Block layer core and image format patches

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQIcBAABAgAGBQJVevYFAAoJEH8JsnLIjy/W3jEP/0hiQ3rCRZ/he8s5maTdT+TR
 YSeHkB5rKpz0Uopn1DMn1QrIbUVzX7dyb+uf9zQ0/xRQIzf6k8uxqU/NWrdoF3NK
 qx91dGWedwnG+TEBIMbcR7nMrw4dP6kH7uPz/VWMXDHVLz0HIcD95qhKgs0mSY6J
 dWqex6ACjXM68zJU5IioagU9evV80WZE1S8z7zfixxtTBx5hCaTVbwalkaCxcrXw
 PbZle55rjI8B10+OzgBw0fq10nias+NTndU9CwNBboxmEtAjq8/mQ663vcWlmiFo
 9a/hkda27Z5ut/0Tqk1v4uLHauylp++rrAabPBAuCFMKes6cdkddP15Q/r52aJ29
 5meodQtbet1rGrM+Aq4vuSuWId71PGypEI/3URDdNfYFNISoeLLsk4lcQUu7VrDD
 sRX3Jt8SI3nkIgOnhPyi7NDPmafxFt8yRt5vM8MyR5ynF8NS/2hiAc3wqnbXGjUj
 a5GqDCefb1yM0R5HvksuFFt3OnXlKJQ3J+ksXNUJf9DSAZPauqWD696pcTeg8wyy
 3PIGkczgUuKTVfFWd3THZxJLAo7ZuqvXBHHV8o1SeMBDxwh4FhTd8Kjvm3rUNFfl
 VDox4qwZ1AcxLrxgqazKU7sD9iWBDHURRcpOoUsBys7oxQZnhcmMp1fRlEkTOyrD
 HNiSNByqBrtkfeVzHlSe
 =QgYk
 -----END PGP SIGNATURE-----

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

Block layer core and image format patches

# gpg: Signature made Fri Jun 12 16:08:53 2015 BST using RSA key ID C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"

* remotes/kevin/tags/for-upstream: (25 commits)
  block: Fix reopen flag inheritance
  block: Add BlockDriverState.inherits_from
  block: Add list of children to BlockDriverState
  queue.h: Add QLIST_FIX_HEAD_PTR()
  block: Drain requests before swapping nodes in bdrv_swap()
  block: Move flag inheritance to bdrv_open_inherit()
  block: Use QemuOpts in bdrv_open_common()
  block: Use macro for cache option names
  vmdk: Use bdrv_open_image()
  quorum: Use bdrv_open_image()
  check-qdict: Test cases for new functions
  qdict: Add qdict_{set,copy}_default()
  qdict: Add qdict_array_entries()
  iotests: Add tests for overriding BDRV_O_PROTOCOL
  block: driver should override flags in bdrv_open()
  block: Change bitmap truncate conditional to assertion
  block: record new size in bdrv_dirty_bitmap_truncate
  raw-posix: Fix .bdrv_co_get_block_status() for unaligned image size
  vmdk: Use vmdk_find_index_in_cluster everywhere
  vmdk: Fix index_in_cluster calculation in vmdk_co_get_block_status
  ...

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

block.c

@@ -80,6 +80,12 @@ static QTAILQ_HEAD(, BlockDriverState) graph_bdrv_states =
 static QLIST_HEAD(, BlockDriver) bdrv_drivers =
     QLIST_HEAD_INITIALIZER(bdrv_drivers);
 
+static int bdrv_open_inherit(BlockDriverState **pbs, const char *filename,
+                             const char *reference, QDict *options, int flags,
+                             BlockDriverState *parent,
+                             const BdrvChildRole *child_role,
+                             BlockDriver *drv, Error **errp);
+
 static void bdrv_dirty_bitmap_truncate(BlockDriverState *bs);
 /* If non-zero, use only whitelisted block drivers */
 static int use_bdrv_whitelist;
@@ -683,8 +689,8 @@ static int bdrv_temp_snapshot_flags(int flags)
 }
 
 /*
- * Returns the flags that bs->file should get, based on the given flags for
+ * Returns the flags that bs->file should get if a protocol driver is expected,
- * the parent BDS
+ * based on the given flags for the parent BDS
  */
 static int bdrv_inherited_flags(int flags)
 {
@@ -701,6 +707,25 @@ static int bdrv_inherited_flags(int flags)
     return flags;
 }
 
+const BdrvChildRole child_file = {
+    .inherit_flags = bdrv_inherited_flags,
+};
+
+/*
+ * Returns the flags that bs->file should get if the use of formats (and not
+ * only protocols) is permitted for it, based on the given flags for the parent
+ * BDS
+ */
+static int bdrv_inherited_fmt_flags(int parent_flags)
+{
+    int flags = child_file.inherit_flags(parent_flags);
+    return flags & ~BDRV_O_PROTOCOL;
+}
+
+const BdrvChildRole child_format = {
+    .inherit_flags = bdrv_inherited_fmt_flags,
+};
+
 /*
  * Returns the flags that bs->backing_hd should get, based on the given flags
  * for the parent BDS
@@ -716,6 +741,10 @@ static int bdrv_backing_flags(int flags)
     return flags;
 }
 
+static const BdrvChildRole child_backing = {
+    .inherit_flags = bdrv_backing_flags,
+};
+
 static int bdrv_open_flags(BlockDriverState *bs, int flags)
 {
     int open_flags = flags | BDRV_O_CACHE_WB;
@@ -768,6 +797,19 @@ static void bdrv_assign_node_name(BlockDriverState *bs,
     QTAILQ_INSERT_TAIL(&graph_bdrv_states, bs, node_list);
 }
 
+static QemuOptsList bdrv_runtime_opts = {
+    .name = "bdrv_common",
+    .head = QTAILQ_HEAD_INITIALIZER(bdrv_runtime_opts.head),
+    .desc = {
+        {
+            .name = "node-name",
+            .type = QEMU_OPT_STRING,
+            .help = "Node name of the block device node",
+        },
+        { /* end of list */ }
+    },
+};
+
 /*
  * Common part for opening disk images and files
  *
@@ -779,6 +821,7 @@ static int bdrv_open_common(BlockDriverState *bs, BlockDriverState *file,
     int ret, open_flags;
     const char *filename;
     const char *node_name = NULL;
+    QemuOpts *opts;
     Error *local_err = NULL;
 
     assert(drv != NULL);
@@ -799,23 +842,22 @@ static int bdrv_open_common(BlockDriverState *bs, BlockDriverState *file,
 
     trace_bdrv_open_common(bs, filename ?: "", flags, drv->format_name);
 
-    node_name = qdict_get_try_str(options, "node-name");
+    opts = qemu_opts_create(&bdrv_runtime_opts, NULL, 0, &error_abort);
+    qemu_opts_absorb_qdict(opts, options, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto fail_opts;
+    }
+
+    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);
-        return -EINVAL;
+        ret = -EINVAL;
-    }
+        goto fail_opts;
-    qdict_del(options, "node-name");
-
-    /* bdrv_open() with directly using a protocol as drv. This layer is already
-     * opened, so assign it to bs (while file becomes a closed BlockDriverState)
-     * and return immediately. */
-    if (file != NULL && drv->bdrv_file_open) {
-        bdrv_swap(file, bs);
-        return 0;
     }
 
-    bs->open_flags = flags;
     bs->guest_block_size = 512;
     bs->request_alignment = 512;
     bs->zero_beyond_eof = true;
@@ -828,7 +870,8 @@ static int bdrv_open_common(BlockDriverState *bs, BlockDriverState *file,
                         ? "Driver '%s' can only be used for read-only devices"
                         : "Driver '%s' is not whitelisted",
                    drv->format_name);
-        return -ENOTSUP;
+        ret = -ENOTSUP;
+        goto fail_opts;
     }
 
     assert(bs->copy_on_read == 0); /* bdrv_new() and bdrv_close() make it so */
@@ -837,7 +880,8 @@ static int bdrv_open_common(BlockDriverState *bs, BlockDriverState *file,
             bdrv_enable_copy_on_read(bs);
         } else {
             error_setg(errp, "Can't use copy-on-read on read-only device");
-            return -EINVAL;
+            ret = -EINVAL;
+            goto fail_opts;
         }
     }
 
@@ -903,6 +947,8 @@ static int bdrv_open_common(BlockDriverState *bs, BlockDriverState *file,
     assert(bdrv_opt_mem_align(bs) != 0);
     assert(bdrv_min_mem_align(bs) != 0);
     assert((bs->request_alignment != 0) || bs->sg);
+
+    qemu_opts_del(opts);
     return 0;
 
 free_and_fail:
@@ -910,6 +956,8 @@ free_and_fail:
     g_free(bs->opaque);
     bs->opaque = NULL;
     bs->drv = NULL;
+fail_opts:
+    qemu_opts_del(opts);
     return ret;
 }
 
@@ -943,14 +991,17 @@ static QDict *parse_json_filename(const char *filename, Error **errp)
 /*
  * Fills in default options for opening images and converts the legacy
  * filename/flags pair to option QDict entries.
+ * The BDRV_O_PROTOCOL flag in *flags will be set or cleared accordingly if a
+ * block driver has been specified explicitly.
  */
-static int bdrv_fill_options(QDict **options, const char **pfilename, int flags,
+static int bdrv_fill_options(QDict **options, const char **pfilename,
-                             BlockDriver *drv, Error **errp)
+                             int *flags, BlockDriver *drv, Error **errp)
 {
     const char *filename = *pfilename;
     const char *drvname;
-    bool protocol = flags & BDRV_O_PROTOCOL;
+    bool protocol = *flags & BDRV_O_PROTOCOL;
     bool parse_filename = false;
+    BlockDriver *tmp_drv;
     Error *local_err = NULL;
 
     /* Parse json: pseudo-protocol */
@@ -968,6 +1019,24 @@ static int bdrv_fill_options(QDict **options, const char **pfilename, int flags,
         *pfilename = filename = NULL;
     }
 
+    drvname = qdict_get_try_str(*options, "driver");
+
+    /* If the user has explicitly specified the driver, this choice should
+     * override the BDRV_O_PROTOCOL flag */
+    tmp_drv = drv;
+    if (!tmp_drv && drvname) {
+        tmp_drv = bdrv_find_format(drvname);
+    }
+    if (tmp_drv) {
+        protocol = tmp_drv->bdrv_file_open;
+    }
+
+    if (protocol) {
+        *flags |= BDRV_O_PROTOCOL;
+    } else {
+        *flags &= ~BDRV_O_PROTOCOL;
+    }
+
     /* Fetch the file name from the options QDict if necessary */
     if (protocol && filename) {
         if (!qdict_haskey(*options, "filename")) {
@@ -982,7 +1051,6 @@ static int bdrv_fill_options(QDict **options, const char **pfilename, int flags,
 
     /* Find the right block driver */
     filename = qdict_get_try_str(*options, "filename");
-    drvname = qdict_get_try_str(*options, "driver");
 
     if (drv) {
         if (drvname) {
@@ -1119,9 +1187,10 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
     }
 
     assert(bs->backing_hd == NULL);
-    ret = bdrv_open(&backing_hd,
+    ret = bdrv_open_inherit(&backing_hd,
-                    *backing_filename ? backing_filename : NULL, NULL, options,
+                            *backing_filename ? backing_filename : NULL,
-                    bdrv_backing_flags(bs->open_flags), NULL, &local_err);
+                            NULL, options, 0, bs, &child_backing,
+                            NULL, &local_err);
     if (ret < 0) {
         bdrv_unref(backing_hd);
         backing_hd = NULL;
@@ -1155,7 +1224,8 @@ free_exit:
  * To conform with the behavior of bdrv_open(), *pbs has to be NULL.
  */
 int bdrv_open_image(BlockDriverState **pbs, const char *filename,
-                    QDict *options, const char *bdref_key, int flags,
+                    QDict *options, const char *bdref_key,
+                    BlockDriverState* parent, const BdrvChildRole *child_role,
                     bool allow_none, Error **errp)
 {
     QDict *image_options;
@@ -1183,7 +1253,8 @@ int bdrv_open_image(BlockDriverState **pbs, const char *filename,
         goto done;
     }
 
-    ret = bdrv_open(pbs, filename, reference, image_options, flags, NULL, errp);
+    ret = bdrv_open_inherit(pbs, filename, reference, image_options, 0,
+                            parent, child_role, NULL, errp);
 
 done:
     qdict_del(options, bdref_key);
@@ -1255,6 +1326,19 @@ out:
     return ret;
 }
 
+static void bdrv_attach_child(BlockDriverState *parent_bs,
+                              BlockDriverState *child_bs,
+                              const BdrvChildRole *child_role)
+{
+    BdrvChild *child = g_new(BdrvChild, 1);
+    *child = (BdrvChild) {
+        .bs     = child_bs,
+        .role   = child_role,
+    };
+
+    QLIST_INSERT_HEAD(&parent_bs->children, child, next);
+}
+
 /*
  * Opens a disk image (raw, qcow2, vmdk, ...)
  *
@@ -1270,9 +1354,11 @@ out:
  * should be opened. If specified, neither options nor a filename may be given,
  * nor can an existing BDS be reused (that is, *pbs has to be NULL).
  */
-int bdrv_open(BlockDriverState **pbs, const char *filename,
+static int bdrv_open_inherit(BlockDriverState **pbs, const char *filename,
-              const char *reference, QDict *options, int flags,
+                             const char *reference, QDict *options, int flags,
-              BlockDriver *drv, Error **errp)
+                             BlockDriverState *parent,
+                             const BdrvChildRole *child_role,
+                             BlockDriver *drv, Error **errp)
 {
     int ret;
     BlockDriverState *file = NULL, *bs;
@@ -1281,6 +1367,8 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
     int snapshot_flags = 0;
 
     assert(pbs);
+    assert(!child_role || !flags);
+    assert(!child_role == !parent);
 
     if (reference) {
         bool options_non_empty = options ? qdict_size(options) : false;
@@ -1303,6 +1391,9 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
             return -ENODEV;
         }
         bdrv_ref(bs);
+        if (child_role) {
+            bdrv_attach_child(parent, bs, child_role);
+        }
         *pbs = bs;
         return 0;
     }
@@ -1318,7 +1409,12 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
         options = qdict_new();
     }
 
-    ret = bdrv_fill_options(&options, &filename, flags, drv, &local_err);
+    if (child_role) {
+        bs->inherits_from = parent;
+        flags = child_role->inherit_flags(parent->open_flags);
+    }
+
+    ret = bdrv_fill_options(&options, &filename, &flags, drv, &local_err);
     if (local_err) {
         goto fail;
     }
@@ -1337,12 +1433,8 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
     }
 
     assert(drvname || !(flags & BDRV_O_PROTOCOL));
-    if (drv && !drv->bdrv_file_open) {
-        /* If the user explicitly wants a format driver here, we'll need to add
-         * another layer for the protocol in bs->file */
-        flags &= ~BDRV_O_PROTOCOL;
-    }
 
+    bs->open_flags = flags;
     bs->options = options;
     options = qdict_clone_shallow(options);
 
@@ -1357,9 +1449,9 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
         }
 
         assert(file == NULL);
+        bs->open_flags = flags;
         ret = bdrv_open_image(&file, filename, options, "file",
-                              bdrv_inherited_flags(flags),
+                              bs, &child_file, true, &local_err);
-                              true, &local_err);
         if (ret < 0) {
             goto fail;
         }
@@ -1378,6 +1470,12 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
         goto fail;
     }
 
+    /* BDRV_O_PROTOCOL must be set iff a protocol BDS is about to be created */
+    assert(!!(flags & BDRV_O_PROTOCOL) == !!drv->bdrv_file_open);
+    /* file must be NULL if a protocol BDS is about to be created
+     * (the inverse results in an error message from bdrv_open_common()) */
+    assert(!(flags & BDRV_O_PROTOCOL) || !file);
+
     /* Open the image */
     ret = bdrv_open_common(bs, file, options, flags, drv, &local_err);
     if (ret < 0) {
@@ -1440,6 +1538,10 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
         goto close_and_fail;
     }
 
+    if (child_role) {
+        bdrv_attach_child(parent, bs, child_role);
+    }
+
     QDECREF(options);
     *pbs = bs;
     return 0;
@@ -1476,6 +1578,14 @@ close_and_fail:
     return ret;
 }
 
+int bdrv_open(BlockDriverState **pbs, const char *filename,
+              const char *reference, QDict *options, int flags,
+              BlockDriver *drv, Error **errp)
+{
+    return bdrv_open_inherit(pbs, filename, reference, options, flags, NULL,
+                             NULL, drv, errp);
+}
+
 typedef struct BlockReopenQueueEntry {
      bool prepared;
      BDRVReopenState state;
@@ -1506,6 +1616,8 @@ BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
     assert(bs != NULL);
 
     BlockReopenQueueEntry *bs_entry;
+    BdrvChild *child;
+
     if (bs_queue == NULL) {
         bs_queue = g_new0(BlockReopenQueue, 1);
         QSIMPLEQ_INIT(bs_queue);
@@ -1514,8 +1626,15 @@ BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
     /* bdrv_open() masks this flag out */
     flags &= ~BDRV_O_PROTOCOL;
 
-    if (bs->file) {
+    QLIST_FOREACH(child, &bs->children, next) {
-        bdrv_reopen_queue(bs_queue, bs->file, bdrv_inherited_flags(flags));
+        int child_flags;
+
+        if (child->bs->inherits_from != bs) {
+            continue;
+        }
+
+        child_flags = child->role->inherit_flags(flags);
+        bdrv_reopen_queue(bs_queue, child->bs, child_flags);
     }
 
     bs_entry = g_new0(BlockReopenQueueEntry, 1);
@@ -1726,6 +1845,16 @@ void bdrv_close(BlockDriverState *bs)
     notifier_list_notify(&bs->close_notifiers, bs);
 
     if (bs->drv) {
+        BdrvChild *child, *next;
+
+        QLIST_FOREACH_SAFE(child, &bs->children, next, next) {
+            if (child->bs->inherits_from == bs) {
+                child->bs->inherits_from = NULL;
+            }
+            QLIST_REMOVE(child, next);
+            g_free(child);
+        }
+
         if (bs->backing_hd) {
             BlockDriverState *backing_hd = bs->backing_hd;
             bdrv_set_backing_hd(bs, NULL);
@@ -1876,6 +2005,10 @@ static void bdrv_move_feature_fields(BlockDriverState *bs_dest,
 void bdrv_swap(BlockDriverState *bs_new, BlockDriverState *bs_old)
 {
     BlockDriverState tmp;
+    BdrvChild *child;
+
+    bdrv_drain(bs_new);
+    bdrv_drain(bs_old);
 
     /* The code needs to swap the node_name but simply swapping node_list won't
      * work so first remove the nodes from the graph list, do the swap then
@@ -1935,6 +2068,30 @@ void bdrv_swap(BlockDriverState *bs_new, BlockDriverState *bs_old)
         QTAILQ_INSERT_TAIL(&graph_bdrv_states, bs_old, node_list);
     }
 
+    /*
+     * Update lh_first.le_prev for non-empty lists.
+     *
+     * The head of the op blocker list doesn't change because it is moved back
+     * in bdrv_move_feature_fields().
+     */
+    assert(QLIST_EMPTY(&bs_old->tracked_requests));
+    assert(QLIST_EMPTY(&bs_new->tracked_requests));
+
+    QLIST_FIX_HEAD_PTR(&bs_new->children, next);
+    QLIST_FIX_HEAD_PTR(&bs_old->children, next);
+
+    /* Update references in bs->opaque and children */
+    QLIST_FOREACH(child, &bs_old->children, next) {
+        if (child->bs->inherits_from == bs_new) {
+            child->bs->inherits_from = bs_old;
+        }
+    }
+    QLIST_FOREACH(child, &bs_new->children, next) {
+        if (child->bs->inherits_from == bs_old) {
+            child->bs->inherits_from = bs_new;
+        }
+    }
+
     bdrv_rebind(bs_new);
     bdrv_rebind(bs_old);
 }
@@ -1957,6 +2114,7 @@ void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top)
     /* The contents of 'tmp' will become bs_top, as we are
      * swapping bs_new and bs_top contents. */
     bdrv_set_backing_hd(bs_top, bs_new);
+    bdrv_attach_child(bs_top, bs_new, &child_backing);
 }
 
 static void bdrv_delete(BlockDriverState *bs)
@@ -3242,10 +3400,9 @@ static void bdrv_dirty_bitmap_truncate(BlockDriverState *bs)
     uint64_t size = bdrv_nb_sectors(bs);
 
     QLIST_FOREACH(bitmap, &bs->dirty_bitmaps, list) {
-        if (bdrv_dirty_bitmap_frozen(bitmap)) {
+        assert(!bdrv_dirty_bitmap_frozen(bitmap));
-            continue;
-        }
         hbitmap_truncate(bitmap->bitmap, size);
+        bitmap->size = size;
     }
 }
 

block/blkdebug.c

@@ -429,7 +429,7 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
     /* Open the backing file */
     assert(bs->file == NULL);
     ret = bdrv_open_image(&bs->file, qemu_opt_get(opts, "x-image"), options, "image",
-                          flags | BDRV_O_PROTOCOL, false, &local_err);
+                          bs, &child_file, false, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         goto out;

block/blkverify.c

@@ -125,7 +125,7 @@ static int blkverify_open(BlockDriverState *bs, QDict *options, int flags,
     /* Open the raw file */
     assert(bs->file == NULL);
     ret = bdrv_open_image(&bs->file, qemu_opt_get(opts, "x-raw"), options,
-                          "raw", flags | BDRV_O_PROTOCOL, false, &local_err);
+                          "raw", bs, &child_file, false, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         goto fail;
@@ -134,7 +134,7 @@ static int blkverify_open(BlockDriverState *bs, QDict *options, int flags,
     /* Open the test file */
     assert(s->test_file == NULL);
     ret = bdrv_open_image(&s->test_file, qemu_opt_get(opts, "x-image"), options,
-                          "test", flags, false, &local_err);
+                          "test", bs, &child_format, false, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         s->test_file = NULL;

block/qcow2.c

@@ -483,9 +483,11 @@ static const char *overlap_bool_option_names[QCOW2_OL_MAX_BITNR] = {
     [QCOW2_OL_INACTIVE_L2_BITNR]    = QCOW2_OPT_OVERLAP_INACTIVE_L2,
 };
 
-static void read_cache_sizes(QemuOpts *opts, uint64_t *l2_cache_size,
+static void read_cache_sizes(BlockDriverState *bs, QemuOpts *opts,
+                             uint64_t *l2_cache_size,
                              uint64_t *refcount_cache_size, Error **errp)
 {
+    BDRVQcowState *s = bs->opaque;
     uint64_t combined_cache_size;
     bool l2_cache_size_set, refcount_cache_size_set, combined_cache_size_set;
 
@@ -525,7 +527,9 @@ static void read_cache_sizes(QemuOpts *opts, uint64_t *l2_cache_size,
         }
     } else {
         if (!l2_cache_size_set && !refcount_cache_size_set) {
-            *l2_cache_size = DEFAULT_L2_CACHE_BYTE_SIZE;
+            *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) {
@@ -803,7 +807,8 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    read_cache_sizes(opts, &l2_cache_size, &refcount_cache_size, &local_err);
+    read_cache_sizes(bs, opts, &l2_cache_size, &refcount_cache_size,
+                     &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         ret = -EINVAL;

block/qcow2.h

@@ -62,11 +62,14 @@
 #define MIN_CLUSTER_BITS 9
 #define MAX_CLUSTER_BITS 21
 
-#define MIN_L2_CACHE_SIZE 1 /* cluster */
+/* Must be at least 2 to cover COW */
+#define MIN_L2_CACHE_SIZE 2 /* clusters */
 
 /* Must be at least 4 to cover all cases of refcount table growth */
 #define MIN_REFCOUNT_CACHE_SIZE 4 /* clusters */
 
+/* Whichever is more */
+#define DEFAULT_L2_CACHE_CLUSTERS 8 /* clusters */
 #define DEFAULT_L2_CACHE_BYTE_SIZE 1048576 /* bytes */
 
 /* The refblock cache needs only a fourth of the L2 cache size to cover as many

block/quorum.c

@@ -866,25 +866,18 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
     Error *local_err = NULL;
     QemuOpts *opts = NULL;
     bool *opened;
-    QDict *sub = NULL;
-    QList *list = NULL;
-    const QListEntry *lentry;
     int i;
     int ret = 0;
 
     qdict_flatten(options);
-    qdict_extract_subqdict(options, &sub, "children.");
-    qdict_array_split(sub, &list);
 
-    if (qdict_size(sub)) {
+    /* count how many different children are present */
-        error_setg(&local_err, "Invalid option children.%s",
+    s->num_children = qdict_array_entries(options, "children.");
-                   qdict_first(sub)->key);
+    if (s->num_children < 0) {
+        error_setg(&local_err, "Option children is not a valid array");
         ret = -EINVAL;
         goto exit;
     }
-
-    /* count how many different children are present */
-    s->num_children = qlist_size(list);
     if (s->num_children < 2) {
         error_setg(&local_err,
                    "Number of provided children must be greater than 1");
@@ -937,37 +930,17 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
     s->bs = g_new0(BlockDriverState *, s->num_children);
     opened = g_new0(bool, s->num_children);
 
-    for (i = 0, lentry = qlist_first(list); lentry;
+    for (i = 0; i < s->num_children; i++) {
-         lentry = qlist_next(lentry), i++) {
+        char indexstr[32];
-        QDict *d;
+        ret = snprintf(indexstr, 32, "children.%d", i);
-        QString *string;
+        assert(ret < 32);
-
-        switch (qobject_type(lentry->value))
-        {
-            /* List of options */
-            case QTYPE_QDICT:
-                d = qobject_to_qdict(lentry->value);
-                QINCREF(d);
-                ret = bdrv_open(&s->bs[i], NULL, NULL, d, flags, NULL,
-                                &local_err);
-                break;
-
-            /* QMP reference */
-            case QTYPE_QSTRING:
-                string = qobject_to_qstring(lentry->value);
-                ret = bdrv_open(&s->bs[i], NULL, qstring_get_str(string), NULL,
-                                flags, NULL, &local_err);
-                break;
-
-            default:
-                error_setg(&local_err, "Specification of child block device %i "
-                           "is invalid", i);
-                ret = -EINVAL;
-        }
 
+        ret = bdrv_open_image(&s->bs[i], NULL, options, indexstr, bs,
+                              &child_format, false, &local_err);
         if (ret < 0) {
             goto close_exit;
         }
+
         opened[i] = true;
     }
 
@@ -990,8 +963,6 @@ exit:
     if (local_err) {
         error_propagate(errp, local_err);
     }
-    QDECREF(list);
-    QDECREF(sub);
     return ret;
 }
 

block/vmdk.c

@@ -321,37 +321,13 @@ static int vmdk_is_cid_valid(BlockDriverState *bs)
     return 1;
 }
 
-/* Queue extents, if any, for reopen() */
+/* We have nothing to do for VMDK reopen, stubs just return success */
 static int vmdk_reopen_prepare(BDRVReopenState *state,
                                BlockReopenQueue *queue, Error **errp)
 {
-    BDRVVmdkState *s;
-    int ret = -1;
-    int i;
-    VmdkExtent *e;
-
     assert(state != NULL);
     assert(state->bs != NULL);
-
+    return 0;
-    if (queue == NULL) {
-        error_setg(errp, "No reopen queue for VMDK extents");
-        goto exit;
-    }
-
-    s = state->bs->opaque;
-
-    assert(s != NULL);
-
-    for (i = 0; i < s->num_extents; i++) {
-        e = &s->extents[i];
-        if (e->file != state->bs->file) {
-            bdrv_reopen_queue(queue, e->file, state->flags);
-        }
-    }
-    ret = 0;
-
-exit:
-    return ret;
 }
 
 static int vmdk_parent_open(BlockDriverState *bs)
@@ -543,7 +519,7 @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs,
 }
 
 static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
-                               Error **errp);
+                               QDict *options, Error **errp);
 
 static char *vmdk_read_desc(BlockDriverState *file, uint64_t desc_offset,
                             Error **errp)
@@ -582,7 +558,7 @@ static char *vmdk_read_desc(BlockDriverState *file, uint64_t desc_offset,
 
 static int vmdk_open_vmdk4(BlockDriverState *bs,
                            BlockDriverState *file,
-                           int flags, Error **errp)
+                           int flags, QDict *options, Error **errp)
 {
     int ret;
     uint32_t magic;
@@ -606,7 +582,7 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
             if (!buf) {
                 return -EINVAL;
             }
-            ret = vmdk_open_desc_file(bs, flags, buf, errp);
+            ret = vmdk_open_desc_file(bs, flags, buf, options, errp);
             g_free(buf);
             return ret;
         }
@@ -763,7 +739,7 @@ static int vmdk_parse_description(const char *desc, const char *opt_name,
 /* Open an extent file and append to bs array */
 static int vmdk_open_sparse(BlockDriverState *bs,
                             BlockDriverState *file, int flags,
-                            char *buf, Error **errp)
+                            char *buf, QDict *options, Error **errp)
 {
     uint32_t magic;
 
@@ -773,7 +749,7 @@ static int vmdk_open_sparse(BlockDriverState *bs,
             return vmdk_open_vmfs_sparse(bs, file, flags, errp);
             break;
         case VMDK4_MAGIC:
-            return vmdk_open_vmdk4(bs, file, flags, errp);
+            return vmdk_open_vmdk4(bs, file, flags, options, errp);
             break;
         default:
             error_setg(errp, "Image not in VMDK format");
@@ -783,7 +759,8 @@ static int vmdk_open_sparse(BlockDriverState *bs,
 }
 
 static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
-                              const char *desc_file_path, Error **errp)
+                              const char *desc_file_path, QDict *options,
+                              Error **errp)
 {
     int ret;
     int matches;
@@ -797,6 +774,7 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
     BlockDriverState *extent_file;
     BDRVVmdkState *s = bs->opaque;
     VmdkExtent *extent;
+    char extent_opt_prefix[32];
 
     while (*p) {
         /* parse extent line in one of below formats:
@@ -846,8 +824,12 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
         extent_path = g_malloc0(PATH_MAX);
         path_combine(extent_path, PATH_MAX, desc_file_path, fname);
         extent_file = NULL;
-        ret = bdrv_open(&extent_file, extent_path, NULL, NULL,
+
-                        bs->open_flags | BDRV_O_PROTOCOL, NULL, errp);
+        ret = snprintf(extent_opt_prefix, 32, "extents.%d", s->num_extents);
+        assert(ret < 32);
+
+        ret = bdrv_open_image(&extent_file, extent_path, options,
+                              extent_opt_prefix, bs, &child_file, false, errp);
         g_free(extent_path);
         if (ret) {
             return ret;
@@ -870,7 +852,8 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
             if (!buf) {
                 ret = -EINVAL;
             } else {
-                ret = vmdk_open_sparse(bs, extent_file, bs->open_flags, buf, errp);
+                ret = vmdk_open_sparse(bs, extent_file, bs->open_flags, buf,
+                                       options, errp);
             }
             g_free(buf);
             if (ret) {
@@ -898,7 +881,7 @@ next_line:
 }
 
 static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
-                               Error **errp)
+                               QDict *options, Error **errp)
 {
     int ret;
     char ct[128];
@@ -920,7 +903,7 @@ static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
     }
     s->create_type = g_strdup(ct);
     s->desc_offset = 0;
-    ret = vmdk_parse_extents(buf, bs, bs->file->exact_filename, errp);
+    ret = vmdk_parse_extents(buf, bs, bs->file->exact_filename, options, errp);
 exit:
     return ret;
 }
@@ -942,11 +925,11 @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags,
     switch (magic) {
         case VMDK3_MAGIC:
         case VMDK4_MAGIC:
-            ret = vmdk_open_sparse(bs, bs->file, flags, buf, errp);
+            ret = vmdk_open_sparse(bs, bs->file, flags, buf, options, errp);
             s->desc_offset = 0x200;
             break;
         default:
-            ret = vmdk_open_desc_file(bs, flags, buf, errp);
+            ret = vmdk_open_desc_file(bs, flags, buf, options, errp);
             break;
     }
     if (ret) {
@@ -1248,6 +1231,17 @@ static VmdkExtent *find_extent(BDRVVmdkState *s,
     return NULL;
 }
 
+static inline uint64_t vmdk_find_index_in_cluster(VmdkExtent *extent,
+                                                  int64_t sector_num)
+{
+    uint64_t index_in_cluster, extent_begin_sector, extent_relative_sector_num;
+
+    extent_begin_sector = extent->end_sector - extent->sectors;
+    extent_relative_sector_num = sector_num - extent_begin_sector;
+    index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
+    return index_in_cluster;
+}
+
 static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, int *pnum)
 {
@@ -1285,7 +1279,7 @@ static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
         break;
     }
 
-    index_in_cluster = sector_num % extent->cluster_sectors;
+    index_in_cluster = vmdk_find_index_in_cluster(extent, sector_num);
     n = extent->cluster_sectors - index_in_cluster;
     if (n > nb_sectors) {
         n = nb_sectors;
@@ -1413,7 +1407,6 @@ static int vmdk_read(BlockDriverState *bs, int64_t sector_num,
     BDRVVmdkState *s = bs->opaque;
     int ret;
     uint64_t n, index_in_cluster;
-    uint64_t extent_begin_sector, extent_relative_sector_num;
     VmdkExtent *extent = NULL;
     uint64_t cluster_offset;
 
@@ -1425,9 +1418,7 @@ static int vmdk_read(BlockDriverState *bs, int64_t sector_num,
         ret = get_cluster_offset(bs, extent, NULL,
                                  sector_num << 9, false, &cluster_offset,
                                  0, 0);
-        extent_begin_sector = extent->end_sector - extent->sectors;
+        index_in_cluster = vmdk_find_index_in_cluster(extent, sector_num);
-        extent_relative_sector_num = sector_num - extent_begin_sector;
-        index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
         n = extent->cluster_sectors - index_in_cluster;
         if (n > nb_sectors) {
             n = nb_sectors;
@@ -1489,7 +1480,6 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
     VmdkExtent *extent = NULL;
     int ret;
     int64_t index_in_cluster, n;
-    uint64_t extent_begin_sector, extent_relative_sector_num;
     uint64_t cluster_offset;
     VmdkMetaData m_data;
 
@@ -1505,9 +1495,7 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
         if (!extent) {
             return -EIO;
         }
-        extent_begin_sector = extent->end_sector - extent->sectors;
+        index_in_cluster = vmdk_find_index_in_cluster(extent, sector_num);
-        extent_relative_sector_num = sector_num - extent_begin_sector;
-        index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
         n = extent->cluster_sectors - index_in_cluster;
         if (n > nb_sectors) {
             n = nb_sectors;

blockdev.c

@@ -393,13 +393,13 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
         }
     }
 
-    if (qemu_opt_get_bool(opts, "cache.writeback", true)) {
+    if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_WB, true)) {
         bdrv_flags |= BDRV_O_CACHE_WB;
     }
-    if (qemu_opt_get_bool(opts, "cache.direct", false)) {
+    if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_DIRECT, false)) {
         bdrv_flags |= BDRV_O_NOCACHE;
     }
-    if (qemu_opt_get_bool(opts, "cache.no-flush", false)) {
+    if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_NO_FLUSH, false)) {
         bdrv_flags |= BDRV_O_NO_FLUSH;
     }
 
@@ -742,16 +742,16 @@ DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type)
         }
 
         /* Specific options take precedence */
-        if (!qemu_opt_get(all_opts, "cache.writeback")) {
+        if (!qemu_opt_get(all_opts, BDRV_OPT_CACHE_WB)) {
-            qemu_opt_set_bool(all_opts, "cache.writeback",
+            qemu_opt_set_bool(all_opts, BDRV_OPT_CACHE_WB,
                               !!(flags & BDRV_O_CACHE_WB), &error_abort);
         }
-        if (!qemu_opt_get(all_opts, "cache.direct")) {
+        if (!qemu_opt_get(all_opts, BDRV_OPT_CACHE_DIRECT)) {
-            qemu_opt_set_bool(all_opts, "cache.direct",
+            qemu_opt_set_bool(all_opts, BDRV_OPT_CACHE_DIRECT,
                               !!(flags & BDRV_O_NOCACHE), &error_abort);
         }
-        if (!qemu_opt_get(all_opts, "cache.no-flush")) {
+        if (!qemu_opt_get(all_opts, BDRV_OPT_CACHE_NO_FLUSH)) {
-            qemu_opt_set_bool(all_opts, "cache.no-flush",
+            qemu_opt_set_bool(all_opts, BDRV_OPT_CACHE_NO_FLUSH,
                               !!(flags & BDRV_O_NO_FLUSH), &error_abort);
         }
         qemu_opt_unset(all_opts, "cache");
@@ -3121,15 +3121,15 @@ QemuOptsList qemu_common_drive_opts = {
             .type = QEMU_OPT_STRING,
             .help = "discard operation (ignore/off, unmap/on)",
         },{
-            .name = "cache.writeback",
+            .name = BDRV_OPT_CACHE_WB,
             .type = QEMU_OPT_BOOL,
             .help = "enables writeback mode for any caches",
         },{
-            .name = "cache.direct",
+            .name = BDRV_OPT_CACHE_DIRECT,
             .type = QEMU_OPT_BOOL,
             .help = "enables use of O_DIRECT (bypass the host page cache)",
         },{
-            .name = "cache.no-flush",
+            .name = BDRV_OPT_CACHE_NO_FLUSH,
             .type = QEMU_OPT_BOOL,
             .help = "ignore any flush requests for the device",
         },{

include/block/block.h

@@ -12,6 +12,7 @@
 /* block.c */
 typedef struct BlockDriver BlockDriver;
 typedef struct BlockJob BlockJob;
+typedef struct BdrvChildRole BdrvChildRole;
 
 typedef struct BlockDriverInfo {
     /* in bytes, 0 if irrelevant */
@@ -90,6 +91,14 @@ typedef struct HDGeometry {
 
 #define BDRV_O_CACHE_MASK  (BDRV_O_NOCACHE | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH)
 
+
+/* Option names of options parsed by the block layer */
+
+#define BDRV_OPT_CACHE_WB       "cache.writeback"
+#define BDRV_OPT_CACHE_DIRECT   "cache.direct"
+#define BDRV_OPT_CACHE_NO_FLUSH "cache.no-flush"
+
+
 #define BDRV_SECTOR_BITS   9
 #define BDRV_SECTOR_SIZE   (1ULL << BDRV_SECTOR_BITS)
 #define BDRV_SECTOR_MASK   ~(BDRV_SECTOR_SIZE - 1)
@@ -196,7 +205,8 @@ void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top);
 int bdrv_parse_cache_flags(const char *mode, int *flags);
 int bdrv_parse_discard_flags(const char *mode, int *flags);
 int bdrv_open_image(BlockDriverState **pbs, const char *filename,
-                    QDict *options, const char *bdref_key, int flags,
+                    QDict *options, const char *bdref_key,
+                    BlockDriverState* parent, const BdrvChildRole *child_role,
                     bool allow_none, Error **errp);
 void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd);
 int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp);

include/block/block_int.h

@@ -330,6 +330,19 @@ typedef struct BdrvAioNotifier {
     QLIST_ENTRY(BdrvAioNotifier) list;
 } BdrvAioNotifier;
 
+struct BdrvChildRole {
+    int (*inherit_flags)(int parent_flags);
+};
+
+extern const BdrvChildRole child_file;
+extern const BdrvChildRole child_format;
+
+typedef struct BdrvChild {
+    BlockDriverState *bs;
+    const BdrvChildRole *role;
+    QLIST_ENTRY(BdrvChild) next;
+} BdrvChild;
+
 /*
  * Note: the function bdrv_append() copies and swaps contents of
  * BlockDriverStates, so if you add new fields to this struct, please
@@ -429,6 +442,12 @@ struct BlockDriverState {
     /* long-running background operation */
     BlockJob *job;
 
+    /* The node that this node inherited default options from (and a reopen on
+     * which can affect this node by changing these defaults). This is always a
+     * parent node of this node. */
+    BlockDriverState *inherits_from;
+    QLIST_HEAD(, BdrvChild) children;
+
     QDict *options;
     BlockdevDetectZeroesOptions detect_zeroes;
 

include/qapi/qmp/qdict.h

@@ -65,11 +65,15 @@ int64_t qdict_get_try_int(const QDict *qdict, const char *key,
 int qdict_get_try_bool(const QDict *qdict, const char *key, int def_value);
 const char *qdict_get_try_str(const QDict *qdict, const char *key);
 
+void qdict_copy_default(QDict *dst, QDict *src, const char *key);
+void qdict_set_default_str(QDict *dst, const char *key, const char *val);
+
 QDict *qdict_clone_shallow(const QDict *src);
 void qdict_flatten(QDict *qdict);
 
 void qdict_extract_subqdict(QDict *src, QDict **dst, const char *start);
 void qdict_array_split(QDict *src, QList **dst);
+int qdict_array_entries(QDict *src, const char *subqdict);
 
 void qdict_join(QDict *dest, QDict *src, bool overwrite);
 

include/qemu/queue.h

@@ -117,6 +117,12 @@ struct {                                                                \
         }                                                               \
 } while (/*CONSTCOND*/0)
 
+#define QLIST_FIX_HEAD_PTR(head, field) do {                            \
+        if ((head)->lh_first != NULL) {                                 \
+            (head)->lh_first->field.le_prev = &(head)->lh_first;        \
+        }                                                               \
+} while (/*CONSTCOND*/0)
+
 #define QLIST_INSERT_AFTER(listelm, elm, field) do {                    \
         if (((elm)->field.le_next = (listelm)->field.le_next) != NULL)  \
                 (listelm)->field.le_next->field.le_prev =               \

qobject/qdict.c

@@ -477,6 +477,39 @@ static void qdict_destroy_obj(QObject *obj)
     g_free(qdict);
 }
 
+/**
+ * qdict_copy_default(): If no entry mapped by 'key' exists in 'dst' yet, the
+ * value of 'key' in 'src' is copied there (and the refcount increased
+ * accordingly).
+ */
+void qdict_copy_default(QDict *dst, QDict *src, const char *key)
+{
+    QObject *val;
+
+    if (qdict_haskey(dst, key)) {
+        return;
+    }
+
+    val = qdict_get(src, key);
+    if (val) {
+        qobject_incref(val);
+        qdict_put_obj(dst, key, val);
+    }
+}
+
+/**
+ * qdict_set_default_str(): If no entry mapped by 'key' exists in 'dst' yet, a
+ * new QString initialised by 'val' is put there.
+ */
+void qdict_set_default_str(QDict *dst, const char *key, const char *val)
+{
+    if (qdict_haskey(dst, key)) {
+        return;
+    }
+
+    qdict_put(dst, key, qstring_from_str(val));
+}
+
 static void qdict_flatten_qdict(QDict *qdict, QDict *target,
                                 const char *prefix);
 
@@ -597,17 +630,21 @@ void qdict_extract_subqdict(QDict *src, QDict **dst, const char *start)
     }
 }
 
-static bool qdict_has_prefixed_entries(const QDict *src, const char *start)
+static int qdict_count_prefixed_entries(const QDict *src, const char *start)
 {
     const QDictEntry *entry;
+    int count = 0;
 
     for (entry = qdict_first(src); entry; entry = qdict_next(src, entry)) {
         if (strstart(entry->key, start, NULL)) {
-            return true;
+            if (count == INT_MAX) {
+                return -ERANGE;
+            }
+            count++;
         }
     }
 
-    return false;
+    return count;
 }
 
 /**
@@ -646,7 +683,8 @@ void qdict_array_split(QDict *src, QList **dst)
         snprintf_ret = snprintf(prefix, 32, "%u.", i);
         assert(snprintf_ret < 32);
 
-        is_subqdict = qdict_has_prefixed_entries(src, prefix);
+        /* Overflow is the same as positive non-zero results */
+        is_subqdict = qdict_count_prefixed_entries(src, prefix);
 
         // There may be either a single subordinate object (named "%u") or
         // multiple objects (each with a key prefixed "%u."), but not both.
@@ -666,6 +704,71 @@ void qdict_array_split(QDict *src, QList **dst)
     }
 }
 
+/**
+ * qdict_array_entries(): Returns the number of direct array entries if the
+ * sub-QDict of src specified by the prefix in subqdict (or src itself for
+ * prefix == "") is valid as an array, i.e. the length of the created list if
+ * the sub-QDict would become empty after calling qdict_array_split() on it. If
+ * the array is not valid, -EINVAL is returned.
+ */
+int qdict_array_entries(QDict *src, const char *subqdict)
+{
+    const QDictEntry *entry;
+    unsigned i;
+    unsigned entries = 0;
+    size_t subqdict_len = strlen(subqdict);
+
+    assert(!subqdict_len || subqdict[subqdict_len - 1] == '.');
+
+    /* qdict_array_split() loops until UINT_MAX, but as we want to return
+     * negative errors, we only have a signed return value here. Any additional
+     * entries will lead to -EINVAL. */
+    for (i = 0; i < INT_MAX; i++) {
+        QObject *subqobj;
+        int subqdict_entries;
+        size_t slen = 32 + subqdict_len;
+        char indexstr[slen], prefix[slen];
+        size_t snprintf_ret;
+
+        snprintf_ret = snprintf(indexstr, slen, "%s%u", subqdict, i);
+        assert(snprintf_ret < slen);
+
+        subqobj = qdict_get(src, indexstr);
+
+        snprintf_ret = snprintf(prefix, slen, "%s%u.", subqdict, i);
+        assert(snprintf_ret < slen);
+
+        subqdict_entries = qdict_count_prefixed_entries(src, prefix);
+        if (subqdict_entries < 0) {
+            return subqdict_entries;
+        }
+
+        /* There may be either a single subordinate object (named "%u") or
+         * multiple objects (each with a key prefixed "%u."), but not both. */
+        if (subqobj && subqdict_entries) {
+            return -EINVAL;
+        } else if (!subqobj && !subqdict_entries) {
+            break;
+        }
+
+        entries += subqdict_entries ? subqdict_entries : 1;
+    }
+
+    /* Consider everything handled that isn't part of the given sub-QDict */
+    for (entry = qdict_first(src); entry; entry = qdict_next(src, entry)) {
+        if (!strstart(qdict_entry_key(entry), subqdict, NULL)) {
+            entries++;
+        }
+    }
+
+    /* Anything left in the sub-QDict that wasn't handled? */
+    if (qdict_size(src) != entries) {
+        return -EINVAL;
+    }
+
+    return i;
+}
+
 /**
  * qdict_join(): Absorb the src QDict into the dest QDict, that is, move all
  * elements from src to dest.

tests/check-qdict.c

@@ -152,6 +152,28 @@ static void qdict_get_try_str_test(void)
     QDECREF(tests_dict);
 }
 
+static void qdict_defaults_test(void)
+{
+    QDict *dict, *copy;
+
+    dict = qdict_new();
+    copy = qdict_new();
+
+    qdict_set_default_str(dict, "foo", "abc");
+    qdict_set_default_str(dict, "foo", "def");
+    g_assert_cmpstr(qdict_get_str(dict, "foo"), ==, "abc");
+    qdict_set_default_str(dict, "bar", "ghi");
+
+    qdict_copy_default(copy, dict, "foo");
+    g_assert_cmpstr(qdict_get_str(copy, "foo"), ==, "abc");
+    qdict_set_default_str(copy, "bar", "xyz");
+    qdict_copy_default(copy, dict, "bar");
+    g_assert_cmpstr(qdict_get_str(copy, "bar"), ==, "xyz");
+
+    QDECREF(copy);
+    QDECREF(dict);
+}
+
 static void qdict_haskey_not_test(void)
 {
     QDict *tests_dict = qdict_new();
@@ -444,6 +466,49 @@ static void qdict_array_split_test(void)
     QDECREF(test_dict);
 }
 
+static void qdict_array_entries_test(void)
+{
+    QDict *dict = qdict_new();
+
+    g_assert_cmpint(qdict_array_entries(dict, "foo."), ==, 0);
+
+    qdict_put(dict, "bar", qint_from_int(0));
+    qdict_put(dict, "baz.0", qint_from_int(0));
+    g_assert_cmpint(qdict_array_entries(dict, "foo."), ==, 0);
+
+    qdict_put(dict, "foo.1", qint_from_int(0));
+    g_assert_cmpint(qdict_array_entries(dict, "foo."), ==, -EINVAL);
+    qdict_put(dict, "foo.0", qint_from_int(0));
+    g_assert_cmpint(qdict_array_entries(dict, "foo."), ==, 2);
+    qdict_put(dict, "foo.bar", qint_from_int(0));
+    g_assert_cmpint(qdict_array_entries(dict, "foo."), ==, -EINVAL);
+    qdict_del(dict, "foo.bar");
+
+    qdict_put(dict, "foo.2.a", qint_from_int(0));
+    qdict_put(dict, "foo.2.b", qint_from_int(0));
+    qdict_put(dict, "foo.2.c", qint_from_int(0));
+    g_assert_cmpint(qdict_array_entries(dict, "foo."), ==, 3);
+    g_assert_cmpint(qdict_array_entries(dict, ""), ==, -EINVAL);
+
+    QDECREF(dict);
+
+    dict = qdict_new();
+    qdict_put(dict, "1", qint_from_int(0));
+    g_assert_cmpint(qdict_array_entries(dict, ""), ==, -EINVAL);
+    qdict_put(dict, "0", qint_from_int(0));
+    g_assert_cmpint(qdict_array_entries(dict, ""), ==, 2);
+    qdict_put(dict, "bar", qint_from_int(0));
+    g_assert_cmpint(qdict_array_entries(dict, ""), ==, -EINVAL);
+    qdict_del(dict, "bar");
+
+    qdict_put(dict, "2.a", qint_from_int(0));
+    qdict_put(dict, "2.b", qint_from_int(0));
+    qdict_put(dict, "2.c", qint_from_int(0));
+    g_assert_cmpint(qdict_array_entries(dict, ""), ==, 3);
+
+    QDECREF(dict);
+}
+
 static void qdict_join_test(void)
 {
     QDict *dict1, *dict2;
@@ -663,6 +728,7 @@ int main(int argc, char **argv)
     g_test_add_func("/public/get_try_int", qdict_get_try_int_test);
     g_test_add_func("/public/get_str", qdict_get_str_test);
     g_test_add_func("/public/get_try_str", qdict_get_try_str_test);
+    g_test_add_func("/public/defaults", qdict_defaults_test);
     g_test_add_func("/public/haskey_not", qdict_haskey_not_test);
     g_test_add_func("/public/haskey", qdict_haskey_test);
     g_test_add_func("/public/del", qdict_del_test);
@@ -670,6 +736,7 @@ int main(int argc, char **argv)
     g_test_add_func("/public/iterapi", qdict_iterapi_test);
     g_test_add_func("/public/flatten", qdict_flatten_test);
     g_test_add_func("/public/array_split", qdict_array_split_test);
+    g_test_add_func("/public/array_entries", qdict_array_entries_test);
     g_test_add_func("/public/join", qdict_join_test);
 
     g_test_add_func("/errors/put_exists", qdict_put_exists_test);

tests/qemu-iotests/051

@@ -194,7 +194,6 @@ echo === Specifying the protocol layer ===
 echo
 
 run_qemu -drive file="$TEST_IMG",file.driver=file
-run_qemu -drive file="$TEST_IMG",file.driver=qcow2
 
 echo
 echo === Leaving out required options ===

tests/qemu-iotests/051.out

@@ -253,9 +253,6 @@ Testing: -drive file=TEST_DIR/t.qcow2,file.driver=file
 QEMU X.Y.Z monitor - type 'help' for more information
 (qemu) qququiquit
 
-Testing: -drive file=TEST_DIR/t.qcow2,file.driver=qcow2
-QEMU_PROG: -drive file=TEST_DIR/t.qcow2,file.driver=qcow2: Block format 'qcow2' used by device '' doesn't support the option 'filename'
-
 
 === Leaving out required options ===
 

tests/qemu-iotests/103

@@ -93,6 +93,16 @@ $QEMU_IO -c "open -o l2-cache-size=1M,refcount-cache-size=0.25M $TEST_IMG" \
          -c 'read -P 42 0 64k' \
     | _filter_qemu_io
 
+echo
+echo '=== Testing minimal L2 cache and COW ==='
+echo
+
+$QEMU_IMG snapshot -c foo "$TEST_IMG"
+# This requires a COW operation, which accesses two L2 tables simultaneously
+# (COW source and destination), so there must be enough space in the cache to
+# place both tables there (and qemu should not crash)
+$QEMU_IO -c "open -o cache-size=0 $TEST_IMG" -c 'write 0 64k' | _filter_qemu_io
+
 # success, all done
 echo '*** done'
 rm -f $seq.full

tests/qemu-iotests/103.out

@@ -26,4 +26,9 @@ read 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 read 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+=== Testing minimal L2 cache and COW ===
+
+wrote 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 *** done

tests/qemu-iotests/119

@@ -0,0 +1,60 @@
+#!/bin/bash
+#
+# NBD test case for overriding BDRV_O_PROTOCOL by explicitly specifying
+# a driver
+#
+# Copyright (C) 2015 Red Hat, Inc.
+#
+# 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=mreitz@redhat.com
+
+seq="$(basename $0)"
+echo "QA output created by $seq"
+
+here="$PWD"
+tmp=/tmp/$$
+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 nbd
+_supported_os Linux
+
+_make_test_img 64M
+# This should not crash
+echo "{'execute': 'qmp_capabilities'}
+      {'execute': 'human-monitor-command',
+       'arguments': {'command-line': 'qemu-io drv \"read -P 0 0 64k\"'}}
+      {'execute': 'quit'}" \
+    | $QEMU -drive id=drv,if=none,file="$TEST_IMG",driver=nbd \
+            -qmp stdio -nodefaults \
+    | _filter_qmp | _filter_qemu_io
+
+# success, all done
+echo
+echo '*** done'
+rm -f $seq.full
+status=0

tests/qemu-iotests/119.out

@@ -0,0 +1,11 @@
+QA output created by 119
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864
+QMP_VERSION
+{"return": {}}
+read 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+{"return": ""}
+{"return": {}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "SHUTDOWN"}
+
+*** done

tests/qemu-iotests/120

@@ -0,0 +1,65 @@
+#!/bin/bash
+#
+# Non-NBD test cases for overriding BDRV_O_PROTOCOL by explicitly
+# specifying a driver
+#
+# Copyright (C) 2015 Red Hat, Inc.
+#
+# 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=mreitz@redhat.com
+
+seq="$(basename $0)"
+echo "QA output created by $seq"
+
+here="$PWD"
+tmp=/tmp/$$
+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 generic
+_supported_proto file
+_supported_os Linux
+
+_make_test_img 64M
+
+echo "{'execute': 'qmp_capabilities'}
+      {'execute': 'human-monitor-command',
+       'arguments': {'command-line': 'qemu-io drv \"write -P 42 0 64k\"'}}
+      {'execute': 'quit'}" \
+    | $QEMU -qmp stdio -nodefaults \
+            -drive id=drv,if=none,file="$TEST_IMG",driver=raw,file.driver=$IMGFMT \
+    | _filter_qmp | _filter_qemu_io
+$QEMU_IO -c 'read -P 42 0 64k' "$TEST_IMG" | _filter_qemu_io
+
+$QEMU_IO_PROG -c 'read -P 42 0 64k' \
+    "json:{'driver': 'raw', 'file': {'driver': '$IMGFMT', 'file': {'filename': '$TEST_IMG'}}}" \
+    | _filter_qemu_io
+
+# success, all done
+echo
+echo '*** done'
+rm -f $seq.full
+status=0

tests/qemu-iotests/120.out

@@ -0,0 +1,15 @@
+QA output created by 120
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864
+QMP_VERSION
+{"return": {}}
+wrote 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+{"return": ""}
+{"return": {}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "SHUTDOWN"}
+read 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+*** done

tests/qemu-iotests/124

@@ -125,7 +125,7 @@ class TestIncrementalBackup(iotests.QMPTestCase):
 
         event = self.vm.event_wait(name="BLOCK_JOB_COMPLETED",
                                    match={'data': {'device': kwargs['device']}})
-        self.assertIsNotNone(event)
+        self.assertNotEqual(event, None)
 
         try:
             failure = self.dictpath(event, 'data/error')

tests/qemu-iotests/128

@@ -29,6 +29,7 @@ tmp=/tmp/$$
 status=1	# failure is the default!
 
 devname="eiodev$$"
+sudo=""
 
 _setup_eiodev()
 {
@@ -37,6 +38,7 @@ _setup_eiodev()
 		echo "0 $((1024 * 1024 * 1024 / 512)) error" | \
 			$cmd dmsetup create "$devname" 2>/dev/null
 		if [ "$?" -eq 0 ]; then
+			sudo="$cmd"
 			return
 		fi
 	done
@@ -74,7 +76,7 @@ TEST_IMG="/dev/mapper/$devname"
 echo
 echo "== reading from error device =="
 # Opening image should succeed but the read operation should fail
-$QEMU_IO --format "$IMGFMT" --nocache -c "read 0 65536" "$TEST_IMG" | _filter_qemu_io
+$sudo $QEMU_IO --format "$IMGFMT" --nocache -c "read 0 65536" "$TEST_IMG" | _filter_qemu_io
 
 # success, all done
 echo "*** done"

tests/qemu-iotests/group

@@ -121,6 +121,8 @@
 114 rw auto quick
 115 rw auto
 116 rw auto quick
+119 rw auto quick
+120 rw auto quick
 121 rw auto
 122 rw auto
 123 rw auto quick