Block layer patches

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQIcBAABAgAGBQJYtd8UAAoJEH8JsnLIjy/WuK0P/i3yi29JOZTEeUIUc+QXHm4b
 iXRj/3uLwLD5IJqfjLeDmOPUfI+w0SAkGTidSlKrS5maypW366ke/+CY8QZtbxiH
 qTazKrXNumhvJuJVXQ0L8bAwDC/r8pPlrvLJ3bfBOK6t6fu//M/nUZP/N92UMX87
 w1xA+PNq1TNZEKC6VwdY50fsrhOxIR1ZoS2rEKseEBuYqTm2q5Q0Y8EXhbReO0LE
 Pb0vAOEmZg6K2Awv4Cg2L8BZlz+tGgUd+3eWV8zzCshHkAc2J/OaxjLCG/KUgXb4
 MbdACnIHOUOGqhLfM9wjrVYJAhM/4F1sR0hDm8uUngFWlWsGwTdhH5bRlfat3QQs
 E4oNt6ORHiEis0l7pXfwHTDC3ChockArxdJlOvmpRm6EUSBs132IJS3TrlKBCr+R
 CBdoC3k1eXC6uHF4KCrsnW2u26D4Ju9V6Yb5h/RqYPJCc+o16BsD31/WOLhH4WTq
 M7A9ZbH4jBDHTO3A5zho0x7AGbVGDVMzKssU9MUOkUuPB+yM2KMg/Kr0kUDhrl0k
 aOdRfCF+OcsiXzM97U3msv0udbHr0/tUtE+/3tL3kcXjEHoaFECUdV8mU9F3KleZ
 5MQP2vNcAZA96zuV1qMhPlDwWBoEwBebDnvM3LuTvkHdbBQZv+6A6XiCw/hXdh6o
 zyUn+/2KKGoPiNv/B6PD
 =g3ew
 -----END PGP SIGNATURE-----

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

Block layer patches

# gpg: Signature made Tue 28 Feb 2017 20:35:32 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: (46 commits)
  block: Add Error parameter to bdrv_append()
  block: Add Error parameter to bdrv_set_backing_hd()
  block: Assertions for resize permission
  block: Assertions for write permissions
  block: Pass BdrvChild to bdrv_aligned_preadv/pwritev and copy-on-read
  tests: Remove FIXME comments
  nbd/server: Use real permissions for NBD exports
  migration/block: Use real permissions
  hmp: Request permissions in qemu-io
  commit: Add filter-node-name to block-commit
  mirror: Add filter-node-name to blockdev-mirror
  stream: Use real permissions in streaming block job
  mirror: Use real permissions in mirror/active commit block job
  blockjob: Factor out block_job_remove_all_bdrv()
  block: Allow backing file links in change_parent_backing_link()
  block: BdrvChildRole.attach/detach() callbacks
  block: Fix pending requests check in bdrv_append()
  backup: Use real permissions in backup block job
  commit: Use real permissions for HMP 'commit'
  commit: Use real permissions in commit block job
  ...

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

block.c

@@ -707,6 +707,12 @@ int bdrv_parse_cache_mode(const char *mode, int *flags, bool *writethrough)
     return 0;
 }
 
+static char *bdrv_child_get_parent_desc(BdrvChild *c)
+{
+    BlockDriverState *parent = c->opaque;
+    return g_strdup(bdrv_get_device_or_node_name(parent));
+}
+
 static void bdrv_child_cb_drained_begin(BdrvChild *child)
 {
     BlockDriverState *bs = child->opaque;
@@ -774,6 +780,7 @@ static void bdrv_inherited_options(int *child_flags, QDict *child_options,
 }
 
 const BdrvChildRole child_file = {
+    .get_parent_desc = bdrv_child_get_parent_desc,
     .inherit_options = bdrv_inherited_options,
     .drained_begin   = bdrv_child_cb_drained_begin,
     .drained_end     = bdrv_child_cb_drained_end,
@@ -794,11 +801,63 @@ static void bdrv_inherited_fmt_options(int *child_flags, QDict *child_options,
 }
 
 const BdrvChildRole child_format = {
+    .get_parent_desc = bdrv_child_get_parent_desc,
     .inherit_options = bdrv_inherited_fmt_options,
     .drained_begin   = bdrv_child_cb_drained_begin,
     .drained_end     = bdrv_child_cb_drained_end,
 };
 
+static void bdrv_backing_attach(BdrvChild *c)
+{
+    BlockDriverState *parent = c->opaque;
+    BlockDriverState *backing_hd = c->bs;
+
+    assert(!parent->backing_blocker);
+    error_setg(&parent->backing_blocker,
+               "node is used as backing hd of '%s'",
+               bdrv_get_device_or_node_name(parent));
+
+    parent->open_flags &= ~BDRV_O_NO_BACKING;
+    pstrcpy(parent->backing_file, sizeof(parent->backing_file),
+            backing_hd->filename);
+    pstrcpy(parent->backing_format, sizeof(parent->backing_format),
+            backing_hd->drv ? backing_hd->drv->format_name : "");
+
+    bdrv_op_block_all(backing_hd, parent->backing_blocker);
+    /* Otherwise we won't be able to commit or stream */
+    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_COMMIT_TARGET,
+                    parent->backing_blocker);
+    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_STREAM,
+                    parent->backing_blocker);
+    /*
+     * We do backup in 3 ways:
+     * 1. drive backup
+     *    The target bs is new opened, and the source is top BDS
+     * 2. blockdev backup
+     *    Both the source and the target are top BDSes.
+     * 3. internal backup(used for block replication)
+     *    Both the source and the target are backing file
+     *
+     * In case 1 and 2, neither the source nor the target is the backing file.
+     * In case 3, we will block the top BDS, so there is only one block job
+     * for the top BDS and its backing chain.
+     */
+    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_SOURCE,
+                    parent->backing_blocker);
+    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_TARGET,
+                    parent->backing_blocker);
+}
+
+static void bdrv_backing_detach(BdrvChild *c)
+{
+    BlockDriverState *parent = c->opaque;
+
+    assert(parent->backing_blocker);
+    bdrv_op_unblock_all(c->bs, parent->backing_blocker);
+    error_free(parent->backing_blocker);
+    parent->backing_blocker = NULL;
+}
+
 /*
  * Returns the options and flags that bs->backing should get, based on the
  * given options and flags for the parent BDS
@@ -823,7 +882,10 @@ static void bdrv_backing_options(int *child_flags, QDict *child_options,
     *child_flags = flags;
 }
 
-static const BdrvChildRole child_backing = {
+const BdrvChildRole child_backing = {
+    .get_parent_desc = bdrv_child_get_parent_desc,
+    .attach          = bdrv_backing_attach,
+    .detach          = bdrv_backing_detach,
     .inherit_options = bdrv_backing_options,
     .drained_begin   = bdrv_child_cb_drained_begin,
     .drained_end     = bdrv_child_cb_drained_end,
@@ -1326,15 +1388,352 @@ static int bdrv_fill_options(QDict **options, const char *filename,
     return 0;
 }
 
-static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs)
+/*
+ * Check whether permissions on this node can be changed in a way that
+ * @cumulative_perms and @cumulative_shared_perms are the new cumulative
+ * permissions of all its parents. This involves checking whether all necessary
+ * permission changes to child nodes can be performed.
+ *
+ * A call to this function must always be followed by a call to bdrv_set_perm()
+ * or bdrv_abort_perm_update().
+ */
+static int bdrv_check_perm(BlockDriverState *bs, uint64_t cumulative_perms,
+                           uint64_t cumulative_shared_perms, Error **errp)
+{
+    BlockDriver *drv = bs->drv;
+    BdrvChild *c;
+    int ret;
+
+    /* Write permissions never work with read-only images */
+    if ((cumulative_perms & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) &&
+        bdrv_is_read_only(bs))
+    {
+        error_setg(errp, "Block node is read-only");
+        return -EPERM;
+    }
+
+    /* Check this node */
+    if (!drv) {
+        return 0;
+    }
+
+    if (drv->bdrv_check_perm) {
+        return drv->bdrv_check_perm(bs, cumulative_perms,
+                                    cumulative_shared_perms, errp);
+    }
+
+    /* Drivers that never have children can omit .bdrv_child_perm() */
+    if (!drv->bdrv_child_perm) {
+        assert(QLIST_EMPTY(&bs->children));
+        return 0;
+    }
+
+    /* Check all children */
+    QLIST_FOREACH(c, &bs->children, next) {
+        uint64_t cur_perm, cur_shared;
+        drv->bdrv_child_perm(bs, c, c->role,
+                             cumulative_perms, cumulative_shared_perms,
+                             &cur_perm, &cur_shared);
+        ret = bdrv_child_check_perm(c, cur_perm, cur_shared, errp);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+
+    return 0;
+}
+
+/*
+ * Notifies drivers that after a previous bdrv_check_perm() call, the
+ * permission update is not performed and any preparations made for it (e.g.
+ * taken file locks) need to be undone.
+ *
+ * This function recursively notifies all child nodes.
+ */
+static void bdrv_abort_perm_update(BlockDriverState *bs)
+{
+    BlockDriver *drv = bs->drv;
+    BdrvChild *c;
+
+    if (!drv) {
+        return;
+    }
+
+    if (drv->bdrv_abort_perm_update) {
+        drv->bdrv_abort_perm_update(bs);
+    }
+
+    QLIST_FOREACH(c, &bs->children, next) {
+        bdrv_child_abort_perm_update(c);
+    }
+}
+
+static void bdrv_set_perm(BlockDriverState *bs, uint64_t cumulative_perms,
+                          uint64_t cumulative_shared_perms)
+{
+    BlockDriver *drv = bs->drv;
+    BdrvChild *c;
+
+    if (!drv) {
+        return;
+    }
+
+    /* Update this node */
+    if (drv->bdrv_set_perm) {
+        drv->bdrv_set_perm(bs, cumulative_perms, cumulative_shared_perms);
+    }
+
+    /* Drivers that never have children can omit .bdrv_child_perm() */
+    if (!drv->bdrv_child_perm) {
+        assert(QLIST_EMPTY(&bs->children));
+        return;
+    }
+
+    /* Update all children */
+    QLIST_FOREACH(c, &bs->children, next) {
+        uint64_t cur_perm, cur_shared;
+        drv->bdrv_child_perm(bs, c, c->role,
+                             cumulative_perms, cumulative_shared_perms,
+                             &cur_perm, &cur_shared);
+        bdrv_child_set_perm(c, cur_perm, cur_shared);
+    }
+}
+
+static void bdrv_get_cumulative_perm(BlockDriverState *bs, uint64_t *perm,
+                                     uint64_t *shared_perm)
+{
+    BdrvChild *c;
+    uint64_t cumulative_perms = 0;
+    uint64_t cumulative_shared_perms = BLK_PERM_ALL;
+
+    QLIST_FOREACH(c, &bs->parents, next_parent) {
+        cumulative_perms |= c->perm;
+        cumulative_shared_perms &= c->shared_perm;
+    }
+
+    *perm = cumulative_perms;
+    *shared_perm = cumulative_shared_perms;
+}
+
+static char *bdrv_child_user_desc(BdrvChild *c)
+{
+    if (c->role->get_parent_desc) {
+        return c->role->get_parent_desc(c);
+    }
+
+    return g_strdup("another user");
+}
+
+static char *bdrv_perm_names(uint64_t perm)
+{
+    struct perm_name {
+        uint64_t perm;
+        const char *name;
+    } permissions[] = {
+        { BLK_PERM_CONSISTENT_READ, "consistent read" },
+        { BLK_PERM_WRITE,           "write" },
+        { BLK_PERM_WRITE_UNCHANGED, "write unchanged" },
+        { BLK_PERM_RESIZE,          "resize" },
+        { BLK_PERM_GRAPH_MOD,       "change children" },
+        { 0, NULL }
+    };
+
+    char *result = g_strdup("");
+    struct perm_name *p;
+
+    for (p = permissions; p->name; p++) {
+        if (perm & p->perm) {
+            char *old = result;
+            result = g_strdup_printf("%s%s%s", old, *old ? ", " : "", p->name);
+            g_free(old);
+        }
+    }
+
+    return result;
+}
+
+/*
+ * Checks whether a new reference to @bs can be added if the new user requires
+ * @new_used_perm/@new_shared_perm as its permissions. If @ignore_child is set,
+ * this old reference is ignored in the calculations; this allows checking
+ * permission updates for an existing reference.
+ *
+ * Needs to be followed by a call to either bdrv_set_perm() or
+ * bdrv_abort_perm_update(). */
+static int bdrv_check_update_perm(BlockDriverState *bs, uint64_t new_used_perm,
+                                  uint64_t new_shared_perm,
+                                  BdrvChild *ignore_child, Error **errp)
+{
+    BdrvChild *c;
+    uint64_t cumulative_perms = new_used_perm;
+    uint64_t cumulative_shared_perms = new_shared_perm;
+
+    /* There is no reason why anyone couldn't tolerate write_unchanged */
+    assert(new_shared_perm & BLK_PERM_WRITE_UNCHANGED);
+
+    QLIST_FOREACH(c, &bs->parents, next_parent) {
+        if (c == ignore_child) {
+            continue;
+        }
+
+        if ((new_used_perm & c->shared_perm) != new_used_perm) {
+            char *user = bdrv_child_user_desc(c);
+            char *perm_names = bdrv_perm_names(new_used_perm & ~c->shared_perm);
+            error_setg(errp, "Conflicts with use by %s as '%s', which does not "
+                             "allow '%s' on %s",
+                       user, c->name, perm_names, bdrv_get_node_name(c->bs));
+            g_free(user);
+            g_free(perm_names);
+            return -EPERM;
+        }
+
+        if ((c->perm & new_shared_perm) != c->perm) {
+            char *user = bdrv_child_user_desc(c);
+            char *perm_names = bdrv_perm_names(c->perm & ~new_shared_perm);
+            error_setg(errp, "Conflicts with use by %s as '%s', which uses "
+                             "'%s' on %s",
+                       user, c->name, perm_names, bdrv_get_node_name(c->bs));
+            g_free(user);
+            g_free(perm_names);
+            return -EPERM;
+        }
+
+        cumulative_perms |= c->perm;
+        cumulative_shared_perms &= c->shared_perm;
+    }
+
+    return bdrv_check_perm(bs, cumulative_perms, cumulative_shared_perms, errp);
+}
+
+/* Needs to be followed by a call to either bdrv_child_set_perm() or
+ * bdrv_child_abort_perm_update(). */
+int bdrv_child_check_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
+                          Error **errp)
+{
+    return bdrv_check_update_perm(c->bs, perm, shared, c, errp);
+}
+
+void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared)
+{
+    uint64_t cumulative_perms, cumulative_shared_perms;
+
+    c->perm = perm;
+    c->shared_perm = shared;
+
+    bdrv_get_cumulative_perm(c->bs, &cumulative_perms,
+                             &cumulative_shared_perms);
+    bdrv_set_perm(c->bs, cumulative_perms, cumulative_shared_perms);
+}
+
+void bdrv_child_abort_perm_update(BdrvChild *c)
+{
+    bdrv_abort_perm_update(c->bs);
+}
+
+int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
+                            Error **errp)
+{
+    int ret;
+
+    ret = bdrv_child_check_perm(c, perm, shared, errp);
+    if (ret < 0) {
+        bdrv_child_abort_perm_update(c);
+        return ret;
+    }
+
+    bdrv_child_set_perm(c, perm, shared);
+
+    return 0;
+}
+
+#define DEFAULT_PERM_PASSTHROUGH (BLK_PERM_CONSISTENT_READ \
+                                 | BLK_PERM_WRITE \
+                                 | BLK_PERM_WRITE_UNCHANGED \
+                                 | BLK_PERM_RESIZE)
+#define DEFAULT_PERM_UNCHANGED (BLK_PERM_ALL & ~DEFAULT_PERM_PASSTHROUGH)
+
+void bdrv_filter_default_perms(BlockDriverState *bs, BdrvChild *c,
+                               const BdrvChildRole *role,
+                               uint64_t perm, uint64_t shared,
+                               uint64_t *nperm, uint64_t *nshared)
+{
+    if (c == NULL) {
+        *nperm = perm & DEFAULT_PERM_PASSTHROUGH;
+        *nshared = (shared & DEFAULT_PERM_PASSTHROUGH) | DEFAULT_PERM_UNCHANGED;
+        return;
+    }
+
+    *nperm = (perm & DEFAULT_PERM_PASSTHROUGH) |
+             (c->perm & DEFAULT_PERM_UNCHANGED);
+    *nshared = (shared & DEFAULT_PERM_PASSTHROUGH) |
+               (c->shared_perm & DEFAULT_PERM_UNCHANGED);
+}
+
+void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c,
+                               const BdrvChildRole *role,
+                               uint64_t perm, uint64_t shared,
+                               uint64_t *nperm, uint64_t *nshared)
+{
+    bool backing = (role == &child_backing);
+    assert(role == &child_backing || role == &child_file);
+
+    if (!backing) {
+        /* Apart from the modifications below, the same permissions are
+         * forwarded and left alone as for filters */
+        bdrv_filter_default_perms(bs, c, role, perm, shared, &perm, &shared);
+
+        /* Format drivers may touch metadata even if the guest doesn't write */
+        if (!bdrv_is_read_only(bs)) {
+            perm |= BLK_PERM_WRITE | BLK_PERM_RESIZE;
+        }
+
+        /* bs->file always needs to be consistent because of the metadata. We
+         * can never allow other users to resize or write to it. */
+        perm |= BLK_PERM_CONSISTENT_READ;
+        shared &= ~(BLK_PERM_WRITE | BLK_PERM_RESIZE);
+    } else {
+        /* We want consistent read from backing files if the parent needs it.
+         * No other operations are performed on backing files. */
+        perm &= BLK_PERM_CONSISTENT_READ;
+
+        /* If the parent can deal with changing data, we're okay with a
+         * writable and resizable backing file. */
+        /* TODO Require !(perm & BLK_PERM_CONSISTENT_READ), too? */
+        if (shared & BLK_PERM_WRITE) {
+            shared = BLK_PERM_WRITE | BLK_PERM_RESIZE;
+        } else {
+            shared = 0;
+        }
+
+        shared |= BLK_PERM_CONSISTENT_READ | BLK_PERM_GRAPH_MOD |
+                  BLK_PERM_WRITE_UNCHANGED;
+    }
+
+    *nperm = perm;
+    *nshared = shared;
+}
+
+static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs,
+                               bool check_new_perm)
 {
     BlockDriverState *old_bs = child->bs;
+    uint64_t perm, shared_perm;
 
     if (old_bs) {
         if (old_bs->quiesce_counter && child->role->drained_end) {
             child->role->drained_end(child);
         }
+        if (child->role->detach) {
+            child->role->detach(child);
+        }
         QLIST_REMOVE(child, next_parent);
+
+        /* Update permissions for old node. This is guaranteed to succeed
+         * because we're just taking a parent away, so we're loosening
+         * restrictions. */
+        bdrv_get_cumulative_perm(old_bs, &perm, &shared_perm);
+        bdrv_check_perm(old_bs, perm, shared_perm, &error_abort);
+        bdrv_set_perm(old_bs, perm, shared_perm);
     }
 
     child->bs = new_bs;
@@ -1344,23 +1743,46 @@ static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs)
         if (new_bs->quiesce_counter && child->role->drained_begin) {
             child->role->drained_begin(child);
         }
+
+        bdrv_get_cumulative_perm(new_bs, &perm, &shared_perm);
+        if (check_new_perm) {
+            bdrv_check_perm(new_bs, perm, shared_perm, &error_abort);
+        }
+        bdrv_set_perm(new_bs, perm, shared_perm);
+
+        if (child->role->attach) {
+            child->role->attach(child);
+        }
     }
 }
 
 BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
                                   const char *child_name,
                                   const BdrvChildRole *child_role,
-                                  void *opaque)
+                                  uint64_t perm, uint64_t shared_perm,
+                                  void *opaque, Error **errp)
 {
-    BdrvChild *child = g_new(BdrvChild, 1);
+    BdrvChild *child;
+    int ret;
+
+    ret = bdrv_check_update_perm(child_bs, perm, shared_perm, NULL, errp);
+    if (ret < 0) {
+        bdrv_abort_perm_update(child_bs);
+        return NULL;
+    }
+
+    child = g_new(BdrvChild, 1);
     *child = (BdrvChild) {
-        .bs     = NULL,
+        .bs             = NULL,
-        .name   = g_strdup(child_name),
+        .name           = g_strdup(child_name),
-        .role   = child_role,
+        .role           = child_role,
-        .opaque = opaque,
+        .perm           = perm,
+        .shared_perm    = shared_perm,
+        .opaque         = opaque,
     };
 
-    bdrv_replace_child(child, child_bs);
+    /* This performs the matching bdrv_set_perm() for the above check. */
+    bdrv_replace_child(child, child_bs, false);
 
     return child;
 }
@@ -1368,10 +1790,24 @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
 BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs,
                              BlockDriverState *child_bs,
                              const char *child_name,
-                             const BdrvChildRole *child_role)
+                             const BdrvChildRole *child_role,
+                             Error **errp)
 {
-    BdrvChild *child = bdrv_root_attach_child(child_bs, child_name, child_role,
+    BdrvChild *child;
-                                              parent_bs);
+    uint64_t perm, shared_perm;
+
+    bdrv_get_cumulative_perm(parent_bs, &perm, &shared_perm);
+
+    assert(parent_bs->drv);
+    parent_bs->drv->bdrv_child_perm(parent_bs, NULL, child_role,
+                                    perm, shared_perm, &perm, &shared_perm);
+
+    child = bdrv_root_attach_child(child_bs, child_name, child_role,
+                                   perm, shared_perm, parent_bs, errp);
+    if (child == NULL) {
+        return NULL;
+    }
+
     QLIST_INSERT_HEAD(&parent_bs->children, child, next);
     return child;
 }
@@ -1383,7 +1819,7 @@ static void bdrv_detach_child(BdrvChild *child)
         child->next.le_prev = NULL;
     }
 
-    bdrv_replace_child(child, NULL);
+    bdrv_replace_child(child, NULL, false);
 
     g_free(child->name);
     g_free(child);
@@ -1447,57 +1883,28 @@ static void bdrv_parent_cb_resize(BlockDriverState *bs)
  * Sets the backing file link of a BDS. A new reference is created; callers
  * which don't need their own reference any more must call bdrv_unref().
  */
-void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd)
+void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
+                         Error **errp)
 {
     if (backing_hd) {
         bdrv_ref(backing_hd);
     }
 
     if (bs->backing) {
-        assert(bs->backing_blocker);
-        bdrv_op_unblock_all(bs->backing->bs, bs->backing_blocker);
         bdrv_unref_child(bs, bs->backing);
-    } else if (backing_hd) {
-        error_setg(&bs->backing_blocker,
-                   "node is used as backing hd of '%s'",
-                   bdrv_get_device_or_node_name(bs));
     }
 
     if (!backing_hd) {
-        error_free(bs->backing_blocker);
-        bs->backing_blocker = NULL;
         bs->backing = NULL;
         goto out;
     }
-    bs->backing = bdrv_attach_child(bs, backing_hd, "backing", &child_backing);
-    bs->open_flags &= ~BDRV_O_NO_BACKING;
-    pstrcpy(bs->backing_file, sizeof(bs->backing_file), backing_hd->filename);
-    pstrcpy(bs->backing_format, sizeof(bs->backing_format),
-            backing_hd->drv ? backing_hd->drv->format_name : "");
 
-    bdrv_op_block_all(backing_hd, bs->backing_blocker);
+    bs->backing = bdrv_attach_child(bs, backing_hd, "backing", &child_backing,
-    /* Otherwise we won't be able to commit or stream */
+                                    errp);
-    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_COMMIT_TARGET,
+    if (!bs->backing) {
-                    bs->backing_blocker);
+        bdrv_unref(backing_hd);
-    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_STREAM,
+    }
-                    bs->backing_blocker);
+
-    /*
-     * We do backup in 3 ways:
-     * 1. drive backup
-     *    The target bs is new opened, and the source is top BDS
-     * 2. blockdev backup
-     *    Both the source and the target are top BDSes.
-     * 3. internal backup(used for block replication)
-     *    Both the source and the target are backing file
-     *
-     * In case 1 and 2, neither the source nor the target is the backing file.
-     * In case 3, we will block the top BDS, so there is only one block job
-     * for the top BDS and its backing chain.
-     */
-    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_SOURCE,
-                    bs->backing_blocker);
-    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_TARGET,
-                    bs->backing_blocker);
 out:
     bdrv_refresh_limits(bs, NULL);
 }
@@ -1580,8 +1987,12 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
 
     /* Hook up the backing file link; drop our reference, bs owns the
      * backing_hd reference now */
-    bdrv_set_backing_hd(bs, backing_hd);
+    bdrv_set_backing_hd(bs, backing_hd, &local_err);
     bdrv_unref(backing_hd);
+    if (local_err) {
+        ret = -EINVAL;
+        goto free_exit;
+    }
 
     qdict_del(parent_options, bdref_key);
 
@@ -1648,6 +2059,7 @@ BdrvChild *bdrv_open_child(const char *filename,
                            const BdrvChildRole *child_role,
                            bool allow_none, Error **errp)
 {
+    BdrvChild *c;
     BlockDriverState *bs;
 
     bs = bdrv_open_child_bs(filename, options, bdref_key, parent, child_role,
@@ -1656,7 +2068,13 @@ BdrvChild *bdrv_open_child(const char *filename,
         return NULL;
     }
 
-    return bdrv_attach_child(parent, bs, bdref_key, child_role);
+    c = bdrv_attach_child(parent, bs, bdref_key, child_role, errp);
+    if (!c) {
+        bdrv_unref(bs);
+        return NULL;
+    }
+
+    return c;
 }
 
 static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs,
@@ -1669,6 +2087,7 @@ static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs,
     int64_t total_size;
     QemuOpts *opts = NULL;
     BlockDriverState *bs_snapshot;
+    Error *local_err = NULL;
     int ret;
 
     /* if snapshot, we create a temporary backing file and open it
@@ -1718,7 +2137,12 @@ static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs,
      * call bdrv_unref() on it), so in order to be able to return one, we have
      * to increase bs_snapshot's refcount here */
     bdrv_ref(bs_snapshot);
-    bdrv_append(bs_snapshot, bs);
+    bdrv_append(bs_snapshot, bs, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto out;
+    }
 
     g_free(tmp_filename);
     return bs_snapshot;
@@ -1862,9 +2286,12 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
             goto fail;
         }
         if (file_bs != NULL) {
-            file = blk_new();
+            file = blk_new(BLK_PERM_CONSISTENT_READ, BLK_PERM_ALL);
-            blk_insert_bs(file, file_bs);
+            blk_insert_bs(file, file_bs, &local_err);
             bdrv_unref(file_bs);
+            if (local_err) {
+                goto fail;
+            }
 
             qdict_put(options, "file",
                       qstring_from_str(bdrv_get_node_name(file_bs)));
@@ -2405,7 +2832,7 @@ static void bdrv_close(BlockDriverState *bs)
         bs->drv->bdrv_close(bs);
         bs->drv = NULL;
 
-        bdrv_set_backing_hd(bs, NULL);
+        bdrv_set_backing_hd(bs, NULL, &error_abort);
 
         if (bs->file != NULL) {
             bdrv_unref_child(bs, bs->file);
@@ -2465,10 +2892,13 @@ static void change_parent_backing_link(BlockDriverState *from,
     BdrvChild *c, *next, *to_c;
 
     QLIST_FOREACH_SAFE(c, &from->parents, next_parent, next) {
+        if (c->role->stay_at_node) {
+            continue;
+        }
         if (c->role == &child_backing) {
-            /* @from is generally not allowed to be a backing file, except for
+            /* If @from is a backing file of @to, ignore the child to avoid
-             * when @to is the overlay. In that case, @from may not be replaced
+             * creating a loop. We only want to change the pointer of other
-             * by @to as @to's backing node. */
+             * parents. */
             QLIST_FOREACH(to_c, &to->children, next) {
                 if (to_c == c) {
                     break;
@@ -2479,9 +2909,10 @@ static void change_parent_backing_link(BlockDriverState *from,
             }
         }
 
-        assert(c->role != &child_backing);
         bdrv_ref(to);
-        bdrv_replace_child(c, to);
+        /* FIXME Are we sure that bdrv_replace_child() can't run into
+         * &error_abort because of permissions? */
+        bdrv_replace_child(c, to, true);
         bdrv_unref(from);
     }
 }
@@ -2502,19 +2933,25 @@ static void change_parent_backing_link(BlockDriverState *from,
  * parents of bs_top after bdrv_append() returns. If the caller needs to keep a
  * reference of its own, it must call bdrv_ref().
  */
-void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top)
+void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
+                 Error **errp)
 {
-    assert(!bdrv_requests_pending(bs_top));
+    Error *local_err = NULL;
-    assert(!bdrv_requests_pending(bs_new));
 
-    bdrv_ref(bs_top);
+    assert(!atomic_read(&bs_top->in_flight));
+    assert(!atomic_read(&bs_new->in_flight));
+
+    bdrv_set_backing_hd(bs_new, bs_top, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        goto out;
+    }
 
     change_parent_backing_link(bs_top, bs_new);
-    bdrv_set_backing_hd(bs_new, bs_top);
-    bdrv_unref(bs_top);
 
     /* bs_new is now referenced by its new parents, we don't need the
      * additional reference any more. */
+out:
     bdrv_unref(bs_new);
 }
 
@@ -2658,6 +3095,7 @@ int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top,
                            BlockDriverState *base, const char *backing_file_str)
 {
     BlockDriverState *new_top_bs = NULL;
+    Error *local_err = NULL;
     int ret = -EIO;
 
     if (!top->drv || !base->drv) {
@@ -2690,7 +3128,13 @@ int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top,
     if (ret) {
         goto exit;
     }
-    bdrv_set_backing_hd(new_top_bs, base);
+
+    bdrv_set_backing_hd(new_top_bs, base, &local_err);
+    if (local_err) {
+        ret = -EPERM;
+        error_report_err(local_err);
+        goto exit;
+    }
 
     ret = 0;
 exit:
@@ -2705,6 +3149,9 @@ int bdrv_truncate(BdrvChild *child, int64_t offset)
     BlockDriverState *bs = child->bs;
     BlockDriver *drv = bs->drv;
     int ret;
+
+    assert(child->perm & BLK_PERM_RESIZE);
+
     if (!drv)
         return -ENOMEDIUM;
     if (!drv->bdrv_truncate)

block/backup.c

@@ -618,14 +618,24 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
         goto error;
     }
 
-    job = block_job_create(job_id, &backup_job_driver, bs, speed,
+    /* job->common.len is fixed, so we can't allow resize */
-                           creation_flags, cb, opaque, errp);
+    job = block_job_create(job_id, &backup_job_driver, bs,
+                           BLK_PERM_CONSISTENT_READ,
+                           BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE |
+                           BLK_PERM_WRITE_UNCHANGED | BLK_PERM_GRAPH_MOD,
+                           speed, creation_flags, cb, opaque, errp);
     if (!job) {
         goto error;
     }
 
-    job->target = blk_new();
+    /* The target must match the source in size, so no resize here either */
-    blk_insert_bs(job->target, target);
+    job->target = blk_new(BLK_PERM_WRITE,
+                          BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE |
+                          BLK_PERM_WRITE_UNCHANGED | BLK_PERM_GRAPH_MOD);
+    ret = blk_insert_bs(job->target, target, errp);
+    if (ret < 0) {
+        goto error;
+    }
 
     job->on_source_error = on_source_error;
     job->on_target_error = on_target_error;
@@ -652,7 +662,9 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
         job->cluster_size = MAX(BACKUP_CLUSTER_SIZE_DEFAULT, bdi.cluster_size);
     }
 
-    block_job_add_bdrv(&job->common, target);
+    /* Required permissions are already taken with target's blk_new() */
+    block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL,
+                       &error_abort);
     job->common.len = len;
     block_job_txn_add_job(txn, &job->common);
 

block/blkdebug.c

@@ -734,6 +734,8 @@ static BlockDriver bdrv_blkdebug = {
     .bdrv_file_open         = blkdebug_open,
     .bdrv_close             = blkdebug_close,
     .bdrv_reopen_prepare    = blkdebug_reopen_prepare,
+    .bdrv_child_perm        = bdrv_filter_default_perms,
+
     .bdrv_getlength         = blkdebug_getlength,
     .bdrv_truncate          = blkdebug_truncate,
     .bdrv_refresh_filename  = blkdebug_refresh_filename,

block/blkreplay.c

@@ -137,6 +137,7 @@ static BlockDriver bdrv_blkreplay = {
 
     .bdrv_file_open         = blkreplay_open,
     .bdrv_close             = blkreplay_close,
+    .bdrv_child_perm        = bdrv_filter_default_perms,
     .bdrv_getlength         = blkreplay_getlength,
 
     .bdrv_co_preadv         = blkreplay_co_preadv,

block/blkverify.c

@@ -320,6 +320,7 @@ static BlockDriver bdrv_blkverify = {
     .bdrv_parse_filename              = blkverify_parse_filename,
     .bdrv_file_open                   = blkverify_open,
     .bdrv_close                       = blkverify_close,
+    .bdrv_child_perm                  = bdrv_filter_default_perms,
     .bdrv_getlength                   = blkverify_getlength,
     .bdrv_refresh_filename            = blkverify_refresh_filename,
 

block/block-backend.c

@@ -59,6 +59,9 @@ struct BlockBackend {
     bool iostatus_enabled;
     BlockDeviceIoStatus iostatus;
 
+    uint64_t perm;
+    uint64_t shared_perm;
+
     bool allow_write_beyond_eof;
 
     NotifierList remove_bs_notifiers, insert_bs_notifiers;
@@ -77,6 +80,7 @@ static const AIOCBInfo block_backend_aiocb_info = {
 
 static void drive_info_del(DriveInfo *dinfo);
 static BlockBackend *bdrv_first_blk(BlockDriverState *bs);
+static char *blk_get_attached_dev_id(BlockBackend *blk);
 
 /* All BlockBackends */
 static QTAILQ_HEAD(, BlockBackend) block_backends =
@@ -99,6 +103,25 @@ static void blk_root_drained_end(BdrvChild *child);
 static void blk_root_change_media(BdrvChild *child, bool load);
 static void blk_root_resize(BdrvChild *child);
 
+static char *blk_root_get_parent_desc(BdrvChild *child)
+{
+    BlockBackend *blk = child->opaque;
+    char *dev_id;
+
+    if (blk->name) {
+        return g_strdup(blk->name);
+    }
+
+    dev_id = blk_get_attached_dev_id(blk);
+    if (*dev_id) {
+        return dev_id;
+    } else {
+        /* TODO Callback into the BB owner for something more detailed */
+        g_free(dev_id);
+        return g_strdup("a block device");
+    }
+}
+
 static const char *blk_root_get_name(BdrvChild *child)
 {
     return blk_name(child->opaque);
@@ -110,6 +133,7 @@ static const BdrvChildRole child_root = {
     .change_media       = blk_root_change_media,
     .resize             = blk_root_resize,
     .get_name           = blk_root_get_name,
+    .get_parent_desc    = blk_root_get_parent_desc,
 
     .drained_begin      = blk_root_drained_begin,
     .drained_end        = blk_root_drained_end,
@@ -117,15 +141,23 @@ static const BdrvChildRole child_root = {
 
 /*
  * Create a new BlockBackend with a reference count of one.
- * Store an error through @errp on failure, unless it's null.
+ *
+ * @perm is a bitmasks of BLK_PERM_* constants which describes the permissions
+ * to request for a block driver node that is attached to this BlockBackend.
+ * @shared_perm is a bitmask which describes which permissions may be granted
+ * to other users of the attached node.
+ * Both sets of permissions can be changed later using blk_set_perm().
+ *
  * Return the new BlockBackend on success, null on failure.
  */
-BlockBackend *blk_new(void)
+BlockBackend *blk_new(uint64_t perm, uint64_t shared_perm)
 {
     BlockBackend *blk;
 
     blk = g_new0(BlockBackend, 1);
     blk->refcnt = 1;
+    blk->perm = perm;
+    blk->shared_perm = shared_perm;
     blk_set_enable_write_cache(blk, true);
 
     qemu_co_queue_init(&blk->public.throttled_reqs[0]);
@@ -155,15 +187,33 @@ BlockBackend *blk_new_open(const char *filename, const char *reference,
 {
     BlockBackend *blk;
     BlockDriverState *bs;
+    uint64_t perm;
 
-    blk = blk_new();
+    /* blk_new_open() is mainly used in .bdrv_create implementations and the
+     * tools where sharing isn't a concern because the BDS stays private, so we
+     * just request permission according to the flags.
+     *
+     * The exceptions are xen_disk and blockdev_init(); in these cases, the
+     * caller of blk_new_open() doesn't make use of the permissions, but they
+     * shouldn't hurt either. We can still share everything here because the
+     * guest devices will add their own blockers if they can't share. */
+    perm = BLK_PERM_CONSISTENT_READ;
+    if (flags & BDRV_O_RDWR) {
+        perm |= BLK_PERM_WRITE;
+    }
+    if (flags & BDRV_O_RESIZE) {
+        perm |= BLK_PERM_RESIZE;
+    }
+
+    blk = blk_new(perm, BLK_PERM_ALL);
     bs = bdrv_open(filename, reference, options, flags, errp);
     if (!bs) {
         blk_unref(blk);
         return NULL;
     }
 
-    blk->root = bdrv_root_attach_child(bs, "root", &child_root, blk);
+    blk->root = bdrv_root_attach_child(bs, "root", &child_root,
+                                       perm, BLK_PERM_ALL, blk, &error_abort);
 
     return blk;
 }
@@ -495,16 +545,49 @@ void blk_remove_bs(BlockBackend *blk)
 /*
  * Associates a new BlockDriverState with @blk.
  */
-void blk_insert_bs(BlockBackend *blk, BlockDriverState *bs)
+int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp)
 {
+    blk->root = bdrv_root_attach_child(bs, "root", &child_root,
+                                       blk->perm, blk->shared_perm, blk, errp);
+    if (blk->root == NULL) {
+        return -EPERM;
+    }
     bdrv_ref(bs);
-    blk->root = bdrv_root_attach_child(bs, "root", &child_root, blk);
 
     notifier_list_notify(&blk->insert_bs_notifiers, blk);
     if (blk->public.throttle_state) {
         throttle_timers_attach_aio_context(
             &blk->public.throttle_timers, bdrv_get_aio_context(bs));
     }
+
+    return 0;
+}
+
+/*
+ * Sets the permission bitmasks that the user of the BlockBackend needs.
+ */
+int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
+                 Error **errp)
+{
+    int ret;
+
+    if (blk->root) {
+        ret = bdrv_child_try_set_perm(blk->root, perm, shared_perm, errp);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+
+    blk->perm = perm;
+    blk->shared_perm = shared_perm;
+
+    return 0;
+}
+
+void blk_get_perm(BlockBackend *blk, uint64_t *perm, uint64_t *shared_perm)
+{
+    *perm = blk->perm;
+    *shared_perm = blk->shared_perm;
 }
 
 static int blk_do_attach_dev(BlockBackend *blk, void *dev)
@@ -553,6 +636,7 @@ void blk_detach_dev(BlockBackend *blk, void *dev)
     blk->dev_ops = NULL;
     blk->dev_opaque = NULL;
     blk->guest_block_size = 512;
+    blk_set_perm(blk, 0, BLK_PERM_ALL, &error_abort);
     blk_unref(blk);
 }
 
@@ -620,19 +704,29 @@ void blk_set_dev_ops(BlockBackend *blk, const BlockDevOps *ops,
 
 /*
  * Notify @blk's attached device model of media change.
- * If @load is true, notify of media load.
+ *
- * Else, notify of media eject.
+ * If @load is true, notify of media load. This action can fail, meaning that
+ * the medium cannot be loaded. @errp is set then.
+ *
+ * If @load is false, notify of media eject. This can never fail.
+ *
  * Also send DEVICE_TRAY_MOVED events as appropriate.
  */
-void blk_dev_change_media_cb(BlockBackend *blk, bool load)
+void blk_dev_change_media_cb(BlockBackend *blk, bool load, Error **errp)
 {
     if (blk->dev_ops && blk->dev_ops->change_media_cb) {
         bool tray_was_open, tray_is_open;
+        Error *local_err = NULL;
 
         assert(!blk->legacy_dev);
 
         tray_was_open = blk_dev_is_tray_open(blk);
-        blk->dev_ops->change_media_cb(blk->dev_opaque, load);
+        blk->dev_ops->change_media_cb(blk->dev_opaque, load, &local_err);
+        if (local_err) {
+            assert(load == true);
+            error_propagate(errp, local_err);
+            return;
+        }
         tray_is_open = blk_dev_is_tray_open(blk);
 
         if (tray_was_open != tray_is_open) {
@@ -646,7 +740,7 @@ void blk_dev_change_media_cb(BlockBackend *blk, bool load)
 
 static void blk_root_change_media(BdrvChild *child, bool load)
 {
-    blk_dev_change_media_cb(child->opaque, load);
+    blk_dev_change_media_cb(child->opaque, load, NULL);
 }
 
 /*

block/bochs.c

@@ -293,6 +293,7 @@ static BlockDriver bdrv_bochs = {
     .instance_size	= sizeof(BDRVBochsState),
     .bdrv_probe		= bochs_probe,
     .bdrv_open		= bochs_open,
+    .bdrv_child_perm     = bdrv_format_default_perms,
     .bdrv_refresh_limits = bochs_refresh_limits,
     .bdrv_co_preadv = bochs_co_preadv,
     .bdrv_close		= bochs_close,

block/cloop.c

@@ -290,6 +290,7 @@ static BlockDriver bdrv_cloop = {
     .instance_size  = sizeof(BDRVCloopState),
     .bdrv_probe     = cloop_probe,
     .bdrv_open      = cloop_open,
+    .bdrv_child_perm     = bdrv_format_default_perms,
     .bdrv_refresh_limits = cloop_refresh_limits,
     .bdrv_co_preadv = cloop_co_preadv,
     .bdrv_close     = cloop_close,

block/commit.c

@@ -36,6 +36,7 @@ typedef struct CommitBlockJob {
     BlockJob common;
     RateLimit limit;
     BlockDriverState *active;
+    BlockDriverState *commit_top_bs;
     BlockBackend *top;
     BlockBackend *base;
     BlockdevOnError on_error;
@@ -83,12 +84,23 @@ static void commit_complete(BlockJob *job, void *opaque)
     BlockDriverState *active = s->active;
     BlockDriverState *top = blk_bs(s->top);
     BlockDriverState *base = blk_bs(s->base);
-    BlockDriverState *overlay_bs = bdrv_find_overlay(active, top);
+    BlockDriverState *overlay_bs = bdrv_find_overlay(active, s->commit_top_bs);
     int ret = data->ret;
+    bool remove_commit_top_bs = false;
+
+    /* Remove base node parent that still uses BLK_PERM_WRITE/RESIZE before
+     * the normal backing chain can be restored. */
+    blk_unref(s->base);
 
     if (!block_job_is_cancelled(&s->common) && ret == 0) {
         /* success */
-        ret = bdrv_drop_intermediate(active, top, base, s->backing_file_str);
+        ret = bdrv_drop_intermediate(active, s->commit_top_bs, base,
+                                     s->backing_file_str);
+    } else if (overlay_bs) {
+        /* XXX Can (or should) we somehow keep 'consistent read' blocked even
+         * after the failed/cancelled commit job is gone? If we already wrote
+         * something to base, the intermediate images aren't valid any more. */
+        remove_commit_top_bs = true;
     }
 
     /* restore base open flags here if appropriate (e.g., change the base back
@@ -102,9 +114,15 @@ static void commit_complete(BlockJob *job, void *opaque)
     }
     g_free(s->backing_file_str);
     blk_unref(s->top);
-    blk_unref(s->base);
     block_job_completed(&s->common, ret);
     g_free(data);
+
+    /* If bdrv_drop_intermediate() didn't already do that, remove the commit
+     * filter driver from the backing chain. Do this as the final step so that
+     * the 'consistent read' permission can be granted.  */
+    if (remove_commit_top_bs) {
+        bdrv_set_backing_hd(overlay_bs, top, &error_abort);
+    }
 }
 
 static void coroutine_fn commit_run(void *opaque)
@@ -208,10 +226,38 @@ static const BlockJobDriver commit_job_driver = {
     .start         = commit_run,
 };
 
+static int coroutine_fn bdrv_commit_top_preadv(BlockDriverState *bs,
+    uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
+{
+    return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags);
+}
+
+static void bdrv_commit_top_close(BlockDriverState *bs)
+{
+}
+
+static void bdrv_commit_top_child_perm(BlockDriverState *bs, BdrvChild *c,
+                                       const BdrvChildRole *role,
+                                       uint64_t perm, uint64_t shared,
+                                       uint64_t *nperm, uint64_t *nshared)
+{
+    *nperm = 0;
+    *nshared = BLK_PERM_ALL;
+}
+
+/* Dummy node that provides consistent read to its users without requiring it
+ * from its backing file and that allows writes on the backing file chain. */
+static BlockDriver bdrv_commit_top = {
+    .format_name        = "commit_top",
+    .bdrv_co_preadv     = bdrv_commit_top_preadv,
+    .bdrv_close         = bdrv_commit_top_close,
+    .bdrv_child_perm    = bdrv_commit_top_child_perm,
+};
+
 void commit_start(const char *job_id, BlockDriverState *bs,
                   BlockDriverState *base, BlockDriverState *top, int64_t speed,
                   BlockdevOnError on_error, const char *backing_file_str,
-                  Error **errp)
+                  const char *filter_node_name, Error **errp)
 {
     CommitBlockJob *s;
     BlockReopenQueue *reopen_queue = NULL;
@@ -219,7 +265,9 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     int orig_base_flags;
     BlockDriverState *iter;
     BlockDriverState *overlay_bs;
+    BlockDriverState *commit_top_bs = NULL;
     Error *local_err = NULL;
+    int ret;
 
     assert(top != bs);
     if (top == base) {
@@ -234,8 +282,8 @@ void commit_start(const char *job_id, BlockDriverState *bs,
         return;
     }
 
-    s = block_job_create(job_id, &commit_job_driver, bs, speed,
+    s = block_job_create(job_id, &commit_job_driver, bs, 0, BLK_PERM_ALL,
-                         BLOCK_JOB_DEFAULT, NULL, NULL, errp);
+                         speed, BLOCK_JOB_DEFAULT, NULL, NULL, errp);
     if (!s) {
         return;
     }
@@ -256,30 +304,70 @@ void commit_start(const char *job_id, BlockDriverState *bs,
         bdrv_reopen_multiple(bdrv_get_aio_context(bs), reopen_queue, &local_err);
         if (local_err != NULL) {
             error_propagate(errp, local_err);
-            block_job_unref(&s->common);
+            goto fail;
-            return;
         }
     }
 
+    /* Insert commit_top block node above top, so we can block consistent read
+     * on the backing chain below it */
+    commit_top_bs = bdrv_new_open_driver(&bdrv_commit_top, filter_node_name, 0,
+                                         errp);
+    if (commit_top_bs == NULL) {
+        goto fail;
+    }
+
+    bdrv_set_backing_hd(commit_top_bs, top, &error_abort);
+    bdrv_set_backing_hd(overlay_bs, commit_top_bs, &error_abort);
+
+    s->commit_top_bs = commit_top_bs;
+    bdrv_unref(commit_top_bs);
 
     /* Block all nodes between top and base, because they will
      * disappear from the chain after this operation. */
     assert(bdrv_chain_contains(top, base));
-    for (iter = top; iter != backing_bs(base); iter = backing_bs(iter)) {
+    for (iter = top; iter != base; iter = backing_bs(iter)) {
-        block_job_add_bdrv(&s->common, iter);
+        /* XXX BLK_PERM_WRITE needs to be allowed so we don't block ourselves
+         * at s->base (if writes are blocked for a node, they are also blocked
+         * for its backing file). The other options would be a second filter
+         * driver above s->base. */
+        ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
+                                 BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
+                                 errp);
+        if (ret < 0) {
+            goto fail;
+        }
     }
+
+    ret = block_job_add_bdrv(&s->common, "base", base, 0, BLK_PERM_ALL, errp);
+    if (ret < 0) {
+        goto fail;
+    }
+
     /* overlay_bs must be blocked because it needs to be modified to
-     * update the backing image string, but if it's the root node then
+     * update the backing image string. */
-     * don't block it again */
+    ret = block_job_add_bdrv(&s->common, "overlay of top", overlay_bs,
-    if (bs != overlay_bs) {
+                             BLK_PERM_GRAPH_MOD, BLK_PERM_ALL, errp);
-        block_job_add_bdrv(&s->common, overlay_bs);
+    if (ret < 0) {
+        goto fail;
     }
 
-    s->base = blk_new();
+    s->base = blk_new(BLK_PERM_CONSISTENT_READ
-    blk_insert_bs(s->base, base);
+                      | BLK_PERM_WRITE
+                      | BLK_PERM_RESIZE,
+                      BLK_PERM_CONSISTENT_READ
+                      | BLK_PERM_GRAPH_MOD
+                      | BLK_PERM_WRITE_UNCHANGED);
+    ret = blk_insert_bs(s->base, base, errp);
+    if (ret < 0) {
+        goto fail;
+    }
 
-    s->top = blk_new();
+    /* Required permissions are already taken with block_job_add_bdrv() */
-    blk_insert_bs(s->top, top);
+    s->top = blk_new(0, BLK_PERM_ALL);
+    blk_insert_bs(s->top, top, errp);
+    if (ret < 0) {
+        goto fail;
+    }
 
     s->active = bs;
 
@@ -292,6 +380,19 @@ void commit_start(const char *job_id, BlockDriverState *bs,
 
     trace_commit_start(bs, base, top, s);
     block_job_start(&s->common);
+    return;
+
+fail:
+    if (s->base) {
+        blk_unref(s->base);
+    }
+    if (s->top) {
+        blk_unref(s->top);
+    }
+    if (commit_top_bs) {
+        bdrv_set_backing_hd(overlay_bs, top, &error_abort);
+    }
+    block_job_unref(&s->common);
 }
 
 
@@ -301,11 +402,14 @@ void commit_start(const char *job_id, BlockDriverState *bs,
 int bdrv_commit(BlockDriverState *bs)
 {
     BlockBackend *src, *backing;
+    BlockDriverState *backing_file_bs = NULL;
+    BlockDriverState *commit_top_bs = NULL;
     BlockDriver *drv = bs->drv;
     int64_t sector, total_sectors, length, backing_length;
     int n, ro, open_flags;
     int ret = 0;
     uint8_t *buf = NULL;
+    Error *local_err = NULL;
 
     if (!drv)
         return -ENOMEDIUM;
@@ -328,11 +432,33 @@ int bdrv_commit(BlockDriverState *bs)
         }
     }
 
-    src = blk_new();
+    src = blk_new(BLK_PERM_CONSISTENT_READ, BLK_PERM_ALL);
-    blk_insert_bs(src, bs);
+    backing = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
 
-    backing = blk_new();
+    ret = blk_insert_bs(src, bs, &local_err);
-    blk_insert_bs(backing, bs->backing->bs);
+    if (ret < 0) {
+        error_report_err(local_err);
+        goto ro_cleanup;
+    }
+
+    /* Insert commit_top block node above backing, so we can write to it */
+    backing_file_bs = backing_bs(bs);
+
+    commit_top_bs = bdrv_new_open_driver(&bdrv_commit_top, NULL, BDRV_O_RDWR,
+                                         &local_err);
+    if (commit_top_bs == NULL) {
+        error_report_err(local_err);
+        goto ro_cleanup;
+    }
+
+    bdrv_set_backing_hd(commit_top_bs, backing_file_bs, &error_abort);
+    bdrv_set_backing_hd(bs, commit_top_bs, &error_abort);
+
+    ret = blk_insert_bs(backing, backing_file_bs, &local_err);
+    if (ret < 0) {
+        error_report_err(local_err);
+        goto ro_cleanup;
+    }
 
     length = blk_getlength(src);
     if (length < 0) {
@@ -404,8 +530,12 @@ int bdrv_commit(BlockDriverState *bs)
 ro_cleanup:
     qemu_vfree(buf);
 
-    blk_unref(src);
     blk_unref(backing);
+    if (backing_file_bs) {
+        bdrv_set_backing_hd(bs, backing_file_bs, &error_abort);
+    }
+    bdrv_unref(commit_top_bs);
+    blk_unref(src);
 
     if (ro) {
         /* ignoring error return here */

block/crypto.c

@@ -628,6 +628,7 @@ BlockDriver bdrv_crypto_luks = {
     .bdrv_probe         = block_crypto_probe_luks,
     .bdrv_open          = block_crypto_open_luks,
     .bdrv_close         = block_crypto_close,
+    .bdrv_child_perm    = bdrv_format_default_perms,
     .bdrv_create        = block_crypto_create_luks,
     .bdrv_truncate      = block_crypto_truncate,
     .create_opts        = &block_crypto_create_opts_luks,

block/dmg.c

@@ -697,6 +697,7 @@ static BlockDriver bdrv_dmg = {
     .bdrv_probe     = dmg_probe,
     .bdrv_open      = dmg_open,
     .bdrv_refresh_limits = dmg_refresh_limits,
+    .bdrv_child_perm     = bdrv_format_default_perms,
     .bdrv_co_preadv = dmg_co_preadv,
     .bdrv_close     = dmg_close,
 };

block/io.c

@@ -925,9 +925,11 @@ bdrv_driver_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
     return drv->bdrv_co_pwritev_compressed(bs, offset, bytes, qiov);
 }
 
-static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
+static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child,
         int64_t offset, unsigned int bytes, QEMUIOVector *qiov)
 {
+    BlockDriverState *bs = child->bs;
+
     /* Perform I/O through a temporary buffer so that users who scribble over
      * their read buffer while the operation is in progress do not end up
      * modifying the image file.  This is critical for zero-copy guest I/O
@@ -943,6 +945,8 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
     size_t skip_bytes;
     int ret;
 
+    assert(child->perm & (BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE));
+
     /* Cover entire cluster so no additional backing file I/O is required when
      * allocating cluster in the image file.
      */
@@ -1001,10 +1005,11 @@ err:
  * handles copy on read, zeroing after EOF, and fragmentation of large
  * reads; any other features must be implemented by the caller.
  */
-static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
+static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child,
     BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
     int64_t align, QEMUIOVector *qiov, int flags)
 {
+    BlockDriverState *bs = child->bs;
     int64_t total_bytes, max_bytes;
     int ret = 0;
     uint64_t bytes_remaining = bytes;
@@ -1050,7 +1055,7 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
         }
 
         if (!ret || pnum != nb_sectors) {
-            ret = bdrv_co_do_copy_on_readv(bs, offset, bytes, qiov);
+            ret = bdrv_co_do_copy_on_readv(child, offset, bytes, qiov);
             goto out;
         }
     }
@@ -1158,7 +1163,7 @@ int coroutine_fn bdrv_co_preadv(BdrvChild *child,
     }
 
     tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_READ);
-    ret = bdrv_aligned_preadv(bs, &req, offset, bytes, align,
+    ret = bdrv_aligned_preadv(child, &req, offset, bytes, align,
                               use_local_qiov ? &local_qiov : qiov,
                               flags);
     tracked_request_end(&req);
@@ -1306,10 +1311,11 @@ fail:
  * Forwards an already correctly aligned write request to the BlockDriver,
  * after possibly fragmenting it.
  */
-static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
+static int coroutine_fn bdrv_aligned_pwritev(BdrvChild *child,
     BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
     int64_t align, QEMUIOVector *qiov, int flags)
 {
+    BlockDriverState *bs = child->bs;
     BlockDriver *drv = bs->drv;
     bool waited;
     int ret;
@@ -1332,6 +1338,8 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
     assert(!waited || !req->serialising);
     assert(req->overlap_offset <= offset);
     assert(offset + bytes <= req->overlap_offset + req->overlap_bytes);
+    assert(child->perm & BLK_PERM_WRITE);
+    assert(end_sector <= bs->total_sectors || child->perm & BLK_PERM_RESIZE);
 
     ret = notifier_with_return_list_notify(&bs->before_write_notifiers, req);
 
@@ -1397,12 +1405,13 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
     return ret;
 }
 
-static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
+static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child,
                                                 int64_t offset,
                                                 unsigned int bytes,
                                                 BdrvRequestFlags flags,
                                                 BdrvTrackedRequest *req)
 {
+    BlockDriverState *bs = child->bs;
     uint8_t *buf = NULL;
     QEMUIOVector local_qiov;
     struct iovec iov;
@@ -1430,7 +1439,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
         mark_request_serialising(req, align);
         wait_serialising_requests(req);
         bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_HEAD);
-        ret = bdrv_aligned_preadv(bs, req, offset & ~(align - 1), align,
+        ret = bdrv_aligned_preadv(child, req, offset & ~(align - 1), align,
                                   align, &local_qiov, 0);
         if (ret < 0) {
             goto fail;
@@ -1438,7 +1447,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
         bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_AFTER_HEAD);
 
         memset(buf + head_padding_bytes, 0, zero_bytes);
-        ret = bdrv_aligned_pwritev(bs, req, offset & ~(align - 1), align,
+        ret = bdrv_aligned_pwritev(child, req, offset & ~(align - 1), align,
                                    align, &local_qiov,
                                    flags & ~BDRV_REQ_ZERO_WRITE);
         if (ret < 0) {
@@ -1452,7 +1461,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
     if (bytes >= align) {
         /* Write the aligned part in the middle. */
         uint64_t aligned_bytes = bytes & ~(align - 1);
-        ret = bdrv_aligned_pwritev(bs, req, offset, aligned_bytes, align,
+        ret = bdrv_aligned_pwritev(child, req, offset, aligned_bytes, align,
                                    NULL, flags);
         if (ret < 0) {
             goto fail;
@@ -1468,7 +1477,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
         mark_request_serialising(req, align);
         wait_serialising_requests(req);
         bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_TAIL);
-        ret = bdrv_aligned_preadv(bs, req, offset, align,
+        ret = bdrv_aligned_preadv(child, req, offset, align,
                                   align, &local_qiov, 0);
         if (ret < 0) {
             goto fail;
@@ -1476,7 +1485,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
         bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_AFTER_TAIL);
 
         memset(buf, 0, bytes);
-        ret = bdrv_aligned_pwritev(bs, req, offset, align, align,
+        ret = bdrv_aligned_pwritev(child, req, offset, align, align,
                                    &local_qiov, flags & ~BDRV_REQ_ZERO_WRITE);
     }
 fail:
@@ -1523,7 +1532,7 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
     tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_WRITE);
 
     if (!qiov) {
-        ret = bdrv_co_do_zero_pwritev(bs, offset, bytes, flags, &req);
+        ret = bdrv_co_do_zero_pwritev(child, offset, bytes, flags, &req);
         goto out;
     }
 
@@ -1542,7 +1551,7 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
         qemu_iovec_init_external(&head_qiov, &head_iov, 1);
 
         bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_HEAD);
-        ret = bdrv_aligned_preadv(bs, &req, offset & ~(align - 1), align,
+        ret = bdrv_aligned_preadv(child, &req, offset & ~(align - 1), align,
                                   align, &head_qiov, 0);
         if (ret < 0) {
             goto fail;
@@ -1584,8 +1593,8 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
         qemu_iovec_init_external(&tail_qiov, &tail_iov, 1);
 
         bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_TAIL);
-        ret = bdrv_aligned_preadv(bs, &req, (offset + bytes) & ~(align - 1), align,
+        ret = bdrv_aligned_preadv(child, &req, (offset + bytes) & ~(align - 1),
-                                  align, &tail_qiov, 0);
+                                  align, align, &tail_qiov, 0);
         if (ret < 0) {
             goto fail;
         }
@@ -1603,7 +1612,7 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
         bytes = ROUND_UP(bytes, align);
     }
 
-    ret = bdrv_aligned_pwritev(bs, &req, offset, bytes, align,
+    ret = bdrv_aligned_pwritev(child, &req, offset, bytes, align,
                                use_local_qiov ? &local_qiov : qiov,
                                flags);
 

block/mirror.c

@@ -38,7 +38,10 @@ typedef struct MirrorBlockJob {
     BlockJob common;
     RateLimit limit;
     BlockBackend *target;
+    BlockDriverState *mirror_top_bs;
+    BlockDriverState *source;
     BlockDriverState *base;
+
     /* The name of the graph node to replace */
     char *replaces;
     /* The BDS to replace */
@@ -327,7 +330,7 @@ static void mirror_do_zero_or_discard(MirrorBlockJob *s,
 
 static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
 {
-    BlockDriverState *source = blk_bs(s->common.blk);
+    BlockDriverState *source = s->source;
     int64_t sector_num, first_chunk;
     uint64_t delay_ns = 0;
     /* At least the first dirty chunk is mirrored in one iteration. */
@@ -497,12 +500,30 @@ static void mirror_exit(BlockJob *job, void *opaque)
     MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
     MirrorExitData *data = opaque;
     AioContext *replace_aio_context = NULL;
-    BlockDriverState *src = blk_bs(s->common.blk);
+    BlockDriverState *src = s->source;
     BlockDriverState *target_bs = blk_bs(s->target);
+    BlockDriverState *mirror_top_bs = s->mirror_top_bs;
+    Error *local_err = NULL;
 
     /* Make sure that the source BDS doesn't go away before we called
      * block_job_completed(). */
     bdrv_ref(src);
+    bdrv_ref(mirror_top_bs);
+
+    /* We don't access the source any more. Dropping any WRITE/RESIZE is
+     * required before it could become a backing file of target_bs. */
+    bdrv_child_try_set_perm(mirror_top_bs->backing, 0, BLK_PERM_ALL,
+                            &error_abort);
+    if (s->backing_mode == MIRROR_SOURCE_BACKING_CHAIN) {
+        BlockDriverState *backing = s->is_none_mode ? src : s->base;
+        if (backing_bs(target_bs) != backing) {
+            bdrv_set_backing_hd(target_bs, backing, &local_err);
+            if (local_err) {
+                error_report_err(local_err);
+                data->ret = -EPERM;
+            }
+        }
+    }
 
     if (s->to_replace) {
         replace_aio_context = bdrv_get_aio_context(s->to_replace);
@@ -524,10 +545,6 @@ static void mirror_exit(BlockJob *job, void *opaque)
         bdrv_drained_begin(target_bs);
         bdrv_replace_in_backing_chain(to_replace, target_bs);
         bdrv_drained_end(target_bs);
-
-        /* We just changed the BDS the job BB refers to */
-        blk_remove_bs(job->blk);
-        blk_insert_bs(job->blk, src);
     }
     if (s->to_replace) {
         bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
@@ -540,9 +557,26 @@ static void mirror_exit(BlockJob *job, void *opaque)
     g_free(s->replaces);
     blk_unref(s->target);
     s->target = NULL;
+
+    /* Remove the mirror filter driver from the graph. Before this, get rid of
+     * the blockers on the intermediate nodes so that the resulting state is
+     * valid. */
+    block_job_remove_all_bdrv(job);
+    bdrv_replace_in_backing_chain(mirror_top_bs, backing_bs(mirror_top_bs));
+
+    /* We just changed the BDS the job BB refers to (with either or both of the
+     * bdrv_replace_in_backing_chain() calls), so switch the BB back so the
+     * cleanup does the right thing. We don't need any permissions any more
+     * now. */
+    blk_remove_bs(job->blk);
+    blk_set_perm(job->blk, 0, BLK_PERM_ALL, &error_abort);
+    blk_insert_bs(job->blk, mirror_top_bs, &error_abort);
+
     block_job_completed(&s->common, data->ret);
+
     g_free(data);
     bdrv_drained_end(src);
+    bdrv_unref(mirror_top_bs);
     bdrv_unref(src);
 }
 
@@ -562,7 +596,7 @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s)
 {
     int64_t sector_num, end;
     BlockDriverState *base = s->base;
-    BlockDriverState *bs = blk_bs(s->common.blk);
+    BlockDriverState *bs = s->source;
     BlockDriverState *target_bs = blk_bs(s->target);
     int ret, n;
 
@@ -644,7 +678,7 @@ static void coroutine_fn mirror_run(void *opaque)
 {
     MirrorBlockJob *s = opaque;
     MirrorExitData *data;
-    BlockDriverState *bs = blk_bs(s->common.blk);
+    BlockDriverState *bs = s->source;
     BlockDriverState *target_bs = blk_bs(s->target);
     bool need_drain = true;
     int64_t length;
@@ -876,9 +910,8 @@ static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
 static void mirror_complete(BlockJob *job, Error **errp)
 {
     MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
-    BlockDriverState *src, *target;
+    BlockDriverState *target;
 
-    src = blk_bs(job->blk);
     target = blk_bs(s->target);
 
     if (!s->synced) {
@@ -910,6 +943,10 @@ static void mirror_complete(BlockJob *job, Error **errp)
         replace_aio_context = bdrv_get_aio_context(s->to_replace);
         aio_context_acquire(replace_aio_context);
 
+        /* TODO Translate this into permission system. Current definition of
+         * GRAPH_MOD would require to request it for the parents; they might
+         * not even be BlockDriverStates, however, so a BdrvChild can't address
+         * them. May need redefinition of GRAPH_MOD. */
         error_setg(&s->replace_blocker,
                    "block device is in use by block-job-complete");
         bdrv_op_block_all(s->to_replace, s->replace_blocker);
@@ -918,13 +955,6 @@ static void mirror_complete(BlockJob *job, Error **errp)
         aio_context_release(replace_aio_context);
     }
 
-    if (s->backing_mode == MIRROR_SOURCE_BACKING_CHAIN) {
-        BlockDriverState *backing = s->is_none_mode ? src : s->base;
-        if (backing_bs(target) != backing) {
-            bdrv_set_backing_hd(target, backing);
-        }
-    }
-
     s->should_complete = true;
     block_job_enter(&s->common);
 }
@@ -980,6 +1010,77 @@ static const BlockJobDriver commit_active_job_driver = {
     .drain                  = mirror_drain,
 };
 
+static int coroutine_fn bdrv_mirror_top_preadv(BlockDriverState *bs,
+    uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
+{
+    return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags);
+}
+
+static int coroutine_fn bdrv_mirror_top_pwritev(BlockDriverState *bs,
+    uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
+{
+    return bdrv_co_pwritev(bs->backing, offset, bytes, qiov, flags);
+}
+
+static int coroutine_fn bdrv_mirror_top_flush(BlockDriverState *bs)
+{
+    return bdrv_co_flush(bs->backing->bs);
+}
+
+static int64_t coroutine_fn bdrv_mirror_top_get_block_status(
+    BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum,
+    BlockDriverState **file)
+{
+    *pnum = nb_sectors;
+    *file = bs->backing->bs;
+    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID | BDRV_BLOCK_DATA |
+           (sector_num << BDRV_SECTOR_BITS);
+}
+
+static int coroutine_fn bdrv_mirror_top_pwrite_zeroes(BlockDriverState *bs,
+    int64_t offset, int count, BdrvRequestFlags flags)
+{
+    return bdrv_co_pwrite_zeroes(bs->backing, offset, count, flags);
+}
+
+static int coroutine_fn bdrv_mirror_top_pdiscard(BlockDriverState *bs,
+    int64_t offset, int count)
+{
+    return bdrv_co_pdiscard(bs->backing->bs, offset, count);
+}
+
+static void bdrv_mirror_top_close(BlockDriverState *bs)
+{
+}
+
+static void bdrv_mirror_top_child_perm(BlockDriverState *bs, BdrvChild *c,
+                                       const BdrvChildRole *role,
+                                       uint64_t perm, uint64_t shared,
+                                       uint64_t *nperm, uint64_t *nshared)
+{
+    /* Must be able to forward guest writes to the real image */
+    *nperm = 0;
+    if (perm & BLK_PERM_WRITE) {
+        *nperm |= BLK_PERM_WRITE;
+    }
+
+    *nshared = BLK_PERM_ALL;
+}
+
+/* Dummy node that provides consistent read to its users without requiring it
+ * from its backing file and that allows writes on the backing file chain. */
+static BlockDriver bdrv_mirror_top = {
+    .format_name                = "mirror_top",
+    .bdrv_co_preadv             = bdrv_mirror_top_preadv,
+    .bdrv_co_pwritev            = bdrv_mirror_top_pwritev,
+    .bdrv_co_pwrite_zeroes      = bdrv_mirror_top_pwrite_zeroes,
+    .bdrv_co_pdiscard           = bdrv_mirror_top_pdiscard,
+    .bdrv_co_flush              = bdrv_mirror_top_flush,
+    .bdrv_co_get_block_status   = bdrv_mirror_top_get_block_status,
+    .bdrv_close                 = bdrv_mirror_top_close,
+    .bdrv_child_perm            = bdrv_mirror_top_child_perm,
+};
+
 static void mirror_start_job(const char *job_id, BlockDriverState *bs,
                              int creation_flags, BlockDriverState *target,
                              const char *replaces, int64_t speed,
@@ -992,9 +1093,14 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
                              void *opaque, Error **errp,
                              const BlockJobDriver *driver,
                              bool is_none_mode, BlockDriverState *base,
-                             bool auto_complete)
+                             bool auto_complete, const char *filter_node_name)
 {
     MirrorBlockJob *s;
+    BlockDriverState *mirror_top_bs;
+    bool target_graph_mod;
+    bool target_is_backing;
+    Error *local_err = NULL;
+    int ret;
 
     if (granularity == 0) {
         granularity = bdrv_get_default_bitmap_granularity(target);
@@ -1011,14 +1117,62 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
         buf_size = DEFAULT_MIRROR_BUF_SIZE;
     }
 
-    s = block_job_create(job_id, driver, bs, speed, creation_flags,
+    /* In the case of active commit, add dummy driver to provide consistent
-                         cb, opaque, errp);
+     * reads on the top, while disabling it in the intermediate nodes, and make
-    if (!s) {
+     * the backing chain writable. */
+    mirror_top_bs = bdrv_new_open_driver(&bdrv_mirror_top, filter_node_name,
+                                         BDRV_O_RDWR, errp);
+    if (mirror_top_bs == NULL) {
+        return;
+    }
+    mirror_top_bs->total_sectors = bs->total_sectors;
+
+    /* bdrv_append takes ownership of the mirror_top_bs reference, need to keep
+     * it alive until block_job_create() even if bs has no parent. */
+    bdrv_ref(mirror_top_bs);
+    bdrv_drained_begin(bs);
+    bdrv_append(mirror_top_bs, bs, &local_err);
+    bdrv_drained_end(bs);
+
+    if (local_err) {
+        bdrv_unref(mirror_top_bs);
+        error_propagate(errp, local_err);
         return;
     }
 
-    s->target = blk_new();
+    /* Make sure that the source is not resized while the job is running */
-    blk_insert_bs(s->target, target);
+    s = block_job_create(job_id, driver, mirror_top_bs,
+                         BLK_PERM_CONSISTENT_READ,
+                         BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+                         BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD, speed,
+                         creation_flags, cb, opaque, errp);
+    bdrv_unref(mirror_top_bs);
+    if (!s) {
+        goto fail;
+    }
+    s->source = bs;
+    s->mirror_top_bs = mirror_top_bs;
+
+    /* No resize for the target either; while the mirror is still running, a
+     * consistent read isn't necessarily possible. We could possibly allow
+     * writes and graph modifications, though it would likely defeat the
+     * purpose of a mirror, so leave them blocked for now.
+     *
+     * In the case of active commit, things look a bit different, though,
+     * because the target is an already populated backing file in active use.
+     * We can allow anything except resize there.*/
+    target_is_backing = bdrv_chain_contains(bs, target);
+    target_graph_mod = (backing_mode != MIRROR_LEAVE_BACKING_CHAIN);
+    s->target = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE |
+                        (target_graph_mod ? BLK_PERM_GRAPH_MOD : 0),
+                        BLK_PERM_WRITE_UNCHANGED |
+                        (target_is_backing ? BLK_PERM_CONSISTENT_READ |
+                                             BLK_PERM_WRITE |
+                                             BLK_PERM_GRAPH_MOD : 0));
+    ret = blk_insert_bs(s->target, target, errp);
+    if (ret < 0) {
+        goto fail;
+    }
 
     s->replaces = g_strdup(replaces);
     s->on_source_error = on_source_error;
@@ -1041,18 +1195,40 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
         return;
     }
 
-    block_job_add_bdrv(&s->common, target);
+    /* Required permissions are already taken with blk_new() */
+    block_job_add_bdrv(&s->common, "target", target, 0, BLK_PERM_ALL,
+                       &error_abort);
+
     /* In commit_active_start() all intermediate nodes disappear, so
      * any jobs in them must be blocked */
-    if (bdrv_chain_contains(bs, target)) {
+    if (target_is_backing) {
         BlockDriverState *iter;
         for (iter = backing_bs(bs); iter != target; iter = backing_bs(iter)) {
-            block_job_add_bdrv(&s->common, iter);
+            /* XXX BLK_PERM_WRITE needs to be allowed so we don't block
+             * ourselves at s->base (if writes are blocked for a node, they are
+             * also blocked for its backing file). The other options would be a
+             * second filter driver above s->base (== target). */
+            ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
+                                     BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
+                                     errp);
+            if (ret < 0) {
+                goto fail;
+            }
         }
     }
 
     trace_mirror_start(bs, s, opaque);
     block_job_start(&s->common);
+    return;
+
+fail:
+    if (s) {
+        g_free(s->replaces);
+        blk_unref(s->target);
+        block_job_unref(&s->common);
+    }
+
+    bdrv_replace_in_backing_chain(mirror_top_bs, backing_bs(mirror_top_bs));
 }
 
 void mirror_start(const char *job_id, BlockDriverState *bs,
@@ -1061,7 +1237,7 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
                   MirrorSyncMode mode, BlockMirrorBackingMode backing_mode,
                   BlockdevOnError on_source_error,
                   BlockdevOnError on_target_error,
-                  bool unmap, Error **errp)
+                  bool unmap, const char *filter_node_name, Error **errp)
 {
     bool is_none_mode;
     BlockDriverState *base;
@@ -1075,12 +1251,14 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
     mirror_start_job(job_id, bs, BLOCK_JOB_DEFAULT, target, replaces,
                      speed, granularity, buf_size, backing_mode,
                      on_source_error, on_target_error, unmap, NULL, NULL, errp,
-                     &mirror_job_driver, is_none_mode, base, false);
+                     &mirror_job_driver, is_none_mode, base, false,
+                     filter_node_name);
 }
 
 void commit_active_start(const char *job_id, BlockDriverState *bs,
                          BlockDriverState *base, int creation_flags,
                          int64_t speed, BlockdevOnError on_error,
+                         const char *filter_node_name,
                          BlockCompletionFunc *cb, void *opaque, Error **errp,
                          bool auto_complete)
 {
@@ -1096,7 +1274,8 @@ void commit_active_start(const char *job_id, BlockDriverState *bs,
     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,
-                     &commit_active_job_driver, false, base, auto_complete);
+                     &commit_active_job_driver, false, base, auto_complete,
+                     filter_node_name);
     if (local_err) {
         error_propagate(errp, local_err);
         goto error_restore_flags;

block/parallels.c

@@ -488,7 +488,8 @@ static int parallels_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     file = blk_new_open(filename, NULL, NULL,
-                        BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                        BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                        &local_err);
     if (file == NULL) {
         error_propagate(errp, local_err);
         return -EIO;
@@ -762,6 +763,7 @@ static BlockDriver bdrv_parallels = {
     .bdrv_probe		= parallels_probe,
     .bdrv_open		= parallels_open,
     .bdrv_close		= parallels_close,
+    .bdrv_child_perm          = bdrv_format_default_perms,
     .bdrv_co_get_block_status = parallels_co_get_block_status,
     .bdrv_has_zero_init       = bdrv_has_zero_init_1,
     .bdrv_co_flush_to_os      = parallels_co_flush_to_os,

block/qcow.c

@@ -823,7 +823,8 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     qcow_blk = blk_new_open(filename, NULL, NULL,
-                            BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                            BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                            &local_err);
     if (qcow_blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -1052,6 +1053,7 @@ static BlockDriver bdrv_qcow = {
     .bdrv_probe		= qcow_probe,
     .bdrv_open		= qcow_open,
     .bdrv_close		= qcow_close,
+    .bdrv_child_perm        = bdrv_format_default_perms,
     .bdrv_reopen_prepare    = qcow_reopen_prepare,
     .bdrv_create            = qcow_create,
     .bdrv_has_zero_init     = bdrv_has_zero_init_1,

block/qcow2.c

@@ -2202,7 +2202,8 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         return -EIO;
@@ -2266,7 +2267,8 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     options = qdict_new();
     qdict_put(options, "driver", qstring_from_str("qcow2"));
     blk = blk_new_open(filename, NULL, options,
-                       BDRV_O_RDWR | BDRV_O_NO_FLUSH, &local_err);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_NO_FLUSH,
+                       &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -3113,6 +3115,7 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
     uint64_t cluster_size = s->cluster_size;
     bool encrypt;
     int refcount_bits = s->refcount_bits;
+    Error *local_err = NULL;
     int ret;
     QemuOptDesc *desc = opts->list->desc;
     Qcow2AmendHelperCBInfo helper_cb_info;
@@ -3262,11 +3265,16 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
     }
 
     if (new_size) {
-        BlockBackend *blk = blk_new();
+        BlockBackend *blk = blk_new(BLK_PERM_RESIZE, BLK_PERM_ALL);
-        blk_insert_bs(blk, bs);
+        ret = blk_insert_bs(blk, bs, &local_err);
+        if (ret < 0) {
+            error_report_err(local_err);
+            blk_unref(blk);
+            return ret;
+        }
+
         ret = blk_truncate(blk, new_size);
         blk_unref(blk);
-
         if (ret < 0) {
             return ret;
         }
@@ -3403,6 +3411,7 @@ BlockDriver bdrv_qcow2 = {
     .bdrv_reopen_commit   = qcow2_reopen_commit,
     .bdrv_reopen_abort    = qcow2_reopen_abort,
     .bdrv_join_options    = qcow2_join_options,
+    .bdrv_child_perm      = bdrv_format_default_perms,
     .bdrv_create        = qcow2_create,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
     .bdrv_co_get_block_status = qcow2_co_get_block_status,

block/qed.c

@@ -625,7 +625,8 @@ static int qed_create(const char *filename, uint32_t cluster_size,
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         return -EIO;
@@ -1704,6 +1705,7 @@ static BlockDriver bdrv_qed = {
     .bdrv_open                = bdrv_qed_open,
     .bdrv_close               = bdrv_qed_close,
     .bdrv_reopen_prepare      = bdrv_qed_reopen_prepare,
+    .bdrv_child_perm          = bdrv_format_default_perms,
     .bdrv_create              = bdrv_qed_create,
     .bdrv_has_zero_init       = bdrv_has_zero_init_1,
     .bdrv_co_get_block_status = bdrv_qed_co_get_block_status,

block/quorum.c

@@ -1032,10 +1032,17 @@ static void quorum_add_child(BlockDriverState *bs, BlockDriverState *child_bs,
 
     /* We can safely add the child now */
     bdrv_ref(child_bs);
-    child = bdrv_attach_child(bs, child_bs, indexstr, &child_format);
+
+    child = bdrv_attach_child(bs, child_bs, indexstr, &child_format, errp);
+    if (child == NULL) {
+        s->next_child_index--;
+        bdrv_unref(child_bs);
+        goto out;
+    }
     s->children = g_renew(BdrvChild *, s->children, s->num_children + 1);
     s->children[s->num_children++] = child;
 
+out:
     bdrv_drained_end(bs);
 }
 
@@ -1126,6 +1133,8 @@ static BlockDriver bdrv_quorum = {
     .bdrv_add_child                     = quorum_add_child,
     .bdrv_del_child                     = quorum_del_child,
 
+    .bdrv_child_perm                    = bdrv_filter_default_perms,
+
     .is_filter                          = true,
     .bdrv_recurse_is_first_non_filter   = quorum_recurse_is_first_non_filter,
 };

block/raw-format.c

@@ -467,6 +467,7 @@ BlockDriver bdrv_raw = {
     .bdrv_reopen_abort    = &raw_reopen_abort,
     .bdrv_open            = &raw_open,
     .bdrv_close           = &raw_close,
+    .bdrv_child_perm      = bdrv_filter_default_perms,
     .bdrv_create          = &raw_create,
     .bdrv_co_preadv       = &raw_co_preadv,
     .bdrv_co_pwritev      = &raw_co_pwritev,

block/replication.c

@@ -644,7 +644,7 @@ static void replication_stop(ReplicationState *rs, bool failover, Error **errp)
         s->replication_state = BLOCK_REPLICATION_FAILOVER;
         commit_active_start(NULL, s->active_disk->bs, s->secondary_disk->bs,
                             BLOCK_JOB_INTERNAL, 0, BLOCKDEV_ON_ERROR_REPORT,
-                            replication_done, bs, errp, true);
+                            NULL, replication_done, bs, errp, true);
         break;
     default:
         aio_context_release(aio_context);
@@ -660,6 +660,7 @@ BlockDriver bdrv_replication = {
 
     .bdrv_open                  = replication_open,
     .bdrv_close                 = replication_close,
+    .bdrv_child_perm            = bdrv_filter_default_perms,
 
     .bdrv_getlength             = replication_getlength,
     .bdrv_co_readv              = replication_co_readv,

block/sheepdog.c

@@ -1609,7 +1609,7 @@ static int sd_prealloc(const char *filename, Error **errp)
     int ret;
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_PROTOCOL, errp);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp);
     if (blk == NULL) {
         ret = -EIO;
         goto out_with_err_set;

block/stream.c

@@ -68,6 +68,7 @@ static void stream_complete(BlockJob *job, void *opaque)
     StreamCompleteData *data = opaque;
     BlockDriverState *bs = blk_bs(job->blk);
     BlockDriverState *base = s->base;
+    Error *local_err = NULL;
 
     if (!block_job_is_cancelled(&s->common) && data->reached_end &&
         data->ret == 0) {
@@ -79,11 +80,19 @@ static void stream_complete(BlockJob *job, void *opaque)
             }
         }
         data->ret = bdrv_change_backing_file(bs, base_id, base_fmt);
-        bdrv_set_backing_hd(bs, base);
+        bdrv_set_backing_hd(bs, base, &local_err);
+        if (local_err) {
+            error_report_err(local_err);
+            data->ret = -EPERM;
+            goto out;
+        }
     }
 
+out:
     /* Reopen the image back in read-only mode if necessary */
     if (s->bs_flags != bdrv_get_flags(bs)) {
+        /* Give up write permissions before making it read-only */
+        blk_set_perm(job->blk, 0, BLK_PERM_ALL, &error_abort);
         bdrv_reopen(bs, s->bs_flags, NULL);
     }
 
@@ -229,25 +238,35 @@ void stream_start(const char *job_id, BlockDriverState *bs,
     BlockDriverState *iter;
     int orig_bs_flags;
 
-    s = block_job_create(job_id, &stream_job_driver, bs, speed,
-                         BLOCK_JOB_DEFAULT, NULL, NULL, errp);
-    if (!s) {
-        return;
-    }
-
     /* Make sure that the image is opened in read-write mode */
     orig_bs_flags = bdrv_get_flags(bs);
     if (!(orig_bs_flags & BDRV_O_RDWR)) {
         if (bdrv_reopen(bs, orig_bs_flags | BDRV_O_RDWR, errp) != 0) {
-            block_job_unref(&s->common);
             return;
         }
     }
 
-    /* Block all intermediate nodes between bs and base, because they
+    /* Prevent concurrent jobs trying to modify the graph structure here, we
-     * will disappear from the chain after this operation */
+     * already have our own plans. Also don't allow resize as the image size is
+     * queried only at the job start and then cached. */
+    s = block_job_create(job_id, &stream_job_driver, bs,
+                         BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+                         BLK_PERM_GRAPH_MOD,
+                         BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+                         BLK_PERM_WRITE,
+                         speed, BLOCK_JOB_DEFAULT, NULL, NULL, errp);
+    if (!s) {
+        goto fail;
+    }
+
+    /* Block all intermediate nodes between bs and base, because they will
+     * disappear from the chain after this operation. The streaming job reads
+     * every block only once, assuming that it doesn't change, so block writes
+     * and resizes. */
     for (iter = backing_bs(bs); iter && iter != base; iter = backing_bs(iter)) {
-        block_job_add_bdrv(&s->common, iter);
+        block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
+                           BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED,
+                           &error_abort);
     }
 
     s->base = base;
@@ -257,4 +276,10 @@ void stream_start(const char *job_id, BlockDriverState *bs,
     s->on_error = on_error;
     trace_stream_start(bs, base, s);
     block_job_start(&s->common);
+    return;
+
+fail:
+    if (orig_bs_flags != bdrv_get_flags(bs)) {
+        bdrv_reopen(bs, s->bs_flags, NULL);
+    }
 }

block/vdi.c

@@ -763,7 +763,8 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -891,6 +892,7 @@ static BlockDriver bdrv_vdi = {
     .bdrv_open = vdi_open,
     .bdrv_close = vdi_close,
     .bdrv_reopen_prepare = vdi_reopen_prepare,
+    .bdrv_child_perm          = bdrv_format_default_perms,
     .bdrv_create = vdi_create,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
     .bdrv_co_get_block_status = vdi_co_get_block_status,

block/vhdx.c

@@ -1859,7 +1859,8 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -1983,6 +1984,7 @@ static BlockDriver bdrv_vhdx = {
     .bdrv_open              = vhdx_open,
     .bdrv_close             = vhdx_close,
     .bdrv_reopen_prepare    = vhdx_reopen_prepare,
+    .bdrv_child_perm        = bdrv_format_default_perms,
     .bdrv_co_readv          = vhdx_co_readv,
     .bdrv_co_writev         = vhdx_co_writev,
     .bdrv_create            = vhdx_create,

block/vmdk.c

@@ -1703,7 +1703,8 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -2071,7 +2072,8 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     new_blk = blk_new_open(filename, NULL, NULL,
-                           BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                           BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                           &local_err);
     if (new_blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -2359,6 +2361,7 @@ static BlockDriver bdrv_vmdk = {
     .bdrv_open                    = vmdk_open,
     .bdrv_check                   = vmdk_check,
     .bdrv_reopen_prepare          = vmdk_reopen_prepare,
+    .bdrv_child_perm              = bdrv_format_default_perms,
     .bdrv_co_preadv               = vmdk_co_preadv,
     .bdrv_co_pwritev              = vmdk_co_pwritev,
     .bdrv_co_pwritev_compressed   = vmdk_co_pwritev_compressed,

block/vpc.c

@@ -915,7 +915,8 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -1067,6 +1068,7 @@ static BlockDriver bdrv_vpc = {
     .bdrv_open              = vpc_open,
     .bdrv_close             = vpc_close,
     .bdrv_reopen_prepare    = vpc_reopen_prepare,
+    .bdrv_child_perm        = bdrv_format_default_perms,
     .bdrv_create            = vpc_create,
 
     .bdrv_co_preadv             = vpc_co_preadv,

block/vvfat.c

@@ -3041,7 +3041,7 @@ static int enable_write_target(BlockDriverState *bs, Error **errp)
                                    &error_abort);
     *(void**) backing->opaque = s;
 
-    bdrv_set_backing_hd(s->bs, backing);
+    bdrv_set_backing_hd(s->bs, backing, &error_abort);
     bdrv_unref(backing);
 
     return 0;
@@ -3052,6 +3052,27 @@ err:
     return ret;
 }
 
+static void vvfat_child_perm(BlockDriverState *bs, BdrvChild *c,
+                             const BdrvChildRole *role,
+                             uint64_t perm, uint64_t shared,
+                             uint64_t *nperm, uint64_t *nshared)
+{
+    BDRVVVFATState *s = bs->opaque;
+
+    assert(c == s->qcow || role == &child_backing);
+
+    if (c == s->qcow) {
+        /* This is a private node, nobody should try to attach to it */
+        *nperm = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE;
+        *nshared = BLK_PERM_WRITE_UNCHANGED;
+    } else {
+        /* The backing file is there so 'commit' can use it. vvfat doesn't
+         * access it in any way. */
+        *nperm = 0;
+        *nshared = BLK_PERM_ALL;
+    }
+}
+
 static void vvfat_close(BlockDriverState *bs)
 {
     BDRVVVFATState *s = bs->opaque;
@@ -3077,6 +3098,7 @@ static BlockDriver bdrv_vvfat = {
     .bdrv_file_open         = vvfat_open,
     .bdrv_refresh_limits    = vvfat_refresh_limits,
     .bdrv_close             = vvfat_close,
+    .bdrv_child_perm        = vvfat_child_perm,
 
     .bdrv_co_preadv         = vvfat_co_preadv,
     .bdrv_co_pwritev        = vvfat_co_pwritev,

blockdev.c

@@ -558,7 +558,7 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
     if ((!file || !*file) && !qdict_size(bs_opts)) {
         BlockBackendRootState *blk_rs;
 
-        blk = blk_new();
+        blk = blk_new(0, BLK_PERM_ALL);
         blk_rs = blk_get_root_state(blk);
         blk_rs->open_flags    = bdrv_flags;
         blk_rs->read_only     = read_only;
@@ -1768,6 +1768,17 @@ static void external_snapshot_prepare(BlkActionState *common,
 
     if (!state->new_bs->drv->supports_backing) {
         error_setg(errp, "The snapshot does not support backing images");
+        return;
+    }
+
+    /* This removes our old bs and adds the new bs. This is an operation that
+     * can fail, so we need to do it in .prepare; undoing it for abort is
+     * always possible. */
+    bdrv_ref(state->new_bs);
+    bdrv_append(state->new_bs, state->old_bs, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
     }
 }
 
@@ -1778,8 +1789,6 @@ static void external_snapshot_commit(BlkActionState *common)
 
     bdrv_set_aio_context(state->new_bs, state->aio_context);
 
-    /* This removes our old bs and adds the new bs */
-    bdrv_append(state->new_bs, state->old_bs);
     /* We don't need (or want) to use the transactional
      * bdrv_reopen_multiple() across all the entries at once, because we
      * don't want to abort all of them if one of them fails the reopen */
@@ -1794,7 +1803,9 @@ static void external_snapshot_abort(BlkActionState *common)
     ExternalSnapshotState *state =
                              DO_UPCAST(ExternalSnapshotState, common, common);
     if (state->new_bs) {
-        bdrv_unref(state->new_bs);
+        if (state->new_bs->backing) {
+            bdrv_replace_in_backing_chain(state->new_bs, state->old_bs);
+        }
     }
 }
 
@@ -1805,6 +1816,7 @@ static void external_snapshot_clean(BlkActionState *common)
     if (state->aio_context) {
         bdrv_drained_end(state->old_bs);
         aio_context_release(state->aio_context);
+        bdrv_unref(state->new_bs);
     }
 }
 
@@ -2311,7 +2323,7 @@ static int do_open_tray(const char *blk_name, const char *qdev_id,
     }
 
     if (!locked || force) {
-        blk_dev_change_media_cb(blk, false);
+        blk_dev_change_media_cb(blk, false, &error_abort);
     }
 
     if (locked && !force) {
@@ -2349,6 +2361,7 @@ void qmp_blockdev_close_tray(bool has_device, const char *device,
                              Error **errp)
 {
     BlockBackend *blk;
+    Error *local_err = NULL;
 
     device = has_device ? device : NULL;
     id = has_id ? id : NULL;
@@ -2372,7 +2385,11 @@ void qmp_blockdev_close_tray(bool has_device, const char *device,
         return;
     }
 
-    blk_dev_change_media_cb(blk, true);
+    blk_dev_change_media_cb(blk, true, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
 }
 
 void qmp_x_blockdev_remove_medium(bool has_device, const char *device,
@@ -2425,7 +2442,7 @@ void qmp_x_blockdev_remove_medium(bool has_device, const char *device,
          * called at all); therefore, the medium needs to be ejected here.
          * Do it after blk_remove_bs() so blk_is_inserted(blk) returns the @load
          * value passed here (i.e. false). */
-        blk_dev_change_media_cb(blk, false);
+        blk_dev_change_media_cb(blk, false, &error_abort);
     }
 
 out:
@@ -2435,7 +2452,9 @@ out:
 static void qmp_blockdev_insert_anon_medium(BlockBackend *blk,
                                             BlockDriverState *bs, Error **errp)
 {
+    Error *local_err = NULL;
     bool has_device;
+    int ret;
 
     /* For BBs without a device, we can exchange the BDS tree at will */
     has_device = blk_get_attached_dev(blk);
@@ -2455,7 +2474,10 @@ static void qmp_blockdev_insert_anon_medium(BlockBackend *blk,
         return;
     }
 
-    blk_insert_bs(blk, bs);
+    ret = blk_insert_bs(blk, bs, errp);
+    if (ret < 0) {
+        return;
+    }
 
     if (!blk_dev_has_tray(blk)) {
         /* For tray-less devices, blockdev-close-tray is a no-op (or may not be
@@ -2463,7 +2485,12 @@ static void qmp_blockdev_insert_anon_medium(BlockBackend *blk,
          * slot here.
          * Do it after blk_insert_bs() so blk_is_inserted(blk) returns the @load
          * value passed here (i.e. true). */
-        blk_dev_change_media_cb(blk, true);
+        blk_dev_change_media_cb(blk, true, &local_err);
+        if (local_err) {
+            error_propagate(errp, local_err);
+            blk_remove_bs(blk);
+            return;
+        }
     }
 }
 
@@ -2890,8 +2917,11 @@ void qmp_block_resize(bool has_device, const char *device,
         goto out;
     }
 
-    blk = blk_new();
+    blk = blk_new(BLK_PERM_RESIZE, BLK_PERM_ALL);
-    blk_insert_bs(blk, bs);
+    ret = blk_insert_bs(blk, bs, errp);
+    if (ret < 0) {
+        goto out;
+    }
 
     /* complete all in-flight operations before resizing the device */
     bdrv_drain_all();
@@ -3014,6 +3044,7 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
                       bool has_top, const char *top,
                       bool has_backing_file, const char *backing_file,
                       bool has_speed, int64_t speed,
+                      bool has_filter_node_name, const char *filter_node_name,
                       Error **errp)
 {
     BlockDriverState *bs;
@@ -3029,6 +3060,9 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
     if (!has_speed) {
         speed = 0;
     }
+    if (!has_filter_node_name) {
+        filter_node_name = NULL;
+    }
 
     /* Important Note:
      *  libvirt relies on the DeviceNotFound error class in order to probe for
@@ -3103,8 +3137,8 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
             goto out;
         }
         commit_active_start(has_job_id ? job_id : NULL, bs, base_bs,
-                            BLOCK_JOB_DEFAULT, speed, on_error, NULL, NULL,
+                            BLOCK_JOB_DEFAULT, speed, on_error,
-                            &local_err, false);
+                            filter_node_name, NULL, NULL, &local_err, false);
     } else {
         BlockDriverState *overlay_bs = bdrv_find_overlay(bs, top_bs);
         if (bdrv_op_is_blocked(overlay_bs, BLOCK_OP_TYPE_COMMIT_TARGET, errp)) {
@@ -3112,7 +3146,7 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
         }
         commit_start(has_job_id ? job_id : NULL, bs, base_bs, top_bs, speed,
                      on_error, has_backing_file ? backing_file : NULL,
-                     &local_err);
+                     filter_node_name, &local_err);
     }
     if (local_err != NULL) {
         error_propagate(errp, local_err);
@@ -3348,6 +3382,8 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
                                    bool has_on_target_error,
                                    BlockdevOnError on_target_error,
                                    bool has_unmap, bool unmap,
+                                   bool has_filter_node_name,
+                                   const char *filter_node_name,
                                    Error **errp)
 {
 
@@ -3369,6 +3405,9 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
     if (!has_unmap) {
         unmap = true;
     }
+    if (!has_filter_node_name) {
+        filter_node_name = NULL;
+    }
 
     if (granularity != 0 && (granularity < 512 || granularity > 1048576 * 64)) {
         error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "granularity",
@@ -3398,7 +3437,8 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
     mirror_start(job_id, bs, target,
                  has_replaces ? replaces : NULL,
                  speed, granularity, buf_size, sync, backing_mode,
-                 on_source_error, on_target_error, unmap, errp);
+                 on_source_error, on_target_error, unmap, filter_node_name,
+                 errp);
 }
 
 void qmp_drive_mirror(DriveMirror *arg, Error **errp)
@@ -3536,6 +3576,7 @@ void qmp_drive_mirror(DriveMirror *arg, Error **errp)
                            arg->has_on_source_error, arg->on_source_error,
                            arg->has_on_target_error, arg->on_target_error,
                            arg->has_unmap, arg->unmap,
+                           false, NULL,
                            &local_err);
     bdrv_unref(target_bs);
     error_propagate(errp, local_err);
@@ -3554,6 +3595,8 @@ void qmp_blockdev_mirror(bool has_job_id, const char *job_id,
                          BlockdevOnError on_source_error,
                          bool has_on_target_error,
                          BlockdevOnError on_target_error,
+                         bool has_filter_node_name,
+                         const char *filter_node_name,
                          Error **errp)
 {
     BlockDriverState *bs;
@@ -3585,6 +3628,7 @@ void qmp_blockdev_mirror(bool has_job_id, const char *job_id,
                            has_on_source_error, on_source_error,
                            has_on_target_error, on_target_error,
                            true, true,
+                           has_filter_node_name, filter_node_name,
                            &local_err);
     error_propagate(errp, local_err);
 

blockjob.c

@@ -55,6 +55,19 @@ struct BlockJobTxn {
 
 static QLIST_HEAD(, BlockJob) block_jobs = QLIST_HEAD_INITIALIZER(block_jobs);
 
+static char *child_job_get_parent_desc(BdrvChild *c)
+{
+    BlockJob *job = c->opaque;
+    return g_strdup_printf("%s job '%s'",
+                           BlockJobType_lookup[job->driver->job_type],
+                           job->id);
+}
+
+static const BdrvChildRole child_job = {
+    .get_parent_desc    = child_job_get_parent_desc,
+    .stay_at_node       = true,
+};
+
 BlockJob *block_job_next(BlockJob *job)
 {
     if (!job) {
@@ -115,19 +128,44 @@ static void block_job_detach_aio_context(void *opaque)
     block_job_unref(job);
 }
 
-void block_job_add_bdrv(BlockJob *job, BlockDriverState *bs)
+void block_job_remove_all_bdrv(BlockJob *job)
 {
-    job->nodes = g_slist_prepend(job->nodes, bs);
+    GSList *l;
+    for (l = job->nodes; l; l = l->next) {
+        BdrvChild *c = l->data;
+        bdrv_op_unblock_all(c->bs, job->blocker);
+        bdrv_root_unref_child(c);
+    }
+    g_slist_free(job->nodes);
+    job->nodes = NULL;
+}
+
+int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs,
+                       uint64_t perm, uint64_t shared_perm, Error **errp)
+{
+    BdrvChild *c;
+
+    c = bdrv_root_attach_child(bs, name, &child_job, perm, shared_perm,
+                               job, errp);
+    if (c == NULL) {
+        return -EPERM;
+    }
+
+    job->nodes = g_slist_prepend(job->nodes, c);
     bdrv_ref(bs);
     bdrv_op_block_all(bs, job->blocker);
+
+    return 0;
 }
 
 void *block_job_create(const char *job_id, const BlockJobDriver *driver,
-                       BlockDriverState *bs, int64_t speed, int flags,
+                       BlockDriverState *bs, uint64_t perm,
+                       uint64_t shared_perm, int64_t speed, int flags,
                        BlockCompletionFunc *cb, void *opaque, Error **errp)
 {
     BlockBackend *blk;
     BlockJob *job;
+    int ret;
 
     if (bs->job) {
         error_setg(errp, QERR_DEVICE_IN_USE, bdrv_get_device_name(bs));
@@ -159,13 +197,17 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver,
         }
     }
 
-    blk = blk_new();
+    blk = blk_new(perm, shared_perm);
-    blk_insert_bs(blk, bs);
+    ret = blk_insert_bs(blk, bs, errp);
+    if (ret < 0) {
+        blk_unref(blk);
+        return NULL;
+    }
 
     job = g_malloc0(driver->instance_size);
     error_setg(&job->blocker, "block device is in use by block job: %s",
                BlockJobType_lookup[driver->job_type]);
-    block_job_add_bdrv(job, bs);
+    block_job_add_bdrv(job, "main node", bs, 0, BLK_PERM_ALL, &error_abort);
     bdrv_op_unblock(bs, BLOCK_OP_TYPE_DATAPLANE, job->blocker);
 
     job->driver        = driver;
@@ -228,15 +270,9 @@ void block_job_ref(BlockJob *job)
 void block_job_unref(BlockJob *job)
 {
     if (--job->refcnt == 0) {
-        GSList *l;
         BlockDriverState *bs = blk_bs(job->blk);
         bs->job = NULL;
-        for (l = job->nodes; l; l = l->next) {
+        block_job_remove_all_bdrv(job);
-            bs = l->data;
-            bdrv_op_unblock_all(bs, job->blocker);
-            bdrv_unref(bs);
-        }
-        g_slist_free(job->nodes);
         blk_remove_aio_context_notifier(job->blk,
                                         block_job_attached_aio_context,
                                         block_job_detach_aio_context, job);

hmp.c

@@ -2045,13 +2045,17 @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict)
     const char* device = qdict_get_str(qdict, "device");
     const char* command = qdict_get_str(qdict, "command");
     Error *err = NULL;
+    int ret;
 
     blk = blk_by_name(device);
     if (!blk) {
         BlockDriverState *bs = bdrv_lookup_bs(NULL, device, &err);
         if (bs) {
-            blk = local_blk = blk_new();
+            blk = local_blk = blk_new(0, BLK_PERM_ALL);
-            blk_insert_bs(blk, bs);
+            ret = blk_insert_bs(blk, bs, &err);
+            if (ret < 0) {
+                goto fail;
+            }
         } else {
             goto fail;
         }
@@ -2060,6 +2064,31 @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict)
     aio_context = blk_get_aio_context(blk);
     aio_context_acquire(aio_context);
 
+    /*
+     * Notably absent: Proper permission management. This is sad, but it seems
+     * almost impossible to achieve without changing the semantics and thereby
+     * limiting the use cases of the qemu-io HMP command.
+     *
+     * In an ideal world we would unconditionally create a new BlockBackend for
+     * qemuio_command(), but we have commands like 'reopen' and want them to
+     * take effect on the exact BlockBackend whose name the user passed instead
+     * of just on a temporary copy of it.
+     *
+     * Another problem is that deleting the temporary BlockBackend involves
+     * draining all requests on it first, but some qemu-iotests cases want to
+     * issue multiple aio_read/write requests and expect them to complete in
+     * the background while the monitor has already returned.
+     *
+     * This is also what prevents us from saving the original permissions and
+     * restoring them later: We can't revoke permissions until all requests
+     * have completed, and we don't know when that is nor can we really let
+     * anything else run before we have revoken them to avoid race conditions.
+     *
+     * What happens now is that command() in qemu-io-cmds.c can extend the
+     * permissions if necessary for the qemu-io command. And they simply stay
+     * extended, possibly resulting in a read-only guest device keeping write
+     * permissions. Ugly, but it appears to be the lesser evil.
+     */
     qemuio_command(blk, command);
 
     aio_context_release(aio_context);

hw/block/block.c

@@ -51,11 +51,33 @@ void blkconf_blocksizes(BlockConf *conf)
     }
 }
 
-void blkconf_apply_backend_options(BlockConf *conf)
+void blkconf_apply_backend_options(BlockConf *conf, bool readonly,
+                                   bool resizable, Error **errp)
 {
     BlockBackend *blk = conf->blk;
     BlockdevOnError rerror, werror;
+    uint64_t perm, shared_perm;
     bool wce;
+    int ret;
+
+    perm = BLK_PERM_CONSISTENT_READ;
+    if (!readonly) {
+        perm |= BLK_PERM_WRITE;
+    }
+
+    shared_perm = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+                  BLK_PERM_GRAPH_MOD;
+    if (resizable) {
+        shared_perm |= BLK_PERM_RESIZE;
+    }
+    if (conf->share_rw) {
+        shared_perm |= BLK_PERM_WRITE;
+    }
+
+    ret = blk_set_perm(blk, perm, shared_perm, errp);
+    if (ret < 0) {
+        return;
+    }
 
     switch (conf->wce) {
     case ON_OFF_AUTO_ON:    wce = true; break;

hw/block/fdc.c

@@ -186,6 +186,7 @@ typedef enum FDiskFlags {
 struct FDrive {
     FDCtrl *fdctrl;
     BlockBackend *blk;
+    BlockConf *conf;
     /* Drive status */
     FloppyDriveType drive;    /* CMOS drive type        */
     uint8_t perpendicular;    /* 2.88 MB access mode    */
@@ -469,9 +470,22 @@ static void fd_revalidate(FDrive *drv)
     }
 }
 
-static void fd_change_cb(void *opaque, bool load)
+static void fd_change_cb(void *opaque, bool load, Error **errp)
 {
     FDrive *drive = opaque;
+    Error *local_err = NULL;
+
+    if (!load) {
+        blk_set_perm(drive->blk, 0, BLK_PERM_ALL, &error_abort);
+    } else {
+        blkconf_apply_backend_options(drive->conf,
+                                      blk_is_read_only(drive->blk), false,
+                                      &local_err);
+        if (local_err) {
+            error_propagate(errp, local_err);
+            return;
+        }
+    }
 
     drive->media_changed = 1;
     drive->media_validated = false;
@@ -508,6 +522,7 @@ static int floppy_drive_init(DeviceState *qdev)
     FloppyDrive *dev = FLOPPY_DRIVE(qdev);
     FloppyBus *bus = FLOPPY_BUS(qdev->parent_bus);
     FDrive *drive;
+    Error *local_err = NULL;
     int ret;
 
     if (dev->unit == -1) {
@@ -533,7 +548,7 @@ static int floppy_drive_init(DeviceState *qdev)
 
     if (!dev->conf.blk) {
         /* Anonymous BlockBackend for an empty drive */
-        dev->conf.blk = blk_new();
+        dev->conf.blk = blk_new(0, BLK_PERM_ALL);
         ret = blk_attach_dev(dev->conf.blk, qdev);
         assert(ret == 0);
     }
@@ -551,7 +566,13 @@ static int floppy_drive_init(DeviceState *qdev)
      * blkconf_apply_backend_options(). */
     dev->conf.rerror = BLOCKDEV_ON_ERROR_AUTO;
     dev->conf.werror = BLOCKDEV_ON_ERROR_AUTO;
-    blkconf_apply_backend_options(&dev->conf);
+
+    blkconf_apply_backend_options(&dev->conf, blk_is_read_only(dev->conf.blk),
+                                  false, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+        return -1;
+    }
 
     /* 'enospc' is the default for -drive, 'report' is what blk_new() gives us
      * for empty drives. */
@@ -565,6 +586,7 @@ static int floppy_drive_init(DeviceState *qdev)
         return -1;
     }
 
+    drive->conf = &dev->conf;
     drive->blk = dev->conf.blk;
     drive->fdctrl = bus->fdc;
 

hw/block/m25p80.c

@@ -1215,6 +1215,7 @@ static void m25p80_realize(SSISlave *ss, Error **errp)
 {
     Flash *s = M25P80(ss);
     M25P80Class *mc = M25P80_GET_CLASS(s);
+    int ret;
 
     s->pi = mc->pi;
 
@@ -1222,6 +1223,13 @@ static void m25p80_realize(SSISlave *ss, Error **errp)
     s->dirty_page = -1;
 
     if (s->blk) {
+        uint64_t perm = BLK_PERM_CONSISTENT_READ |
+                        (blk_is_read_only(s->blk) ? 0 : BLK_PERM_WRITE);
+        ret = blk_set_perm(s->blk, perm, BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
+
         DB_PRINT_L(0, "Binding to IF_MTD drive\n");
         s->storage = blk_blockalign(s->blk, s->size);
 

hw/block/nand.c

@@ -373,6 +373,8 @@ static void nand_realize(DeviceState *dev, Error **errp)
 {
     int pagesize;
     NANDFlashState *s = NAND(dev);
+    int ret;
+
 
     s->buswidth = nand_flash_ids[s->chip_id].width >> 3;
     s->size = nand_flash_ids[s->chip_id].size << 20;
@@ -407,6 +409,11 @@ static void nand_realize(DeviceState *dev, Error **errp)
             error_setg(errp, "Can't use a read-only drive");
             return;
         }
+        ret = blk_set_perm(s->blk, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE,
+                           BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
         if (blk_getlength(s->blk) >=
                 (s->pages << s->page_shift) + (s->pages << s->oob_shift)) {
             pagesize = 0;

hw/block/nvme.c

@@ -835,6 +835,7 @@ static int nvme_init(PCIDevice *pci_dev)
     int i;
     int64_t bs_size;
     uint8_t *pci_conf;
+    Error *local_err = NULL;
 
     if (!n->conf.blk) {
         return -1;
@@ -850,7 +851,12 @@ static int nvme_init(PCIDevice *pci_dev)
         return -1;
     }
     blkconf_blocksizes(&n->conf);
-    blkconf_apply_backend_options(&n->conf);
+    blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
+                                  false, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+        return -1;
+    }
 
     pci_conf = pci_dev->config;
     pci_conf[PCI_INTERRUPT_PIN] = 1;

hw/block/onenand.c

@@ -778,6 +778,7 @@ static int onenand_initfn(SysBusDevice *sbd)
     OneNANDState *s = ONE_NAND(dev);
     uint32_t size = 1 << (24 + ((s->id.dev >> 4) & 7));
     void *ram;
+    Error *local_err = NULL;
 
     s->base = (hwaddr)-1;
     s->rdy = NULL;
@@ -796,6 +797,12 @@ static int onenand_initfn(SysBusDevice *sbd)
             error_report("Can't use a read-only drive");
             return -1;
         }
+        blk_set_perm(s->blk, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE,
+                     BLK_PERM_ALL, &local_err);
+        if (local_err) {
+            error_report_err(local_err);
+            return -1;
+        }
         s->blk_cur = s->blk;
     }
     s->otp = memset(g_malloc((64 + 2) << PAGE_SHIFT),

hw/block/pflash_cfi01.c

@@ -757,6 +757,18 @@ static void pflash_cfi01_realize(DeviceState *dev, Error **errp)
     pfl->storage = memory_region_get_ram_ptr(&pfl->mem);
     sysbus_init_mmio(SYS_BUS_DEVICE(dev), &pfl->mem);
 
+    if (pfl->blk) {
+        uint64_t perm;
+        pfl->ro = blk_is_read_only(pfl->blk);
+        perm = BLK_PERM_CONSISTENT_READ | (pfl->ro ? 0 : BLK_PERM_WRITE);
+        ret = blk_set_perm(pfl->blk, perm, BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
+    } else {
+        pfl->ro = 0;
+    }
+
     if (pfl->blk) {
         /* read the initial flash content */
         ret = blk_pread(pfl->blk, 0, pfl->storage, total_len);
@@ -768,12 +780,6 @@ static void pflash_cfi01_realize(DeviceState *dev, Error **errp)
         }
     }
 
-    if (pfl->blk) {
-        pfl->ro = blk_is_read_only(pfl->blk);
-    } else {
-        pfl->ro = 0;
-    }
-
     /* Default to devices being used at their maximum device width. This was
      * assumed before the device_width support was added.
      */

hw/block/pflash_cfi02.c

@@ -632,6 +632,19 @@ static void pflash_cfi02_realize(DeviceState *dev, Error **errp)
     vmstate_register_ram(&pfl->orig_mem, DEVICE(pfl));
     pfl->storage = memory_region_get_ram_ptr(&pfl->orig_mem);
     pfl->chip_len = chip_len;
+
+    if (pfl->blk) {
+        uint64_t perm;
+        pfl->ro = blk_is_read_only(pfl->blk);
+        perm = BLK_PERM_CONSISTENT_READ | (pfl->ro ? 0 : BLK_PERM_WRITE);
+        ret = blk_set_perm(pfl->blk, perm, BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
+    } else {
+        pfl->ro = 0;
+    }
+
     if (pfl->blk) {
         /* read the initial flash content */
         ret = blk_pread(pfl->blk, 0, pfl->storage, chip_len);
@@ -646,12 +659,6 @@ static void pflash_cfi02_realize(DeviceState *dev, Error **errp)
     pfl->rom_mode = 1;
     sysbus_init_mmio(SYS_BUS_DEVICE(dev), &pfl->mem);
 
-    if (pfl->blk) {
-        pfl->ro = blk_is_read_only(pfl->blk);
-    } else {
-        pfl->ro = 0;
-    }
-
     pfl->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, pflash_timer, pfl);
     pfl->wcycle = 0;
     pfl->cmd = 0;

hw/block/virtio-blk.c

@@ -928,7 +928,13 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
     }
 
     blkconf_serial(&conf->conf, &conf->serial);
-    blkconf_apply_backend_options(&conf->conf);
+    blkconf_apply_backend_options(&conf->conf,
+                                  blk_is_read_only(conf->conf.blk), true,
+                                  &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
     s->original_wce = blk_enable_write_cache(conf->conf.blk);
     blkconf_geometry(&conf->conf, NULL, 65535, 255, 255, &err);
     if (err) {

hw/core/qdev-properties-system.c

@@ -73,14 +73,19 @@ static void parse_drive(DeviceState *dev, const char *str, void **ptr,
 {
     BlockBackend *blk;
     bool blk_created = false;
+    int ret;
 
     blk = blk_by_name(str);
     if (!blk) {
         BlockDriverState *bs = bdrv_lookup_bs(NULL, str, NULL);
         if (bs) {
-            blk = blk_new();
+            blk = blk_new(0, BLK_PERM_ALL);
-            blk_insert_bs(blk, bs);
             blk_created = true;
+
+            ret = blk_insert_bs(blk, bs, errp);
+            if (ret < 0) {
+                goto fail;
+            }
         }
     }
     if (!blk) {

hw/ide/core.c

@@ -1120,7 +1120,7 @@ static void ide_cfata_metadata_write(IDEState *s)
 }
 
 /* called when the inserted state of the media has changed */
-static void ide_cd_change_cb(void *opaque, bool load)
+static void ide_cd_change_cb(void *opaque, bool load, Error **errp)
 {
     IDEState *s = opaque;
     uint64_t nb_sectors;

hw/ide/qdev.c

@@ -170,7 +170,7 @@ static int ide_dev_initfn(IDEDevice *dev, IDEDriveKind kind)
             return -1;
         } else {
             /* Anonymous BlockBackend for an empty drive */
-            dev->conf.blk = blk_new();
+            dev->conf.blk = blk_new(0, BLK_PERM_ALL);
         }
     }
 
@@ -196,7 +196,12 @@ static int ide_dev_initfn(IDEDevice *dev, IDEDriveKind kind)
             return -1;
         }
     }
-    blkconf_apply_backend_options(&dev->conf);
+    blkconf_apply_backend_options(&dev->conf, kind == IDE_CD, kind != IDE_CD,
+                                  &err);
+    if (err) {
+        error_report_err(err);
+        return -1;
+    }
 
     if (ide_init_drive(s, dev->conf.blk, kind,
                        dev->version, dev->serial, dev->model, dev->wwn,

hw/nvram/spapr_nvram.c

@@ -141,9 +141,17 @@ static void rtas_nvram_store(PowerPCCPU *cpu, sPAPRMachineState *spapr,
 static void spapr_nvram_realize(VIOsPAPRDevice *dev, Error **errp)
 {
     sPAPRNVRAM *nvram = VIO_SPAPR_NVRAM(dev);
+    int ret;
 
     if (nvram->blk) {
         nvram->size = blk_getlength(nvram->blk);
+
+        ret = blk_set_perm(nvram->blk,
+                           BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE,
+                           BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
     } else {
         nvram->size = DEFAULT_NVRAM_SIZE;
     }

hw/scsi/scsi-disk.c

@@ -2240,7 +2240,7 @@ static void scsi_disk_resize_cb(void *opaque)
     }
 }
 
-static void scsi_cd_change_media_cb(void *opaque, bool load)
+static void scsi_cd_change_media_cb(void *opaque, bool load, Error **errp)
 {
     SCSIDiskState *s = opaque;
 
@@ -2328,7 +2328,13 @@ static void scsi_realize(SCSIDevice *dev, Error **errp)
             return;
         }
     }
-    blkconf_apply_backend_options(&dev->conf);
+    blkconf_apply_backend_options(&dev->conf,
+                                  blk_is_read_only(s->qdev.conf.blk),
+                                  dev->type == TYPE_DISK, &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
 
     if (s->qdev.conf.discard_granularity == -1) {
         s->qdev.conf.discard_granularity =
@@ -2380,7 +2386,7 @@ static void scsi_cd_realize(SCSIDevice *dev, Error **errp)
     SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, dev);
 
     if (!dev->conf.blk) {
-        dev->conf.blk = blk_new();
+        dev->conf.blk = blk_new(0, BLK_PERM_ALL);
     }
 
     s->qdev.blocksize = 2048;

hw/sd/sd.c

@@ -458,7 +458,7 @@ static bool sd_get_readonly(SDState *sd)
     return sd->wp_switch;
 }
 
-static void sd_cardchange(void *opaque, bool load)
+static void sd_cardchange(void *opaque, bool load, Error **errp)
 {
     SDState *sd = opaque;
     DeviceState *dev = DEVICE(sd);
@@ -1887,6 +1887,7 @@ static void sd_instance_finalize(Object *obj)
 static void sd_realize(DeviceState *dev, Error **errp)
 {
     SDState *sd = SD_CARD(dev);
+    int ret;
 
     if (sd->blk && blk_is_read_only(sd->blk)) {
         error_setg(errp, "Cannot use read-only drive as SD card");
@@ -1894,6 +1895,11 @@ static void sd_realize(DeviceState *dev, Error **errp)
     }
 
     if (sd->blk) {
+        ret = blk_set_perm(sd->blk, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE,
+                           BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
         blk_set_dev_ops(sd->blk, &sd_block_ops, sd);
     }
 }

hw/usb/dev-storage.c

@@ -603,7 +603,11 @@ static void usb_msd_realize_storage(USBDevice *dev, Error **errp)
 
     blkconf_serial(&s->conf, &dev->serial);
     blkconf_blocksizes(&s->conf);
-    blkconf_apply_backend_options(&s->conf);
+    blkconf_apply_backend_options(&s->conf, blk_is_read_only(blk), true, &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
 
     /*
      * Hack alert: this pretends to be a block device, but it's really

include/block/block.h

@@ -82,6 +82,7 @@ typedef struct HDGeometry {
 } HDGeometry;
 
 #define BDRV_O_RDWR        0x0002
+#define BDRV_O_RESIZE      0x0004 /* request permission for resizing the node */
 #define BDRV_O_SNAPSHOT    0x0008 /* open the file read only and save writes in a snapshot */
 #define BDRV_O_TEMPORARY   0x0010 /* delete the file after use */
 #define BDRV_O_NOCACHE     0x0020 /* do not use the host page cache */
@@ -187,6 +188,42 @@ typedef enum BlockOpType {
     BLOCK_OP_TYPE_MAX,
 } BlockOpType;
 
+/* Block node permission constants */
+enum {
+    /**
+     * A user that has the "permission" of consistent reads is guaranteed that
+     * their view of the contents of the block device is complete and
+     * self-consistent, representing the contents of a disk at a specific
+     * point.
+     *
+     * For most block devices (including their backing files) this is true, but
+     * the property cannot be maintained in a few situations like for
+     * intermediate nodes of a commit block job.
+     */
+    BLK_PERM_CONSISTENT_READ    = 0x01,
+
+    /** This permission is required to change the visible disk contents. */
+    BLK_PERM_WRITE              = 0x02,
+
+    /**
+     * This permission (which is weaker than BLK_PERM_WRITE) is both enough and
+     * required for writes to the block node when the caller promises that
+     * the visible disk content doesn't change.
+     */
+    BLK_PERM_WRITE_UNCHANGED    = 0x04,
+
+    /** This permission is required to change the size of a block node. */
+    BLK_PERM_RESIZE             = 0x08,
+
+    /**
+     * This permission is required to change the node that this BdrvChild
+     * points to.
+     */
+    BLK_PERM_GRAPH_MOD          = 0x10,
+
+    BLK_PERM_ALL                = 0x1f,
+};
+
 /* disk I/O throttling */
 void bdrv_init(void);
 void bdrv_init_with_whitelist(void);
@@ -199,7 +236,8 @@ int bdrv_create(BlockDriver *drv, const char* filename,
                 QemuOpts *opts, Error **errp);
 int bdrv_create_file(const char *filename, QemuOpts *opts, Error **errp);
 BlockDriverState *bdrv_new(void);
-void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top);
+void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
+                 Error **errp);
 void bdrv_replace_in_backing_chain(BlockDriverState *old,
                                    BlockDriverState *new);
 
@@ -210,7 +248,8 @@ BdrvChild *bdrv_open_child(const char *filename,
                            BlockDriverState* parent,
                            const BdrvChildRole *child_role,
                            bool allow_none, Error **errp);
-void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd);
+void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
+                         Error **errp);
 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,
@@ -484,7 +523,8 @@ void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child);
 BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs,
                              BlockDriverState *child_bs,
                              const char *child_name,
-                             const BdrvChildRole *child_role);
+                             const BdrvChildRole *child_role,
+                             Error **errp);
 
 bool bdrv_op_is_blocked(BlockDriverState *bs, BlockOpType op, Error **errp);
 void bdrv_op_block(BlockDriverState *bs, BlockOpType op, Error *reason);

include/block/block_int.h

@@ -320,6 +320,59 @@ struct BlockDriver {
     void (*bdrv_del_child)(BlockDriverState *parent, BdrvChild *child,
                            Error **errp);
 
+    /**
+     * Informs the block driver that a permission change is intended. The
+     * driver checks whether the change is permissible and may take other
+     * preparations for the change (e.g. get file system locks). This operation
+     * is always followed either by a call to either .bdrv_set_perm or
+     * .bdrv_abort_perm_update.
+     *
+     * Checks whether the requested set of cumulative permissions in @perm
+     * can be granted for accessing @bs and whether no other users are using
+     * permissions other than those given in @shared (both arguments take
+     * BLK_PERM_* bitmasks).
+     *
+     * If both conditions are met, 0 is returned. Otherwise, -errno is returned
+     * and errp is set to an error describing the conflict.
+     */
+    int (*bdrv_check_perm)(BlockDriverState *bs, uint64_t perm,
+                           uint64_t shared, Error **errp);
+
+    /**
+     * Called to inform the driver that the set of cumulative set of used
+     * permissions for @bs has changed to @perm, and the set of sharable
+     * permission to @shared. The driver can use this to propagate changes to
+     * its children (i.e. request permissions only if a parent actually needs
+     * them).
+     *
+     * This function is only invoked after bdrv_check_perm(), so block drivers
+     * may rely on preparations made in their .bdrv_check_perm implementation.
+     */
+    void (*bdrv_set_perm)(BlockDriverState *bs, uint64_t perm, uint64_t shared);
+
+    /*
+     * Called to inform the driver that after a previous bdrv_check_perm()
+     * call, the permission update is not performed and any preparations made
+     * for it (e.g. taken file locks) need to be undone.
+     *
+     * This function can be called even for nodes that never saw a
+     * bdrv_check_perm() call. It is a no-op then.
+     */
+    void (*bdrv_abort_perm_update)(BlockDriverState *bs);
+
+    /**
+     * Returns in @nperm and @nshared the permissions that the driver for @bs
+     * needs on its child @c, based on the cumulative permissions requested by
+     * the parents in @parent_perm and @parent_shared.
+     *
+     * If @c is NULL, return the permissions for attaching a new child for the
+     * given @role.
+     */
+     void (*bdrv_child_perm)(BlockDriverState *bs, BdrvChild *c,
+                             const BdrvChildRole *role,
+                             uint64_t parent_perm, uint64_t parent_shared,
+                             uint64_t *nperm, uint64_t *nshared);
+
     QLIST_ENTRY(BlockDriver) list;
 };
 
@@ -388,6 +441,10 @@ typedef struct BdrvAioNotifier {
 } BdrvAioNotifier;
 
 struct BdrvChildRole {
+    /* If true, bdrv_replace_in_backing_chain() doesn't change the node this
+     * BdrvChild points to. */
+    bool stay_at_node;
+
     void (*inherit_options)(int *child_flags, QDict *child_options,
                             int parent_flags, QDict *parent_options);
 
@@ -399,6 +456,12 @@ struct BdrvChildRole {
      * name), or NULL if the parent can't provide a better name. */
     const char* (*get_name)(BdrvChild *child);
 
+    /* Returns a malloced string that describes the parent of the child for a
+     * human reader. This could be a node-name, BlockBackend name, qdev ID or
+     * QOM path of the device owning the BlockBackend, job type and ID etc. The
+     * caller is responsible for freeing the memory. */
+    char* (*get_parent_desc)(BdrvChild *child);
+
     /*
      * If this pair of functions is implemented, the parent doesn't issue new
      * requests after returning from .drained_begin() until .drained_end() is
@@ -409,16 +472,32 @@ struct BdrvChildRole {
      */
     void (*drained_begin)(BdrvChild *child);
     void (*drained_end)(BdrvChild *child);
+
+    void (*attach)(BdrvChild *child);
+    void (*detach)(BdrvChild *child);
 };
 
 extern const BdrvChildRole child_file;
 extern const BdrvChildRole child_format;
+extern const BdrvChildRole child_backing;
 
 struct BdrvChild {
     BlockDriverState *bs;
     char *name;
     const BdrvChildRole *role;
     void *opaque;
+
+    /**
+     * Granted permissions for operating on this BdrvChild (BLK_PERM_* bitmask)
+     */
+    uint64_t perm;
+
+    /**
+     * Permissions that can still be granted to other users of @bs while this
+     * BdrvChild is still attached to it. (BLK_PERM_* bitmask)
+     */
+    uint64_t shared_perm;
+
     QLIST_ENTRY(BdrvChild) next;
     QLIST_ENTRY(BdrvChild) next_parent;
 };
@@ -701,13 +780,16 @@ void stream_start(const char *job_id, BlockDriverState *bs,
  * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
  * @on_error: The action to take upon error.
  * @backing_file_str: String to use as the backing file in @top's overlay
+ * @filter_node_name: The node name that should be assigned to the filter
+ * driver that the commit job inserts into the graph above @top. NULL means
+ * that a node name should be autogenerated.
  * @errp: Error object.
  *
  */
 void commit_start(const char *job_id, BlockDriverState *bs,
                   BlockDriverState *base, BlockDriverState *top, int64_t speed,
                   BlockdevOnError on_error, const char *backing_file_str,
-                  Error **errp);
+                  const char *filter_node_name, Error **errp);
 /**
  * commit_active_start:
  * @job_id: The id of the newly-created job, or %NULL to use the
@@ -718,6 +800,9 @@ void commit_start(const char *job_id, BlockDriverState *bs,
  *                  See @BlockJobCreateFlags
  * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
  * @on_error: The action to take upon error.
+ * @filter_node_name: The node name that should be assigned to the filter
+ * driver that the commit job inserts into the graph above @bs. NULL means that
+ * a node name should be autogenerated.
  * @cb: Completion function for the job.
  * @opaque: Opaque pointer value passed to @cb.
  * @errp: Error object.
@@ -727,8 +812,9 @@ void commit_start(const char *job_id, BlockDriverState *bs,
 void commit_active_start(const char *job_id, BlockDriverState *bs,
                          BlockDriverState *base, int creation_flags,
                          int64_t speed, BlockdevOnError on_error,
-                         BlockCompletionFunc *cb,
+                         const char *filter_node_name,
-                         void *opaque, Error **errp, bool auto_complete);
+                         BlockCompletionFunc *cb, void *opaque, Error **errp,
+                         bool auto_complete);
 /*
  * mirror_start:
  * @job_id: The id of the newly-created job, or %NULL to use the
@@ -745,6 +831,9 @@ void commit_active_start(const char *job_id, BlockDriverState *bs,
  * @on_source_error: The action to take upon error reading from the source.
  * @on_target_error: The action to take upon error writing to the target.
  * @unmap: Whether to unmap target where source sectors only contain zeroes.
+ * @filter_node_name: The node name that should be assigned to the filter
+ * driver that the mirror job inserts into the graph above @bs. NULL means that
+ * a node name should be autogenerated.
  * @errp: Error object.
  *
  * Start a mirroring operation on @bs.  Clusters that are allocated
@@ -758,7 +847,7 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
                   MirrorSyncMode mode, BlockMirrorBackingMode backing_mode,
                   BlockdevOnError on_source_error,
                   BlockdevOnError on_target_error,
-                  bool unmap, Error **errp);
+                  bool unmap, const char *filter_node_name, Error **errp);
 
 /*
  * backup_job_create:
@@ -796,11 +885,36 @@ void hmp_drive_add_node(Monitor *mon, const char *optstr);
 BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
                                   const char *child_name,
                                   const BdrvChildRole *child_role,
-                                  void *opaque);
+                                  uint64_t perm, uint64_t shared_perm,
+                                  void *opaque, Error **errp);
 void bdrv_root_unref_child(BdrvChild *child);
 
+int bdrv_child_check_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
+                          Error **errp);
+void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared);
+void bdrv_child_abort_perm_update(BdrvChild *c);
+int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
+                            Error **errp);
+
+/* Default implementation for BlockDriver.bdrv_child_perm() that can be used by
+ * block filters: Forward CONSISTENT_READ, WRITE, WRITE_UNCHANGED and RESIZE to
+ * all children */
+void bdrv_filter_default_perms(BlockDriverState *bs, BdrvChild *c,
+                               const BdrvChildRole *role,
+                               uint64_t perm, uint64_t shared,
+                               uint64_t *nperm, uint64_t *nshared);
+
+/* Default implementation for BlockDriver.bdrv_child_perm() that can be used by
+ * (non-raw) image formats: Like above for bs->backing, but for bs->file it
+ * requires WRITE | RESIZE for read-write images, always requires
+ * CONSISTENT_READ and doesn't share WRITE. */
+void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c,
+                               const BdrvChildRole *role,
+                               uint64_t perm, uint64_t shared,
+                               uint64_t *nperm, uint64_t *nshared);
+
 const char *bdrv_get_parent_name(const BlockDriverState *bs);
-void blk_dev_change_media_cb(BlockBackend *blk, bool load);
+void blk_dev_change_media_cb(BlockBackend *blk, bool load, Error **errp);
 bool blk_dev_has_removable_media(BlockBackend *blk);
 bool blk_dev_has_tray(BlockBackend *blk);
 void blk_dev_eject_request(BlockBackend *blk, bool force);

include/block/blockjob.h

@@ -169,13 +169,25 @@ BlockJob *block_job_get(const char *id);
 /**
  * block_job_add_bdrv:
  * @job: A block job
+ * @name: The name to assign to the new BdrvChild
  * @bs: A BlockDriverState that is involved in @job
+ * @perm, @shared_perm: Permissions to request on the node
  *
  * Add @bs to the list of BlockDriverState that are involved in
  * @job. This means that all operations will be blocked on @bs while
  * @job exists.
  */
-void block_job_add_bdrv(BlockJob *job, BlockDriverState *bs);
+int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs,
+                       uint64_t perm, uint64_t shared_perm, Error **errp);
+
+/**
+ * block_job_remove_all_bdrv:
+ * @job: The block job
+ *
+ * Remove all BlockDriverStates from the list of nodes that are involved in the
+ * job. This removes the blockers added with block_job_add_bdrv().
+ */
+void block_job_remove_all_bdrv(BlockJob *job);
 
 /**
  * block_job_set_speed:

include/block/blockjob_int.h

@@ -119,6 +119,7 @@ struct BlockJobDriver {
  * generated automatically.
  * @job_type: The class object for the newly-created job.
  * @bs: The block
+ * @perm, @shared_perm: Permissions to request for @bs
  * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
  * @cb: Completion function for the job.
  * @opaque: Opaque pointer value passed to @cb.
@@ -134,7 +135,8 @@ struct BlockJobDriver {
  * called from a wrapper that is specific to the job type.
  */
 void *block_job_create(const char *job_id, const BlockJobDriver *driver,
-                       BlockDriverState *bs, int64_t speed, int flags,
+                       BlockDriverState *bs, uint64_t perm,
+                       uint64_t shared_perm, int64_t speed, int flags,
                        BlockCompletionFunc *cb, void *opaque, Error **errp);
 
 /**

include/hw/block/block.h

@@ -26,6 +26,7 @@ typedef struct BlockConf {
     /* geometry, not all devices use this */
     uint32_t cyls, heads, secs;
     OnOffAuto wce;
+    bool share_rw;
     BlockdevOnError rerror;
     BlockdevOnError werror;
 } BlockConf;
@@ -53,7 +54,9 @@ static inline unsigned int get_physical_block_exp(BlockConf *conf)
     DEFINE_PROP_UINT32("opt_io_size", _state, _conf.opt_io_size, 0),    \
     DEFINE_PROP_UINT32("discard_granularity", _state, \
                        _conf.discard_granularity, -1), \
-    DEFINE_PROP_ON_OFF_AUTO("write-cache", _state, _conf.wce, ON_OFF_AUTO_AUTO)
+    DEFINE_PROP_ON_OFF_AUTO("write-cache", _state, _conf.wce, \
+                            ON_OFF_AUTO_AUTO), \
+    DEFINE_PROP_BOOL("share-rw", _state, _conf.share_rw, false)
 
 #define DEFINE_BLOCK_CHS_PROPERTIES(_state, _conf)      \
     DEFINE_PROP_UINT32("cyls", _state, _conf.cyls, 0),  \
@@ -73,7 +76,8 @@ void blkconf_geometry(BlockConf *conf, int *trans,
                       unsigned cyls_max, unsigned heads_max, unsigned secs_max,
                       Error **errp);
 void blkconf_blocksizes(BlockConf *conf);
-void blkconf_apply_backend_options(BlockConf *conf);
+void blkconf_apply_backend_options(BlockConf *conf, bool readonly,
+                                   bool resizable, Error **errp);
 
 /* Hard disk geometry */
 

include/qemu-io.h

@@ -36,6 +36,7 @@ typedef struct cmdinfo {
     const char  *args;
     const char  *oneline;
     helpfunc_t  help;
+    uint64_t    perm;
 } cmdinfo_t;
 
 extern bool qemuio_misalign;

include/sysemu/block-backend.h

@@ -34,7 +34,7 @@ typedef struct BlockDevOps {
      * changes.  Sure would be useful if it did.
      * Device models with removable media must implement this callback.
      */
-    void (*change_media_cb)(void *opaque, bool load);
+    void (*change_media_cb)(void *opaque, bool load, Error **errp);
     /*
      * Runs when an eject request is issued from the monitor, the tray
      * is closed, and the medium is locked.
@@ -84,7 +84,7 @@ typedef struct BlockBackendPublic {
     QLIST_ENTRY(BlockBackendPublic) round_robin;
 } BlockBackendPublic;
 
-BlockBackend *blk_new(void);
+BlockBackend *blk_new(uint64_t perm, uint64_t shared_perm);
 BlockBackend *blk_new_open(const char *filename, const char *reference,
                            QDict *options, int flags, Error **errp);
 int blk_get_refcnt(BlockBackend *blk);
@@ -102,9 +102,12 @@ BlockBackend *blk_by_public(BlockBackendPublic *public);
 
 BlockDriverState *blk_bs(BlockBackend *blk);
 void blk_remove_bs(BlockBackend *blk);
-void blk_insert_bs(BlockBackend *blk, BlockDriverState *bs);
+int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp);
 bool bdrv_has_blk(BlockDriverState *bs);
 bool bdrv_is_root_node(BlockDriverState *bs);
+int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
+                 Error **errp);
+void blk_get_perm(BlockBackend *blk, uint64_t *perm, uint64_t *shared_perm);
 
 void blk_set_allow_write_beyond_eof(BlockBackend *blk, bool allow);
 void blk_iostatus_enable(BlockBackend *blk);

migration/block.c

@@ -379,7 +379,7 @@ static void unset_dirty_tracking(void)
     }
 }
 
-static void init_blk_migration(QEMUFile *f)
+static int init_blk_migration(QEMUFile *f)
 {
     BlockDriverState *bs;
     BlkMigDevState *bmds;
@@ -390,6 +390,8 @@ static void init_blk_migration(QEMUFile *f)
         BlkMigDevState *bmds;
         BlockDriverState *bs;
     } *bmds_bs;
+    Error *local_err = NULL;
+    int ret;
 
     block_mig_state.submitted = 0;
     block_mig_state.read_done = 0;
@@ -411,11 +413,12 @@ static void init_blk_migration(QEMUFile *f)
 
         sectors = bdrv_nb_sectors(bs);
         if (sectors <= 0) {
+            ret = sectors;
             goto out;
         }
 
         bmds = g_new0(BlkMigDevState, 1);
-        bmds->blk = blk_new();
+        bmds->blk = blk_new(BLK_PERM_CONSISTENT_READ, BLK_PERM_ALL);
         bmds->blk_name = g_strdup(bdrv_get_device_name(bs));
         bmds->bulk_completed = 0;
         bmds->total_sectors = sectors;
@@ -445,7 +448,11 @@ static void init_blk_migration(QEMUFile *f)
         BlockDriverState *bs = bmds_bs[i].bs;
 
         if (bmds) {
-            blk_insert_bs(bmds->blk, bs);
+            ret = blk_insert_bs(bmds->blk, bs, &local_err);
+            if (ret < 0) {
+                error_report_err(local_err);
+                goto out;
+            }
 
             alloc_aio_bitmap(bmds);
             error_setg(&bmds->blocker, "block device is in use by migration");
@@ -453,8 +460,10 @@ static void init_blk_migration(QEMUFile *f)
         }
     }
 
+    ret = 0;
 out:
     g_free(bmds_bs);
+    return ret;
 }
 
 /* Called with no lock taken.  */
@@ -705,7 +714,11 @@ static int block_save_setup(QEMUFile *f, void *opaque)
             block_mig_state.submitted, block_mig_state.transferred);
 
     qemu_mutex_lock_iothread();
-    init_blk_migration(f);
+    ret = init_blk_migration(f);
+    if (ret < 0) {
+        qemu_mutex_unlock_iothread();
+        return ret;
+    }
 
     /* start track dirty blocks */
     ret = set_dirty_tracking();

nbd/server.c

@@ -891,9 +891,21 @@ NBDExport *nbd_export_new(BlockDriverState *bs, off_t dev_offset, off_t size,
 {
     BlockBackend *blk;
     NBDExport *exp = g_malloc0(sizeof(NBDExport));
+    uint64_t perm;
+    int ret;
 
-    blk = blk_new();
+    /* Don't allow resize while the NBD server is running, otherwise we don't
-    blk_insert_bs(blk, bs);
+     * care what happens with the node. */
+    perm = BLK_PERM_CONSISTENT_READ;
+    if ((nbdflags & NBD_FLAG_READ_ONLY) == 0) {
+        perm |= BLK_PERM_WRITE;
+    }
+    blk = blk_new(perm, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+                        BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD);
+    ret = blk_insert_bs(blk, bs, errp);
+    if (ret < 0) {
+        goto fail;
+    }
     blk_set_enable_write_cache(blk, !writethrough);
 
     exp->refcount = 1;

qapi/block-core.json

@@ -1304,6 +1304,11 @@
 #
 # @speed:  #optional the maximum speed, in bytes per second
 #
+# @filter-node-name: #optional the node name that should be assigned to the
+#                    filter driver that the commit job inserts into the graph
+#                    above @top. If this option is not given, a node name is
+#                    autogenerated. (Since: 2.9)
+#
 # Returns: Nothing on success
 #          If commit or stream is already active on this device, DeviceInUse
 #          If @device does not exist, DeviceNotFound
@@ -1323,7 +1328,8 @@
 ##
 { 'command': 'block-commit',
   'data': { '*job-id': 'str', 'device': 'str', '*base': 'str', '*top': 'str',
-            '*backing-file': 'str', '*speed': 'int' } }
+            '*backing-file': 'str', '*speed': 'int',
+            '*filter-node-name': 'str' } }
 
 ##
 # @drive-backup:
@@ -1671,6 +1677,11 @@
 #                   default 'report' (no limitations, since this applies to
 #                   a different block device than @device).
 #
+# @filter-node-name: #optional the node name that should be assigned to the
+#                    filter driver that the mirror job inserts into the graph
+#                    above @device. If this option is not given, a node name is
+#                    autogenerated. (Since: 2.9)
+#
 # Returns: nothing on success.
 #
 # Since: 2.6
@@ -1690,7 +1701,8 @@
             'sync': 'MirrorSyncMode',
             '*speed': 'int', '*granularity': 'uint32',
             '*buf-size': 'int', '*on-source-error': 'BlockdevOnError',
-            '*on-target-error': 'BlockdevOnError' } }
+            '*on-target-error': 'BlockdevOnError',
+            '*filter-node-name': 'str' } }
 
 ##
 # @block_set_io_throttle:

qemu-img-cmds.hx

@@ -40,9 +40,9 @@ STEXI
 ETEXI
 
 DEF("convert", img_convert,
-    "convert [--object objectdef] [--image-opts] [-c] [-p] [-q] [-n] [-f fmt] [-t cache] [-T src_cache] [-O output_fmt] [-o options] [-s snapshot_id_or_name] [-l snapshot_param] [-S sparse_size] filename [filename2 [...]] output_filename")
+    "convert [--object objectdef] [--image-opts] [-c] [-p] [-q] [-n] [-f fmt] [-t cache] [-T src_cache] [-O output_fmt] [-o options] [-s snapshot_id_or_name] [-l snapshot_param] [-S sparse_size] [-m num_coroutines] [-W] filename [filename2 [...]] output_filename")
 STEXI
-@item convert [--object @var{objectdef}] [--image-opts] [-c] [-p] [-q] [-n] [-f @var{fmt}] [-t @var{cache}] [-T @var{src_cache}] [-O @var{output_fmt}] [-o @var{options}] [-s @var{snapshot_id_or_name}] [-l @var{snapshot_param}] [-S @var{sparse_size}] @var{filename} [@var{filename2} [...]] @var{output_filename}
+@item convert [--object @var{objectdef}] [--image-opts] [-c] [-p] [-q] [-n] [-f @var{fmt}] [-t @var{cache}] [-T @var{src_cache}] [-O @var{output_fmt}] [-o @var{options}] [-s @var{snapshot_id_or_name}] [-l @var{snapshot_param}] [-S @var{sparse_size}] [-m @var{num_coroutines}] [-W] @var{filename} [@var{filename2} [...]] @var{output_filename}
 ETEXI
 
 DEF("dd", img_dd,

qemu-img.c

@@ -156,6 +156,11 @@ static void QEMU_NORETURN help(void)
            "       kinds of errors, with a higher risk of choosing the wrong fix or\n"
            "       hiding corruption that has already occurred.\n"
            "\n"
+           "Parameters to convert subcommand:\n"
+           "  '-m' specifies how many coroutines work in parallel during the convert\n"
+           "       process (defaults to 8)\n"
+           "  '-W' allow to write to the target out of order rather than sequential\n"
+           "\n"
            "Parameters to snapshot subcommand:\n"
            "  'snapshot' is the name of the snapshot to create, apply or delete\n"
            "  '-a' applies a snapshot (revert disk to saved state)\n"
@@ -809,6 +814,8 @@ static void run_block_job(BlockJob *job, Error **errp)
 {
     AioContext *aio_context = blk_get_aio_context(job->blk);
 
+    /* FIXME In error cases, the job simply goes away and we access a dangling
+     * pointer below. */
     aio_context_acquire(aio_context);
     do {
         aio_poll(aio_context, true);
@@ -830,6 +837,7 @@ static int img_commit(int argc, char **argv)
     const char *filename, *fmt, *cache, *base;
     BlockBackend *blk;
     BlockDriverState *bs, *base_bs;
+    BlockJob *job;
     bool progress = false, quiet = false, drop = false;
     bool writethrough;
     Error *local_err = NULL;
@@ -950,8 +958,8 @@ static int img_commit(int argc, char **argv)
     aio_context = bdrv_get_aio_context(bs);
     aio_context_acquire(aio_context);
     commit_active_start("commit", bs, base_bs, BLOCK_JOB_DEFAULT, 0,
-                        BLOCKDEV_ON_ERROR_REPORT, common_block_job_cb, &cbi,
+                        BLOCKDEV_ON_ERROR_REPORT, NULL, common_block_job_cb,
-                        &local_err, false);
+                        &cbi, &local_err, false);
     aio_context_release(aio_context);
     if (local_err) {
         goto done;
@@ -965,7 +973,8 @@ static int img_commit(int argc, char **argv)
         bdrv_ref(bs);
     }
 
-    run_block_job(bs->job, &local_err);
+    job = block_job_get("commit");
+    run_block_job(job, &local_err);
     if (local_err) {
         goto unref_backing;
     }
@@ -1462,48 +1471,61 @@ enum ImgConvertBlockStatus {
     BLK_BACKING_FILE,
 };
 
+#define MAX_COROUTINES 16
+
 typedef struct ImgConvertState {
     BlockBackend **src;
     int64_t *src_sectors;
-    int src_cur, src_num;
+    int src_num;
-    int64_t src_cur_offset;
     int64_t total_sectors;
     int64_t allocated_sectors;
+    int64_t allocated_done;
+    int64_t sector_num;
+    int64_t wr_offs;
     enum ImgConvertBlockStatus status;
     int64_t sector_next_status;
     BlockBackend *target;
     bool has_zero_init;
     bool compressed;
     bool target_has_backing;
+    bool wr_in_order;
     int min_sparse;
     size_t cluster_sectors;
     size_t buf_sectors;
+    int num_coroutines;
+    int running_coroutines;
+    Coroutine *co[MAX_COROUTINES];
+    int64_t wait_sector_num[MAX_COROUTINES];
+    CoMutex lock;
+    int ret;
 } ImgConvertState;
 
-static void convert_select_part(ImgConvertState *s, int64_t sector_num)
+static void convert_select_part(ImgConvertState *s, int64_t sector_num,
+                                int *src_cur, int64_t *src_cur_offset)
 {
-    assert(sector_num >= s->src_cur_offset);
+    *src_cur = 0;
-    while (sector_num - s->src_cur_offset >= s->src_sectors[s->src_cur]) {
+    *src_cur_offset = 0;
-        s->src_cur_offset += s->src_sectors[s->src_cur];
+    while (sector_num - *src_cur_offset >= s->src_sectors[*src_cur]) {
-        s->src_cur++;
+        *src_cur_offset += s->src_sectors[*src_cur];
-        assert(s->src_cur < s->src_num);
+        (*src_cur)++;
+        assert(*src_cur < s->src_num);
     }
 }
 
 static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num)
 {
-    int64_t ret;
+    int64_t ret, src_cur_offset;
-    int n;
+    int n, src_cur;
 
-    convert_select_part(s, sector_num);
+    convert_select_part(s, sector_num, &src_cur, &src_cur_offset);
 
     assert(s->total_sectors > sector_num);
     n = MIN(s->total_sectors - sector_num, BDRV_REQUEST_MAX_SECTORS);
 
     if (s->sector_next_status <= sector_num) {
         BlockDriverState *file;
-        ret = bdrv_get_block_status(blk_bs(s->src[s->src_cur]),
+        ret = bdrv_get_block_status(blk_bs(s->src[src_cur]),
-                                    sector_num - s->src_cur_offset,
+                                    sector_num - src_cur_offset,
                                     n, &n, &file);
         if (ret < 0) {
             return ret;
@@ -1519,8 +1541,8 @@ static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num)
             /* Check block status of the backing file chain to avoid
              * needlessly reading zeroes and limiting the iteration to the
              * buffer size */
-            ret = bdrv_get_block_status_above(blk_bs(s->src[s->src_cur]), NULL,
+            ret = bdrv_get_block_status_above(blk_bs(s->src[src_cur]), NULL,
-                                              sector_num - s->src_cur_offset,
+                                              sector_num - src_cur_offset,
                                               n, &n, &file);
             if (ret < 0) {
                 return ret;
@@ -1558,28 +1580,34 @@ static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num)
     return n;
 }
 
-static int convert_read(ImgConvertState *s, int64_t sector_num, int nb_sectors,
+static int coroutine_fn convert_co_read(ImgConvertState *s, int64_t sector_num,
-                        uint8_t *buf)
+                                        int nb_sectors, uint8_t *buf)
 {
-    int n;
+    int n, ret;
-    int ret;
+    QEMUIOVector qiov;
+    struct iovec iov;
 
     assert(nb_sectors <= s->buf_sectors);
     while (nb_sectors > 0) {
         BlockBackend *blk;
-        int64_t bs_sectors;
+        int src_cur;
+        int64_t bs_sectors, src_cur_offset;
 
         /* In the case of compression with multiple source files, we can get a
          * nb_sectors that spreads into the next part. So we must be able to
          * read across multiple BDSes for one convert_read() call. */
-        convert_select_part(s, sector_num);
+        convert_select_part(s, sector_num, &src_cur, &src_cur_offset);
-        blk = s->src[s->src_cur];
+        blk = s->src[src_cur];
-        bs_sectors = s->src_sectors[s->src_cur];
+        bs_sectors = s->src_sectors[src_cur];
 
-        n = MIN(nb_sectors, bs_sectors - (sector_num - s->src_cur_offset));
+        n = MIN(nb_sectors, bs_sectors - (sector_num - src_cur_offset));
-        ret = blk_pread(blk,
+        iov.iov_base = buf;
-                        (sector_num - s->src_cur_offset) << BDRV_SECTOR_BITS,
+        iov.iov_len = n << BDRV_SECTOR_BITS;
-                        buf, n << BDRV_SECTOR_BITS);
+        qemu_iovec_init_external(&qiov, &iov, 1);
+
+        ret = blk_co_preadv(
+                blk, (sector_num - src_cur_offset) << BDRV_SECTOR_BITS,
+                n << BDRV_SECTOR_BITS, &qiov, 0);
         if (ret < 0) {
             return ret;
         }
@@ -1592,15 +1620,18 @@ static int convert_read(ImgConvertState *s, int64_t sector_num, int nb_sectors,
     return 0;
 }
 
-static int convert_write(ImgConvertState *s, int64_t sector_num, int nb_sectors,
+
-                         const uint8_t *buf)
+static int coroutine_fn convert_co_write(ImgConvertState *s, int64_t sector_num,
+                                         int nb_sectors, uint8_t *buf,
+                                         enum ImgConvertBlockStatus status)
 {
     int ret;
+    QEMUIOVector qiov;
+    struct iovec iov;
 
     while (nb_sectors > 0) {
         int n = nb_sectors;
-
+        switch (status) {
-        switch (s->status) {
         case BLK_BACKING_FILE:
             /* If we have a backing file, leave clusters unallocated that are
              * unallocated in the source image, so that the backing file is
@@ -1621,9 +1652,13 @@ static int convert_write(ImgConvertState *s, int64_t sector_num, int nb_sectors,
                     break;
                 }
 
-                ret = blk_pwrite_compressed(s->target,
+                iov.iov_base = buf;
-                                            sector_num << BDRV_SECTOR_BITS,
+                iov.iov_len = n << BDRV_SECTOR_BITS;
-                                            buf, n << BDRV_SECTOR_BITS);
+                qemu_iovec_init_external(&qiov, &iov, 1);
+
+                ret = blk_co_pwritev(s->target, sector_num << BDRV_SECTOR_BITS,
+                                     n << BDRV_SECTOR_BITS, &qiov,
+                                     BDRV_REQ_WRITE_COMPRESSED);
                 if (ret < 0) {
                     return ret;
                 }
@@ -1636,8 +1671,12 @@ static int convert_write(ImgConvertState *s, int64_t sector_num, int nb_sectors,
             if (!s->min_sparse ||
                 is_allocated_sectors_min(buf, n, &n, s->min_sparse))
             {
-                ret = blk_pwrite(s->target, sector_num << BDRV_SECTOR_BITS,
+                iov.iov_base = buf;
-                                 buf, n << BDRV_SECTOR_BITS, 0);
+                iov.iov_len = n << BDRV_SECTOR_BITS;
+                qemu_iovec_init_external(&qiov, &iov, 1);
+
+                ret = blk_co_pwritev(s->target, sector_num << BDRV_SECTOR_BITS,
+                                     n << BDRV_SECTOR_BITS, &qiov, 0);
                 if (ret < 0) {
                     return ret;
                 }
@@ -1649,8 +1688,9 @@ static int convert_write(ImgConvertState *s, int64_t sector_num, int nb_sectors,
             if (s->has_zero_init) {
                 break;
             }
-            ret = blk_pwrite_zeroes(s->target, sector_num << BDRV_SECTOR_BITS,
+            ret = blk_co_pwrite_zeroes(s->target,
-                                    n << BDRV_SECTOR_BITS, 0);
+                                       sector_num << BDRV_SECTOR_BITS,
+                                       n << BDRV_SECTOR_BITS, 0);
             if (ret < 0) {
                 return ret;
             }
@@ -1665,12 +1705,122 @@ static int convert_write(ImgConvertState *s, int64_t sector_num, int nb_sectors,
     return 0;
 }
 
+static void coroutine_fn convert_co_do_copy(void *opaque)
+{
+    ImgConvertState *s = opaque;
+    uint8_t *buf = NULL;
+    int ret, i;
+    int index = -1;
+
+    for (i = 0; i < s->num_coroutines; i++) {
+        if (s->co[i] == qemu_coroutine_self()) {
+            index = i;
+            break;
+        }
+    }
+    assert(index >= 0);
+
+    s->running_coroutines++;
+    buf = blk_blockalign(s->target, s->buf_sectors * BDRV_SECTOR_SIZE);
+
+    while (1) {
+        int n;
+        int64_t sector_num;
+        enum ImgConvertBlockStatus status;
+
+        qemu_co_mutex_lock(&s->lock);
+        if (s->ret != -EINPROGRESS || s->sector_num >= s->total_sectors) {
+            qemu_co_mutex_unlock(&s->lock);
+            goto out;
+        }
+        n = convert_iteration_sectors(s, s->sector_num);
+        if (n < 0) {
+            qemu_co_mutex_unlock(&s->lock);
+            s->ret = n;
+            goto out;
+        }
+        /* save current sector and allocation status to local variables */
+        sector_num = s->sector_num;
+        status = s->status;
+        if (!s->min_sparse && s->status == BLK_ZERO) {
+            n = MIN(n, s->buf_sectors);
+        }
+        /* increment global sector counter so that other coroutines can
+         * already continue reading beyond this request */
+        s->sector_num += n;
+        qemu_co_mutex_unlock(&s->lock);
+
+        if (status == BLK_DATA || (!s->min_sparse && status == BLK_ZERO)) {
+            s->allocated_done += n;
+            qemu_progress_print(100.0 * s->allocated_done /
+                                        s->allocated_sectors, 0);
+        }
+
+        if (status == BLK_DATA) {
+            ret = convert_co_read(s, sector_num, n, buf);
+            if (ret < 0) {
+                error_report("error while reading sector %" PRId64
+                             ": %s", sector_num, strerror(-ret));
+                s->ret = ret;
+                goto out;
+            }
+        } else if (!s->min_sparse && status == BLK_ZERO) {
+            status = BLK_DATA;
+            memset(buf, 0x00, n * BDRV_SECTOR_SIZE);
+        }
+
+        if (s->wr_in_order) {
+            /* keep writes in order */
+            while (s->wr_offs != sector_num) {
+                if (s->ret != -EINPROGRESS) {
+                    goto out;
+                }
+                s->wait_sector_num[index] = sector_num;
+                qemu_coroutine_yield();
+            }
+            s->wait_sector_num[index] = -1;
+        }
+
+        ret = convert_co_write(s, sector_num, n, buf, status);
+        if (ret < 0) {
+            error_report("error while writing sector %" PRId64
+                         ": %s", sector_num, strerror(-ret));
+            s->ret = ret;
+            goto out;
+        }
+
+        if (s->wr_in_order) {
+            /* reenter the coroutine that might have waited
+             * for this write to complete */
+            s->wr_offs = sector_num + n;
+            for (i = 0; i < s->num_coroutines; i++) {
+                if (s->co[i] && s->wait_sector_num[i] == s->wr_offs) {
+                    /*
+                     * A -> B -> A cannot occur because A has
+                     * s->wait_sector_num[i] == -1 during A -> B.  Therefore
+                     * B will never enter A during this time window.
+                     */
+                    qemu_coroutine_enter(s->co[i]);
+                    break;
+                }
+            }
+        }
+    }
+
+out:
+    qemu_vfree(buf);
+    s->co[index] = NULL;
+    s->running_coroutines--;
+    if (!s->running_coroutines && s->ret == -EINPROGRESS) {
+        /* the convert job finished successfully */
+        s->ret = 0;
+    }
+}
+
 static int convert_do_copy(ImgConvertState *s)
 {
-    uint8_t *buf = NULL;
+    int ret, i, n;
-    int64_t sector_num, allocated_done;
+    int64_t sector_num = 0;
-    int ret;
-    int n;
 
     /* Check whether we have zero initialisation or can get it efficiently */
     s->has_zero_init = s->min_sparse && !s->target_has_backing
@@ -1691,21 +1841,15 @@ static int convert_do_copy(ImgConvertState *s)
     if (s->compressed) {
         if (s->cluster_sectors <= 0 || s->cluster_sectors > s->buf_sectors) {
             error_report("invalid cluster size");
-            ret = -EINVAL;
+            return -EINVAL;
-            goto fail;
         }
         s->buf_sectors = s->cluster_sectors;
     }
-    buf = blk_blockalign(s->target, s->buf_sectors * BDRV_SECTOR_SIZE);
 
-    /* Calculate allocated sectors for progress */
-    s->allocated_sectors = 0;
-    sector_num = 0;
     while (sector_num < s->total_sectors) {
         n = convert_iteration_sectors(s, sector_num);
         if (n < 0) {
-            ret = n;
+            return n;
-            goto fail;
         }
         if (s->status == BLK_DATA || (!s->min_sparse && s->status == BLK_ZERO))
         {
@@ -1715,61 +1859,29 @@ static int convert_do_copy(ImgConvertState *s)
     }
 
     /* Do the copy */
-    s->src_cur = 0;
-    s->src_cur_offset = 0;
     s->sector_next_status = 0;
+    s->ret = -EINPROGRESS;
 
-    sector_num = 0;
+    qemu_co_mutex_init(&s->lock);
-    allocated_done = 0;
+    for (i = 0; i < s->num_coroutines; i++) {
-
+        s->co[i] = qemu_coroutine_create(convert_co_do_copy, s);
-    while (sector_num < s->total_sectors) {
+        s->wait_sector_num[i] = -1;
-        n = convert_iteration_sectors(s, sector_num);
+        qemu_coroutine_enter(s->co[i]);
-        if (n < 0) {
-            ret = n;
-            goto fail;
-        }
-        if (s->status == BLK_DATA || (!s->min_sparse && s->status == BLK_ZERO))
-        {
-            allocated_done += n;
-            qemu_progress_print(100.0 * allocated_done / s->allocated_sectors,
-                                0);
-        }
-
-        if (s->status == BLK_DATA) {
-            ret = convert_read(s, sector_num, n, buf);
-            if (ret < 0) {
-                error_report("error while reading sector %" PRId64
-                             ": %s", sector_num, strerror(-ret));
-                goto fail;
-            }
-        } else if (!s->min_sparse && s->status == BLK_ZERO) {
-            n = MIN(n, s->buf_sectors);
-            memset(buf, 0, n * BDRV_SECTOR_SIZE);
-            s->status = BLK_DATA;
-        }
-
-        ret = convert_write(s, sector_num, n, buf);
-        if (ret < 0) {
-            error_report("error while writing sector %" PRId64
-                         ": %s", sector_num, strerror(-ret));
-            goto fail;
-        }
-
-        sector_num += n;
     }
 
-    if (s->compressed) {
+    while (s->ret == -EINPROGRESS) {
+        main_loop_wait(false);
+    }
+
+    if (s->compressed && !s->ret) {
         /* signal EOF to align */
         ret = blk_pwrite_compressed(s->target, 0, NULL, 0);
         if (ret < 0) {
-            goto fail;
+            return ret;
         }
     }
 
-    ret = 0;
+    return s->ret;
-fail:
-    qemu_vfree(buf);
-    return ret;
 }
 
 static int img_convert(int argc, char **argv)
@@ -1797,6 +1909,8 @@ static int img_convert(int argc, char **argv)
     QemuOpts *sn_opts = NULL;
     ImgConvertState state;
     bool image_opts = false;
+    bool wr_in_order = true;
+    long num_coroutines = 8;
 
     fmt = NULL;
     out_fmt = "raw";
@@ -1812,7 +1926,7 @@ static int img_convert(int argc, char **argv)
             {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
             {0, 0, 0, 0}
         };
-        c = getopt_long(argc, argv, "hf:O:B:ce6o:s:l:S:pt:T:qn",
+        c = getopt_long(argc, argv, "hf:O:B:ce6o:s:l:S:pt:T:qnm:W",
                         long_options, NULL);
         if (c == -1) {
             break;
@@ -1904,6 +2018,18 @@ static int img_convert(int argc, char **argv)
         case 'n':
             skip_create = 1;
             break;
+        case 'm':
+            if (qemu_strtol(optarg, NULL, 0, &num_coroutines) ||
+                num_coroutines < 1 || num_coroutines > MAX_COROUTINES) {
+                error_report("Invalid number of coroutines. Allowed number of"
+                             " coroutines is between 1 and %d", MAX_COROUTINES);
+                ret = -1;
+                goto fail_getopt;
+            }
+            break;
+        case 'W':
+            wr_in_order = false;
+            break;
         case OPTION_OBJECT:
             opts = qemu_opts_parse_noisily(&qemu_object_opts,
                                            optarg, true);
@@ -1923,6 +2049,12 @@ static int img_convert(int argc, char **argv)
         goto fail_getopt;
     }
 
+    if (!wr_in_order && compress) {
+        error_report("Out of order write and compress are mutually exclusive");
+        ret = -1;
+        goto fail_getopt;
+    }
+
     /* Initialize before goto out */
     if (quiet) {
         progress = 0;
@@ -2163,6 +2295,8 @@ static int img_convert(int argc, char **argv)
         .min_sparse         = min_sparse,
         .cluster_sectors    = cluster_sectors,
         .buf_sectors        = bufsectors,
+        .wr_in_order        = wr_in_order,
+        .num_coroutines     = num_coroutines,
     };
     ret = convert_do_copy(&state);
 
@@ -3289,7 +3423,7 @@ static int img_resize(int argc, char **argv)
     qemu_opts_del(param);
 
     blk = img_open(image_opts, filename, fmt,
-                   BDRV_O_RDWR, false, quiet);
+                   BDRV_O_RDWR | BDRV_O_RESIZE, false, quiet);
     if (!blk) {
         ret = -1;
         goto out;

qemu-img.texi

@@ -137,6 +137,12 @@ Parameters to convert subcommand:
 
 @item -n
 Skip the creation of the target volume
+@item -m
+Number of parallel coroutines for the convert process
+@item -W
+Allow out-of-order writes to the destination. This option improves performance,
+but is only recommended for preallocated devices like host devices or other
+raw block devices.
 @end table
 
 Parameters to dd subcommand:
@@ -296,7 +302,7 @@ Error on reading data
 
 @end table
 
-@item convert [-c] [-p] [-n] [-f @var{fmt}] [-t @var{cache}] [-T @var{src_cache}] [-O @var{output_fmt}] [-o @var{options}] [-s @var{snapshot_id_or_name}] [-l @var{snapshot_param}] [-S @var{sparse_size}] @var{filename} [@var{filename2} [...]] @var{output_filename}
+@item convert [-c] [-p] [-n] [-f @var{fmt}] [-t @var{cache}] [-T @var{src_cache}] [-O @var{output_fmt}] [-o @var{options}] [-s @var{snapshot_id_or_name}] [-l @var{snapshot_param}] [-m @var{num_coroutines}] [-W] [-S @var{sparse_size}] @var{filename} [@var{filename2} [...]] @var{output_filename}
 
 Convert the disk image @var{filename} or a snapshot @var{snapshot_param}(@var{snapshot_id_or_name} is deprecated)
 to disk image @var{output_filename} using format @var{output_fmt}. It can be optionally compressed (@code{-c}
@@ -326,6 +332,14 @@ skipped. This is useful for formats such as @code{rbd} if the target
 volume has already been created with site specific options that cannot
 be supplied through qemu-img.
 
+Out of order writes can be enabled with @code{-W} to improve performance.
+This is only recommended for preallocated devices like host devices or other
+raw block devices. Out of order write does not work in combination with
+creating compressed images.
+
+@var{num_coroutines} specifies how many coroutines work in parallel during
+the convert process (defaults to 8).
+
 @item dd [-f @var{fmt}] [-O @var{output_fmt}] [bs=@var{block_size}] [count=@var{blocks}] [skip=@var{blocks}] if=@var{input} of=@var{output}
 
 Dd copies from @var{input} file to @var{output} file converting it from

qemu-io-cmds.c

@@ -83,6 +83,29 @@ static int command(BlockBackend *blk, const cmdinfo_t *ct, int argc,
         }
         return 0;
     }
+
+    /* Request additional permissions if necessary for this command. The caller
+     * is responsible for restoring the original permissions afterwards if this
+     * is what it wants. */
+    if (ct->perm && blk_is_available(blk)) {
+        uint64_t orig_perm, orig_shared_perm;
+        blk_get_perm(blk, &orig_perm, &orig_shared_perm);
+
+        if (ct->perm & ~orig_perm) {
+            uint64_t new_perm;
+            Error *local_err = NULL;
+            int ret;
+
+            new_perm = orig_perm | ct->perm;
+
+            ret = blk_set_perm(blk, new_perm, orig_shared_perm, &local_err);
+            if (ret < 0) {
+                error_report_err(local_err);
+                return 0;
+            }
+        }
+    }
+
     optind = 0;
     return ct->cfunc(blk, argc, argv);
 }
@@ -918,6 +941,7 @@ static const cmdinfo_t write_cmd = {
     .name       = "write",
     .altname    = "w",
     .cfunc      = write_f,
+    .perm       = BLK_PERM_WRITE,
     .argmin     = 2,
     .argmax     = -1,
     .args       = "[-bcCfquz] [-P pattern] off len",
@@ -1093,6 +1117,7 @@ static int writev_f(BlockBackend *blk, int argc, char **argv);
 static const cmdinfo_t writev_cmd = {
     .name       = "writev",
     .cfunc      = writev_f,
+    .perm       = BLK_PERM_WRITE,
     .argmin     = 2,
     .argmax     = -1,
     .args       = "[-Cfq] [-P pattern] off len [len..]",
@@ -1392,6 +1417,7 @@ static int aio_write_f(BlockBackend *blk, int argc, char **argv);
 static const cmdinfo_t aio_write_cmd = {
     .name       = "aio_write",
     .cfunc      = aio_write_f,
+    .perm       = BLK_PERM_WRITE,
     .argmin     = 2,
     .argmax     = -1,
     .args       = "[-Cfiquz] [-P pattern] off len [len..]",
@@ -1556,6 +1582,7 @@ static const cmdinfo_t truncate_cmd = {
     .name       = "truncate",
     .altname    = "t",
     .cfunc      = truncate_f,
+    .perm       = BLK_PERM_WRITE | BLK_PERM_RESIZE,
     .argmin     = 1,
     .argmax     = 1,
     .args       = "off",
@@ -1653,6 +1680,7 @@ static const cmdinfo_t discard_cmd = {
     .name       = "discard",
     .altname    = "d",
     .cfunc      = discard_f,
+    .perm       = BLK_PERM_WRITE,
     .argmin     = 2,
     .argmax     = -1,
     .args       = "[-Cq] off len",

tests/qemu-iotests/049.out

@@ -95,14 +95,14 @@ qemu-img create -f qcow2 TEST_DIR/t.qcow2 -- -1024
 qemu-img: Image size must be less than 8 EiB!
 
 qemu-img create -f qcow2 -o size=-1024 TEST_DIR/t.qcow2
-qemu-img: Parameter 'size' expects a non-negative number below 2^64
+qemu-img: Value '-1024' is out of range for parameter 'size'
 qemu-img: TEST_DIR/t.qcow2: Invalid options for file format 'qcow2'
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 -- -1k
 qemu-img: Image size must be less than 8 EiB!
 
 qemu-img create -f qcow2 -o size=-1k TEST_DIR/t.qcow2
-qemu-img: Parameter 'size' expects a non-negative number below 2^64
+qemu-img: Value '-1k' is out of range for parameter 'size'
 qemu-img: TEST_DIR/t.qcow2: Invalid options for file format 'qcow2'
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 -- 1kilobyte
@@ -110,15 +110,19 @@ qemu-img: Invalid image size specified! You may use k, M, G, T, P or E suffixes
 qemu-img: kilobytes, megabytes, gigabytes, terabytes, petabytes and exabytes.
 
 qemu-img create -f qcow2 -o size=1kilobyte TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 encryption=off cluster_size=65536 lazy_refcounts=off refcount_bits=16
+qemu-img: Parameter 'size' expects a non-negative number below 2^64
+Optional suffix k, M, G, T, P or E means kilo-, mega-, giga-, tera-, peta-
+and exabytes, respectively.
+qemu-img: TEST_DIR/t.qcow2: Invalid options for file format 'qcow2'
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 -- foobar
 qemu-img: Invalid image size specified! You may use k, M, G, T, P or E suffixes for
 qemu-img: kilobytes, megabytes, gigabytes, terabytes, petabytes and exabytes.
 
 qemu-img create -f qcow2 -o size=foobar TEST_DIR/t.qcow2
-qemu-img: Parameter 'size' expects a size
+qemu-img: Parameter 'size' expects a non-negative number below 2^64
-You may use k, M, G or T suffixes for kilobytes, megabytes, gigabytes and terabytes.
+Optional suffix k, M, G, T, P or E means kilo-, mega-, giga-, tera-, peta-
+and exabytes, respectively.
 qemu-img: TEST_DIR/t.qcow2: Invalid options for file format 'qcow2'
 
 == Check correct interpretation of suffixes for cluster size ==

tests/qemu-iotests/051.pc.out

@@ -179,7 +179,7 @@ qququiquit
 
 Testing: -drive file=TEST_DIR/t.qcow2,if=ide,readonly=on
 QEMU X.Y.Z monitor - type 'help' for more information
-(qemu) QEMU_PROG: Can't use a read-only drive
+(qemu) QEMU_PROG: Block node is read-only
 QEMU_PROG: Initialization of device ide-hd failed: Device initialization failed.
 
 Testing: -drive file=TEST_DIR/t.qcow2,if=scsi,readonly=on
@@ -201,12 +201,12 @@ QEMU X.Y.Z monitor - type 'help' for more information
 
 Testing: -drive file=TEST_DIR/t.qcow2,if=none,id=disk,readonly=on -device ide-drive,drive=disk
 QEMU X.Y.Z monitor - type 'help' for more information
-(qemu) QEMU_PROG: -device ide-drive,drive=disk: Can't use a read-only drive
+(qemu) QEMU_PROG: -device ide-drive,drive=disk: Block node is read-only
 QEMU_PROG: -device ide-drive,drive=disk: Device initialization failed.
 
 Testing: -drive file=TEST_DIR/t.qcow2,if=none,id=disk,readonly=on -device ide-hd,drive=disk
 QEMU X.Y.Z monitor - type 'help' for more information
-(qemu) QEMU_PROG: -device ide-hd,drive=disk: Can't use a read-only drive
+(qemu) QEMU_PROG: -device ide-hd,drive=disk: Block node is read-only
 QEMU_PROG: -device ide-hd,drive=disk: Device initialization failed.
 
 Testing: -drive file=TEST_DIR/t.qcow2,if=none,id=disk,readonly=on -device lsi53c895a -device scsi-disk,drive=disk

tests/qemu-iotests/055

@@ -48,7 +48,8 @@ class TestSingleDrive(iotests.QMPTestCase):
     def setUp(self):
         qemu_img('create', '-f', iotests.imgfmt, blockdev_target_img, str(image_len))
 
-        self.vm = iotests.VM().add_drive(test_img).add_drive(blockdev_target_img)
+        self.vm = iotests.VM().add_drive(test_img)
+        self.vm.add_drive(blockdev_target_img, interface="none")
         if iotests.qemu_default_machine == 'pc':
             self.vm.add_drive(None, 'media=cdrom', 'ide')
         self.vm.launch()
@@ -164,7 +165,8 @@ class TestSetSpeed(iotests.QMPTestCase):
     def setUp(self):
         qemu_img('create', '-f', iotests.imgfmt, blockdev_target_img, str(image_len))
 
-        self.vm = iotests.VM().add_drive(test_img).add_drive(blockdev_target_img)
+        self.vm = iotests.VM().add_drive(test_img)
+        self.vm.add_drive(blockdev_target_img, interface="none")
         self.vm.launch()
 
     def tearDown(self):
@@ -247,7 +249,8 @@ class TestSingleTransaction(iotests.QMPTestCase):
     def setUp(self):
         qemu_img('create', '-f', iotests.imgfmt, blockdev_target_img, str(image_len))
 
-        self.vm = iotests.VM().add_drive(test_img).add_drive(blockdev_target_img)
+        self.vm = iotests.VM().add_drive(test_img)
+        self.vm.add_drive(blockdev_target_img, interface="none")
         if iotests.qemu_default_machine == 'pc':
             self.vm.add_drive(None, 'media=cdrom', 'ide')
         self.vm.launch()
@@ -460,7 +463,7 @@ class TestDriveCompression(iotests.QMPTestCase):
 
         qemu_img('create', '-f', fmt, blockdev_target_img,
                  str(TestDriveCompression.image_len), *args)
-        self.vm.add_drive(blockdev_target_img, format=fmt)
+        self.vm.add_drive(blockdev_target_img, format=fmt, interface="none")
 
         self.vm.launch()
 

tests/qemu-iotests/085.out

@@ -74,7 +74,7 @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/
 
 === Invalid command - snapshot node used as backing hd ===
 
-{"error": {"class": "GenericError", "desc": "Node 'snap_11' is busy: node is used as backing hd of 'virtio0'"}}
+{"error": {"class": "GenericError", "desc": "Node 'snap_11' is busy: node is used as backing hd of 'snap_12'"}}
 
 === Invalid command - snapshot node has a backing image ===
 

tests/qemu-iotests/141

@@ -67,7 +67,7 @@ test_blockjob()
     _send_qemu_cmd $QEMU_HANDLE \
         "{'execute': 'x-blockdev-del',
           'arguments': {'node-name': 'drv0'}}" \
-        'error'
+        'error' | _filter_generated_node_ids
 
     _send_qemu_cmd $QEMU_HANDLE \
         "{'execute': 'block-job-cancel',

tests/qemu-iotests/141.out

@@ -20,7 +20,7 @@ Formatting 'TEST_DIR/o.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.
 Formatting 'TEST_DIR/o.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.IMGFMT backing_fmt=IMGFMT
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "mirror"}}
 {"return": {}}
-{"error": {"class": "GenericError", "desc": "Node drv0 is in use"}}
+{"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: node is used as backing hd of 'NODE_NAME'"}}
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "mirror"}}
 {"return": {}}
@@ -30,7 +30,7 @@ Formatting 'TEST_DIR/o.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}}
 {"return": {}}
-{"error": {"class": "GenericError", "desc": "Node drv0 is in use"}}
+{"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: node is used as backing hd of 'NODE_NAME'"}}
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}}
 {"return": {}}

tests/qemu-iotests/172.out

@@ -28,6 +28,7 @@ Testing:
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "288"
 
 
@@ -57,6 +58,7 @@ Testing: -fda TEST_DIR/t.qcow2
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -fdb TEST_DIR/t.qcow2
@@ -83,6 +85,7 @@ Testing: -fdb TEST_DIR/t.qcow2
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 0 (0x0)
@@ -93,6 +96,7 @@ Testing: -fdb TEST_DIR/t.qcow2
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "288"
 
 Testing: -fda TEST_DIR/t.qcow2 -fdb TEST_DIR/t.qcow2
@@ -119,6 +123,7 @@ Testing: -fda TEST_DIR/t.qcow2 -fdb TEST_DIR/t.qcow2
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 0 (0x0)
@@ -129,6 +134,7 @@ Testing: -fda TEST_DIR/t.qcow2 -fdb TEST_DIR/t.qcow2
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 
@@ -158,6 +164,7 @@ Testing: -drive if=floppy,file=TEST_DIR/t.qcow2
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -drive if=floppy,file=TEST_DIR/t.qcow2,index=1
@@ -184,6 +191,7 @@ Testing: -drive if=floppy,file=TEST_DIR/t.qcow2,index=1
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 0 (0x0)
@@ -194,6 +202,7 @@ Testing: -drive if=floppy,file=TEST_DIR/t.qcow2,index=1
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "288"
 
 Testing: -drive if=floppy,file=TEST_DIR/t.qcow2 -drive if=floppy,file=TEST_DIR/t.qcow2,index=1
@@ -220,6 +229,7 @@ Testing: -drive if=floppy,file=TEST_DIR/t.qcow2 -drive if=floppy,file=TEST_DIR/t
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 0 (0x0)
@@ -230,6 +240,7 @@ Testing: -drive if=floppy,file=TEST_DIR/t.qcow2 -drive if=floppy,file=TEST_DIR/t
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 
@@ -259,6 +270,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -global isa-fdc.driveA=none0
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -drive if=none,file=TEST_DIR/t.qcow2 -global isa-fdc.driveB=none0
@@ -285,6 +297,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -global isa-fdc.driveB=none0
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -global isa-fdc.driveA=none0 -global isa-fdc.driveB=none1
@@ -311,6 +324,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qco
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 0 (0x0)
@@ -321,6 +335,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qco
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 
@@ -350,6 +365,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0,unit=1
@@ -376,6 +392,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0,unit=1
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0 -device floppy,drive=none1,unit=1
@@ -402,6 +419,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qco
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 0 (0x0)
@@ -412,6 +430,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qco
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 
@@ -441,6 +460,7 @@ Testing: -fda TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -global isa-
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 0 (0x0)
@@ -451,6 +471,7 @@ Testing: -fda TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -global isa-
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -fdb TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -global isa-fdc.driveA=none0
@@ -477,6 +498,7 @@ Testing: -fdb TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -global isa-
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 0 (0x0)
@@ -487,6 +509,7 @@ Testing: -fdb TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -global isa-
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -fda TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -global isa-fdc.driveA=none0
@@ -513,6 +536,7 @@ Testing: -fda TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -global isa-
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -fdb TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -global isa-fdc.driveB=none0
@@ -539,6 +563,7 @@ Testing: -fdb TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -global isa-
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 
@@ -568,6 +593,7 @@ Testing: -fda TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device flop
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 0 (0x0)
@@ -578,6 +604,7 @@ Testing: -fda TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device flop
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -fda TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0,unit=1
@@ -604,6 +631,7 @@ Testing: -fda TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device flop
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 0 (0x0)
@@ -614,6 +642,7 @@ Testing: -fda TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device flop
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -fdb TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0
@@ -640,6 +669,7 @@ Testing: -fdb TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device flop
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 1 (0x1)
@@ -650,6 +680,7 @@ Testing: -fdb TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device flop
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -fdb TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0,unit=0
@@ -676,6 +707,7 @@ Testing: -fdb TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device flop
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 1 (0x1)
@@ -686,6 +718,7 @@ Testing: -fdb TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device flop
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -fda TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0,unit=0
@@ -723,6 +756,7 @@ Testing: -drive if=floppy,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.q
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 0 (0x0)
@@ -733,6 +767,7 @@ Testing: -drive if=floppy,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.q
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -drive if=floppy,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0,unit=1
@@ -759,6 +794,7 @@ Testing: -drive if=floppy,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.q
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 0 (0x0)
@@ -769,6 +805,7 @@ Testing: -drive if=floppy,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.q
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -drive if=floppy,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0,unit=0
@@ -802,6 +839,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qco
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 0 (0x0)
@@ -812,6 +850,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qco
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -global isa-fdc.driveA=none0 -device floppy,drive=none1,unit=1
@@ -838,6 +877,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qco
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 0 (0x0)
@@ -848,6 +888,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qco
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -global isa-fdc.driveB=none0 -device floppy,drive=none1
@@ -874,6 +915,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qco
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 1 (0x1)
@@ -884,6 +926,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qco
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -global isa-fdc.driveB=none0 -device floppy,drive=none1,unit=0
@@ -910,6 +953,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qco
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
               dev: floppy, id ""
                 unit = 1 (0x1)
@@ -920,6 +964,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qco
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -drive if=none,file=TEST_DIR/t.qcow2 -drive if=none,file=TEST_DIR/t.qcow2 -global isa-fdc.driveA=none0 -device floppy,drive=none1,unit=0
@@ -964,6 +1009,7 @@ Testing: -device floppy
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "288"
 
 Testing: -device floppy,drive-type=120
@@ -990,6 +1036,7 @@ Testing: -device floppy,drive-type=120
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "120"
 
 Testing: -device floppy,drive-type=144
@@ -1016,6 +1063,7 @@ Testing: -device floppy,drive-type=144
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -device floppy,drive-type=288
@@ -1042,6 +1090,7 @@ Testing: -device floppy,drive-type=288
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "288"
 
 
@@ -1071,6 +1120,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0,drive-t
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "120"
 
 Testing: -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0,drive-type=288
@@ -1097,6 +1147,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0,drive-t
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "288"
 
 
@@ -1126,6 +1177,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0,logical
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0,physical_block_size=512
@@ -1152,6 +1204,7 @@ Testing: -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0,physica
                 opt_io_size = 0 (0x0)
                 discard_granularity = 4294967295 (0xffffffff)
                 write-cache = "auto"
+                share-rw = false
                 drive-type = "144"
 
 Testing: -drive if=none,file=TEST_DIR/t.qcow2 -device floppy,drive=none0,logical_block_size=4096

tests/test-blockjob-txn.c

@@ -101,9 +101,9 @@ static BlockJob *test_block_job_start(unsigned int iterations,
     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,
+    s = block_job_create(job_id, &test_block_job_driver, bs,
-                         BLOCK_JOB_DEFAULT, test_block_job_cb,
+                         0, BLK_PERM_ALL, 0, BLOCK_JOB_DEFAULT,
-                         data, &error_abort);
+                         test_block_job_cb, data, &error_abort);
     s->iterations = iterations;
     s->use_timer = use_timer;
     s->rc = rc;

tests/test-blockjob.c

@@ -30,8 +30,9 @@ static BlockJob *do_test_id(BlockBackend *blk, const char *id,
     BlockJob *job;
     Error *errp = NULL;
 
-    job = block_job_create(id, &test_block_job_driver, blk_bs(blk), 0,
+    job = block_job_create(id, &test_block_job_driver, blk_bs(blk),
-                           BLOCK_JOB_DEFAULT, block_job_cb, NULL, &errp);
+                           0, BLK_PERM_ALL, 0, BLOCK_JOB_DEFAULT, block_job_cb,
+                           NULL, &errp);
     if (should_succeed) {
         g_assert_null(errp);
         g_assert_nonnull(job);
@@ -53,13 +54,14 @@ static BlockJob *do_test_id(BlockBackend *blk, const char *id,
  * BlockDriverState inserted. */
 static BlockBackend *create_blk(const char *name)
 {
-    BlockBackend *blk = blk_new();
+    /* No I/O is performed on this device */
+    BlockBackend *blk = blk_new(0, BLK_PERM_ALL);
     BlockDriverState *bs;
 
     bs = bdrv_open("null-co://", NULL, NULL, 0, &error_abort);
     g_assert_nonnull(bs);
 
-    blk_insert_bs(blk, bs);
+    blk_insert_bs(blk, bs, &error_abort);
     bdrv_unref(bs);
 
     if (name) {

tests/test-throttle.c

@@ -593,9 +593,10 @@ static void test_groups(void)
     BlockBackend *blk1, *blk2, *blk3;
     BlockBackendPublic *blkp1, *blkp2, *blkp3;
 
-    blk1 = blk_new();
+    /* No actual I/O is performed on these devices */
-    blk2 = blk_new();
+    blk1 = blk_new(0, BLK_PERM_ALL);
-    blk3 = blk_new();
+    blk2 = blk_new(0, BLK_PERM_ALL);
+    blk3 = blk_new(0, BLK_PERM_ALL);
 
     blkp1 = blk_get_public(blk1);
     blkp2 = blk_get_public(blk2);

util/qemu-option.c

@@ -179,7 +179,7 @@ void parse_option_size(const char *name, const char *value,
 
     err = qemu_strtosz(value, NULL, &size);
     if (err == -ERANGE) {
-        error_setg(errp, "Value '%s' is too large for parameter '%s'",
+        error_setg(errp, "Value '%s' is out of range for parameter '%s'",
                    value, name);
         return;
     }