases the refcount for a range of clusters in a given refcount table.
* This is used to construct a temporary refcount table out of L1 and L2 tables
- * which can be compared the the refcount table saved in the image.
+ * which can be compared to the refcount table saved in the image.
*
* Modifies the number of errors in res.
*/
static int inc_refcounts(BlockDriverState *bs,
BdrvCheckResult *res,
- uint16_t **refcount_table,
+ void **refcount_table,
int64_t *refcount_table_size,
int64_t offset, int64_t size)
{
- BDRVQcowState *s = bs->opaque;
- uint64_t start, last, cluster_offset, k;
+ BDRVQcow2State *s = bs->opaque;
+ uint64_t start, last, cluster_offset, k, refcount;
+ int ret;
if (size <= 0) {
return 0;
cluster_offset += s->cluster_size) {
k = cluster_offset >> s->cluster_bits;
if (k >= *refcount_table_size) {
- int64_t old_refcount_table_size = *refcount_table_size;
- uint16_t *new_refcount_table;
-
- *refcount_table_size = k + 1;
- new_refcount_table = g_try_realloc(*refcount_table,
- *refcount_table_size *
- sizeof(**refcount_table));
- if (!new_refcount_table) {
- *refcount_table_size = old_refcount_table_size;
+ ret = realloc_refcount_array(s, refcount_table,
+ refcount_table_size, k + 1);
+ if (ret < 0) {
res->check_errors++;
- return -ENOMEM;
+ return ret;
}
- *refcount_table = new_refcount_table;
-
- memset(*refcount_table + old_refcount_table_size, 0,
- (*refcount_table_size - old_refcount_table_size) *
- sizeof(**refcount_table));
}
- if (++(*refcount_table)[k] == 0) {
+ refcount = s->get_refcount(*refcount_table, k);
+ if (refcount == s->refcount_max) {
fprintf(stderr, "ERROR: overflow cluster offset=0x%" PRIx64
"\n", cluster_offset);
+ fprintf(stderr, "Use qemu-img amend to increase the refcount entry "
+ "width or qemu-img convert to create a clean copy if the "
+ "image cannot be opened for writing\n");
res->corruptions++;
+ continue;
}
+ s->set_refcount(*refcount_table, k, refcount + 1);
}
return 0;
* error occurred.
*/
static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res,
- uint16_t **refcount_table, int64_t *refcount_table_size, int64_t l2_offset,
- int flags)
+ void **refcount_table,
+ int64_t *refcount_table_size, int64_t l2_offset,
+ int flags)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
uint64_t *l2_table, l2_entry;
uint64_t next_contiguous_offset = 0;
int i, l2_size, nb_csectors, ret;
l2_size = s->l2_size * sizeof(uint64_t);
l2_table = g_malloc(l2_size);
- ret = bdrv_pread(bs->file, l2_offset, l2_table, l2_size);
+ ret = bdrv_pread(bs->file->bs, l2_offset, l2_table, l2_size);
if (ret < 0) {
fprintf(stderr, "ERROR: I/O error in check_refcounts_l2\n");
res->check_errors++;
*/
static int check_refcounts_l1(BlockDriverState *bs,
BdrvCheckResult *res,
- uint16_t **refcount_table,
+ void **refcount_table,
int64_t *refcount_table_size,
int64_t l1_table_offset, int l1_size,
int flags)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
uint64_t *l1_table = NULL, l2_offset, l1_size2;
int i, ret;
res->check_errors++;
goto fail;
}
- ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size2);
+ ret = bdrv_pread(bs->file->bs, l1_table_offset, l1_table, l1_size2);
if (ret < 0) {
fprintf(stderr, "ERROR: I/O error in check_refcounts_l1\n");
res->check_errors++;
static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res,
BdrvCheckMode fix)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
uint64_t *l2_table = qemu_blockalign(bs, s->cluster_size);
int ret;
- uint16_t refcount;
+ uint64_t refcount;
int i, j;
for (i = 0; i < s->l1_size; i++) {
}
if ((refcount == 1) != ((l1_entry & QCOW_OFLAG_COPIED) != 0)) {
fprintf(stderr, "%s OFLAG_COPIED L2 cluster: l1_index=%d "
- "l1_entry=%" PRIx64 " refcount=%d\n",
+ "l1_entry=%" PRIx64 " refcount=%" PRIu64 "\n",
fix & BDRV_FIX_ERRORS ? "Repairing" :
"ERROR",
i, l1_entry, refcount);
}
}
- ret = bdrv_pread(bs->file, l2_offset, l2_table,
+ ret = bdrv_pread(bs->file->bs, l2_offset, l2_table,
s->l2_size * sizeof(uint64_t));
if (ret < 0) {
fprintf(stderr, "ERROR: Could not read L2 table: %s\n",
}
if ((refcount == 1) != ((l2_entry & QCOW_OFLAG_COPIED) != 0)) {
fprintf(stderr, "%s OFLAG_COPIED data cluster: "
- "l2_entry=%" PRIx64 " refcount=%d\n",
+ "l2_entry=%" PRIx64 " refcount=%" PRIu64 "\n",
fix & BDRV_FIX_ERRORS ? "Repairing" :
"ERROR",
l2_entry, refcount);
goto fail;
}
- ret = bdrv_pwrite(bs->file, l2_offset, l2_table, s->cluster_size);
+ ret = bdrv_pwrite(bs->file->bs, l2_offset, l2_table,
+ s->cluster_size);
if (ret < 0) {
fprintf(stderr, "ERROR: Could not write L2 table: %s\n",
strerror(-ret));
*/
static int check_refblocks(BlockDriverState *bs, BdrvCheckResult *res,
BdrvCheckMode fix, bool *rebuild,
- uint16_t **refcount_table, int64_t *nb_clusters)
+ void **refcount_table, int64_t *nb_clusters)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
int64_t i, size;
int ret;
fix & BDRV_FIX_ERRORS ? "Repairing" : "ERROR", i);
if (fix & BDRV_FIX_ERRORS) {
- int64_t old_nb_clusters = *nb_clusters;
- uint16_t *new_refcount_table;
+ int64_t new_nb_clusters;
if (offset > INT64_MAX - s->cluster_size) {
ret = -EINVAL;
goto resize_fail;
}
- ret = bdrv_truncate(bs->file, offset + s->cluster_size);
+ ret = bdrv_truncate(bs->file->bs, offset + s->cluster_size);
if (ret < 0) {
goto resize_fail;
}
- size = bdrv_getlength(bs->file);
+ size = bdrv_getlength(bs->file->bs);
if (size < 0) {
ret = size;
goto resize_fail;
}
- *nb_clusters = size_to_clusters(s, size);
- assert(*nb_clusters >= old_nb_clusters);
+ new_nb_clusters = size_to_clusters(s, size);
+ assert(new_nb_clusters >= *nb_clusters);
- new_refcount_table = g_try_realloc(*refcount_table,
- *nb_clusters *
- sizeof(**refcount_table));
- if (!new_refcount_table) {
- *nb_clusters = old_nb_clusters;
+ ret = realloc_refcount_array(s, refcount_table,
+ nb_clusters, new_nb_clusters);
+ if (ret < 0) {
res->check_errors++;
- return -ENOMEM;
+ return ret;
}
- *refcount_table = new_refcount_table;
-
- memset(*refcount_table + old_nb_clusters, 0,
- (*nb_clusters - old_nb_clusters) *
- sizeof(**refcount_table));
if (cluster >= *nb_clusters) {
ret = -EINVAL;
if (ret < 0) {
return ret;
}
- if ((*refcount_table)[cluster] != 1) {
+ if (s->get_refcount(*refcount_table, cluster) != 1) {
fprintf(stderr, "ERROR refcount block %" PRId64
- " refcount=%d\n", i, (*refcount_table)[cluster]);
+ " refcount=%" PRIu64 "\n", i,
+ s->get_refcount(*refcount_table, cluster));
res->corruptions++;
*rebuild = true;
}
*/
static int calculate_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
BdrvCheckMode fix, bool *rebuild,
- uint16_t **refcount_table, int64_t *nb_clusters)
+ void **refcount_table, int64_t *nb_clusters)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
int64_t i;
QCowSnapshot *sn;
int ret;
if (!*refcount_table) {
- *refcount_table = g_try_new0(uint16_t, *nb_clusters);
- if (*nb_clusters && *refcount_table == NULL) {
+ int64_t old_size = 0;
+ ret = realloc_refcount_array(s, refcount_table,
+ &old_size, *nb_clusters);
+ if (ret < 0) {
res->check_errors++;
- return -ENOMEM;
+ return ret;
}
}
static void compare_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
BdrvCheckMode fix, bool *rebuild,
int64_t *highest_cluster,
- uint16_t *refcount_table, int64_t nb_clusters)
+ void *refcount_table, int64_t nb_clusters)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
int64_t i;
- uint16_t refcount1, refcount2;
+ uint64_t refcount1, refcount2;
int ret;
for (i = 0, *highest_cluster = 0; i < nb_clusters; i++) {
continue;
}
- refcount2 = refcount_table[i];
+ refcount2 = s->get_refcount(refcount_table, i);
if (refcount1 > 0 || refcount2 > 0) {
*highest_cluster = i;
num_fixed = &res->corruptions_fixed;
}
- fprintf(stderr, "%s cluster %" PRId64 " refcount=%d reference=%d\n",
+ fprintf(stderr, "%s cluster %" PRId64 " refcount=%" PRIu64
+ " reference=%" PRIu64 "\n",
num_fixed != NULL ? "Repairing" :
refcount1 < refcount2 ? "ERROR" :
"Leaked",
*/
static int64_t alloc_clusters_imrt(BlockDriverState *bs,
int cluster_count,
- uint16_t **refcount_table,
+ void **refcount_table,
int64_t *imrt_nb_clusters,
int64_t *first_free_cluster)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
int64_t cluster = *first_free_cluster, i;
bool first_gap = true;
int contiguous_free_clusters;
+ int ret;
/* Starting at *first_free_cluster, find a range of at least cluster_count
* continuously free clusters */
contiguous_free_clusters < cluster_count;
cluster++)
{
- if (!(*refcount_table)[cluster]) {
+ if (!s->get_refcount(*refcount_table, cluster)) {
contiguous_free_clusters++;
if (first_gap) {
/* If this is the first free cluster found, update
/* If no such range could be found, grow the in-memory refcount table
* accordingly to append free clusters at the end of the image */
if (contiguous_free_clusters < cluster_count) {
- int64_t old_imrt_nb_clusters = *imrt_nb_clusters;
- uint16_t *new_refcount_table;
-
/* contiguous_free_clusters clusters are already empty at the image end;
* we need cluster_count clusters; therefore, we have to allocate
* cluster_count - contiguous_free_clusters new clusters at the end of
* the image (which is the current value of cluster; note that cluster
* may exceed old_imrt_nb_clusters if *first_free_cluster pointed beyond
* the image end) */
- *imrt_nb_clusters = cluster + cluster_count - contiguous_free_clusters;
- new_refcount_table = g_try_realloc(*refcount_table,
- *imrt_nb_clusters *
- sizeof(**refcount_table));
- if (!new_refcount_table) {
- *imrt_nb_clusters = old_imrt_nb_clusters;
- return -ENOMEM;
+ ret = realloc_refcount_array(s, refcount_table, imrt_nb_clusters,
+ cluster + cluster_count
+ - contiguous_free_clusters);
+ if (ret < 0) {
+ return ret;
}
- *refcount_table = new_refcount_table;
-
- memset(*refcount_table + old_imrt_nb_clusters, 0,
- (*imrt_nb_clusters - old_imrt_nb_clusters) *
- sizeof(**refcount_table));
}
/* Go back to the first free cluster */
cluster -= contiguous_free_clusters;
for (i = 0; i < cluster_count; i++) {
- (*refcount_table)[cluster + i] = 1;
+ s->set_refcount(*refcount_table, cluster + i, 1);
}
return cluster << s->cluster_bits;
*/
static int rebuild_refcount_structure(BlockDriverState *bs,
BdrvCheckResult *res,
- uint16_t **refcount_table,
+ void **refcount_table,
int64_t *nb_clusters)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
int64_t first_free_cluster = 0, reftable_offset = -1, cluster = 0;
int64_t refblock_offset, refblock_start, refblock_index;
uint32_t reftable_size = 0;
uint64_t *on_disk_reftable = NULL;
- uint16_t *on_disk_refblock;
- int i, ret = 0;
+ void *on_disk_refblock;
+ int ret = 0;
struct {
uint64_t reftable_offset;
uint32_t reftable_clusters;
write_refblocks:
for (; cluster < *nb_clusters; cluster++) {
- if (!(*refcount_table)[cluster]) {
+ if (!s->get_refcount(*refcount_table, cluster)) {
continue;
}
goto fail;
}
- on_disk_refblock = qemu_blockalign0(bs->file, s->cluster_size);
- for (i = 0; i < s->refcount_block_size &&
- refblock_start + i < *nb_clusters; i++)
- {
- on_disk_refblock[i] =
- cpu_to_be16((*refcount_table)[refblock_start + i]);
- }
+ /* The size of *refcount_table is always cluster-aligned, therefore the
+ * write operation will not overflow */
+ on_disk_refblock = (void *)((char *) *refcount_table +
+ refblock_index * s->cluster_size);
- ret = bdrv_write(bs->file, refblock_offset / BDRV_SECTOR_SIZE,
- (void *)on_disk_refblock, s->cluster_sectors);
- qemu_vfree(on_disk_refblock);
+ ret = bdrv_write(bs->file->bs, refblock_offset / BDRV_SECTOR_SIZE,
+ on_disk_refblock, s->cluster_sectors);
if (ret < 0) {
fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret));
goto fail;
}
assert(reftable_size < INT_MAX / sizeof(uint64_t));
- ret = bdrv_pwrite(bs->file, reftable_offset, on_disk_reftable,
+ ret = bdrv_pwrite(bs->file->bs, reftable_offset, on_disk_reftable,
reftable_size * sizeof(uint64_t));
if (ret < 0) {
fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret));
reftable_offset);
cpu_to_be32w(&reftable_offset_and_clusters.reftable_clusters,
size_to_clusters(s, reftable_size * sizeof(uint64_t)));
- ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader,
- refcount_table_offset),
+ ret = bdrv_pwrite_sync(bs->file->bs, offsetof(QCowHeader,
+ refcount_table_offset),
&reftable_offset_and_clusters,
sizeof(reftable_offset_and_clusters));
if (ret < 0) {
int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
BdrvCheckMode fix)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
BdrvCheckResult pre_compare_res;
int64_t size, highest_cluster, nb_clusters;
- uint16_t *refcount_table = NULL;
+ void *refcount_table = NULL;
bool rebuild = false;
int ret;
- size = bdrv_getlength(bs->file);
+ size = bdrv_getlength(bs->file->bs);
if (size < 0) {
res->check_errors++;
return size;
/* Because the old reftable has been exchanged for a new one the
* references have to be recalculated */
rebuild = false;
- memset(refcount_table, 0, nb_clusters * sizeof(uint16_t));
+ memset(refcount_table, 0, refcount_array_byte_size(s, nb_clusters));
ret = calculate_refcounts(bs, res, 0, &rebuild, &refcount_table,
&nb_clusters);
if (ret < 0) {
int qcow2_check_metadata_overlap(BlockDriverState *bs, int ign, int64_t offset,
int64_t size)
{
- BDRVQcowState *s = bs->opaque;
+ BDRVQcow2State *s = bs->opaque;
int chk = s->overlap_check & ~ign;
int i, j;
return -ENOMEM;
}
- ret = bdrv_pread(bs->file, l1_ofs, l1, l1_sz2);
+ ret = bdrv_pread(bs->file->bs, l1_ofs, l1, l1_sz2);
if (ret < 0) {
g_free(l1);
return ret;
if (ret < 0) {
return ret;
} else if (ret > 0) {
- int metadata_ol_bitnr = ffs(ret) - 1;
+ int metadata_ol_bitnr = ctz32(ret);
assert(metadata_ol_bitnr < QCOW2_OL_MAX_BITNR);
qcow2_signal_corruption(bs, true, offset, size, "Preventing invalid "
return 0;
}
+
+/* A pointer to a function of this type is given to walk_over_reftable(). That
+ * function will create refblocks and pass them to a RefblockFinishOp once they
+ * are completed (@refblock). @refblock_empty is set if the refblock is
+ * completely empty.
+ *
+ * Along with the refblock, a corresponding reftable entry is passed, in the
+ * reftable @reftable (which may be reallocated) at @reftable_index.
+ *
+ * @allocated should be set to true if a new cluster has been allocated.
+ */
+typedef int (RefblockFinishOp)(BlockDriverState *bs, uint64_t **reftable,
+ uint64_t reftable_index, uint64_t *reftable_size,
+ void *refblock, bool refblock_empty,
+ bool *allocated, Error **errp);
+
+/**
+ * This "operation" for walk_over_reftable() allocates the refblock on disk (if
+ * it is not empty) and inserts its offset into the new reftable. The size of
+ * this new reftable is increased as required.
+ */
+static int alloc_refblock(BlockDriverState *bs, uint64_t **reftable,
+ uint64_t reftable_index, uint64_t *reftable_size,
+ void *refblock, bool refblock_empty, bool *allocated,
+ Error **errp)
+{
+ BDRVQcow2State *s = bs->opaque;
+ int64_t offset;
+
+ if (!refblock_empty && reftable_index >= *reftable_size) {
+ uint64_t *new_reftable;
+ uint64_t new_reftable_size;
+
+ new_reftable_size = ROUND_UP(reftable_index + 1,
+ s->cluster_size / sizeof(uint64_t));
+ if (new_reftable_size > QCOW_MAX_REFTABLE_SIZE / sizeof(uint64_t)) {
+ error_setg(errp,
+ "This operation would make the refcount table grow "
+ "beyond the maximum size supported by QEMU, aborting");
+ return -ENOTSUP;
+ }
+
+ new_reftable = g_try_realloc(*reftable, new_reftable_size *
+ sizeof(uint64_t));
+ if (!new_reftable) {
+ error_setg(errp, "Failed to increase reftable buffer size");
+ return -ENOMEM;
+ }
+
+ memset(new_reftable + *reftable_size, 0,
+ (new_reftable_size - *reftable_size) * sizeof(uint64_t));
+
+ *reftable = new_reftable;
+ *reftable_size = new_reftable_size;
+ }
+
+ if (!refblock_empty && !(*reftable)[reftable_index]) {
+ offset = qcow2_alloc_clusters(bs, s->cluster_size);
+ if (offset < 0) {
+ error_setg_errno(errp, -offset, "Failed to allocate refblock");
+ return offset;
+ }
+ (*reftable)[reftable_index] = offset;
+ *allocated = true;
+ }
+
+ return 0;
+}
+
+/**
+ * This "operation" for walk_over_reftable() writes the refblock to disk at the
+ * offset specified by the new reftable's entry. It does not modify the new
+ * reftable or change any refcounts.
+ */
+static int flush_refblock(BlockDriverState *bs, uint64_t **reftable,
+ uint64_t reftable_index, uint64_t *reftable_size,
+ void *refblock, bool refblock_empty, bool *allocated,
+ Error **errp)
+{
+ BDRVQcow2State *s = bs->opaque;
+ int64_t offset;
+ int ret;
+
+ if (reftable_index < *reftable_size && (*reftable)[reftable_index]) {
+ offset = (*reftable)[reftable_index];
+
+ ret = qcow2_pre_write_overlap_check(bs, 0, offset, s->cluster_size);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Overlap check failed");
+ return ret;
+ }
+
+ ret = bdrv_pwrite(bs->file->bs, offset, refblock, s->cluster_size);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Failed to write refblock");
+ return ret;
+ }
+ } else {
+ assert(refblock_empty);
+ }
+
+ return 0;
+}
+
+/**
+ * This function walks over the existing reftable and every referenced refblock;
+ * if @new_set_refcount is non-NULL, it is called for every refcount entry to
+ * create an equal new entry in the passed @new_refblock. Once that
+ * @new_refblock is completely filled, @operation will be called.
+ *
+ * @status_cb and @cb_opaque are used for the amend operation's status callback.
+ * @index is the index of the walk_over_reftable() calls and @total is the total
+ * number of walk_over_reftable() calls per amend operation. Both are used for
+ * calculating the parameters for the status callback.
+ *
+ * @allocated is set to true if a new cluster has been allocated.
+ */
+static int walk_over_reftable(BlockDriverState *bs, uint64_t **new_reftable,
+ uint64_t *new_reftable_index,
+ uint64_t *new_reftable_size,
+ void *new_refblock, int new_refblock_size,
+ int new_refcount_bits,
+ RefblockFinishOp *operation, bool *allocated,
+ Qcow2SetRefcountFunc *new_set_refcount,
+ BlockDriverAmendStatusCB *status_cb,
+ void *cb_opaque, int index, int total,
+ Error **errp)
+{
+ BDRVQcow2State *s = bs->opaque;
+ uint64_t reftable_index;
+ bool new_refblock_empty = true;
+ int refblock_index;
+ int new_refblock_index = 0;
+ int ret;
+
+ for (reftable_index = 0; reftable_index < s->refcount_table_size;
+ reftable_index++)
+ {
+ uint64_t refblock_offset = s->refcount_table[reftable_index]
+ & REFT_OFFSET_MASK;
+
+ status_cb(bs, (uint64_t)index * s->refcount_table_size + reftable_index,
+ (uint64_t)total * s->refcount_table_size, cb_opaque);
+
+ if (refblock_offset) {
+ void *refblock;
+
+ if (offset_into_cluster(s, refblock_offset)) {
+ qcow2_signal_corruption(bs, true, -1, -1, "Refblock offset %#"
+ PRIx64 " unaligned (reftable index: %#"
+ PRIx64 ")", refblock_offset,
+ reftable_index);
+ error_setg(errp,
+ "Image is corrupt (unaligned refblock offset)");
+ return -EIO;
+ }
+
+ ret = qcow2_cache_get(bs, s->refcount_block_cache, refblock_offset,
+ &refblock);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Failed to retrieve refblock");
+ return ret;
+ }
+
+ for (refblock_index = 0; refblock_index < s->refcount_block_size;
+ refblock_index++)
+ {
+ uint64_t refcount;
+
+ if (new_refblock_index >= new_refblock_size) {
+ /* new_refblock is now complete */
+ ret = operation(bs, new_reftable, *new_reftable_index,
+ new_reftable_size, new_refblock,
+ new_refblock_empty, allocated, errp);
+ if (ret < 0) {
+ qcow2_cache_put(bs, s->refcount_block_cache, &refblock);
+ return ret;
+ }
+
+ (*new_reftable_index)++;
+ new_refblock_index = 0;
+ new_refblock_empty = true;
+ }
+
+ refcount = s->get_refcount(refblock, refblock_index);
+ if (new_refcount_bits < 64 && refcount >> new_refcount_bits) {
+ uint64_t offset;
+
+ qcow2_cache_put(bs, s->refcount_block_cache, &refblock);
+
+ offset = ((reftable_index << s->refcount_block_bits)
+ + refblock_index) << s->cluster_bits;
+
+ error_setg(errp, "Cannot decrease refcount entry width to "
+ "%i bits: Cluster at offset %#" PRIx64 " has a "
+ "refcount of %" PRIu64, new_refcount_bits,
+ offset, refcount);
+ return -EINVAL;
+ }
+
+ if (new_set_refcount) {
+ new_set_refcount(new_refblock, new_refblock_index++,
+ refcount);
+ } else {
+ new_refblock_index++;
+ }
+ new_refblock_empty = new_refblock_empty && refcount == 0;
+ }
+
+ qcow2_cache_put(bs, s->refcount_block_cache, &refblock);
+ } else {
+ /* No refblock means every refcount is 0 */
+ for (refblock_index = 0; refblock_index < s->refcount_block_size;
+ refblock_index++)
+ {
+ if (new_refblock_index >= new_refblock_size) {
+ /* new_refblock is now complete */
+ ret = operation(bs, new_reftable, *new_reftable_index,
+ new_reftable_size, new_refblock,
+ new_refblock_empty, allocated, errp);
+ if (ret < 0) {
+ return ret;
+ }
+
+ (*new_reftable_index)++;
+ new_refblock_index = 0;
+ new_refblock_empty = true;
+ }
+
+ if (new_set_refcount) {
+ new_set_refcount(new_refblock, new_refblock_index++, 0);
+ } else {
+ new_refblock_index++;
+ }
+ }
+ }
+ }
+
+ if (new_refblock_index > 0) {
+ /* Complete the potentially existing partially filled final refblock */
+ if (new_set_refcount) {
+ for (; new_refblock_index < new_refblock_size;
+ new_refblock_index++)
+ {
+ new_set_refcount(new_refblock, new_refblock_index, 0);
+ }
+ }
+
+ ret = operation(bs, new_reftable, *new_reftable_index,
+ new_reftable_size, new_refblock, new_refblock_empty,
+ allocated, errp);
+ if (ret < 0) {
+ return ret;
+ }
+
+ (*new_reftable_index)++;
+ }
+
+ status_cb(bs, (uint64_t)(index + 1) * s->refcount_table_size,
+ (uint64_t)total * s->refcount_table_size, cb_opaque);
+
+ return 0;
+}
+
+int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order,
+ BlockDriverAmendStatusCB *status_cb,
+ void *cb_opaque, Error **errp)
+{
+ BDRVQcow2State *s = bs->opaque;
+ Qcow2GetRefcountFunc *new_get_refcount;
+ Qcow2SetRefcountFunc *new_set_refcount;
+ void *new_refblock = qemu_blockalign(bs->file->bs, s->cluster_size);
+ uint64_t *new_reftable = NULL, new_reftable_size = 0;
+ uint64_t *old_reftable, old_reftable_size, old_reftable_offset;
+ uint64_t new_reftable_index = 0;
+ uint64_t i;
+ int64_t new_reftable_offset = 0, allocated_reftable_size = 0;
+ int new_refblock_size, new_refcount_bits = 1 << refcount_order;
+ int old_refcount_order;
+ int walk_index = 0;
+ int ret;
+ bool new_allocation;
+
+ assert(s->qcow_version >= 3);
+ assert(refcount_order >= 0 && refcount_order <= 6);
+
+ /* see qcow2_open() */
+ new_refblock_size = 1 << (s->cluster_bits - (refcount_order - 3));
+
+ new_get_refcount = get_refcount_funcs[refcount_order];
+ new_set_refcount = set_refcount_funcs[refcount_order];
+
+
+ do {
+ int total_walks;
+
+ new_allocation = false;
+
+ /* At least we have to do this walk and the one which writes the
+ * refblocks; also, at least we have to do this loop here at least
+ * twice (normally), first to do the allocations, and second to
+ * determine that everything is correctly allocated, this then makes
+ * three walks in total */
+ total_walks = MAX(walk_index + 2, 3);
+
+ /* First, allocate the structures so they are present in the refcount
+ * structures */
+ ret = walk_over_reftable(bs, &new_reftable, &new_reftable_index,
+ &new_reftable_size, NULL, new_refblock_size,
+ new_refcount_bits, &alloc_refblock,
+ &new_allocation, NULL, status_cb, cb_opaque,
+ walk_index++, total_walks, errp);
+ if (ret < 0) {
+ goto done;
+ }
+
+ new_reftable_index = 0;
+
+ if (new_allocation) {
+ if (new_reftable_offset) {
+ qcow2_free_clusters(bs, new_reftable_offset,
+ allocated_reftable_size * sizeof(uint64_t),
+ QCOW2_DISCARD_NEVER);
+ }
+
+ new_reftable_offset = qcow2_alloc_clusters(bs, new_reftable_size *
+ sizeof(uint64_t));
+ if (new_reftable_offset < 0) {
+ error_setg_errno(errp, -new_reftable_offset,
+ "Failed to allocate the new reftable");
+ ret = new_reftable_offset;
+ goto done;
+ }
+ allocated_reftable_size = new_reftable_size;
+ }
+ } while (new_allocation);
+
+ /* Second, write the new refblocks */
+ ret = walk_over_reftable(bs, &new_reftable, &new_reftable_index,
+ &new_reftable_size, new_refblock,
+ new_refblock_size, new_refcount_bits,
+ &flush_refblock, &new_allocation, new_set_refcount,
+ status_cb, cb_opaque, walk_index, walk_index + 1,
+ errp);
+ if (ret < 0) {
+ goto done;
+ }
+ assert(!new_allocation);
+
+
+ /* Write the new reftable */
+ ret = qcow2_pre_write_overlap_check(bs, 0, new_reftable_offset,
+ new_reftable_size * sizeof(uint64_t));
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Overlap check failed");
+ goto done;
+ }
+
+ for (i = 0; i < new_reftable_size; i++) {
+ cpu_to_be64s(&new_reftable[i]);
+ }
+
+ ret = bdrv_pwrite(bs->file->bs, new_reftable_offset, new_reftable,
+ new_reftable_size * sizeof(uint64_t));
+
+ for (i = 0; i < new_reftable_size; i++) {
+ be64_to_cpus(&new_reftable[i]);
+ }
+
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Failed to write the new reftable");
+ goto done;
+ }
+
+
+ /* Empty the refcount cache */
+ ret = qcow2_cache_flush(bs, s->refcount_block_cache);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Failed to flush the refblock cache");
+ goto done;
+ }
+
+ /* Update the image header to point to the new reftable; this only updates
+ * the fields which are relevant to qcow2_update_header(); other fields
+ * such as s->refcount_table or s->refcount_bits stay stale for now
+ * (because we have to restore everything if qcow2_update_header() fails) */
+ old_refcount_order = s->refcount_order;
+ old_reftable_size = s->refcount_table_size;
+ old_reftable_offset = s->refcount_table_offset;
+
+ s->refcount_order = refcount_order;
+ s->refcount_table_size = new_reftable_size;
+ s->refcount_table_offset = new_reftable_offset;
+
+ ret = qcow2_update_header(bs);
+ if (ret < 0) {
+ s->refcount_order = old_refcount_order;
+ s->refcount_table_size = old_reftable_size;
+ s->refcount_table_offset = old_reftable_offset;
+ error_setg_errno(errp, -ret, "Failed to update the qcow2 header");
+ goto done;
+ }
+
+ /* Now update the rest of the in-memory information */
+ old_reftable = s->refcount_table;
+ s->refcount_table = new_reftable;
+
+ s->refcount_bits = 1 << refcount_order;
+ s->refcount_max = UINT64_C(1) << (s->refcount_bits - 1);
+ s->refcount_max += s->refcount_max - 1;
+
+ s->refcount_block_bits = s->cluster_bits - (refcount_order - 3);
+ s->refcount_block_size = 1 << s->refcount_block_bits;
+
+ s->get_refcount = new_get_refcount;
+ s->set_refcount = new_set_refcount;
+
+ /* For cleaning up all old refblocks and the old reftable below the "done"
+ * label */
+ new_reftable = old_reftable;
+ new_reftable_size = old_reftable_size;
+ new_reftable_offset = old_reftable_offset;
+
+done:
+ if (new_reftable) {
+ /* On success, new_reftable actually points to the old reftable (and
+ * new_reftable_size is the old reftable's size); but that is just
+ * fine */
+ for (i = 0; i < new_reftable_size; i++) {
+ uint64_t offset = new_reftable[i] & REFT_OFFSET_MASK;
+ if (offset) {
+ qcow2_free_clusters(bs, offset, s->cluster_size,
+ QCOW2_DISCARD_OTHER);
+ }
+ }
+ g_free(new_reftable);
+
+ if (new_reftable_offset > 0) {
+ qcow2_free_clusters(bs, new_reftable_offset,
+ new_reftable_size * sizeof(uint64_t),
+ QCOW2_DISCARD_OTHER);
+ }
+ }
+
+ qemu_vfree(new_refblock);
+ return ret;
+}
projects / qemu.git / blobdiff