Block layer patches

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQIcBAABAgAGBQJYsHaaAAoJEH8JsnLIjy/WvC4P/iw/WC6XySNzPMOzICrJr9fc
 IHz447+0MqoIBWqGRFLEU8z4t6k8HGt2YnWKFuS1N+2gU5fSgOdp20nAA+pQvxRb
 RTyQL7BNJPvFNzrEQPTpdvBt79veYsoNe5dNfSq01z/PdgxMQR4PkS96Jm8w4Jdu
 20ZPfULws8+Wq1Snsxl4PdnFpY2n97OOGQRCjl50h5ypol5+fXDDzAvp/GPf6Q8B
 09OTWmQ4UIr4OZqT83T1kDdRZRRMIxiRP5qTTKdh0BlJEQdBjrJ9fTClY4bMcIgl
 VP/3kzkmdoqSW+4D+0L88q7vyvM3Kwc6n2PFDaRf6Lgy9ueYoPKuW9AF5vzcxhED
 AI0SN9boM+4z1P75kalBaHg/BiRL7UDwpHgdanPVcENoP8IywsKzOIvdjOpqINmX
 uLU3QfK+qK6x7gflhVXiX2sFzTLzZQlWu5KPjW6QfuMzUuRAeksfMDXh2GXNFVG1
 igGnORyqB2nOGNAsudtMrOvjHQRSbwGsnvWcwvaX0swrxOb3oAwc3X+E4nxE/K5/
 wJQLrCM9DfD3CKKlKiu+1wQXx6zqaGYIsNxLcrSylJ3TPsGuxfkx3b9GVCCQ0Y+e
 YSdwWSAIS9LxR4qISJ5ehlnYDA0sRtdco0xGW6ACNE5IrgREYUcH4EJOXbxZ4NHs
 BK/DVdYhFtNZ60zHeEn4
 =OYgF
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/kevin/tags/for-upstream' into staging

Block layer patches

# gpg: Signature made Fri 24 Feb 2017 18:08:26 GMT
# gpg:                using RSA key 0x7F09B272C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* remotes/kevin/tags/for-upstream:
  tests: Use opened block node for block job tests
  vvfat: Use opened node as backing file
  block: Add bdrv_new_open_driver()
  block: Factor out bdrv_open_driver()
  block: Use BlockBackend for image probing
  block: Factor out bdrv_open_child_bs()
  block: Attach bs->file only during .bdrv_open()
  block: Pass BdrvChild to bdrv_truncate()
  mirror: Resize active commit base in mirror_run()
  qcow2: Use BB for resizing in qcow2_amend_options()
  blockdev: Use BlockBackend to resize in qmp_block_resize()
  iotests: Fix another race in 030
  qemu-img: Improve documentation for PREALLOC_MODE_FALLOC
  qemu-img: Truncate before full preallocation
  qemu-img: Add tests for raw image preallocation
  qemu-img: Do not truncate before preallocation
  qemu-iotests: redirect nbd server stdout to /dev/null
  qemu-iotests: add ability to exclude certain protocols from tests
  qemu-iotests: Test 137 only supports 'file' protocol

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

block.c

@@ -588,21 +588,20 @@ BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size,
     return drv;
 }
 
-static int find_image_format(BdrvChild *file, const char *filename,
+static int find_image_format(BlockBackend *file, const char *filename,
                              BlockDriver **pdrv, Error **errp)
 {
-    BlockDriverState *bs = file->bs;
     BlockDriver *drv;
     uint8_t buf[BLOCK_PROBE_BUF_SIZE];
     int ret = 0;
 
     /* Return the raw BlockDriver * to scsi-generic devices or empty drives */
-    if (bdrv_is_sg(bs) || !bdrv_is_inserted(bs) || bdrv_getlength(bs) == 0) {
+    if (blk_is_sg(file) || !blk_is_inserted(file) || blk_getlength(file) == 0) {
         *pdrv = &bdrv_raw;
         return ret;
     }
 
-    ret = bdrv_pread(file, 0, buf, sizeof(buf));
+    ret = blk_pread(file, 0, buf, sizeof(buf));
     if (ret < 0) {
         error_setg_errno(errp, -ret, "Could not read image for determining its "
                          "format");
@@ -926,6 +925,95 @@ out:
     g_free(gen_node_name);
 }
 
+static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv,
+                            const char *node_name, QDict *options,
+                            int open_flags, Error **errp)
+{
+    Error *local_err = NULL;
+    int ret;
+
+    bdrv_assign_node_name(bs, node_name, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return -EINVAL;
+    }
+
+    bs->drv = drv;
+    bs->read_only = !(bs->open_flags & BDRV_O_RDWR);
+    bs->opaque = g_malloc0(drv->instance_size);
+
+    if (drv->bdrv_file_open) {
+        assert(!drv->bdrv_needs_filename || bs->filename[0]);
+        ret = drv->bdrv_file_open(bs, options, open_flags, &local_err);
+    } else if (drv->bdrv_open) {
+        ret = drv->bdrv_open(bs, options, open_flags, &local_err);
+    } else {
+        ret = 0;
+    }
+
+    if (ret < 0) {
+        if (local_err) {
+            error_propagate(errp, local_err);
+        } else if (bs->filename[0]) {
+            error_setg_errno(errp, -ret, "Could not open '%s'", bs->filename);
+        } else {
+            error_setg_errno(errp, -ret, "Could not open image");
+        }
+        goto free_and_fail;
+    }
+
+    ret = refresh_total_sectors(bs, bs->total_sectors);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Could not refresh total sector count");
+        goto free_and_fail;
+    }
+
+    bdrv_refresh_limits(bs, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto free_and_fail;
+    }
+
+    assert(bdrv_opt_mem_align(bs) != 0);
+    assert(bdrv_min_mem_align(bs) != 0);
+    assert(is_power_of_2(bs->bl.request_alignment));
+
+    return 0;
+
+free_and_fail:
+    /* FIXME Close bs first if already opened*/
+    g_free(bs->opaque);
+    bs->opaque = NULL;
+    bs->drv = NULL;
+    return ret;
+}
+
+BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name,
+                                       int flags, Error **errp)
+{
+    BlockDriverState *bs;
+    int ret;
+
+    bs = bdrv_new();
+    bs->open_flags = flags;
+    bs->explicit_options = qdict_new();
+    bs->options = qdict_new();
+    bs->opaque = NULL;
+
+    update_options_from_flags(bs->options, flags);
+
+    ret = bdrv_open_driver(bs, drv, node_name, bs->options, flags, errp);
+    if (ret < 0) {
+        QDECREF(bs->explicit_options);
+        QDECREF(bs->options);
+        bdrv_unref(bs);
+        return NULL;
+    }
+
+    return bs;
+}
+
 QemuOptsList bdrv_runtime_opts = {
     .name = "bdrv_common",
     .head = QTAILQ_HEAD_INITIALIZER(bdrv_runtime_opts.head),
@@ -974,7 +1062,7 @@ QemuOptsList bdrv_runtime_opts = {
  *
  * Removes all processed options from *options.
  */
-static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file,
+static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file,
                             QDict *options, Error **errp)
 {
     int ret, open_flags;
@@ -1005,7 +1093,7 @@ static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file,
     assert(drv != NULL);
 
     if (file != NULL) {
-        filename = file->bs->filename;
+        filename = blk_bs(file)->filename;
     } else {
         filename = qdict_get_try_str(options, "filename");
     }
@@ -1020,14 +1108,6 @@ static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file,
     trace_bdrv_open_common(bs, filename ?: "", bs->open_flags,
                            drv->format_name);
 
-    node_name = qemu_opt_get(opts, "node-name");
-    bdrv_assign_node_name(bs, node_name, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
-        goto fail_opts;
-    }
-
     bs->read_only = !(bs->open_flags & BDRV_O_RDWR);
 
     if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, bs->read_only)) {
@@ -1093,62 +1173,19 @@ static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file,
     }
     pstrcpy(bs->exact_filename, sizeof(bs->exact_filename), bs->filename);
 
-    bs->drv = drv;
-    bs->opaque = g_malloc0(drv->instance_size);
-
     /* Open the image, either directly or using a protocol */
     open_flags = bdrv_open_flags(bs, bs->open_flags);
-    if (drv->bdrv_file_open) {
+    node_name = qemu_opt_get(opts, "node-name");
-        assert(file == NULL);
-        assert(!drv->bdrv_needs_filename || filename != NULL);
-        ret = drv->bdrv_file_open(bs, options, open_flags, &local_err);
-    } else {
-        if (file == NULL) {
-            error_setg(errp, "Can't use '%s' as a block driver for the "
-                       "protocol level", drv->format_name);
-            ret = -EINVAL;
-            goto free_and_fail;
-        }
-        bs->file = file;
-        ret = drv->bdrv_open(bs, options, open_flags, &local_err);
-    }
 
+    assert(!drv->bdrv_file_open || file == NULL);
+    ret = bdrv_open_driver(bs, drv, node_name, options, open_flags, errp);
     if (ret < 0) {
-        if (local_err) {
+        goto fail_opts;
-            error_propagate(errp, local_err);
-        } else if (bs->filename[0]) {
-            error_setg_errno(errp, -ret, "Could not open '%s'", bs->filename);
-        } else {
-            error_setg_errno(errp, -ret, "Could not open image");
-        }
-        goto free_and_fail;
     }
 
-    ret = refresh_total_sectors(bs, bs->total_sectors);
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "Could not refresh total sector count");
-        goto free_and_fail;
-    }
-
-    bdrv_refresh_limits(bs, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
-        goto free_and_fail;
-    }
-
-    assert(bdrv_opt_mem_align(bs) != 0);
-    assert(bdrv_min_mem_align(bs) != 0);
-    assert(is_power_of_2(bs->bl.request_alignment));
-
     qemu_opts_del(opts);
     return 0;
 
-free_and_fail:
-    bs->file = NULL;
-    g_free(bs->opaque);
-    bs->opaque = NULL;
-    bs->drv = NULL;
 fail_opts:
     qemu_opts_del(opts);
     return ret;
@@ -1368,7 +1405,18 @@ void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child)
     }
 
     if (child->bs->inherits_from == parent) {
-        child->bs->inherits_from = NULL;
+        BdrvChild *c;
+
+        /* Remove inherits_from only when the last reference between parent and
+         * child->bs goes away. */
+        QLIST_FOREACH(c, &parent->children, next) {
+            if (c != child && c->bs == child->bs) {
+                break;
+            }
+        }
+        if (c == NULL) {
+            child->bs->inherits_from = NULL;
+        }
     }
 
     bdrv_root_unref_child(child);
@@ -1543,28 +1591,12 @@ free_exit:
     return ret;
 }
 
-/*
+static BlockDriverState *
- * Opens a disk image whose options are given as BlockdevRef in another block
+bdrv_open_child_bs(const char *filename, QDict *options, const char *bdref_key,
- * device's options.
+                   BlockDriverState *parent, const BdrvChildRole *child_role,
- *
+                   bool allow_none, Error **errp)
- * If allow_none is true, no image will be opened if filename is false and no
- * BlockdevRef is given. NULL will be returned, but errp remains unset.
- *
- * bdrev_key specifies the key for the image's BlockdevRef in the options QDict.
- * That QDict has to be flattened; therefore, if the BlockdevRef is a QDict
- * itself, all options starting with "${bdref_key}." are considered part of the
- * BlockdevRef.
- *
- * The BlockdevRef will be removed from the options QDict.
- */
-BdrvChild *bdrv_open_child(const char *filename,
-                           QDict *options, const char *bdref_key,
-                           BlockDriverState* parent,
-                           const BdrvChildRole *child_role,
-                           bool allow_none, Error **errp)
 {
-    BdrvChild *c = NULL;
+    BlockDriverState *bs = NULL;
-    BlockDriverState *bs;
     QDict *image_options;
     char *bdref_key_dot;
     const char *reference;
@@ -1591,11 +1623,40 @@ BdrvChild *bdrv_open_child(const char *filename,
         goto done;
     }
 
-    c = bdrv_attach_child(parent, bs, bdref_key, child_role);
-
 done:
     qdict_del(options, bdref_key);
-    return c;
+    return bs;
+}
+
+/*
+ * Opens a disk image whose options are given as BlockdevRef in another block
+ * device's options.
+ *
+ * If allow_none is true, no image will be opened if filename is false and no
+ * BlockdevRef is given. NULL will be returned, but errp remains unset.
+ *
+ * bdrev_key specifies the key for the image's BlockdevRef in the options QDict.
+ * That QDict has to be flattened; therefore, if the BlockdevRef is a QDict
+ * itself, all options starting with "${bdref_key}." are considered part of the
+ * BlockdevRef.
+ *
+ * The BlockdevRef will be removed from the options QDict.
+ */
+BdrvChild *bdrv_open_child(const char *filename,
+                           QDict *options, const char *bdref_key,
+                           BlockDriverState *parent,
+                           const BdrvChildRole *child_role,
+                           bool allow_none, Error **errp)
+{
+    BlockDriverState *bs;
+
+    bs = bdrv_open_child_bs(filename, options, bdref_key, parent, child_role,
+                            allow_none, errp);
+    if (bs == NULL) {
+        return NULL;
+    }
+
+    return bdrv_attach_child(parent, bs, bdref_key, child_role);
 }
 
 static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs,
@@ -1691,7 +1752,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
                                            Error **errp)
 {
     int ret;
-    BdrvChild *file = NULL;
+    BlockBackend *file = NULL;
     BlockDriverState *bs;
     BlockDriver *drv = NULL;
     const char *drvname;
@@ -1789,13 +1850,25 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
         qdict_del(options, "backing");
     }
 
-    /* Open image file without format layer */
+    /* Open image file without format layer. This BlockBackend is only used for
+     * probing, the block drivers will do their own bdrv_open_child() for the
+     * same BDS, which is why we put the node name back into options. */
     if ((flags & BDRV_O_PROTOCOL) == 0) {
-        file = bdrv_open_child(filename, options, "file", bs,
+        BlockDriverState *file_bs;
-                               &child_file, true, &local_err);
+
+        file_bs = bdrv_open_child_bs(filename, options, "file", bs,
+                                     &child_file, true, &local_err);
         if (local_err) {
             goto fail;
         }
+        if (file_bs != NULL) {
+            file = blk_new();
+            blk_insert_bs(file, file_bs);
+            bdrv_unref(file_bs);
+
+            qdict_put(options, "file",
+                      qstring_from_str(bdrv_get_node_name(file_bs)));
+        }
     }
 
     /* Image format probing */
@@ -1835,8 +1908,8 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
         goto fail;
     }
 
-    if (file && (bs->file != file)) {
+    if (file) {
-        bdrv_unref_child(bs, file);
+        blk_unref(file);
         file = NULL;
     }
 
@@ -1898,8 +1971,9 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
     return bs;
 
 fail:
-    if (file != NULL) {
+    blk_unref(file);
-        bdrv_unref_child(bs, file);
+    if (bs->file != NULL) {
+        bdrv_unref_child(bs, bs->file);
     }
     QDECREF(snapshot_options);
     QDECREF(bs->explicit_options);
@@ -2626,8 +2700,9 @@ exit:
 /**
  * Truncate file to 'offset' bytes (needed only for file protocols)
  */
-int bdrv_truncate(BlockDriverState *bs, int64_t offset)
+int bdrv_truncate(BdrvChild *child, int64_t offset)
 {
+    BlockDriverState *bs = child->bs;
     BlockDriver *drv = bs->drv;
     int ret;
     if (!drv)

block/blkdebug.c

@@ -663,7 +663,7 @@ static int64_t blkdebug_getlength(BlockDriverState *bs)
 
 static int blkdebug_truncate(BlockDriverState *bs, int64_t offset)
 {
-    return bdrv_truncate(bs->file->bs, offset);
+    return bdrv_truncate(bs->file, offset);
 }
 
 static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)

block/block-backend.c

@@ -1605,7 +1605,7 @@ int blk_truncate(BlockBackend *blk, int64_t offset)
         return -ENOMEDIUM;
     }
 
-    return bdrv_truncate(blk_bs(blk), offset);
+    return bdrv_truncate(blk->root, offset);
 }
 
 static void blk_pdiscard_entry(void *opaque)

block/bochs.c

@@ -104,6 +104,12 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
     struct bochs_header bochs;
     int ret;
 
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
     bs->read_only = true; /* no write support yet */
 
     ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs));

block/cloop.c

@@ -66,6 +66,12 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
     uint32_t offsets_size, max_compressed_block_size = 1, i;
     int ret;
 
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
     bs->read_only = true;
 
     /* read header */

block/crypto.c

@@ -300,6 +300,12 @@ static int block_crypto_open_generic(QCryptoBlockFormat format,
     QCryptoBlockOpenOptions *open_opts = NULL;
     unsigned int cflags = 0;
 
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
     opts = qemu_opts_create(opts_spec, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (local_err) {
@@ -383,7 +389,7 @@ static int block_crypto_truncate(BlockDriverState *bs, int64_t offset)
 
     offset += payload_offset;
 
-    return bdrv_truncate(bs->file->bs, offset);
+    return bdrv_truncate(bs->file, offset);
 }
 
 static void block_crypto_close(BlockDriverState *bs)

block/dmg.c

@@ -413,6 +413,12 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
     int64_t offset;
     int ret;
 
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
     block_module_load_one("dmg-bz2");
     bs->read_only = true;
 

block/file-posix.c

@@ -1591,18 +1591,17 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
 #endif
     }
 
-    if (ftruncate(fd, total_size) != 0) {
-        result = -errno;
-        error_setg_errno(errp, -result, "Could not resize file");
-        goto out_close;
-    }
-
     switch (prealloc) {
 #ifdef CONFIG_POSIX_FALLOCATE
     case PREALLOC_MODE_FALLOC:
-        /* posix_fallocate() doesn't set errno. */
+        /*
+         * Truncating before posix_fallocate() makes it about twice slower on
+         * file systems that do not support fallocate(), trying to check if a
+         * block is allocated before allocating it, so don't do that here.
+         */
         result = -posix_fallocate(fd, 0, total_size);
         if (result != 0) {
+            /* posix_fallocate() doesn't set errno. */
             error_setg_errno(errp, -result,
                              "Could not preallocate data for the new file");
         }
@@ -1610,6 +1609,17 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
 #endif
     case PREALLOC_MODE_FULL:
     {
+        /*
+         * Knowing the final size from the beginning could allow the file
+         * system driver to do less allocations and possibly avoid
+         * fragmentation of the file.
+         */
+        if (ftruncate(fd, total_size) != 0) {
+            result = -errno;
+            error_setg_errno(errp, -result, "Could not resize file");
+            goto out_close;
+        }
+
         int64_t num = 0, left = total_size;
         buf = g_malloc0(65536);
 
@@ -1636,6 +1646,10 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
         break;
     }
     case PREALLOC_MODE_OFF:
+        if (ftruncate(fd, total_size) != 0) {
+            result = -errno;
+            error_setg_errno(errp, -result, "Could not resize file");
+        }
         break;
     default:
         result = -EINVAL;

block/mirror.c

@@ -662,7 +662,28 @@ static void coroutine_fn mirror_run(void *opaque)
     if (s->bdev_length < 0) {
         ret = s->bdev_length;
         goto immediate_exit;
-    } else if (s->bdev_length == 0) {
+    }
+
+    /* Active commit must resize the base image if its size differs from the
+     * active layer. */
+    if (s->base == blk_bs(s->target)) {
+        int64_t base_length;
+
+        base_length = blk_getlength(s->target);
+        if (base_length < 0) {
+            ret = base_length;
+            goto immediate_exit;
+        }
+
+        if (s->bdev_length > base_length) {
+            ret = blk_truncate(s->target, s->bdev_length);
+            if (ret < 0) {
+                goto immediate_exit;
+            }
+        }
+    }
+
+    if (s->bdev_length == 0) {
         /* Report BLOCK_JOB_READY and wait for complete. */
         block_job_event_ready(&s->common);
         s->synced = true;
@@ -1063,9 +1084,7 @@ void commit_active_start(const char *job_id, BlockDriverState *bs,
                          BlockCompletionFunc *cb, void *opaque, Error **errp,
                          bool auto_complete)
 {
-    int64_t length, base_length;
     int orig_base_flags;
-    int ret;
     Error *local_err = NULL;
 
     orig_base_flags = bdrv_get_flags(base);
@@ -1074,31 +1093,6 @@ void commit_active_start(const char *job_id, BlockDriverState *bs,
         return;
     }
 
-    length = bdrv_getlength(bs);
-    if (length < 0) {
-        error_setg_errno(errp, -length,
-                         "Unable to determine length of %s", bs->filename);
-        goto error_restore_flags;
-    }
-
-    base_length = bdrv_getlength(base);
-    if (base_length < 0) {
-        error_setg_errno(errp, -base_length,
-                         "Unable to determine length of %s", base->filename);
-        goto error_restore_flags;
-    }
-
-    if (length > base_length) {
-        ret = bdrv_truncate(base, length);
-        if (ret < 0) {
-            error_setg_errno(errp, -ret,
-                            "Top image %s is larger than base image %s, and "
-                             "resize of base image failed",
-                             bs->filename, base->filename);
-            goto error_restore_flags;
-        }
-    }
-
     mirror_start_job(job_id, bs, creation_flags, base, NULL, speed, 0, 0,
                      MIRROR_LEAVE_BACKING_CHAIN,
                      on_error, on_error, true, cb, opaque, &local_err,

block/parallels.c

@@ -215,7 +215,7 @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num,
                                      s->data_end << BDRV_SECTOR_BITS,
                                      space << BDRV_SECTOR_BITS, 0);
         } else {
-            ret = bdrv_truncate(bs->file->bs,
+            ret = bdrv_truncate(bs->file,
                                 (s->data_end + space) << BDRV_SECTOR_BITS);
         }
         if (ret < 0) {
@@ -449,7 +449,7 @@ static int parallels_check(BlockDriverState *bs, BdrvCheckResult *res,
                 size - res->image_end_offset);
         res->leaks += count;
         if (fix & BDRV_FIX_LEAKS) {
-            ret = bdrv_truncate(bs->file->bs, res->image_end_offset);
+            ret = bdrv_truncate(bs->file, res->image_end_offset);
             if (ret < 0) {
                 res->check_errors++;
                 return ret;
@@ -581,6 +581,12 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
     Error *local_err = NULL;
     char *buf;
 
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
     ret = bdrv_pread(bs->file, 0, &ph, sizeof(ph));
     if (ret < 0) {
         goto fail;
@@ -681,7 +687,7 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail_options;
     }
     if (!bdrv_has_zero_init(bs->file->bs) ||
-            bdrv_truncate(bs->file->bs, bdrv_getlength(bs->file->bs)) != 0) {
+            bdrv_truncate(bs->file, bdrv_getlength(bs->file->bs)) != 0) {
         s->prealloc_mode = PRL_PREALLOC_MODE_FALLOCATE;
     }
 
@@ -724,7 +730,7 @@ static void parallels_close(BlockDriverState *bs)
     }
 
     if (bs->open_flags & BDRV_O_RDWR) {
-        bdrv_truncate(bs->file->bs, s->data_end << BDRV_SECTOR_BITS);
+        bdrv_truncate(bs->file, s->data_end << BDRV_SECTOR_BITS);
     }
 
     g_free(s->bat_dirty_bmap);

block/qcow.c

@@ -106,6 +106,12 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
     QCowHeader header;
     Error *local_err = NULL;
 
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
     ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
     if (ret < 0) {
         goto fail;
@@ -467,7 +473,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
                 /* round to cluster size */
                 cluster_offset = (cluster_offset + s->cluster_size - 1) &
                     ~(s->cluster_size - 1);
-                bdrv_truncate(bs->file->bs, cluster_offset + s->cluster_size);
+                bdrv_truncate(bs->file, cluster_offset + s->cluster_size);
                 /* if encrypted, we must initialize the cluster
                    content which won't be written */
                 if (bs->encrypted &&
@@ -909,7 +915,7 @@ static int qcow_make_empty(BlockDriverState *bs)
     if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, s->l1_table,
             l1_length) < 0)
         return -1;
-    ret = bdrv_truncate(bs->file->bs, s->l1_table_offset + l1_length);
+    ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length);
     if (ret < 0)
         return ret;
 

block/qcow2-refcount.c

@@ -1734,7 +1734,7 @@ static int check_refblocks(BlockDriverState *bs, BdrvCheckResult *res,
                     goto resize_fail;
                 }
 
-                ret = bdrv_truncate(bs->file->bs, offset + s->cluster_size);
+                ret = bdrv_truncate(bs->file, offset + s->cluster_size);
                 if (ret < 0) {
                     goto resize_fail;
                 }

block/qcow2.c

@@ -814,8 +814,8 @@ static int qcow2_update_options(BlockDriverState *bs, QDict *options,
     return ret;
 }
 
-static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
+static int qcow2_do_open(BlockDriverState *bs, QDict *options, int flags,
-                      Error **errp)
+                         Error **errp)
 {
     BDRVQcow2State *s = bs->opaque;
     unsigned int len, i;
@@ -1205,6 +1205,18 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     return ret;
 }
 
+static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
+                      Error **errp)
+{
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
+    return qcow2_do_open(bs, options, flags, errp);
+}
+
 static void qcow2_refresh_limits(BlockDriverState *bs, Error **errp)
 {
     BDRVQcow2State *s = bs->opaque;
@@ -1785,7 +1797,7 @@ static void qcow2_invalidate_cache(BlockDriverState *bs, Error **errp)
     options = qdict_clone_shallow(bs->options);
 
     flags &= ~BDRV_O_INACTIVE;
-    ret = qcow2_open(bs, options, flags, &local_err);
+    ret = qcow2_do_open(bs, options, flags, &local_err);
     QDECREF(options);
     if (local_err) {
         error_propagate(errp, local_err);
@@ -2570,7 +2582,7 @@ qcow2_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
         /* align end of file to a sector boundary to ease reading with
            sector based I/Os */
         cluster_offset = bdrv_getlength(bs->file->bs);
-        return bdrv_truncate(bs->file->bs, cluster_offset);
+        return bdrv_truncate(bs->file, cluster_offset);
     }
 
     buf = qemu_blockalign(bs, s->cluster_size);
@@ -2784,7 +2796,7 @@ static int make_completely_empty(BlockDriverState *bs)
         goto fail;
     }
 
-    ret = bdrv_truncate(bs->file->bs, (3 + l1_clusters) * s->cluster_size);
+    ret = bdrv_truncate(bs->file, (3 + l1_clusters) * s->cluster_size);
     if (ret < 0) {
         goto fail;
     }
@@ -3250,7 +3262,11 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
     }
 
     if (new_size) {
-        ret = bdrv_truncate(bs, new_size);
+        BlockBackend *blk = blk_new();
+        blk_insert_bs(blk, bs);
+        ret = blk_truncate(blk, new_size);
+        blk_unref(blk);
+
         if (ret < 0) {
             return ret;
         }

block/qed.c

@@ -415,8 +415,8 @@ static void bdrv_qed_drain(BlockDriverState *bs)
     }
 }
 
-static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
+static int bdrv_qed_do_open(BlockDriverState *bs, QDict *options, int flags,
-                         Error **errp)
+                            Error **errp)
 {
     BDRVQEDState *s = bs->opaque;
     QEDHeader le_header;
@@ -550,6 +550,18 @@ out:
     return ret;
 }
 
+static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
+                         Error **errp)
+{
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
+    return bdrv_qed_do_open(bs, options, flags, errp);
+}
+
 static void bdrv_qed_refresh_limits(BlockDriverState *bs, Error **errp)
 {
     BDRVQEDState *s = bs->opaque;
@@ -1629,7 +1641,7 @@ static void bdrv_qed_invalidate_cache(BlockDriverState *bs, Error **errp)
     bdrv_qed_close(bs);
 
     memset(s, 0, sizeof(BDRVQEDState));
-    ret = bdrv_qed_open(bs, NULL, bs->open_flags, &local_err);
+    ret = bdrv_qed_do_open(bs, NULL, bs->open_flags, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         error_prepend(errp, "Could not reopen qed layer: ");

block/raw-format.c

@@ -341,7 +341,7 @@ static int raw_truncate(BlockDriverState *bs, int64_t offset)
 
     s->size = offset;
     offset += s->offset;
-    return bdrv_truncate(bs->file->bs, offset);
+    return bdrv_truncate(bs->file, offset);
 }
 
 static int raw_media_changed(BlockDriverState *bs)
@@ -384,6 +384,12 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
     BDRVRawState *s = bs->opaque;
     int ret;
 
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
     bs->sg = bs->file->bs->sg;
     bs->supported_write_flags = BDRV_REQ_FUA &
         bs->file->bs->supported_write_flags;

block/replication.c

@@ -86,6 +86,12 @@ static int replication_open(BlockDriverState *bs, QDict *options,
     const char *mode;
     const char *top_id;
 
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
     ret = -EINVAL;
     opts = qemu_opts_create(&replication_runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);

block/vdi.c

@@ -363,6 +363,12 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
     int ret;
     Error *local_err = NULL;
 
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
     logout("\n");
 
     ret = bdrv_read(bs->file, 0, (uint8_t *)&header, 1);

block/vhdx-log.c

@@ -548,7 +548,7 @@ static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s,
             if (new_file_size % (1024*1024)) {
                 /* round up to nearest 1MB boundary */
                 new_file_size = ((new_file_size >> 20) + 1) << 20;
-                bdrv_truncate(bs->file->bs, new_file_size);
+                bdrv_truncate(bs->file, new_file_size);
             }
         }
         qemu_vfree(desc_entries);

block/vhdx.c

@@ -898,6 +898,12 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
     uint64_t signature;
     Error *local_err = NULL;
 
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
     s->bat = NULL;
     s->first_visible_write = true;
 
@@ -1165,7 +1171,7 @@ static int vhdx_allocate_block(BlockDriverState *bs, BDRVVHDXState *s,
     /* per the spec, the address for a block is in units of 1MB */
     *new_offset = ROUND_UP(*new_offset, 1024 * 1024);
 
-    return bdrv_truncate(bs->file->bs, *new_offset + s->block_size);
+    return bdrv_truncate(bs->file, *new_offset + s->block_size);
 }
 
 /*

block/vmdk.c

@@ -943,6 +943,12 @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags,
     uint32_t magic;
     Error *local_err = NULL;
 
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
     buf = vmdk_read_desc(bs->file, 0, errp);
     if (!buf) {
         return -EINVAL;

block/vpc.c

@@ -220,6 +220,12 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
     int disk_type = VHD_DYNAMIC;
     int ret;
 
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
     opts = qemu_opts_create(&vpc_runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (local_err) {

block/vvfat.c

@@ -2968,6 +2968,7 @@ static void write_target_close(BlockDriverState *bs) {
 
 static BlockDriver vvfat_write_target = {
     .format_name        = "vvfat_write_target",
+    .instance_size      = sizeof(void*),
     .bdrv_co_pwritev    = write_target_commit,
     .bdrv_close         = write_target_close,
 };
@@ -3036,14 +3037,13 @@ static int enable_write_target(BlockDriverState *bs, Error **errp)
     unlink(s->qcow_filename);
 #endif
 
-    backing = bdrv_new();
+    backing = bdrv_new_open_driver(&vvfat_write_target, NULL, BDRV_O_ALLOW_RDWR,
+                                   &error_abort);
+    *(void**) backing->opaque = s;
+
     bdrv_set_backing_hd(s->bs, backing);
     bdrv_unref(backing);
 
-    s->bs->backing->bs->drv = &vvfat_write_target;
-    s->bs->backing->bs->opaque = g_new(void *, 1);
-    *(void**)s->bs->backing->bs->opaque = s;
-
     return 0;
 
 err:

blockdev.c

@@ -2858,6 +2858,7 @@ void qmp_block_resize(bool has_device, const char *device,
                       int64_t size, Error **errp)
 {
     Error *local_err = NULL;
+    BlockBackend *blk = NULL;
     BlockDriverState *bs;
     AioContext *aio_context;
     int ret;
@@ -2888,10 +2889,13 @@ void qmp_block_resize(bool has_device, const char *device,
         goto out;
     }
 
+    blk = blk_new();
+    blk_insert_bs(blk, bs);
+
     /* complete all in-flight operations before resizing the device */
     bdrv_drain_all();
 
-    ret = bdrv_truncate(bs, size);
+    ret = blk_truncate(blk, size);
     switch (ret) {
     case 0:
         break;
@@ -2913,6 +2917,7 @@ void qmp_block_resize(bool has_device, const char *device,
     }
 
 out:
+    blk_unref(blk);
     aio_context_release(aio_context);
 }
 

include/block/block.h

@@ -215,6 +215,8 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
                            const char *bdref_key, Error **errp);
 BlockDriverState *bdrv_open(const char *filename, const char *reference,
                             QDict *options, int flags, Error **errp);
+BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name,
+                                       int flags, Error **errp);
 BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
                                     BlockDriverState *bs,
                                     QDict *options, int flags);
@@ -253,7 +255,7 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
     const char *backing_file);
 int bdrv_get_backing_file_depth(BlockDriverState *bs);
 void bdrv_refresh_filename(BlockDriverState *bs);
-int bdrv_truncate(BlockDriverState *bs, int64_t offset);
+int bdrv_truncate(BdrvChild *child, int64_t offset);
 int64_t bdrv_nb_sectors(BlockDriverState *bs);
 int64_t bdrv_getlength(BlockDriverState *bs);
 int64_t bdrv_get_allocated_file_size(BlockDriverState *bs);

tests/qemu-iotests/030

@@ -547,11 +547,14 @@ class TestEIO(TestErrors):
         while not completed:
             for event in self.vm.get_qmp_events(wait=True):
                 if event['event'] == 'BLOCK_JOB_ERROR':
+                    error = True
                     self.assert_qmp(event, 'data/device', 'drive0')
                     self.assert_qmp(event, 'data/operation', 'read')
                     result = self.vm.qmp('query-block-jobs')
+                    if result == {'return': []}:
+                        # Job finished too quickly
+                        continue
                     self.assert_qmp(result, 'return[0]/paused', False)
-                    error = True
                 elif event['event'] == 'BLOCK_JOB_COMPLETED':
                     self.assertTrue(error, 'job completed unexpectedly')
                     self.assert_qmp(event, 'data/type', 'stream')

tests/qemu-iotests/051.out

@@ -225,7 +225,7 @@ Testing: -drive driver=nbd
 QEMU_PROG: -drive driver=nbd: NBD server address missing
 
 Testing: -drive driver=raw
-QEMU_PROG: -drive driver=raw: Can't use 'raw' as a block driver for the protocol level
+QEMU_PROG: -drive driver=raw: A block device must be specified for "file"
 
 Testing: -drive file.driver=file
 QEMU_PROG: -drive file.driver=file: The 'file' block driver requires a file name
@@ -234,7 +234,7 @@ Testing: -drive file.driver=nbd
 QEMU_PROG: -drive file.driver=nbd: NBD server address missing
 
 Testing: -drive file.driver=raw
-QEMU_PROG: -drive file.driver=raw: Can't use 'raw' as a block driver for the protocol level
+QEMU_PROG: -drive file.driver=raw: A block device must be specified for "file"
 
 Testing: -drive foo=bar
 QEMU_PROG: -drive foo=bar: Must specify either driver or file

tests/qemu-iotests/051.pc.out

@@ -323,7 +323,7 @@ Testing: -drive driver=nbd
 QEMU_PROG: -drive driver=nbd: NBD server address missing
 
 Testing: -drive driver=raw
-QEMU_PROG: -drive driver=raw: Can't use 'raw' as a block driver for the protocol level
+QEMU_PROG: -drive driver=raw: A block device must be specified for "file"
 
 Testing: -drive file.driver=file
 QEMU_PROG: -drive file.driver=file: The 'file' block driver requires a file name
@@ -332,7 +332,7 @@ Testing: -drive file.driver=nbd
 QEMU_PROG: -drive file.driver=nbd: NBD server address missing
 
 Testing: -drive file.driver=raw
-QEMU_PROG: -drive file.driver=raw: Can't use 'raw' as a block driver for the protocol level
+QEMU_PROG: -drive file.driver=raw: A block device must be specified for "file"
 
 Testing: -drive foo=bar
 QEMU_PROG: -drive foo=bar: Must specify either driver or file

tests/qemu-iotests/137

@@ -39,7 +39,7 @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 . ./common.qemu
 
 _supported_fmt qcow2
-_supported_proto generic
+_supported_proto file
 _supported_os Linux
 
 

tests/qemu-iotests/175

@@ -0,0 +1,61 @@
+#!/bin/bash
+#
+# Test creating raw image preallocation mode
+#
+# Copyright (C) 2017 Nir Soffer <nirsof@gmail.com>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+
+# creator
+owner=nirsof@gmail.com
+
+seq=`basename $0`
+echo "QA output created by $seq"
+
+here=`pwd`
+status=1	# failure is the default!
+
+_cleanup()
+{
+	_cleanup_test_img
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+. ./common.rc
+. ./common.filter
+
+_supported_fmt raw
+_supported_proto file
+_supported_os Linux
+
+size=1m
+
+echo
+echo "== creating image with default preallocation =="
+_make_test_img $size | _filter_imgfmt
+stat -c "size=%s, blocks=%b" $TEST_IMG
+
+for mode in off full falloc; do
+    echo
+    echo "== creating image with preallocation $mode =="
+    IMGOPTS=preallocation=$mode _make_test_img $size | _filter_imgfmt
+    stat -c "size=%s, blocks=%b" $TEST_IMG
+done
+
+# success, all done
+echo "*** done"
+rm -f $seq.full
+status=0

tests/qemu-iotests/175.out

@@ -0,0 +1,18 @@
+QA output created by 175
+
+== creating image with default preallocation ==
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576
+size=1048576, blocks=0
+
+== creating image with preallocation off ==
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 preallocation=off
+size=1048576, blocks=0
+
+== creating image with preallocation full ==
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 preallocation=full
+size=1048576, blocks=2048
+
+== creating image with preallocation falloc ==
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 preallocation=falloc
+size=1048576, blocks=2048
+ *** done

tests/qemu-iotests/common.rc

@@ -172,7 +172,7 @@ _make_test_img()
 
     # Start an NBD server on the image file, which is what we'll be talking to
     if [ $IMGPROTO = "nbd" ]; then
-        eval "$QEMU_NBD -v -t -b 127.0.0.1 -p 10810 -f $IMGFMT  $TEST_IMG_FILE &"
+        eval "$QEMU_NBD -v -t -b 127.0.0.1 -p 10810 -f $IMGFMT  $TEST_IMG_FILE >/dev/null &"
         sleep 1 # FIXME: qemu-nbd needs to be listening before we continue
     fi
 }
@@ -379,6 +379,18 @@ _supported_proto()
     _notrun "not suitable for this image protocol: $IMGPROTO"
 }
 
+# tests whether $IMGPROTO is specified as an unsupported image protocol for a test
+#
+_unsupported_proto()
+{
+    for f; do
+        if [ "$f" = "$IMGPROTO" ]; then
+            _notrun "not suitable for this image protocol: $IMGPROTO"
+            return
+        fi
+    done
+}
+
 # tests whether the host OS is one of the supported OSes for a test
 #
 _supported_os()

tests/qemu-iotests/group

@@ -167,3 +167,4 @@
 172 auto
 173 rw auto
 174 auto
+175 auto quick

tests/test-blockjob-txn.c

@@ -96,7 +96,10 @@ static BlockJob *test_block_job_start(unsigned int iterations,
     char job_id[24];
 
     data = g_new0(TestBlockJobCBData, 1);
-    bs = bdrv_new();
+
+    bs = bdrv_open("null-co://", NULL, NULL, 0, &error_abort);
+    g_assert_nonnull(bs);
+
     snprintf(job_id, sizeof(job_id), "job%u", counter++);
     s = block_job_create(job_id, &test_block_job_driver, bs, 0,
                          BLOCK_JOB_DEFAULT, test_block_job_cb,
@@ -242,6 +245,7 @@ static void test_pair_jobs_fail_cancel_race(void)
 int main(int argc, char **argv)
 {
     qemu_init_main_loop(&error_abort);
+    bdrv_init();
 
     g_test_init(&argc, &argv, NULL);
     g_test_add_func("/single/success", test_single_job_success);

tests/test-blockjob.c

@@ -54,7 +54,10 @@ static BlockJob *do_test_id(BlockBackend *blk, const char *id,
 static BlockBackend *create_blk(const char *name)
 {
     BlockBackend *blk = blk_new();
-    BlockDriverState *bs = bdrv_new();
+    BlockDriverState *bs;
+
+    bs = bdrv_open("null-co://", NULL, NULL, 0, &error_abort);
+    g_assert_nonnull(bs);
 
     blk_insert_bs(blk, bs);
     bdrv_unref(bs);
@@ -140,6 +143,7 @@ static void test_job_ids(void)
 int main(int argc, char **argv)
 {
     qemu_init_main_loop(&error_abort);
+    bdrv_init();
 
     g_test_init(&argc, &argv, NULL);
     g_test_add_func("/blockjob/ids", test_job_ids);