#include "qemu/bswap.h"
#include "trace.h"
+int qcow2_shrink_l1_table(BlockDriverState *bs, uint64_t exact_size)
+{
+ BDRVQcow2State *s = bs->opaque;
+ int new_l1_size, i, ret;
+
+ if (exact_size >= s->l1_size) {
+ return 0;
+ }
+
+ new_l1_size = exact_size;
+
+#ifdef DEBUG_ALLOC2
+ fprintf(stderr, "shrink l1_table from %d to %d\n", s->l1_size, new_l1_size);
+#endif
+
+ BLKDBG_EVENT(bs->file, BLKDBG_L1_SHRINK_WRITE_TABLE);
+ ret = bdrv_pwrite_zeroes(bs->file, s->l1_table_offset +
+ new_l1_size * sizeof(uint64_t),
+ (s->l1_size - new_l1_size) * sizeof(uint64_t), 0);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ ret = bdrv_flush(bs->file->bs);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ BLKDBG_EVENT(bs->file, BLKDBG_L1_SHRINK_FREE_L2_CLUSTERS);
+ for (i = s->l1_size - 1; i > new_l1_size - 1; i--) {
+ if ((s->l1_table[i] & L1E_OFFSET_MASK) == 0) {
+ continue;
+ }
+ qcow2_free_clusters(bs, s->l1_table[i] & L1E_OFFSET_MASK,
+ s->cluster_size, QCOW2_DISCARD_ALWAYS);
+ s->l1_table[i] = 0;
+ }
+ return 0;
+
+fail:
+ /*
+ * If the write in the l1_table failed the image may contain a partially
+ * overwritten l1_table. In this case it would be better to clear the
+ * l1_table in memory to avoid possible image corruption.
+ */
+ memset(s->l1_table + new_l1_size, 0,
+ (s->l1_size - new_l1_size) * sizeof(uint64_t));
+ return ret;
+}
+
int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
bool exact_size)
{
new_l1_size = 1;
}
while (min_size > new_l1_size) {
- new_l1_size = (new_l1_size * 3 + 1) / 2;
+ new_l1_size = DIV_ROUND_UP(new_l1_size * 3, 2);
}
}
goto fail;
}
+ /* If we're allocating the table at offset 0 then something is wrong */
+ if (l2_offset == 0) {
+ qcow2_signal_corruption(bs, true, -1, -1, "Preventing invalid "
+ "allocation of L2 table at offset 0");
+ ret = -EIO;
+ goto fail;
+ }
+
ret = qcow2_cache_flush(bs, s->refcount_block_cache);
if (ret < 0) {
goto fail;
uint64_t *l2_table, uint64_t stop_flags)
{
int i;
+ QCow2ClusterType first_cluster_type;
uint64_t mask = stop_flags | L2E_OFFSET_MASK | QCOW_OFLAG_COMPRESSED;
uint64_t first_entry = be64_to_cpu(l2_table[0]);
uint64_t offset = first_entry & mask;
- if (!offset)
+ if (!offset) {
return 0;
+ }
- assert(qcow2_get_cluster_type(first_entry) == QCOW2_CLUSTER_NORMAL);
+ /* must be allocated */
+ first_cluster_type = qcow2_get_cluster_type(first_entry);
+ assert(first_cluster_type == QCOW2_CLUSTER_NORMAL ||
+ first_cluster_type == QCOW2_CLUSTER_ZERO_ALLOC);
for (i = 0; i < nb_clusters; i++) {
uint64_t l2_entry = be64_to_cpu(l2_table[i]) & mask;
return i;
}
-static int count_contiguous_clusters_by_type(int nb_clusters,
- uint64_t *l2_table,
- int wanted_type)
+/*
+ * Checks how many consecutive unallocated clusters in a given L2
+ * table have the same cluster type.
+ */
+static int count_contiguous_clusters_unallocated(int nb_clusters,
+ uint64_t *l2_table,
+ QCow2ClusterType wanted_type)
{
int i;
+ assert(wanted_type == QCOW2_CLUSTER_ZERO_PLAIN ||
+ wanted_type == QCOW2_CLUSTER_UNALLOCATED);
for (i = 0; i < nb_clusters; i++) {
- int type = qcow2_get_cluster_type(be64_to_cpu(l2_table[i]));
+ uint64_t entry = be64_to_cpu(l2_table[i]);
+ QCow2ClusterType type = qcow2_get_cluster_type(entry);
if (type != wanted_type) {
break;
return i;
}
-/* The crypt function is compatible with the linux cryptoloop
- algorithm for < 4 GB images. NOTE: out_buf == in_buf is
- supported */
-int qcow2_encrypt_sectors(BDRVQcow2State *s, int64_t sector_num,
- uint8_t *out_buf, const uint8_t *in_buf,
- int nb_sectors, bool enc,
- Error **errp)
+static int coroutine_fn do_perform_cow_read(BlockDriverState *bs,
+ uint64_t src_cluster_offset,
+ unsigned offset_in_cluster,
+ QEMUIOVector *qiov)
{
- union {
- uint64_t ll[2];
- uint8_t b[16];
- } ivec;
- int i;
int ret;
- for(i = 0; i < nb_sectors; i++) {
- ivec.ll[0] = cpu_to_le64(sector_num);
- ivec.ll[1] = 0;
- if (qcrypto_cipher_setiv(s->cipher,
- ivec.b, G_N_ELEMENTS(ivec.b),
- errp) < 0) {
- return -1;
- }
- if (enc) {
- ret = qcrypto_cipher_encrypt(s->cipher,
- in_buf,
- out_buf,
- 512,
- errp);
- } else {
- ret = qcrypto_cipher_decrypt(s->cipher,
- in_buf,
- out_buf,
- 512,
- errp);
- }
- if (ret < 0) {
- return -1;
- }
- sector_num++;
- in_buf += 512;
- out_buf += 512;
- }
- return 0;
-}
-
-static int coroutine_fn do_perform_cow(BlockDriverState *bs,
- uint64_t src_cluster_offset,
- uint64_t cluster_offset,
- int offset_in_cluster,
- int bytes)
-{
- BDRVQcow2State *s = bs->opaque;
- QEMUIOVector qiov;
- struct iovec iov;
- int ret;
-
- iov.iov_len = bytes;
- iov.iov_base = qemu_try_blockalign(bs, iov.iov_len);
- if (iov.iov_base == NULL) {
- return -ENOMEM;
+ if (qiov->size == 0) {
+ return 0;
}
- qemu_iovec_init_external(&qiov, &iov, 1);
-
BLKDBG_EVENT(bs->file, BLKDBG_COW_READ);
if (!bs->drv) {
- ret = -ENOMEDIUM;
- goto out;
+ return -ENOMEDIUM;
}
/* Call .bdrv_co_readv() directly instead of using the public block-layer
* which can lead to deadlock when block layer copy-on-read is enabled.
*/
ret = bs->drv->bdrv_co_preadv(bs, src_cluster_offset + offset_in_cluster,
- bytes, &qiov, 0);
+ qiov->size, qiov, 0);
if (ret < 0) {
- goto out;
+ return ret;
}
- if (bs->encrypted) {
- Error *err = NULL;
- int64_t sector = (cluster_offset + offset_in_cluster)
- >> BDRV_SECTOR_BITS;
- assert(s->cipher);
+ return 0;
+}
+
+static bool coroutine_fn do_perform_cow_encrypt(BlockDriverState *bs,
+ uint64_t src_cluster_offset,
+ uint64_t cluster_offset,
+ unsigned offset_in_cluster,
+ uint8_t *buffer,
+ unsigned bytes)
+{
+ if (bytes && bs->encrypted) {
+ BDRVQcow2State *s = bs->opaque;
+ int64_t offset = (s->crypt_physical_offset ?
+ (cluster_offset + offset_in_cluster) :
+ (src_cluster_offset + offset_in_cluster));
assert((offset_in_cluster & ~BDRV_SECTOR_MASK) == 0);
assert((bytes & ~BDRV_SECTOR_MASK) == 0);
- if (qcow2_encrypt_sectors(s, sector, iov.iov_base, iov.iov_base,
- bytes >> BDRV_SECTOR_BITS, true, &err) < 0) {
- ret = -EIO;
- error_free(err);
- goto out;
+ assert(s->crypto);
+ if (qcrypto_block_encrypt(s->crypto, offset, buffer, bytes, NULL) < 0) {
+ return false;
}
}
+ return true;
+}
+
+static int coroutine_fn do_perform_cow_write(BlockDriverState *bs,
+ uint64_t cluster_offset,
+ unsigned offset_in_cluster,
+ QEMUIOVector *qiov)
+{
+ int ret;
+
+ if (qiov->size == 0) {
+ return 0;
+ }
ret = qcow2_pre_write_overlap_check(bs, 0,
- cluster_offset + offset_in_cluster, bytes);
+ cluster_offset + offset_in_cluster, qiov->size);
if (ret < 0) {
- goto out;
+ return ret;
}
BLKDBG_EVENT(bs->file, BLKDBG_COW_WRITE);
ret = bdrv_co_pwritev(bs->file, cluster_offset + offset_in_cluster,
- bytes, &qiov, 0);
+ qiov->size, qiov, 0);
if (ret < 0) {
- goto out;
+ return ret;
}
- ret = 0;
-out:
- qemu_vfree(iov.iov_base);
- return ret;
+ return 0;
}
int l1_bits, c;
unsigned int offset_in_cluster;
uint64_t bytes_available, bytes_needed, nb_clusters;
+ QCow2ClusterType type;
int ret;
offset_in_cluster = offset_into_cluster(s, offset);
l1_index = offset >> l1_bits;
if (l1_index >= s->l1_size) {
- ret = QCOW2_CLUSTER_UNALLOCATED;
+ type = QCOW2_CLUSTER_UNALLOCATED;
goto out;
}
l2_offset = s->l1_table[l1_index] & L1E_OFFSET_MASK;
if (!l2_offset) {
- ret = QCOW2_CLUSTER_UNALLOCATED;
+ type = QCOW2_CLUSTER_UNALLOCATED;
goto out;
}
/* find the cluster offset for the given disk offset */
- l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1);
+ l2_index = offset_to_l2_index(s, offset);
*cluster_offset = be64_to_cpu(l2_table[l2_index]);
nb_clusters = size_to_clusters(s, bytes_needed);
* true */
assert(nb_clusters <= INT_MAX);
- ret = qcow2_get_cluster_type(*cluster_offset);
- switch (ret) {
+ type = qcow2_get_cluster_type(*cluster_offset);
+ if (s->qcow_version < 3 && (type == QCOW2_CLUSTER_ZERO_PLAIN ||
+ type == QCOW2_CLUSTER_ZERO_ALLOC)) {
+ qcow2_signal_corruption(bs, true, -1, -1, "Zero cluster entry found"
+ " in pre-v3 image (L2 offset: %#" PRIx64
+ ", L2 index: %#x)", l2_offset, l2_index);
+ ret = -EIO;
+ goto fail;
+ }
+ switch (type) {
case QCOW2_CLUSTER_COMPRESSED:
/* Compressed clusters can only be processed one by one */
c = 1;
*cluster_offset &= L2E_COMPRESSED_OFFSET_SIZE_MASK;
break;
- case QCOW2_CLUSTER_ZERO:
- if (s->qcow_version < 3) {
- qcow2_signal_corruption(bs, true, -1, -1, "Zero cluster entry found"
- " in pre-v3 image (L2 offset: %#" PRIx64
- ", L2 index: %#x)", l2_offset, l2_index);
- ret = -EIO;
- goto fail;
- }
- c = count_contiguous_clusters_by_type(nb_clusters, &l2_table[l2_index],
- QCOW2_CLUSTER_ZERO);
- *cluster_offset = 0;
- break;
+ case QCOW2_CLUSTER_ZERO_PLAIN:
case QCOW2_CLUSTER_UNALLOCATED:
/* how many empty clusters ? */
- c = count_contiguous_clusters_by_type(nb_clusters, &l2_table[l2_index],
- QCOW2_CLUSTER_UNALLOCATED);
+ c = count_contiguous_clusters_unallocated(nb_clusters,
+ &l2_table[l2_index], type);
*cluster_offset = 0;
break;
+ case QCOW2_CLUSTER_ZERO_ALLOC:
case QCOW2_CLUSTER_NORMAL:
/* how many allocated clusters ? */
c = count_contiguous_clusters(nb_clusters, s->cluster_size,
- &l2_table[l2_index], QCOW_OFLAG_ZERO);
+ &l2_table[l2_index], QCOW_OFLAG_ZERO);
*cluster_offset &= L2E_OFFSET_MASK;
if (offset_into_cluster(s, *cluster_offset)) {
- qcow2_signal_corruption(bs, true, -1, -1, "Data cluster offset %#"
+ qcow2_signal_corruption(bs, true, -1, -1,
+ "Cluster allocation offset %#"
PRIx64 " unaligned (L2 offset: %#" PRIx64
", L2 index: %#x)", *cluster_offset,
l2_offset, l2_index);
assert(bytes_available - offset_in_cluster <= UINT_MAX);
*bytes = bytes_available - offset_in_cluster;
- return ret;
+ return type;
fail:
qcow2_cache_put(bs, s->l2_table_cache, (void **)&l2_table);
/* find the cluster offset for the given disk offset */
- l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1);
+ l2_index = offset_to_l2_index(s, offset);
*new_l2_table = l2_table;
*new_l2_index = l2_index;
return cluster_offset;
}
-static int perform_cow(BlockDriverState *bs, QCowL2Meta *m, Qcow2COWRegion *r)
+static int perform_cow(BlockDriverState *bs, QCowL2Meta *m)
{
BDRVQcow2State *s = bs->opaque;
+ Qcow2COWRegion *start = &m->cow_start;
+ Qcow2COWRegion *end = &m->cow_end;
+ unsigned buffer_size;
+ unsigned data_bytes = end->offset - (start->offset + start->nb_bytes);
+ bool merge_reads;
+ uint8_t *start_buffer, *end_buffer;
+ QEMUIOVector qiov;
int ret;
- if (r->nb_bytes == 0) {
+ assert(start->nb_bytes <= UINT_MAX - end->nb_bytes);
+ assert(start->nb_bytes + end->nb_bytes <= UINT_MAX - data_bytes);
+ assert(start->offset + start->nb_bytes <= end->offset);
+ assert(!m->data_qiov || m->data_qiov->size == data_bytes);
+
+ if (start->nb_bytes == 0 && end->nb_bytes == 0) {
return 0;
}
+ /* If we have to read both the start and end COW regions and the
+ * middle region is not too large then perform just one read
+ * operation */
+ merge_reads = start->nb_bytes && end->nb_bytes && data_bytes <= 16384;
+ if (merge_reads) {
+ buffer_size = start->nb_bytes + data_bytes + end->nb_bytes;
+ } else {
+ /* If we have to do two reads, add some padding in the middle
+ * if necessary to make sure that the end region is optimally
+ * aligned. */
+ size_t align = bdrv_opt_mem_align(bs);
+ assert(align > 0 && align <= UINT_MAX);
+ assert(QEMU_ALIGN_UP(start->nb_bytes, align) <=
+ UINT_MAX - end->nb_bytes);
+ buffer_size = QEMU_ALIGN_UP(start->nb_bytes, align) + end->nb_bytes;
+ }
+
+ /* Reserve a buffer large enough to store all the data that we're
+ * going to read */
+ start_buffer = qemu_try_blockalign(bs, buffer_size);
+ if (start_buffer == NULL) {
+ return -ENOMEM;
+ }
+ /* The part of the buffer where the end region is located */
+ end_buffer = start_buffer + buffer_size - end->nb_bytes;
+
+ qemu_iovec_init(&qiov, 2 + (m->data_qiov ? m->data_qiov->niov : 0));
+
qemu_co_mutex_unlock(&s->lock);
- ret = do_perform_cow(bs, m->offset, m->alloc_offset, r->offset, r->nb_bytes);
- qemu_co_mutex_lock(&s->lock);
+ /* First we read the existing data from both COW regions. We
+ * either read the whole region in one go, or the start and end
+ * regions separately. */
+ if (merge_reads) {
+ qemu_iovec_add(&qiov, start_buffer, buffer_size);
+ ret = do_perform_cow_read(bs, m->offset, start->offset, &qiov);
+ } else {
+ qemu_iovec_add(&qiov, start_buffer, start->nb_bytes);
+ ret = do_perform_cow_read(bs, m->offset, start->offset, &qiov);
+ if (ret < 0) {
+ goto fail;
+ }
+ qemu_iovec_reset(&qiov);
+ qemu_iovec_add(&qiov, end_buffer, end->nb_bytes);
+ ret = do_perform_cow_read(bs, m->offset, end->offset, &qiov);
+ }
if (ret < 0) {
- return ret;
+ goto fail;
+ }
+
+ /* Encrypt the data if necessary before writing it */
+ if (bs->encrypted) {
+ if (!do_perform_cow_encrypt(bs, m->offset, m->alloc_offset,
+ start->offset, start_buffer,
+ start->nb_bytes) ||
+ !do_perform_cow_encrypt(bs, m->offset, m->alloc_offset,
+ end->offset, end_buffer, end->nb_bytes)) {
+ ret = -EIO;
+ goto fail;
+ }
+ }
+
+ /* And now we can write everything. If we have the guest data we
+ * can write everything in one single operation */
+ if (m->data_qiov) {
+ qemu_iovec_reset(&qiov);
+ if (start->nb_bytes) {
+ qemu_iovec_add(&qiov, start_buffer, start->nb_bytes);
+ }
+ qemu_iovec_concat(&qiov, m->data_qiov, 0, data_bytes);
+ if (end->nb_bytes) {
+ qemu_iovec_add(&qiov, end_buffer, end->nb_bytes);
+ }
+ /* NOTE: we have a write_aio blkdebug event here followed by
+ * a cow_write one in do_perform_cow_write(), but there's only
+ * one single I/O operation */
+ BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
+ ret = do_perform_cow_write(bs, m->alloc_offset, start->offset, &qiov);
+ } else {
+ /* If there's no guest data then write both COW regions separately */
+ qemu_iovec_reset(&qiov);
+ qemu_iovec_add(&qiov, start_buffer, start->nb_bytes);
+ ret = do_perform_cow_write(bs, m->alloc_offset, start->offset, &qiov);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ qemu_iovec_reset(&qiov);
+ qemu_iovec_add(&qiov, end_buffer, end->nb_bytes);
+ ret = do_perform_cow_write(bs, m->alloc_offset, end->offset, &qiov);
}
+fail:
+ qemu_co_mutex_lock(&s->lock);
+
/*
* Before we update the L2 table to actually point to the new cluster, we
* need to be sure that the refcounts have been increased and COW was
* handled.
*/
- qcow2_cache_depends_on_flush(s->l2_table_cache);
+ if (ret == 0) {
+ qcow2_cache_depends_on_flush(s->l2_table_cache);
+ }
- return 0;
+ qemu_vfree(start_buffer);
+ qemu_iovec_destroy(&qiov);
+ return ret;
}
int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
}
/* copy content of unmodified sectors */
- ret = perform_cow(bs, m, &m->cow_start);
- if (ret < 0) {
- goto err;
- }
-
- ret = perform_cow(bs, m, &m->cow_end);
+ ret = perform_cow(bs, m);
if (ret < 0) {
goto err;
}
* Don't discard clusters that reach a refcount of 0 (e.g. compressed
* clusters), the next write will reuse them anyway.
*/
- if (j != 0) {
+ if (!m->keep_old_clusters && j != 0) {
for (i = 0; i < j; i++) {
qcow2_free_any_clusters(bs, be64_to_cpu(old_cluster[i]), 1,
QCOW2_DISCARD_NEVER);
for (i = 0; i < nb_clusters; i++) {
uint64_t l2_entry = be64_to_cpu(l2_table[l2_index + i]);
- int cluster_type = qcow2_get_cluster_type(l2_entry);
+ QCow2ClusterType cluster_type = qcow2_get_cluster_type(l2_entry);
switch(cluster_type) {
case QCOW2_CLUSTER_NORMAL:
break;
case QCOW2_CLUSTER_UNALLOCATED:
case QCOW2_CLUSTER_COMPRESSED:
- case QCOW2_CLUSTER_ZERO:
+ case QCOW2_CLUSTER_ZERO_PLAIN:
+ case QCOW2_CLUSTER_ZERO_ALLOC:
break;
default:
abort();
if (bytes == 0) {
/* Wait for the dependency to complete. We need to recheck
* the free/allocated clusters when we continue. */
- qemu_co_mutex_unlock(&s->lock);
- qemu_co_queue_wait(&old_alloc->dependent_requests);
- qemu_co_mutex_lock(&s->lock);
+ qemu_co_queue_wait(&old_alloc->dependent_requests, &s->lock);
return -EAGAIN;
}
}
uint64_t entry;
uint64_t nb_clusters;
int ret;
+ bool keep_old_clusters = false;
- uint64_t alloc_cluster_offset;
+ uint64_t alloc_cluster_offset = 0;
trace_qcow2_handle_alloc(qemu_coroutine_self(), guest_offset, *host_offset,
*bytes);
* wrong with our code. */
assert(nb_clusters > 0);
- qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table);
+ if (qcow2_get_cluster_type(entry) == QCOW2_CLUSTER_ZERO_ALLOC &&
+ (entry & QCOW_OFLAG_COPIED) &&
+ (!*host_offset ||
+ start_of_cluster(s, *host_offset) == (entry & L2E_OFFSET_MASK)))
+ {
+ int preallocated_nb_clusters;
- /* Allocate, if necessary at a given offset in the image file */
- alloc_cluster_offset = start_of_cluster(s, *host_offset);
- ret = do_alloc_cluster_offset(bs, guest_offset, &alloc_cluster_offset,
- &nb_clusters);
- if (ret < 0) {
- goto fail;
- }
+ if (offset_into_cluster(s, entry & L2E_OFFSET_MASK)) {
+ qcow2_signal_corruption(bs, true, -1, -1, "Preallocated zero "
+ "cluster offset %#llx unaligned (guest "
+ "offset: %#" PRIx64 ")",
+ entry & L2E_OFFSET_MASK, guest_offset);
+ ret = -EIO;
+ goto fail;
+ }
- /* Can't extend contiguous allocation */
- if (nb_clusters == 0) {
- *bytes = 0;
- return 0;
+ /* Try to reuse preallocated zero clusters; contiguous normal clusters
+ * would be fine, too, but count_cow_clusters() above has limited
+ * nb_clusters already to a range of COW clusters */
+ preallocated_nb_clusters =
+ count_contiguous_clusters(nb_clusters, s->cluster_size,
+ &l2_table[l2_index], QCOW_OFLAG_COPIED);
+ assert(preallocated_nb_clusters > 0);
+
+ nb_clusters = preallocated_nb_clusters;
+ alloc_cluster_offset = entry & L2E_OFFSET_MASK;
+
+ /* We want to reuse these clusters, so qcow2_alloc_cluster_link_l2()
+ * should not free them. */
+ keep_old_clusters = true;
}
- /* !*host_offset would overwrite the image header and is reserved for "no
- * host offset preferred". If 0 was a valid host offset, it'd trigger the
- * following overlap check; do that now to avoid having an invalid value in
- * *host_offset. */
+ qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table);
+
if (!alloc_cluster_offset) {
- ret = qcow2_pre_write_overlap_check(bs, 0, alloc_cluster_offset,
- nb_clusters * s->cluster_size);
- assert(ret < 0);
- goto fail;
+ /* Allocate, if necessary at a given offset in the image file */
+ alloc_cluster_offset = start_of_cluster(s, *host_offset);
+ ret = do_alloc_cluster_offset(bs, guest_offset, &alloc_cluster_offset,
+ &nb_clusters);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* Can't extend contiguous allocation */
+ if (nb_clusters == 0) {
+ *bytes = 0;
+ return 0;
+ }
+
+ /* !*host_offset would overwrite the image header and is reserved for
+ * "no host offset preferred". If 0 was a valid host offset, it'd
+ * trigger the following overlap check; do that now to avoid having an
+ * invalid value in *host_offset. */
+ if (!alloc_cluster_offset) {
+ ret = qcow2_pre_write_overlap_check(bs, 0, alloc_cluster_offset,
+ nb_clusters * s->cluster_size);
+ assert(ret < 0);
+ goto fail;
+ }
}
/*
.offset = start_of_cluster(s, guest_offset),
.nb_clusters = nb_clusters,
+ .keep_old_clusters = keep_old_clusters,
+
.cow_start = {
.offset = 0,
.nb_bytes = offset_into_cluster(s, guest_offset),
nb_csectors = ((cluster_offset >> s->csize_shift) & s->csize_mask) + 1;
sector_offset = coffset & 511;
csize = nb_csectors * 512 - sector_offset;
+
+ /* Allocate buffers on first decompress operation, most images are
+ * uncompressed and the memory overhead can be avoided. The buffers
+ * are freed in .bdrv_close().
+ */
+ if (!s->cluster_data) {
+ /* one more sector for decompressed data alignment */
+ s->cluster_data = qemu_try_blockalign(bs->file->bs,
+ QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size + 512);
+ if (!s->cluster_data) {
+ return -ENOMEM;
+ }
+ }
+ if (!s->cluster_cache) {
+ s->cluster_cache = g_malloc(s->cluster_size);
+ }
+
BLKDBG_EVENT(bs->file, BLKDBG_READ_COMPRESSED);
ret = bdrv_read(bs->file, coffset >> 9, s->cluster_data,
nb_csectors);
* cluster is already marked as zero, or if it's unallocated and we
* don't have a backing file.
*
- * TODO We might want to use bdrv_get_block_status(bs) here, but we're
+ * TODO We might want to use bdrv_block_status(bs) here, but we're
* holding s->lock, so that doesn't work today.
*
* If full_discard is true, the sector should not read back as zeroes,
* but rather fall through to the backing file.
*/
switch (qcow2_get_cluster_type(old_l2_entry)) {
- case QCOW2_CLUSTER_UNALLOCATED:
- if (full_discard || !bs->backing) {
- continue;
- }
- break;
+ case QCOW2_CLUSTER_UNALLOCATED:
+ if (full_discard || !bs->backing) {
+ continue;
+ }
+ break;
- case QCOW2_CLUSTER_ZERO:
- if (!full_discard) {
- continue;
- }
- break;
+ case QCOW2_CLUSTER_ZERO_PLAIN:
+ if (!full_discard) {
+ continue;
+ }
+ break;
- case QCOW2_CLUSTER_NORMAL:
- case QCOW2_CLUSTER_COMPRESSED:
- break;
+ case QCOW2_CLUSTER_ZERO_ALLOC:
+ case QCOW2_CLUSTER_NORMAL:
+ case QCOW2_CLUSTER_COMPRESSED:
+ break;
- default:
- abort();
+ default:
+ abort();
}
/* First remove L2 entries */
return nb_clusters;
}
-int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
- int nb_sectors, enum qcow2_discard_type type, bool full_discard)
+int qcow2_cluster_discard(BlockDriverState *bs, uint64_t offset,
+ uint64_t bytes, enum qcow2_discard_type type,
+ bool full_discard)
{
BDRVQcow2State *s = bs->opaque;
- uint64_t end_offset;
+ uint64_t end_offset = offset + bytes;
uint64_t nb_clusters;
+ int64_t cleared;
int ret;
- end_offset = offset + (nb_sectors << BDRV_SECTOR_BITS);
+ /* Caller must pass aligned values, except at image end */
+ assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
+ assert(QEMU_IS_ALIGNED(end_offset, s->cluster_size) ||
+ end_offset == bs->total_sectors << BDRV_SECTOR_BITS);
- /* Round start up and end down */
- offset = align_offset(offset, s->cluster_size);
- end_offset = start_of_cluster(s, end_offset);
-
- if (offset > end_offset) {
- return 0;
- }
-
- nb_clusters = size_to_clusters(s, end_offset - offset);
+ nb_clusters = size_to_clusters(s, bytes);
s->cache_discards = true;
/* Each L2 table is handled by its own loop iteration */
while (nb_clusters > 0) {
- ret = discard_single_l2(bs, offset, nb_clusters, type, full_discard);
- if (ret < 0) {
+ cleared = discard_single_l2(bs, offset, nb_clusters, type,
+ full_discard);
+ if (cleared < 0) {
+ ret = cleared;
goto fail;
}
- nb_clusters -= ret;
- offset += (ret * s->cluster_size);
+ nb_clusters -= cleared;
+ offset += (cleared * s->cluster_size);
}
ret = 0;
* clusters.
*/
static int zero_single_l2(BlockDriverState *bs, uint64_t offset,
- uint64_t nb_clusters)
+ uint64_t nb_clusters, int flags)
{
BDRVQcow2State *s = bs->opaque;
uint64_t *l2_table;
int l2_index;
int ret;
int i;
+ bool unmap = !!(flags & BDRV_REQ_MAY_UNMAP);
ret = get_cluster_table(bs, offset, &l2_table, &l2_index);
if (ret < 0) {
for (i = 0; i < nb_clusters; i++) {
uint64_t old_offset;
+ QCow2ClusterType cluster_type;
old_offset = be64_to_cpu(l2_table[l2_index + i]);
- /* Update L2 entries */
+ /*
+ * Minimize L2 changes if the cluster already reads back as
+ * zeroes with correct allocation.
+ */
+ cluster_type = qcow2_get_cluster_type(old_offset);
+ if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN ||
+ (cluster_type == QCOW2_CLUSTER_ZERO_ALLOC && !unmap)) {
+ continue;
+ }
+
qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, l2_table);
- if (old_offset & QCOW_OFLAG_COMPRESSED) {
+ if (cluster_type == QCOW2_CLUSTER_COMPRESSED || unmap) {
l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO);
qcow2_free_any_clusters(bs, old_offset, 1, QCOW2_DISCARD_REQUEST);
} else {
return nb_clusters;
}
-int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors)
+int qcow2_cluster_zeroize(BlockDriverState *bs, uint64_t offset,
+ uint64_t bytes, int flags)
{
BDRVQcow2State *s = bs->opaque;
+ uint64_t end_offset = offset + bytes;
uint64_t nb_clusters;
+ int64_t cleared;
int ret;
+ /* Caller must pass aligned values, except at image end */
+ assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
+ assert(QEMU_IS_ALIGNED(end_offset, s->cluster_size) ||
+ end_offset == bs->total_sectors << BDRV_SECTOR_BITS);
+
/* The zero flag is only supported by version 3 and newer */
if (s->qcow_version < 3) {
return -ENOTSUP;
}
/* Each L2 table is handled by its own loop iteration */
- nb_clusters = size_to_clusters(s, nb_sectors << BDRV_SECTOR_BITS);
+ nb_clusters = size_to_clusters(s, bytes);
s->cache_discards = true;
while (nb_clusters > 0) {
- ret = zero_single_l2(bs, offset, nb_clusters);
- if (ret < 0) {
+ cleared = zero_single_l2(bs, offset, nb_clusters, flags);
+ if (cleared < 0) {
+ ret = cleared;
goto fail;
}
- nb_clusters -= ret;
- offset += (ret * s->cluster_size);
+ nb_clusters -= cleared;
+ offset += (cleared * s->cluster_size);
}
ret = 0;
for (j = 0; j < s->l2_size; j++) {
uint64_t l2_entry = be64_to_cpu(l2_table[j]);
int64_t offset = l2_entry & L2E_OFFSET_MASK;
- int cluster_type = qcow2_get_cluster_type(l2_entry);
- bool preallocated = offset != 0;
+ QCow2ClusterType cluster_type = qcow2_get_cluster_type(l2_entry);
- if (cluster_type != QCOW2_CLUSTER_ZERO) {
+ if (cluster_type != QCOW2_CLUSTER_ZERO_PLAIN &&
+ cluster_type != QCOW2_CLUSTER_ZERO_ALLOC) {
continue;
}
- if (!preallocated) {
+ if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) {
if (!bs->backing) {
/* not backed; therefore we can simply deallocate the
* cluster */
}
if (offset_into_cluster(s, offset)) {
- qcow2_signal_corruption(bs, true, -1, -1, "Data cluster offset "
+ qcow2_signal_corruption(bs, true, -1, -1,
+ "Cluster allocation offset "
"%#" PRIx64 " unaligned (L2 offset: %#"
PRIx64 ", L2 index: %#x)", offset,
l2_offset, j);
- if (!preallocated) {
+ if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) {
qcow2_free_clusters(bs, offset, s->cluster_size,
QCOW2_DISCARD_ALWAYS);
}
ret = qcow2_pre_write_overlap_check(bs, 0, offset, s->cluster_size);
if (ret < 0) {
- if (!preallocated) {
+ if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) {
qcow2_free_clusters(bs, offset, s->cluster_size,
QCOW2_DISCARD_ALWAYS);
}
ret = bdrv_pwrite_zeroes(bs->file, offset, s->cluster_size, 0);
if (ret < 0) {
- if (!preallocated) {
+ if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) {
qcow2_free_clusters(bs, offset, s->cluster_size,
QCOW2_DISCARD_ALWAYS);
}
projects / mirror_qemu.git / blobdiff