*/
#include "qemu/osdep.h"
+
+#define ZLIB_CONST
+#include <zlib.h>
+
#include "block/block_int.h"
+#include "block/qdict.h"
#include "sysemu/block-backend.h"
#include "qemu/module.h"
-#include <zlib.h>
-#include "block/qcow2.h"
+#include "qcow2.h"
#include "qemu/error-report.h"
#include "qapi/error.h"
#include "qapi/qapi-events-block-core.h"
#include "qemu/bswap.h"
#include "qapi/qobject-input-visitor.h"
#include "qapi/qapi-visit-block-core.h"
-#include "block/crypto.h"
+#include "crypto.h"
+#include "block/thread-pool.h"
/*
Differences with QCOW:
.type = QEMU_OPT_BOOL,
.help = "Check for unintended writes into an inactive L2 table",
},
+ {
+ .name = QCOW2_OPT_OVERLAP_BITMAP_DIRECTORY,
+ .type = QEMU_OPT_BOOL,
+ .help = "Check for unintended writes into the bitmap directory",
+ },
{
.name = QCOW2_OPT_CACHE_SIZE,
.type = QEMU_OPT_SIZE,
};
static const char *overlap_bool_option_names[QCOW2_OL_MAX_BITNR] = {
- [QCOW2_OL_MAIN_HEADER_BITNR] = QCOW2_OPT_OVERLAP_MAIN_HEADER,
- [QCOW2_OL_ACTIVE_L1_BITNR] = QCOW2_OPT_OVERLAP_ACTIVE_L1,
- [QCOW2_OL_ACTIVE_L2_BITNR] = QCOW2_OPT_OVERLAP_ACTIVE_L2,
- [QCOW2_OL_REFCOUNT_TABLE_BITNR] = QCOW2_OPT_OVERLAP_REFCOUNT_TABLE,
- [QCOW2_OL_REFCOUNT_BLOCK_BITNR] = QCOW2_OPT_OVERLAP_REFCOUNT_BLOCK,
- [QCOW2_OL_SNAPSHOT_TABLE_BITNR] = QCOW2_OPT_OVERLAP_SNAPSHOT_TABLE,
- [QCOW2_OL_INACTIVE_L1_BITNR] = QCOW2_OPT_OVERLAP_INACTIVE_L1,
- [QCOW2_OL_INACTIVE_L2_BITNR] = QCOW2_OPT_OVERLAP_INACTIVE_L2,
+ [QCOW2_OL_MAIN_HEADER_BITNR] = QCOW2_OPT_OVERLAP_MAIN_HEADER,
+ [QCOW2_OL_ACTIVE_L1_BITNR] = QCOW2_OPT_OVERLAP_ACTIVE_L1,
+ [QCOW2_OL_ACTIVE_L2_BITNR] = QCOW2_OPT_OVERLAP_ACTIVE_L2,
+ [QCOW2_OL_REFCOUNT_TABLE_BITNR] = QCOW2_OPT_OVERLAP_REFCOUNT_TABLE,
+ [QCOW2_OL_REFCOUNT_BLOCK_BITNR] = QCOW2_OPT_OVERLAP_REFCOUNT_BLOCK,
+ [QCOW2_OL_SNAPSHOT_TABLE_BITNR] = QCOW2_OPT_OVERLAP_SNAPSHOT_TABLE,
+ [QCOW2_OL_INACTIVE_L1_BITNR] = QCOW2_OPT_OVERLAP_INACTIVE_L1,
+ [QCOW2_OL_INACTIVE_L2_BITNR] = QCOW2_OPT_OVERLAP_INACTIVE_L2,
+ [QCOW2_OL_BITMAP_DIRECTORY_BITNR] = QCOW2_OPT_OVERLAP_BITMAP_DIRECTORY,
};
static void cache_clean_timer_cb(void *opaque)
BDRVQcow2State *s = bs->opaque;
uint64_t combined_cache_size;
bool l2_cache_size_set, refcount_cache_size_set, combined_cache_size_set;
+ int min_refcount_cache = MIN_REFCOUNT_CACHE_SIZE * s->cluster_size;
combined_cache_size_set = qemu_opt_get(opts, QCOW2_OPT_CACHE_SIZE);
l2_cache_size_set = qemu_opt_get(opts, QCOW2_OPT_L2_CACHE_SIZE);
} else if (refcount_cache_size_set) {
*l2_cache_size = combined_cache_size - *refcount_cache_size;
} else {
- *refcount_cache_size = combined_cache_size
- / (DEFAULT_L2_REFCOUNT_SIZE_RATIO + 1);
- *l2_cache_size = combined_cache_size - *refcount_cache_size;
+ uint64_t virtual_disk_size = bs->total_sectors * BDRV_SECTOR_SIZE;
+ uint64_t max_l2_cache = virtual_disk_size / (s->cluster_size / 8);
+
+ /* Assign as much memory as possible to the L2 cache, and
+ * use the remainder for the refcount cache */
+ if (combined_cache_size >= max_l2_cache + min_refcount_cache) {
+ *l2_cache_size = max_l2_cache;
+ *refcount_cache_size = combined_cache_size - *l2_cache_size;
+ } else {
+ *refcount_cache_size =
+ MIN(combined_cache_size, min_refcount_cache);
+ *l2_cache_size = combined_cache_size - *refcount_cache_size;
+ }
}
} else {
- if (!l2_cache_size_set && !refcount_cache_size_set) {
+ if (!l2_cache_size_set) {
*l2_cache_size = MAX(DEFAULT_L2_CACHE_BYTE_SIZE,
(uint64_t)DEFAULT_L2_CACHE_CLUSTERS
* s->cluster_size);
- *refcount_cache_size = *l2_cache_size
- / DEFAULT_L2_REFCOUNT_SIZE_RATIO;
- } else if (!l2_cache_size_set) {
- *l2_cache_size = *refcount_cache_size
- * DEFAULT_L2_REFCOUNT_SIZE_RATIO;
- } else if (!refcount_cache_size_set) {
- *refcount_cache_size = *l2_cache_size
- / DEFAULT_L2_REFCOUNT_SIZE_RATIO;
+ }
+ if (!refcount_cache_size_set) {
+ *refcount_cache_size = min_refcount_cache;
}
}
ret = -EINVAL;
goto fail;
}
- qdict_del(encryptopts, "format");
- r->crypto_opts = block_crypto_open_opts_init(
- Q_CRYPTO_BLOCK_FORMAT_QCOW, encryptopts, errp);
+ qdict_put_str(encryptopts, "format", "qcow");
+ r->crypto_opts = block_crypto_open_opts_init(encryptopts, errp);
break;
case QCOW_CRYPT_LUKS:
ret = -EINVAL;
goto fail;
}
- qdict_del(encryptopts, "format");
- r->crypto_opts = block_crypto_open_opts_init(
- Q_CRYPTO_BLOCK_FORMAT_LUKS, encryptopts, errp);
+ qdict_put_str(encryptopts, "format", "luks");
+ r->crypto_opts = block_crypto_open_opts_init(encryptopts, errp);
break;
default:
ret = 0;
fail:
- QDECREF(encryptopts);
+ qobject_unref(encryptopts);
qemu_opts_del(opts);
opts = NULL;
return ret;
uint64_t ext_end;
uint64_t l1_vm_state_index;
bool update_header = false;
+ bool header_updated = false;
ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
if (ret < 0) {
s->autoclear_features &= QCOW2_AUTOCLEAR_MASK;
}
- if (qcow2_load_dirty_bitmaps(bs, &local_err)) {
- update_header = false;
+ if (s->dirty_bitmaps_loaded) {
+ /* It's some kind of reopen. There are no known cases where we need to
+ * reload bitmaps in such a situation, so it's safer to skip them.
+ *
+ * Moreover, if we have some readonly bitmaps and we are reopening for
+ * rw we should reopen bitmaps correspondingly.
+ */
+ if (bdrv_has_readonly_bitmaps(bs) &&
+ !bdrv_is_read_only(bs) && !(bdrv_get_flags(bs) & BDRV_O_INACTIVE))
+ {
+ qcow2_reopen_bitmaps_rw_hint(bs, &header_updated, &local_err);
+ }
+ } else {
+ header_updated = qcow2_load_dirty_bitmaps(bs, &local_err);
+ s->dirty_bitmaps_loaded = true;
}
+ update_header = update_header && !header_updated;
if (local_err != NULL) {
error_propagate(errp, local_err);
ret = -EINVAL;
qcow2_check_refcounts(bs, &result, 0);
}
#endif
+
+ qemu_co_queue_init(&s->compress_wait_queue);
+
return ret;
fail:
return status;
}
+static coroutine_fn int qcow2_handle_l2meta(BlockDriverState *bs,
+ QCowL2Meta **pl2meta,
+ bool link_l2)
+{
+ int ret = 0;
+ QCowL2Meta *l2meta = *pl2meta;
+
+ while (l2meta != NULL) {
+ QCowL2Meta *next;
+
+ if (link_l2) {
+ ret = qcow2_alloc_cluster_link_l2(bs, l2meta);
+ if (ret) {
+ goto out;
+ }
+ } else {
+ qcow2_alloc_cluster_abort(bs, l2meta);
+ }
+
+ /* Take the request off the list of running requests */
+ if (l2meta->nb_clusters != 0) {
+ QLIST_REMOVE(l2meta, next_in_flight);
+ }
+
+ qemu_co_queue_restart_all(&l2meta->dependent_requests);
+
+ next = l2meta->next;
+ g_free(l2meta);
+ l2meta = next;
+ }
+out:
+ *pl2meta = l2meta;
+ return ret;
+}
+
static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset,
uint64_t bytes, QEMUIOVector *qiov,
int flags)
}
}
- while (l2meta != NULL) {
- QCowL2Meta *next;
-
- ret = qcow2_alloc_cluster_link_l2(bs, l2meta);
- if (ret < 0) {
- goto fail;
- }
-
- /* Take the request off the list of running requests */
- if (l2meta->nb_clusters != 0) {
- QLIST_REMOVE(l2meta, next_in_flight);
- }
-
- qemu_co_queue_restart_all(&l2meta->dependent_requests);
-
- next = l2meta->next;
- g_free(l2meta);
- l2meta = next;
+ ret = qcow2_handle_l2meta(bs, &l2meta, true);
+ if (ret) {
+ goto fail;
}
bytes -= cur_bytes;
ret = 0;
fail:
- while (l2meta != NULL) {
- QCowL2Meta *next;
-
- if (l2meta->nb_clusters != 0) {
- QLIST_REMOVE(l2meta, next_in_flight);
- }
- qemu_co_queue_restart_all(&l2meta->dependent_requests);
-
- next = l2meta->next;
- g_free(l2meta);
- l2meta = next;
- }
+ qcow2_handle_l2meta(bs, &l2meta, false);
qemu_co_mutex_unlock(&s->lock);
qemu_co_mutex_lock(&s->lock);
ret = qcow2_do_open(bs, options, flags, &local_err);
qemu_co_mutex_unlock(&s->lock);
- QDECREF(options);
+ qobject_unref(options);
if (local_err) {
error_propagate(errp, local_err);
error_prepend(errp, "Could not reopen qcow2 layer: ");
return ret;
}
-
-typedef struct PreallocCo {
- BlockDriverState *bs;
- uint64_t offset;
- uint64_t new_length;
-
- int ret;
-} PreallocCo;
-
/**
* Preallocates metadata structures for data clusters between @offset (in the
* guest disk) and @new_length (which is thus generally the new guest disk
*
* Returns: 0 on success, -errno on failure.
*/
-static void coroutine_fn preallocate_co(void *opaque)
+static int coroutine_fn preallocate_co(BlockDriverState *bs, uint64_t offset,
+ uint64_t new_length)
{
- PreallocCo *params = opaque;
- BlockDriverState *bs = params->bs;
- uint64_t offset = params->offset;
- uint64_t new_length = params->new_length;
- BDRVQcow2State *s = bs->opaque;
uint64_t bytes;
uint64_t host_offset = 0;
unsigned int cur_bytes;
int ret;
QCowL2Meta *meta;
- qemu_co_mutex_lock(&s->lock);
-
assert(offset <= new_length);
bytes = new_length - offset;
ret = qcow2_alloc_cluster_offset(bs, offset, &cur_bytes,
&host_offset, &meta);
if (ret < 0) {
- goto done;
+ return ret;
}
while (meta) {
if (ret < 0) {
qcow2_free_any_clusters(bs, meta->alloc_offset,
meta->nb_clusters, QCOW2_DISCARD_NEVER);
- goto done;
+ return ret;
}
/* There are no dependent requests, but we need to remove our
ret = bdrv_pwrite(bs->file, (host_offset + cur_bytes) - 1,
&data, 1);
if (ret < 0) {
- goto done;
+ return ret;
}
}
- ret = 0;
-
-done:
- qemu_co_mutex_unlock(&s->lock);
- params->ret = ret;
-}
-
-static int preallocate(BlockDriverState *bs,
- uint64_t offset, uint64_t new_length)
-{
- PreallocCo params = {
- .bs = bs,
- .offset = offset,
- .new_length = new_length,
- .ret = -EINPROGRESS,
- };
-
- if (qemu_in_coroutine()) {
- preallocate_co(¶ms);
- } else {
- Coroutine *co = qemu_coroutine_create(preallocate_co, ¶ms);
- bdrv_coroutine_enter(bs, co);
- BDRV_POLL_WHILE(bs, params.ret == -EINPROGRESS);
- }
- return params.ret;
+ return 0;
}
/* qcow2_refcount_metadata_size:
/* And if we're supposed to preallocate metadata, do that now */
if (qcow2_opts->preallocation != PREALLOC_MODE_OFF) {
- ret = preallocate(blk_bs(blk), 0, qcow2_opts->size);
+ BDRVQcow2State *s = blk_bs(blk)->opaque;
+ qemu_co_mutex_lock(&s->lock);
+ ret = preallocate_co(blk_bs(blk), 0, qcow2_opts->size);
+ qemu_co_mutex_unlock(&s->lock);
+
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not preallocate metadata");
goto out;
Error **errp)
{
BlockdevCreateOptions *create_options = NULL;
- QDict *qdict = NULL;
- QObject *qobj;
+ QDict *qdict;
Visitor *v;
BlockDriverState *bs = NULL;
Error *local_err = NULL;
qdict_put_str(qdict, "file", bs->node_name);
/* Now get the QAPI type BlockdevCreateOptions */
- qobj = qdict_crumple(qdict, errp);
- QDECREF(qdict);
- qdict = qobject_to(QDict, qobj);
- if (qdict == NULL) {
+ v = qobject_input_visitor_new_flat_confused(qdict, errp);
+ if (!v) {
ret = -EINVAL;
goto finish;
}
- v = qobject_input_visitor_new_keyval(QOBJECT(qdict));
visit_type_BlockdevCreateOptions(v, NULL, &create_options, &local_err);
visit_free(v);
ret = 0;
finish:
- QDECREF(qdict);
+ qobject_unref(qdict);
bdrv_unref(bs);
qapi_free_BlockdevCreateOptions(create_options);
return ret;
return ret;
}
-static int qcow2_truncate(BlockDriverState *bs, int64_t offset,
- PreallocMode prealloc, Error **errp)
+static int coroutine_fn
+qcow2_co_copy_range_from(BlockDriverState *bs,
+ BdrvChild *src, uint64_t src_offset,
+ BdrvChild *dst, uint64_t dst_offset,
+ uint64_t bytes, BdrvRequestFlags flags)
+{
+ BDRVQcow2State *s = bs->opaque;
+ int ret;
+ unsigned int cur_bytes; /* number of bytes in current iteration */
+ BdrvChild *child = NULL;
+ BdrvRequestFlags cur_flags;
+
+ assert(!bs->encrypted);
+ qemu_co_mutex_lock(&s->lock);
+
+ while (bytes != 0) {
+ uint64_t copy_offset = 0;
+ /* prepare next request */
+ cur_bytes = MIN(bytes, INT_MAX);
+ cur_flags = flags;
+
+ ret = qcow2_get_cluster_offset(bs, src_offset, &cur_bytes, ©_offset);
+ if (ret < 0) {
+ goto out;
+ }
+
+ switch (ret) {
+ case QCOW2_CLUSTER_UNALLOCATED:
+ if (bs->backing && bs->backing->bs) {
+ int64_t backing_length = bdrv_getlength(bs->backing->bs);
+ if (src_offset >= backing_length) {
+ cur_flags |= BDRV_REQ_ZERO_WRITE;
+ } else {
+ child = bs->backing;
+ cur_bytes = MIN(cur_bytes, backing_length - src_offset);
+ copy_offset = src_offset;
+ }
+ } else {
+ cur_flags |= BDRV_REQ_ZERO_WRITE;
+ }
+ break;
+
+ case QCOW2_CLUSTER_ZERO_PLAIN:
+ case QCOW2_CLUSTER_ZERO_ALLOC:
+ cur_flags |= BDRV_REQ_ZERO_WRITE;
+ break;
+
+ case QCOW2_CLUSTER_COMPRESSED:
+ ret = -ENOTSUP;
+ goto out;
+
+ case QCOW2_CLUSTER_NORMAL:
+ child = bs->file;
+ copy_offset += offset_into_cluster(s, src_offset);
+ if ((copy_offset & 511) != 0) {
+ ret = -EIO;
+ goto out;
+ }
+ break;
+
+ default:
+ abort();
+ }
+ qemu_co_mutex_unlock(&s->lock);
+ ret = bdrv_co_copy_range_from(child,
+ copy_offset,
+ dst, dst_offset,
+ cur_bytes, cur_flags);
+ qemu_co_mutex_lock(&s->lock);
+ if (ret < 0) {
+ goto out;
+ }
+
+ bytes -= cur_bytes;
+ src_offset += cur_bytes;
+ dst_offset += cur_bytes;
+ }
+ ret = 0;
+
+out:
+ qemu_co_mutex_unlock(&s->lock);
+ return ret;
+}
+
+static int coroutine_fn
+qcow2_co_copy_range_to(BlockDriverState *bs,
+ BdrvChild *src, uint64_t src_offset,
+ BdrvChild *dst, uint64_t dst_offset,
+ uint64_t bytes, BdrvRequestFlags flags)
+{
+ BDRVQcow2State *s = bs->opaque;
+ int offset_in_cluster;
+ int ret;
+ unsigned int cur_bytes; /* number of sectors in current iteration */
+ uint64_t cluster_offset;
+ QCowL2Meta *l2meta = NULL;
+
+ assert(!bs->encrypted);
+ s->cluster_cache_offset = -1; /* disable compressed cache */
+
+ qemu_co_mutex_lock(&s->lock);
+
+ while (bytes != 0) {
+
+ l2meta = NULL;
+
+ offset_in_cluster = offset_into_cluster(s, dst_offset);
+ cur_bytes = MIN(bytes, INT_MAX);
+
+ /* TODO:
+ * If src->bs == dst->bs, we could simply copy by incrementing
+ * the refcnt, without copying user data.
+ * Or if src->bs == dst->bs->backing->bs, we could copy by discarding. */
+ ret = qcow2_alloc_cluster_offset(bs, dst_offset, &cur_bytes,
+ &cluster_offset, &l2meta);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ assert((cluster_offset & 511) == 0);
+
+ ret = qcow2_pre_write_overlap_check(bs, 0,
+ cluster_offset + offset_in_cluster, cur_bytes);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ qemu_co_mutex_unlock(&s->lock);
+ ret = bdrv_co_copy_range_to(src, src_offset,
+ bs->file,
+ cluster_offset + offset_in_cluster,
+ cur_bytes, flags);
+ qemu_co_mutex_lock(&s->lock);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ ret = qcow2_handle_l2meta(bs, &l2meta, true);
+ if (ret) {
+ goto fail;
+ }
+
+ bytes -= cur_bytes;
+ src_offset += cur_bytes;
+ dst_offset += cur_bytes;
+ }
+ ret = 0;
+
+fail:
+ qcow2_handle_l2meta(bs, &l2meta, false);
+
+ qemu_co_mutex_unlock(&s->lock);
+
+ trace_qcow2_writev_done_req(qemu_coroutine_self(), ret);
+
+ return ret;
+}
+
+static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset,
+ PreallocMode prealloc, Error **errp)
{
BDRVQcow2State *s = bs->opaque;
uint64_t old_length;
return -EINVAL;
}
+ qemu_co_mutex_lock(&s->lock);
+
/* cannot proceed if image has snapshots */
if (s->nb_snapshots) {
error_setg(errp, "Can't resize an image which has snapshots");
- return -ENOTSUP;
+ ret = -ENOTSUP;
+ goto fail;
}
/* cannot proceed if image has bitmaps */
if (s->nb_bitmaps) {
/* TODO: resize bitmaps in the image */
error_setg(errp, "Can't resize an image which has bitmaps");
- return -ENOTSUP;
+ ret = -ENOTSUP;
+ goto fail;
}
old_length = bs->total_sectors * 512;
if (prealloc != PREALLOC_MODE_OFF) {
error_setg(errp,
"Preallocation can't be used for shrinking an image");
- return -EINVAL;
+ ret = -EINVAL;
+ goto fail;
}
ret = qcow2_cluster_discard(bs, ROUND_UP(offset, s->cluster_size),
QCOW2_DISCARD_ALWAYS, true);
if (ret < 0) {
error_setg_errno(errp, -ret, "Failed to discard cropped clusters");
- return ret;
+ goto fail;
}
ret = qcow2_shrink_l1_table(bs, new_l1_size);
if (ret < 0) {
error_setg_errno(errp, -ret,
"Failed to reduce the number of L2 tables");
- return ret;
+ goto fail;
}
ret = qcow2_shrink_reftable(bs);
if (ret < 0) {
error_setg_errno(errp, -ret,
"Failed to discard unused refblocks");
- return ret;
+ goto fail;
}
old_file_size = bdrv_getlength(bs->file->bs);
if (old_file_size < 0) {
error_setg_errno(errp, -old_file_size,
"Failed to inquire current file length");
- return old_file_size;
+ ret = old_file_size;
+ goto fail;
}
last_cluster = qcow2_get_last_cluster(bs, old_file_size);
if (last_cluster < 0) {
error_setg_errno(errp, -last_cluster,
"Failed to find the last cluster");
- return last_cluster;
+ ret = last_cluster;
+ goto fail;
}
if ((last_cluster + 1) * s->cluster_size < old_file_size) {
Error *local_err = NULL;
- bdrv_truncate(bs->file, (last_cluster + 1) * s->cluster_size,
- PREALLOC_MODE_OFF, &local_err);
+ bdrv_co_truncate(bs->file, (last_cluster + 1) * s->cluster_size,
+ PREALLOC_MODE_OFF, &local_err);
if (local_err) {
warn_reportf_err(local_err,
"Failed to truncate the tail of the image: ");
ret = qcow2_grow_l1_table(bs, new_l1_size, true);
if (ret < 0) {
error_setg_errno(errp, -ret, "Failed to grow the L1 table");
- return ret;
+ goto fail;
}
}
break;
case PREALLOC_MODE_METADATA:
- ret = preallocate(bs, old_length, offset);
+ ret = preallocate_co(bs, old_length, offset);
if (ret < 0) {
error_setg_errno(errp, -ret, "Preallocation failed");
- return ret;
+ goto fail;
}
break;
if (old_file_size < 0) {
error_setg_errno(errp, -old_file_size,
"Failed to inquire current file length");
- return old_file_size;
+ ret = old_file_size;
+ goto fail;
}
old_file_size = ROUND_UP(old_file_size, s->cluster_size);
if (allocation_start < 0) {
error_setg_errno(errp, -allocation_start,
"Failed to resize refcount structures");
- return allocation_start;
+ ret = allocation_start;
+ goto fail;
}
clusters_allocated = qcow2_alloc_clusters_at(bs, allocation_start,
if (clusters_allocated < 0) {
error_setg_errno(errp, -clusters_allocated,
"Failed to allocate data clusters");
- return -clusters_allocated;
+ ret = clusters_allocated;
+ goto fail;
}
assert(clusters_allocated == nb_new_data_clusters);
/* Allocate the data area */
new_file_size = allocation_start +
nb_new_data_clusters * s->cluster_size;
- ret = bdrv_truncate(bs->file, new_file_size, prealloc, errp);
+ ret = bdrv_co_truncate(bs->file, new_file_size, prealloc, errp);
if (ret < 0) {
error_prepend(errp, "Failed to resize underlying file: ");
qcow2_free_clusters(bs, allocation_start,
nb_new_data_clusters * s->cluster_size,
QCOW2_DISCARD_OTHER);
- return ret;
+ goto fail;
}
/* Create the necessary L2 entries */
qcow2_free_clusters(bs, host_offset,
nb_new_data_clusters * s->cluster_size,
QCOW2_DISCARD_OTHER);
- return ret;
+ goto fail;
}
guest_offset += nb_clusters * s->cluster_size;
if (prealloc != PREALLOC_MODE_OFF) {
/* Flush metadata before actually changing the image size */
- ret = bdrv_flush(bs);
+ ret = qcow2_write_caches(bs);
if (ret < 0) {
error_setg_errno(errp, -ret,
"Failed to flush the preallocated area to disk");
- return ret;
+ goto fail;
}
}
&offset, sizeof(uint64_t));
if (ret < 0) {
error_setg_errno(errp, -ret, "Failed to update the image size");
- return ret;
+ goto fail;
}
s->l1_vm_state_index = new_l1_size;
+ ret = 0;
+fail:
+ qemu_co_mutex_unlock(&s->lock);
+ return ret;
+}
+
+/*
+ * qcow2_compress()
+ *
+ * @dest - destination buffer, at least of @size-1 bytes
+ * @src - source buffer, @size bytes
+ *
+ * Returns: compressed size on success
+ * -1 if compression is inefficient
+ * -2 on any other error
+ */
+static ssize_t qcow2_compress(void *dest, const void *src, size_t size)
+{
+ ssize_t ret;
+ z_stream strm;
+
+ /* best compression, small window, no zlib header */
+ memset(&strm, 0, sizeof(strm));
+ ret = deflateInit2(&strm, Z_DEFAULT_COMPRESSION, Z_DEFLATED,
+ -12, 9, Z_DEFAULT_STRATEGY);
+ if (ret != 0) {
+ return -2;
+ }
+
+ /* strm.next_in is not const in old zlib versions, such as those used on
+ * OpenBSD/NetBSD, so cast the const away */
+ strm.avail_in = size;
+ strm.next_in = (void *) src;
+ strm.avail_out = size - 1;
+ strm.next_out = dest;
+
+ ret = deflate(&strm, Z_FINISH);
+ if (ret == Z_STREAM_END) {
+ ret = size - 1 - strm.avail_out;
+ } else {
+ ret = (ret == Z_OK ? -1 : -2);
+ }
+
+ deflateEnd(&strm);
+
+ return ret;
+}
+
+#define MAX_COMPRESS_THREADS 4
+
+typedef struct Qcow2CompressData {
+ void *dest;
+ const void *src;
+ size_t size;
+ ssize_t ret;
+} Qcow2CompressData;
+
+static int qcow2_compress_pool_func(void *opaque)
+{
+ Qcow2CompressData *data = opaque;
+
+ data->ret = qcow2_compress(data->dest, data->src, data->size);
+
return 0;
}
+static void qcow2_compress_complete(void *opaque, int ret)
+{
+ qemu_coroutine_enter(opaque);
+}
+
+/* See qcow2_compress definition for parameters description */
+static ssize_t qcow2_co_compress(BlockDriverState *bs,
+ void *dest, const void *src, size_t size)
+{
+ BDRVQcow2State *s = bs->opaque;
+ BlockAIOCB *acb;
+ ThreadPool *pool = aio_get_thread_pool(bdrv_get_aio_context(bs));
+ Qcow2CompressData arg = {
+ .dest = dest,
+ .src = src,
+ .size = size,
+ };
+
+ while (s->nb_compress_threads >= MAX_COMPRESS_THREADS) {
+ qemu_co_queue_wait(&s->compress_wait_queue, NULL);
+ }
+
+ s->nb_compress_threads++;
+ acb = thread_pool_submit_aio(pool, qcow2_compress_pool_func, &arg,
+ qcow2_compress_complete,
+ qemu_coroutine_self());
+
+ if (!acb) {
+ s->nb_compress_threads--;
+ return -EINVAL;
+ }
+ qemu_coroutine_yield();
+ s->nb_compress_threads--;
+ qemu_co_queue_next(&s->compress_wait_queue);
+
+ return arg.ret;
+}
+
/* XXX: put compressed sectors first, then all the cluster aligned
tables to avoid losing bytes in alignment */
static coroutine_fn int
BDRVQcow2State *s = bs->opaque;
QEMUIOVector hd_qiov;
struct iovec iov;
- z_stream strm;
- int ret, out_len;
+ int ret;
+ size_t out_len;
uint8_t *buf, *out_buf;
int64_t cluster_offset;
if (cluster_offset < 0) {
return cluster_offset;
}
- return bdrv_truncate(bs->file, cluster_offset, PREALLOC_MODE_OFF, NULL);
+ return bdrv_co_truncate(bs->file, cluster_offset, PREALLOC_MODE_OFF,
+ NULL);
}
if (offset_into_cluster(s, offset)) {
out_buf = g_malloc(s->cluster_size);
- /* best compression, small window, no zlib header */
- memset(&strm, 0, sizeof(strm));
- ret = deflateInit2(&strm, Z_DEFAULT_COMPRESSION,
- Z_DEFLATED, -12,
- 9, Z_DEFAULT_STRATEGY);
- if (ret != 0) {
- ret = -EINVAL;
- goto fail;
- }
-
- strm.avail_in = s->cluster_size;
- strm.next_in = (uint8_t *)buf;
- strm.avail_out = s->cluster_size;
- strm.next_out = out_buf;
-
- ret = deflate(&strm, Z_FINISH);
- if (ret != Z_STREAM_END && ret != Z_OK) {
- deflateEnd(&strm);
+ out_len = qcow2_co_compress(bs, out_buf, buf, s->cluster_size);
+ if (out_len == -2) {
ret = -EINVAL;
goto fail;
- }
- out_len = strm.next_out - out_buf;
-
- deflateEnd(&strm);
-
- if (ret != Z_STREAM_END || out_len >= s->cluster_size) {
+ } else if (out_len == -1) {
/* could not compress: write normal cluster */
ret = qcow2_co_pwritev(bs, offset, bytes, qiov, 0);
if (ret < 0) {
switch (encrypt_info->format) {
case Q_CRYPTO_BLOCK_FORMAT_QCOW:
qencrypt->format = BLOCKDEV_QCOW2_ENCRYPTION_FORMAT_AES;
- qencrypt->u.aes = encrypt_info->u.qcow;
break;
case Q_CRYPTO_BLOCK_FORMAT_LUKS:
qencrypt->format = BLOCKDEV_QCOW2_ENCRYPTION_FORMAT_LUKS;
* have to be removed.
*/
static int qcow2_downgrade(BlockDriverState *bs, int target_version,
- BlockDriverAmendStatusCB *status_cb, void *cb_opaque)
+ BlockDriverAmendStatusCB *status_cb, void *cb_opaque,
+ Error **errp)
{
BDRVQcow2State *s = bs->opaque;
int current_version = s->qcow_version;
int ret;
- if (target_version == current_version) {
- return 0;
- } else if (target_version > current_version) {
- return -EINVAL;
- } else if (target_version != 2) {
- return -EINVAL;
- }
+ /* This is qcow2_downgrade(), not qcow2_upgrade() */
+ assert(target_version < current_version);
+
+ /* There are no other versions (now) that you can downgrade to */
+ assert(target_version == 2);
if (s->refcount_order != 4) {
- error_report("compat=0.10 requires refcount_bits=16");
+ error_setg(errp, "compat=0.10 requires refcount_bits=16");
return -ENOTSUP;
}
if (s->incompatible_features & QCOW2_INCOMPAT_DIRTY) {
ret = qcow2_mark_clean(bs);
if (ret < 0) {
+ error_setg_errno(errp, -ret, "Failed to make the image clean");
return ret;
}
}
* best thing to do anyway */
if (s->incompatible_features) {
+ error_setg(errp, "Cannot downgrade an image with incompatible features "
+ "%#" PRIx64 " set", s->incompatible_features);
return -ENOTSUP;
}
ret = qcow2_expand_zero_clusters(bs, status_cb, cb_opaque);
if (ret < 0) {
+ error_setg_errno(errp, -ret, "Failed to turn zero into data clusters");
return ret;
}
ret = qcow2_update_header(bs);
if (ret < 0) {
s->qcow_version = current_version;
+ error_setg_errno(errp, -ret, "Failed to update the image header");
return ret;
}
return 0;
static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
BlockDriverAmendStatusCB *status_cb,
- void *cb_opaque)
+ void *cb_opaque,
+ Error **errp)
{
BDRVQcow2State *s = bs->opaque;
int old_version = s->qcow_version, new_version = old_version;
bool encrypt;
int encformat;
int refcount_bits = s->refcount_bits;
- Error *local_err = NULL;
int ret;
QemuOptDesc *desc = opts->list->desc;
Qcow2AmendHelperCBInfo helper_cb_info;
} else if (!strcmp(compat, "1.1")) {
new_version = 3;
} else {
- error_report("Unknown compatibility level %s", compat);
+ error_setg(errp, "Unknown compatibility level %s", compat);
return -EINVAL;
}
} else if (!strcmp(desc->name, BLOCK_OPT_PREALLOC)) {
- error_report("Cannot change preallocation mode");
+ error_setg(errp, "Cannot change preallocation mode");
return -ENOTSUP;
} else if (!strcmp(desc->name, BLOCK_OPT_SIZE)) {
new_size = qemu_opt_get_size(opts, BLOCK_OPT_SIZE, 0);
!!s->crypto);
if (encrypt != !!s->crypto) {
- error_report("Changing the encryption flag is not supported");
+ error_setg(errp,
+ "Changing the encryption flag is not supported");
return -ENOTSUP;
}
} else if (!strcmp(desc->name, BLOCK_OPT_ENCRYPT_FORMAT)) {
qemu_opt_get(opts, BLOCK_OPT_ENCRYPT_FORMAT));
if (encformat != s->crypt_method_header) {
- error_report("Changing the encryption format is not supported");
+ error_setg(errp,
+ "Changing the encryption format is not supported");
return -ENOTSUP;
}
} else if (g_str_has_prefix(desc->name, "encrypt.")) {
- error_report("Changing the encryption parameters is not supported");
+ error_setg(errp,
+ "Changing the encryption parameters is not supported");
return -ENOTSUP;
} else if (!strcmp(desc->name, BLOCK_OPT_CLUSTER_SIZE)) {
cluster_size = qemu_opt_get_size(opts, BLOCK_OPT_CLUSTER_SIZE,
cluster_size);
if (cluster_size != s->cluster_size) {
- error_report("Changing the cluster size is not supported");
+ error_setg(errp, "Changing the cluster size is not supported");
return -ENOTSUP;
}
} else if (!strcmp(desc->name, BLOCK_OPT_LAZY_REFCOUNTS)) {
if (refcount_bits <= 0 || refcount_bits > 64 ||
!is_power_of_2(refcount_bits))
{
- error_report("Refcount width must be a power of two and may "
- "not exceed 64 bits");
+ error_setg(errp, "Refcount width must be a power of two and "
+ "may not exceed 64 bits");
return -EINVAL;
}
} else {
ret = qcow2_update_header(bs);
if (ret < 0) {
s->qcow_version = old_version;
+ error_setg_errno(errp, -ret, "Failed to update the image header");
return ret;
}
}
int refcount_order = ctz32(refcount_bits);
if (new_version < 3 && refcount_bits != 16) {
- error_report("Different refcount widths than 16 bits require "
- "compatibility level 1.1 or above (use compat=1.1 or "
- "greater)");
+ error_setg(errp, "Refcount widths other than 16 bits require "
+ "compatibility level 1.1 or above (use compat=1.1 or "
+ "greater)");
return -EINVAL;
}
helper_cb_info.current_operation = QCOW2_CHANGING_REFCOUNT_ORDER;
ret = qcow2_change_refcount_order(bs, refcount_order,
&qcow2_amend_helper_cb,
- &helper_cb_info, &local_err);
+ &helper_cb_info, errp);
if (ret < 0) {
- error_report_err(local_err);
return ret;
}
}
backing_file ?: s->image_backing_file,
backing_format ?: s->image_backing_format);
if (ret < 0) {
+ error_setg_errno(errp, -ret, "Failed to change the backing file");
return ret;
}
}
if (s->use_lazy_refcounts != lazy_refcounts) {
if (lazy_refcounts) {
if (new_version < 3) {
- error_report("Lazy refcounts only supported with compatibility "
- "level 1.1 and above (use compat=1.1 or greater)");
+ error_setg(errp, "Lazy refcounts only supported with "
+ "compatibility level 1.1 and above (use compat=1.1 "
+ "or greater)");
return -EINVAL;
}
s->compatible_features |= QCOW2_COMPAT_LAZY_REFCOUNTS;
ret = qcow2_update_header(bs);
if (ret < 0) {
s->compatible_features &= ~QCOW2_COMPAT_LAZY_REFCOUNTS;
+ error_setg_errno(errp, -ret, "Failed to update the image header");
return ret;
}
s->use_lazy_refcounts = true;
/* make image clean first */
ret = qcow2_mark_clean(bs);
if (ret < 0) {
+ error_setg_errno(errp, -ret, "Failed to make the image clean");
return ret;
}
/* now disallow lazy refcounts */
ret = qcow2_update_header(bs);
if (ret < 0) {
s->compatible_features |= QCOW2_COMPAT_LAZY_REFCOUNTS;
+ error_setg_errno(errp, -ret, "Failed to update the image header");
return ret;
}
s->use_lazy_refcounts = false;
if (new_size) {
BlockBackend *blk = blk_new(BLK_PERM_RESIZE, BLK_PERM_ALL);
- ret = blk_insert_bs(blk, bs, &local_err);
+ ret = blk_insert_bs(blk, bs, errp);
if (ret < 0) {
- error_report_err(local_err);
blk_unref(blk);
return ret;
}
- ret = blk_truncate(blk, new_size, PREALLOC_MODE_OFF, &local_err);
+ ret = blk_truncate(blk, new_size, PREALLOC_MODE_OFF, errp);
blk_unref(blk);
if (ret < 0) {
- error_report_err(local_err);
return ret;
}
}
if (new_version < old_version) {
helper_cb_info.current_operation = QCOW2_DOWNGRADING;
ret = qcow2_downgrade(bs, new_version, &qcow2_amend_helper_cb,
- &helper_cb_info);
+ &helper_cb_info, errp);
if (ret < 0) {
return ret;
}
char *message;
va_list ap;
- fatal = fatal && !bs->read_only;
+ fatal = fatal && bdrv_is_writable(bs);
if (s->signaled_corruption &&
(!fatal || (s->incompatible_features & QCOW2_INCOMPAT_CORRUPT)))
.bdrv_co_pwrite_zeroes = qcow2_co_pwrite_zeroes,
.bdrv_co_pdiscard = qcow2_co_pdiscard,
- .bdrv_truncate = qcow2_truncate,
+ .bdrv_co_copy_range_from = qcow2_co_copy_range_from,
+ .bdrv_co_copy_range_to = qcow2_co_copy_range_to,
+ .bdrv_co_truncate = qcow2_co_truncate,
.bdrv_co_pwritev_compressed = qcow2_co_pwritev_compressed,
.bdrv_make_empty = qcow2_make_empty,
projects / qemu.git / blobdiff