qcow2: Allow writing compressed data of multiple clusters

QEMU currently supports writing compressed data of the size equal to
one cluster. This patch allows writing QCOW2 compressed data that
exceed one cluster. Now, we split buffered data into separate clusters
and write them compressed using the block/aio_task API.

Suggested-by: Pavel Butsykin <pbutsykin@virtuozzo.com>
Suggested-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-id: 1575288906-551879-3-git-send-email-andrey.shinkevich@virtuozzo.com
Signed-off-by: Max Reitz <mreitz@redhat.com>

block/qcow2.c

@@ -4221,10 +4221,8 @@ fail:
     return ret;
 }
 
-/* XXX: put compressed sectors first, then all the cluster aligned
-   tables to avoid losing bytes in alignment */
 static coroutine_fn int
-qcow2_co_pwritev_compressed_part(BlockDriverState *bs,
+qcow2_co_pwritev_compressed_task(BlockDriverState *bs,
                                  uint64_t offset, uint64_t bytes,
                                  QEMUIOVector *qiov, size_t qiov_offset)
 {
@@ -4234,32 +4232,11 @@ qcow2_co_pwritev_compressed_part(BlockDriverState *bs,
     uint8_t *buf, *out_buf;
     uint64_t cluster_offset;
 
-    if (has_data_file(bs)) {
-        return -ENOTSUP;
-    }
-
-    if (bytes == 0) {
-        /* align end of file to a sector boundary to ease reading with
-           sector based I/Os */
-        int64_t len = bdrv_getlength(bs->file->bs);
-        if (len < 0) {
-            return len;
-        }
-        return bdrv_co_truncate(bs->file, len, false, PREALLOC_MODE_OFF, NULL);
-    }
-
-    if (offset_into_cluster(s, offset)) {
-        return -EINVAL;
-    }
+    assert(bytes == s->cluster_size || (bytes < s->cluster_size &&
+           (offset + bytes == bs->total_sectors << BDRV_SECTOR_BITS)));
 
     buf = qemu_blockalign(bs, s->cluster_size);
-    if (bytes != s->cluster_size) {
-        if (bytes > s->cluster_size ||
-            offset + bytes != bs->total_sectors << BDRV_SECTOR_BITS)
-        {
-            qemu_vfree(buf);
-            return -EINVAL;
-        }
+    if (bytes < s->cluster_size) {
         /* Zero-pad last write if image size is not cluster aligned */
         memset(buf + bytes, 0, s->cluster_size - bytes);
     }
@@ -4308,6 +4285,77 @@ fail:
     return ret;
 }
 
+static coroutine_fn int qcow2_co_pwritev_compressed_task_entry(AioTask *task)
+{
+    Qcow2AioTask *t = container_of(task, Qcow2AioTask, task);
+
+    assert(!t->cluster_type && !t->l2meta);
+
+    return qcow2_co_pwritev_compressed_task(t->bs, t->offset, t->bytes, t->qiov,
+                                            t->qiov_offset);
+}
+
+/*
+ * XXX: put compressed sectors first, then all the cluster aligned
+ * tables to avoid losing bytes in alignment
+ */
+static coroutine_fn int
+qcow2_co_pwritev_compressed_part(BlockDriverState *bs,
+                                 uint64_t offset, uint64_t bytes,
+                                 QEMUIOVector *qiov, size_t qiov_offset)
+{
+    BDRVQcow2State *s = bs->opaque;
+    AioTaskPool *aio = NULL;
+    int ret = 0;
+
+    if (has_data_file(bs)) {
+        return -ENOTSUP;
+    }
+
+    if (bytes == 0) {
+        /*
+         * align end of file to a sector boundary to ease reading with
+         * sector based I/Os
+         */
+        int64_t len = bdrv_getlength(bs->file->bs);
+        if (len < 0) {
+            return len;
+        }
+        return bdrv_co_truncate(bs->file, len, false, PREALLOC_MODE_OFF, NULL);
+    }
+
+    if (offset_into_cluster(s, offset)) {
+        return -EINVAL;
+    }
+
+    while (bytes && aio_task_pool_status(aio) == 0) {
+        uint64_t chunk_size = MIN(bytes, s->cluster_size);
+
+        if (!aio && chunk_size != bytes) {
+            aio = aio_task_pool_new(QCOW2_MAX_WORKERS);
+        }
+
+        ret = qcow2_add_task(bs, aio, qcow2_co_pwritev_compressed_task_entry,
+                             0, 0, offset, chunk_size, qiov, qiov_offset, NULL);
+        if (ret < 0) {
+            break;
+        }
+        qiov_offset += chunk_size;
+        offset += chunk_size;
+        bytes -= chunk_size;
+    }
+
+    if (aio) {
+        aio_task_pool_wait_all(aio);
+        if (ret == 0) {
+            ret = aio_task_pool_status(aio);
+        }
+        g_free(aio);
+    }
+
+    return ret;
+}
+
 static int coroutine_fn
 qcow2_co_preadv_compressed(BlockDriverState *bs,
                            uint64_t file_cluster_offset,