@@ -435,17 +435,18 @@ typedef struct Qcow2COWRegion {
/**
* Describes an in-flight (part of a) write request that writes to clusters
- * that are not referenced in their L2 table yet.
+ * that need to have their L2 table entries updated (because they are
+ * newly allocated or need changes in their L2 bitmaps)
*/
typedef struct QCowL2Meta
{
- /** Guest offset of the first newly allocated cluster */
+ /** Guest offset of the first updated cluster */
uint64_t offset;
- /** Host offset of the first newly allocated cluster */
+ /** Host offset of the first updated cluster */
uint64_t alloc_offset;
- /** Number of newly allocated clusters */
+ /** Number of updated clusters */
int nb_clusters;
/** Do not free the old clusters */
@@ -458,14 +459,16 @@ typedef struct QCowL2Meta
CoQueue dependent_requests;
/**
- * The COW Region between the start of the first allocated cluster and the
- * area the guest actually writes to.
+ * The COW Region immediately before the area the guest actually
+ * writes to. This (part of the) write request starts at
+ * cow_start.offset + cow_start.nb_bytes.
*/
Qcow2COWRegion cow_start;
/**
- * The COW Region between the area the guest actually writes to and the
- * end of the last allocated cluster.
+ * The COW Region immediately after the area the guest actually
+ * writes to. This (part of the) write request ends at cow_end.offset
+ * (which must always be set even when cow_end.nb_bytes is 0).
*/
Qcow2COWRegion cow_end;
@@ -1049,6 +1049,8 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_slice);
assert(l2_index + m->nb_clusters <= s->l2_slice_size);
+ assert(m->cow_end.offset + m->cow_end.nb_bytes <=
+ m->nb_clusters << s->cluster_bits);
for (i = 0; i < m->nb_clusters; i++) {
uint64_t offset = cluster_offset + ((uint64_t)i << s->cluster_bits);
/* if two concurrent writes happen to the same unallocated cluster
@@ -1070,8 +1072,7 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
if (has_subclusters(s) && !m->prealloc) {
uint64_t l2_bitmap = get_l2_bitmap(s, l2_slice, l2_index + i);
unsigned written_from = m->cow_start.offset;
- unsigned written_to = m->cow_end.offset + m->cow_end.nb_bytes ?:
- m->nb_clusters << s->cluster_bits;
+ unsigned written_to = m->cow_end.offset + m->cow_end.nb_bytes;
int first_sc, last_sc;
/* Narrow written_from and written_to down to the current cluster */
written_from = MAX(written_from, i << s->cluster_bits);
@@ -2361,15 +2361,26 @@ static bool merge_cow(uint64_t offset, unsigned bytes,
continue;
}
- /* The data (middle) region must be immediately after the
- * start region */
+ /*
+ * The write request should start immediately after the first
+ * COW region. This does not always happen because the area
+ * touched by the request can be larger than the one defined
+ * by @m (a single request can span an area consisting of a
+ * mix of previously unallocated and allocated clusters, that
+ * is why @l2meta is a list).
+ */
if (l2meta_cow_start(m) + m->cow_start.nb_bytes != offset) {
+ /* In this case the request starts before this region */
+ assert(offset < l2meta_cow_start(m));
+ assert(m->cow_start.nb_bytes == 0);
continue;
}
- /* The end region must be immediately after the data (middle)
- * region */
+ /* The write request should end immediately before the second
+ * COW region (see above for why it does not always happen) */
if (m->offset + m->cow_end.offset != offset + bytes) {
+ assert(offset + bytes > m->offset + m->cow_end.offset);
+ assert(m->cow_end.nb_bytes == 0);
continue;
}