Block layer patches:

- qemu-img create: Fail gracefully when backing file is an empty string
 - Fixes related to filter block nodes ("Deal with filters" series)
 - block/nvme: Various cleanups required to use multiple queues
 - block/nvme: Use NvmeBar structure from "block/nvme.h"
 - file-win32: Fix "locking" option
 - iotests: Allow running from different directory
 -----BEGIN PGP SIGNATURE-----
 
 iQJFBAABCAAvFiEE3D3rFZqa+V09dFb+fwmycsiPL9YFAl9Z7bcRHGt3b2xmQHJl
 ZGhhdC5jb20ACgkQfwmycsiPL9ZS6w//bos+A0RfRRF0YFWkIBLQWxqzKcGvMJ8W
 XWv3mFzd47UaDgRYwVnCC3CR6bLYEINISngZ3geA4jI1+w7AtYKDOO0HN32dUg+D
 ZrNMn02701CA6qkmpxJ+yjsrl9ltR3jYe0me4Wr39Pvdexa2pl/e+M4Vas6FhkYL
 ghAwNThypscGCrFjAlz3ru2Sc/K+sPWrGoqkzr+SWvsm9wy4vb8aLxr8Yy50x/zc
 CqALS9SQ/YA93BCVi9CzPkVyV3ioA0kg/y38WvLtAQ9GZ3m/ekMro3WvdYsRsFCN
 LGXsuwFig+U7Kd7lJrCS9TLnlTJstNGqPq9jEoV5cThPvGknFfMvVOzRmmP7tzqT
 YRcPRy39z44OoLKa3kyg3aF38BTxt+9gPqBnivKMr9j9EecMvPsXXHRvF+lP+LsP
 j753Ih561hX6FurcjX8pc9GOM2cQA0GjlyL77UTTAmLZyFXP/8e55oQbBuYTylc/
 Xlvmc/T+yEGiEGTnK+FxgDAiUaxbCCM9cDVStJjTvsIq43dwXb48g1onDsGZ5eDf
 j9lmAD6TJxHNOB5ErNsDPODf4/D1wJ9t9WVF8UZp9ArfPHRdxMzT7Q4LvetaDmVl
 +hQC9cgTq8Qd8LwSqbKEYua4L6iGbmLAT7/N6htq5L1eVLg76/tLg/tKSwh/vKAY
 yzPmyHaVK84=
 =gaaW
 -----END PGP SIGNATURE-----

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

Block layer patches:

- qemu-img create: Fail gracefully when backing file is an empty string
- Fixes related to filter block nodes ("Deal with filters" series)
- block/nvme: Various cleanups required to use multiple queues
- block/nvme: Use NvmeBar structure from "block/nvme.h"
- file-win32: Fix "locking" option
- iotests: Allow running from different directory

# gpg: Signature made Thu 10 Sep 2020 10:11:19 BST
# gpg:                using RSA key DC3DEB159A9AF95D3D7456FE7F09B272C88F2FD6
# gpg:                issuer "kwolf@redhat.com"
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>" [full]
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* remotes/kevin/tags/for-upstream: (65 commits)
  block/qcow2-cluster: Add missing "fallthrough" annotation
  block/nvme: Pair doorbell registers
  block/nvme: Use generic NvmeBar structure
  block/nvme: Group controller registers in NVMeRegs structure
  file-win32: Fix "locking" option
  iotests: Allow running from different directory
  iotests: Test committing to overridden backing
  iotests: Add test for commit in sub directory
  iotests: Add filter mirror test cases
  iotests: Add filter commit test cases
  iotests: Let complete_and_wait() work with commit
  iotests: Test that qcow2's data-file is flushed
  block: Leave BDS.backing_{file,format} constant
  block: Inline bdrv_co_block_status_from_*()
  blockdev: Fix active commit choice
  block: Drop backing_bs()
  qemu-img: Use child access functions
  nbd: Use CAF when looking for dirty bitmap
  commit: Deal with filters
  backup: Deal with filters
  ...

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

block.c

@@ -712,11 +712,12 @@ int coroutine_fn bdrv_co_delete_file(BlockDriverState *bs, Error **errp)
 int bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz)
 {
     BlockDriver *drv = bs->drv;
+    BlockDriverState *filtered = bdrv_filter_bs(bs);
 
     if (drv && drv->bdrv_probe_blocksizes) {
         return drv->bdrv_probe_blocksizes(bs, bsz);
-    } else if (drv && drv->is_filter && bs->file) {
+    } else if (filtered) {
-        return bdrv_probe_blocksizes(bs->file->bs, bsz);
+        return bdrv_probe_blocksizes(filtered, bsz);
     }
 
     return -ENOTSUP;
@@ -731,11 +732,12 @@ int bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz)
 int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo)
 {
     BlockDriver *drv = bs->drv;
+    BlockDriverState *filtered = bdrv_filter_bs(bs);
 
     if (drv && drv->bdrv_probe_geometry) {
         return drv->bdrv_probe_geometry(bs, geo);
-    } else if (drv && drv->is_filter && bs->file) {
+    } else if (filtered) {
-        return bdrv_probe_geometry(bs->file->bs, geo);
+        return bdrv_probe_geometry(filtered, geo);
     }
 
     return -ENOTSUP;
@@ -1153,10 +1155,6 @@ static void bdrv_backing_attach(BdrvChild *c)
     bdrv_refresh_filename(backing_hd);
 
     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 */
@@ -2612,12 +2610,15 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
  * If @new_bs is not NULL, bdrv_check_perm() must be called beforehand, as this
  * function uses bdrv_set_perm() to update the permissions according to the new
  * reference that @new_bs gets.
+ *
+ * Callers must ensure that child->frozen is false.
  */
 static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs)
 {
     BlockDriverState *old_bs = child->bs;
     uint64_t perm, shared_perm;
 
+    /* Asserts that child->frozen == false */
     bdrv_replace_child_noperm(child, new_bs);
 
     /*
@@ -2778,6 +2779,7 @@ static void bdrv_detach_child(BdrvChild *child)
     g_free(child);
 }
 
+/* Callers must ensure that child->frozen is false. */
 void bdrv_root_unref_child(BdrvChild *child)
 {
     BlockDriverState *child_bs;
@@ -2815,6 +2817,7 @@ static void bdrv_unset_inherits_from(BlockDriverState *root, BdrvChild *child)
     }
 }
 
+/* Callers must ensure that child->frozen is false. */
 void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child)
 {
     if (child == NULL) {
@@ -2863,7 +2866,7 @@ static BdrvChildRole bdrv_backing_role(BlockDriverState *bs)
 }
 
 /*
- * Sets the backing file link of a BDS. A new reference is created; callers
+ * Sets the bs->backing 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,
@@ -2872,7 +2875,7 @@ void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
     bool update_inherits_from = bdrv_chain_contains(bs, backing_hd) &&
         bdrv_inherits_from_recursive(backing_hd, bs);
 
-    if (bdrv_is_backing_chain_frozen(bs, backing_bs(bs), errp)) {
+    if (bdrv_is_backing_chain_frozen(bs, child_bs(bs->backing), errp)) {
         return;
     }
 
@@ -2881,6 +2884,7 @@ void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
     }
 
     if (bs->backing) {
+        /* Cannot be frozen, we checked that above */
         bdrv_unref_child(bs, bs->backing);
         bs->backing = NULL;
     }
@@ -3996,7 +4000,7 @@ static int bdrv_reopen_parse_backing(BDRVReopenState *reopen_state,
                                      Error **errp)
 {
     BlockDriverState *bs = reopen_state->bs;
-    BlockDriverState *overlay_bs, *new_backing_bs;
+    BlockDriverState *overlay_bs, *below_bs, *new_backing_bs;
     QObject *value;
     const char *str;
 
@@ -4035,26 +4039,57 @@ static int bdrv_reopen_parse_backing(BDRVReopenState *reopen_state,
         }
     }
 
+    /*
+     * Ensure that @bs can really handle backing files, because we are
+     * about to give it one (or swap the existing one)
+     */
+    if (bs->drv->is_filter) {
+        /* Filters always have a file or a backing child */
+        if (!bs->backing) {
+            error_setg(errp, "'%s' is a %s filter node that does not support a "
+                       "backing child", bs->node_name, bs->drv->format_name);
+            return -EINVAL;
+        }
+    } else if (!bs->drv->supports_backing) {
+        error_setg(errp, "Driver '%s' of node '%s' does not support backing "
+                   "files", bs->drv->format_name, bs->node_name);
+        return -EINVAL;
+    }
+
     /*
      * Find the "actual" backing file by skipping all links that point
      * to an implicit node, if any (e.g. a commit filter node).
+     * We cannot use any of the bdrv_skip_*() functions here because
+     * those return the first explicit node, while we are looking for
+     * its overlay here.
      */
     overlay_bs = bs;
-    while (backing_bs(overlay_bs) && backing_bs(overlay_bs)->implicit) {
+    for (below_bs = bdrv_filter_or_cow_bs(overlay_bs);
-        overlay_bs = backing_bs(overlay_bs);
+         below_bs && below_bs->implicit;
+         below_bs = bdrv_filter_or_cow_bs(overlay_bs))
+    {
+        overlay_bs = below_bs;
     }
 
     /* If we want to replace the backing file we need some extra checks */
-    if (new_backing_bs != backing_bs(overlay_bs)) {
+    if (new_backing_bs != bdrv_filter_or_cow_bs(overlay_bs)) {
         /* Check for implicit nodes between bs and its backing file */
         if (bs != overlay_bs) {
             error_setg(errp, "Cannot change backing link if '%s' has "
                        "an implicit backing file", bs->node_name);
             return -EPERM;
         }
-        /* Check if the backing link that we want to replace is frozen */
+        /*
-        if (bdrv_is_backing_chain_frozen(overlay_bs, backing_bs(overlay_bs),
+         * Check if the backing link that we want to replace is frozen.
-                                         errp)) {
+         * Note that
+         * bdrv_filter_or_cow_child(overlay_bs) == overlay_bs->backing,
+         * because we know that overlay_bs == bs, and that @bs
+         * either is a filter that uses ->backing or a COW format BDS
+         * with bs->drv->supports_backing == true.
+         */
+        if (bdrv_is_backing_chain_frozen(overlay_bs,
+                                         child_bs(overlay_bs->backing), errp))
+        {
             return -EPERM;
         }
         reopen_state->replace_backing_bs = true;
@@ -4203,7 +4238,7 @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
      * its metadata. Otherwise the 'backing' option can be omitted.
      */
     if (drv->supports_backing && reopen_state->backing_missing &&
-        (backing_bs(reopen_state->bs) || reopen_state->bs->backing_file[0])) {
+        (reopen_state->bs->backing || reopen_state->bs->backing_file[0])) {
         error_setg(errp, "backing is missing for '%s'",
                    reopen_state->bs->node_name);
         ret = -EINVAL;
@@ -4344,7 +4379,7 @@ void bdrv_reopen_commit(BDRVReopenState *reopen_state)
      * from bdrv_set_backing_hd()) has the new values.
      */
     if (reopen_state->replace_backing_bs) {
-        BlockDriverState *old_backing_bs = backing_bs(bs);
+        BlockDriverState *old_backing_bs = child_bs(bs->backing);
         assert(!old_backing_bs || !old_backing_bs->implicit);
         /* Abort the permission update on the backing bs we're detaching */
         if (old_backing_bs) {
@@ -4387,6 +4422,7 @@ static void bdrv_close(BlockDriverState *bs)
 
     if (bs->drv) {
         if (bs->drv->bdrv_close) {
+            /* Must unfreeze all children, so bdrv_unref_child() works */
             bs->drv->bdrv_close(bs);
         }
         bs->drv = NULL;
@@ -4736,9 +4772,9 @@ int bdrv_change_backing_file(BlockDriverState *bs, const char *backing_file,
 }
 
 /*
- * Finds the image layer in the chain that has 'bs' as its backing file.
+ * Finds the first non-filter node above bs in the chain between
- *
+ * active and bs.  The returned node is either an immediate parent of
- * active is the current topmost image.
+ * bs, or there are only filter nodes between the two.
  *
  * Returns NULL if bs is not found in active's image chain,
  * or if active == bs.
@@ -4748,11 +4784,18 @@ int bdrv_change_backing_file(BlockDriverState *bs, const char *backing_file,
 BlockDriverState *bdrv_find_overlay(BlockDriverState *active,
                                     BlockDriverState *bs)
 {
-    while (active && bs != backing_bs(active)) {
+    bs = bdrv_skip_filters(bs);
-        active = backing_bs(active);
+    active = bdrv_skip_filters(active);
+
+    while (active) {
+        BlockDriverState *next = bdrv_backing_chain_next(active);
+        if (bs == next) {
+            return active;
+        }
+        active = next;
     }
 
-    return active;
+    return NULL;
 }
 
 /* Given a BDS, searches for the base layer. */
@@ -4762,20 +4805,22 @@ BlockDriverState *bdrv_find_base(BlockDriverState *bs)
 }
 
 /*
- * Return true if at least one of the backing links between @bs and
+ * Return true if at least one of the COW (backing) and filter links
- * @base is frozen. @errp is set if that's the case.
+ * between @bs and @base is frozen. @errp is set if that's the case.
  * @base must be reachable from @bs, or NULL.
  */
 bool bdrv_is_backing_chain_frozen(BlockDriverState *bs, BlockDriverState *base,
                                   Error **errp)
 {
     BlockDriverState *i;
+    BdrvChild *child;
 
-    for (i = bs; i != base; i = backing_bs(i)) {
+    for (i = bs; i != base; i = child_bs(child)) {
-        if (i->backing && i->backing->frozen) {
+        child = bdrv_filter_or_cow_child(i);
+
+        if (child && child->frozen) {
             error_setg(errp, "Cannot change '%s' link from '%s' to '%s'",
-                       i->backing->name, i->node_name,
+                       child->name, i->node_name, child->bs->node_name);
-                       backing_bs(i)->node_name);
             return true;
         }
     }
@@ -4784,7 +4829,7 @@ bool bdrv_is_backing_chain_frozen(BlockDriverState *bs, BlockDriverState *base,
 }
 
 /*
- * Freeze all backing links between @bs and @base.
+ * Freeze all COW (backing) and filter links between @bs and @base.
  * If any of the links is already frozen the operation is aborted and
  * none of the links are modified.
  * @base must be reachable from @bs, or NULL.
@@ -4794,22 +4839,25 @@ int bdrv_freeze_backing_chain(BlockDriverState *bs, BlockDriverState *base,
                               Error **errp)
 {
     BlockDriverState *i;
+    BdrvChild *child;
 
     if (bdrv_is_backing_chain_frozen(bs, base, errp)) {
         return -EPERM;
     }
 
-    for (i = bs; i != base; i = backing_bs(i)) {
+    for (i = bs; i != base; i = child_bs(child)) {
-        if (i->backing && backing_bs(i)->never_freeze) {
+        child = bdrv_filter_or_cow_child(i);
+        if (child && child->bs->never_freeze) {
             error_setg(errp, "Cannot freeze '%s' link to '%s'",
-                       i->backing->name, backing_bs(i)->node_name);
+                       child->name, child->bs->node_name);
             return -EPERM;
         }
     }
 
-    for (i = bs; i != base; i = backing_bs(i)) {
+    for (i = bs; i != base; i = child_bs(child)) {
-        if (i->backing) {
+        child = bdrv_filter_or_cow_child(i);
-            i->backing->frozen = true;
+        if (child) {
+            child->frozen = true;
         }
     }
 
@@ -4817,18 +4865,21 @@ int bdrv_freeze_backing_chain(BlockDriverState *bs, BlockDriverState *base,
 }
 
 /*
- * Unfreeze all backing links between @bs and @base. The caller must
+ * Unfreeze all COW (backing) and filter links between @bs and @base.
- * ensure that all links are frozen before using this function.
+ * The caller must ensure that all links are frozen before using this
+ * function.
  * @base must be reachable from @bs, or NULL.
  */
 void bdrv_unfreeze_backing_chain(BlockDriverState *bs, BlockDriverState *base)
 {
     BlockDriverState *i;
+    BdrvChild *child;
 
-    for (i = bs; i != base; i = backing_bs(i)) {
+    for (i = bs; i != base; i = child_bs(child)) {
-        if (i->backing) {
+        child = bdrv_filter_or_cow_child(i);
-            assert(i->backing->frozen);
+        if (child) {
-            i->backing->frozen = false;
+            assert(child->frozen);
+            child->frozen = false;
         }
     }
 }
@@ -4896,9 +4947,7 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base,
      * other intermediate nodes have been dropped.
      * If 'top' is an implicit node (e.g. "commit_top") we should skip
      * it because no one inherits from it. We use explicit_top for that. */
-    while (explicit_top && explicit_top->implicit) {
+    explicit_top = bdrv_skip_implicit_filters(explicit_top);
-        explicit_top = backing_bs(explicit_top);
-    }
     update_inherits_from = bdrv_inherits_from_recursive(base, explicit_top);
 
     /* success - we can delete the intermediate states, and link top->base */
@@ -4931,8 +4980,11 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base,
             }
         }
 
-        /* Do the actual switch in the in-memory graph.
+        /*
-         * Completes bdrv_check_update_perm() transaction internally. */
+         * Do the actual switch in the in-memory graph.
+         * Completes bdrv_check_update_perm() transaction internally.
+         * c->frozen is false, we have checked that above.
+         */
         bdrv_ref(base);
         bdrv_replace_child(c, base);
         bdrv_unref(top);
@@ -4949,6 +5001,31 @@ exit:
     return ret;
 }
 
+/**
+ * Implementation of BlockDriver.bdrv_get_allocated_file_size() that
+ * sums the size of all data-bearing children.  (This excludes backing
+ * children.)
+ */
+static int64_t bdrv_sum_allocated_file_size(BlockDriverState *bs)
+{
+    BdrvChild *child;
+    int64_t child_size, sum = 0;
+
+    QLIST_FOREACH(child, &bs->children, next) {
+        if (child->role & (BDRV_CHILD_DATA | BDRV_CHILD_METADATA |
+                           BDRV_CHILD_FILTERED))
+        {
+            child_size = bdrv_get_allocated_file_size(child->bs);
+            if (child_size < 0) {
+                return child_size;
+            }
+            sum += child_size;
+        }
+    }
+
+    return sum;
+}
+
 /**
  * Length of a allocated file in bytes. Sparse files are counted by actual
  * allocated space. Return < 0 if error or unknown.
@@ -4962,10 +5039,21 @@ int64_t bdrv_get_allocated_file_size(BlockDriverState *bs)
     if (drv->bdrv_get_allocated_file_size) {
         return drv->bdrv_get_allocated_file_size(bs);
     }
-    if (bs->file) {
+
-        return bdrv_get_allocated_file_size(bs->file->bs);
+    if (drv->bdrv_file_open) {
-    }
+        /*
+         * Protocol drivers default to -ENOTSUP (most of their data is
+         * not stored in any of their children (if they even have any),
+         * so there is no generic way to figure it out).
+         */
         return -ENOTSUP;
+    } else if (drv->is_filter) {
+        /* Filter drivers default to the size of their filtered child */
+        return bdrv_get_allocated_file_size(bdrv_filter_bs(bs));
+    } else {
+        /* Other drivers default to summing their children's sizes */
+        return bdrv_sum_allocated_file_size(bs);
+    }
 }
 
 /*
@@ -5047,12 +5135,27 @@ bool bdrv_is_sg(BlockDriverState *bs)
     return bs->sg;
 }
 
-bool bdrv_is_encrypted(BlockDriverState *bs)
+/**
+ * Return whether the given node supports compressed writes.
+ */
+bool bdrv_supports_compressed_writes(BlockDriverState *bs)
 {
-    if (bs->backing && bs->backing->bs->encrypted) {
+    BlockDriverState *filtered;
-        return true;
+
+    if (!bs->drv || !block_driver_can_compress(bs->drv)) {
+        return false;
     }
-    return bs->encrypted;
+
+    filtered = bdrv_filter_bs(bs);
+    if (filtered) {
+        /*
+         * Filters can only forward compressed writes, so we have to
+         * check the child.
+         */
+        return bdrv_supports_compressed_writes(filtered);
+    }
+
+    return true;
 }
 
 const char *bdrv_get_format_name(BlockDriverState *bs)
@@ -5337,7 +5440,7 @@ BlockDriverState *bdrv_lookup_bs(const char *device,
 bool bdrv_chain_contains(BlockDriverState *top, BlockDriverState *base)
 {
     while (top && top != base) {
-        top = backing_bs(top);
+        top = bdrv_filter_or_cow_bs(top);
     }
 
     return top != NULL;
@@ -5409,20 +5512,24 @@ int bdrv_has_zero_init_1(BlockDriverState *bs)
 
 int bdrv_has_zero_init(BlockDriverState *bs)
 {
+    BlockDriverState *filtered;
+
     if (!bs->drv) {
         return 0;
     }
 
     /* If BS is a copy on write image, it is initialized to
        the contents of the base image, which may not be zeroes.  */
-    if (bs->backing) {
+    if (bdrv_cow_child(bs)) {
         return 0;
     }
     if (bs->drv->bdrv_has_zero_init) {
         return bs->drv->bdrv_has_zero_init(bs);
     }
-    if (bs->file && bs->drv->is_filter) {
+
-        return bdrv_has_zero_init(bs->file->bs);
+    filtered = bdrv_filter_bs(bs);
+    if (filtered) {
+        return bdrv_has_zero_init(filtered);
     }
 
     /* safe default */
@@ -5452,8 +5559,9 @@ int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
         return -ENOMEDIUM;
     }
     if (!drv->bdrv_get_info) {
-        if (bs->file && drv->is_filter) {
+        BlockDriverState *filtered = bdrv_filter_bs(bs);
-            return bdrv_get_info(bs->file->bs, bdi);
+        if (filtered) {
+            return bdrv_get_info(filtered, bdi);
         }
         return -ENOTSUP;
     }
@@ -5492,17 +5600,7 @@ void bdrv_debug_event(BlockDriverState *bs, BlkdebugEvent event)
 static BlockDriverState *bdrv_find_debug_node(BlockDriverState *bs)
 {
     while (bs && bs->drv && !bs->drv->bdrv_debug_breakpoint) {
-        if (bs->file) {
+        bs = bdrv_primary_bs(bs);
-            bs = bs->file->bs;
-            continue;
-        }
-
-        if (bs->drv->is_filter && bs->backing) {
-            bs = bs->backing->bs;
-            continue;
-        }
-
-        break;
     }
 
     if (bs && bs->drv && bs->drv->bdrv_debug_breakpoint) {
@@ -5537,7 +5635,7 @@ int bdrv_debug_remove_breakpoint(BlockDriverState *bs, const char *tag)
 int bdrv_debug_resume(BlockDriverState *bs, const char *tag)
 {
     while (bs && (!bs->drv || !bs->drv->bdrv_debug_resume)) {
-        bs = bs->file ? bs->file->bs : NULL;
+        bs = bdrv_primary_bs(bs);
     }
 
     if (bs && bs->drv && bs->drv->bdrv_debug_resume) {
@@ -5550,7 +5648,7 @@ int bdrv_debug_resume(BlockDriverState *bs, const char *tag)
 bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag)
 {
     while (bs && bs->drv && !bs->drv->bdrv_debug_is_suspended) {
-        bs = bs->file ? bs->file->bs : NULL;
+        bs = bdrv_primary_bs(bs);
     }
 
     if (bs && bs->drv && bs->drv->bdrv_debug_is_suspended) {
@@ -5571,8 +5669,10 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
     char *backing_file_full = NULL;
     char *filename_tmp = NULL;
     int is_protocol = 0;
+    bool filenames_refreshed = false;
     BlockDriverState *curr_bs = NULL;
     BlockDriverState *retval = NULL;
+    BlockDriverState *bs_below;
 
     if (!bs || !bs->drv || !backing_file) {
         return NULL;
@@ -5583,15 +5683,47 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
 
     is_protocol = path_has_protocol(backing_file);
 
-    for (curr_bs = bs; curr_bs->backing; curr_bs = curr_bs->backing->bs) {
+    /*
+     * Being largely a legacy function, skip any filters here
+     * (because filters do not have normal filenames, so they cannot
+     * match anyway; and allowing json:{} filenames is a bit out of
+     * scope).
+     */
+    for (curr_bs = bdrv_skip_filters(bs);
+         bdrv_cow_child(curr_bs) != NULL;
+         curr_bs = bs_below)
+    {
+        bs_below = bdrv_backing_chain_next(curr_bs);
 
-        /* If either of the filename paths is actually a protocol, then
+        if (bdrv_backing_overridden(curr_bs)) {
-         * compare unmodified paths; otherwise make paths relative */
+            /*
-        if (is_protocol || path_has_protocol(curr_bs->backing_file)) {
+             * If the backing file was overridden, we can only compare
+             * directly against the backing node's filename.
+             */
+
+            if (!filenames_refreshed) {
+                /*
+                 * This will automatically refresh all of the
+                 * filenames in the rest of the backing chain, so we
+                 * only need to do this once.
+                 */
+                bdrv_refresh_filename(bs_below);
+                filenames_refreshed = true;
+            }
+
+            if (strcmp(backing_file, bs_below->filename) == 0) {
+                retval = bs_below;
+                break;
+            }
+        } else if (is_protocol || path_has_protocol(curr_bs->backing_file)) {
+            /*
+             * If either of the filename paths is actually a protocol, then
+             * compare unmodified paths; otherwise make paths relative.
+             */
             char *backing_file_full_ret;
 
             if (strcmp(backing_file, curr_bs->backing_file) == 0) {
-                retval = curr_bs->backing->bs;
+                retval = bs_below;
                 break;
             }
             /* Also check against the full backing filename for the image */
@@ -5601,7 +5733,7 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
                 bool equal = strcmp(backing_file, backing_file_full_ret) == 0;
                 g_free(backing_file_full_ret);
                 if (equal) {
-                    retval = curr_bs->backing->bs;
+                    retval = bs_below;
                     break;
                 }
             }
@@ -5627,7 +5759,7 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
             g_free(filename_tmp);
 
             if (strcmp(backing_file_full, filename_full) == 0) {
-                retval = curr_bs->backing->bs;
+                retval = bs_below;
                 break;
             }
         }
@@ -6119,6 +6251,10 @@ void bdrv_img_create(const char *filename, const char *fmt,
                              "same filename as the backing file");
             goto out;
         }
+        if (backing_file[0] == '\0') {
+            error_setg(errp, "Expected backing file name, got empty string");
+            goto out;
+        }
     }
 
     backing_fmt = qemu_opt_get(opts, BLOCK_OPT_BACKING_FMT);
@@ -6534,6 +6670,8 @@ int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts,
 bool bdrv_recurse_can_replace(BlockDriverState *bs,
                               BlockDriverState *to_replace)
 {
+    BlockDriverState *filtered;
+
     if (!bs || !bs->drv) {
         return false;
     }
@@ -6548,9 +6686,9 @@ bool bdrv_recurse_can_replace(BlockDriverState *bs,
     }
 
     /* For filters without an own implementation, we can recurse on our own */
-    if (bs->drv->is_filter) {
+    filtered = bdrv_filter_bs(bs);
-        BdrvChild *child = bs->file ?: bs->backing;
+    if (filtered) {
-        return bdrv_recurse_can_replace(child->bs, to_replace);
+        return bdrv_recurse_can_replace(filtered, to_replace);
     }
 
     /* Safe default */
@@ -6701,7 +6839,7 @@ static bool append_strong_runtime_options(QDict *d, BlockDriverState *bs)
 /* Note: This function may return false positives; it may return true
  * even if opening the backing file specified by bs's image header
  * would result in exactly bs->backing. */
-static bool bdrv_backing_overridden(BlockDriverState *bs)
+bool bdrv_backing_overridden(BlockDriverState *bs)
 {
     if (bs->backing) {
         return strcmp(bs->auto_backing_file,
@@ -6729,6 +6867,7 @@ void bdrv_refresh_filename(BlockDriverState *bs)
 {
     BlockDriver *drv = bs->drv;
     BdrvChild *child;
+    BlockDriverState *primary_child_bs;
     QDict *opts;
     bool backing_overridden;
     bool generate_json_filename; /* Whether our default implementation should
@@ -6798,20 +6937,30 @@ void bdrv_refresh_filename(BlockDriverState *bs)
     qobject_unref(bs->full_open_options);
     bs->full_open_options = opts;
 
+    primary_child_bs = bdrv_primary_bs(bs);
+
     if (drv->bdrv_refresh_filename) {
         /* Obsolete information is of no use here, so drop the old file name
          * information before refreshing it */
         bs->exact_filename[0] = '\0';
 
         drv->bdrv_refresh_filename(bs);
-    } else if (bs->file) {
+    } else if (primary_child_bs) {
-        /* Try to reconstruct valid information from the underlying file */
+        /*
+         * Try to reconstruct valid information from the underlying
+         * file -- this only works for format nodes (filter nodes
+         * cannot be probed and as such must be selected by the user
+         * either through an options dict, or through a special
+         * filename which the filter driver must construct in its
+         * .bdrv_refresh_filename() implementation).
+         */
 
         bs->exact_filename[0] = '\0';
 
         /*
          * We can use the underlying file's filename if:
          * - it has a filename,
+         * - the current BDS is not a filter,
          * - the file is a protocol BDS, and
          * - opening that file (as this BDS's format) will automatically create
          *   the BDS tree we have right now, that is:
@@ -6820,11 +6969,11 @@ void bdrv_refresh_filename(BlockDriverState *bs)
          *   - no non-file child of this BDS has been overridden by the user
          *   Both of these conditions are represented by generate_json_filename.
          */
-        if (bs->file->bs->exact_filename[0] &&
+        if (primary_child_bs->exact_filename[0] &&
-            bs->file->bs->drv->bdrv_file_open &&
+            primary_child_bs->drv->bdrv_file_open &&
-            !generate_json_filename)
+            !drv->is_filter && !generate_json_filename)
         {
-            strcpy(bs->exact_filename, bs->file->bs->exact_filename);
+            strcpy(bs->exact_filename, primary_child_bs->exact_filename);
         }
     }
 
@@ -6844,6 +6993,7 @@ void bdrv_refresh_filename(BlockDriverState *bs)
 char *bdrv_dirname(BlockDriverState *bs, Error **errp)
 {
     BlockDriver *drv = bs->drv;
+    BlockDriverState *child_bs;
 
     if (!drv) {
         error_setg(errp, "Node '%s' is ejected", bs->node_name);
@@ -6854,8 +7004,9 @@ char *bdrv_dirname(BlockDriverState *bs, Error **errp)
         return drv->bdrv_dirname(bs, errp);
     }
 
-    if (bs->file) {
+    child_bs = bdrv_primary_bs(bs);
-        return bdrv_dirname(bs->file->bs, errp);
+    if (child_bs) {
+        return bdrv_dirname(child_bs, errp);
     }
 
     bdrv_refresh_filename(bs);
@@ -6939,3 +7090,156 @@ int bdrv_make_empty(BdrvChild *c, Error **errp)
 
     return 0;
 }
+
+/*
+ * Return the child that @bs acts as an overlay for, and from which data may be
+ * copied in COW or COR operations.  Usually this is the backing file.
+ */
+BdrvChild *bdrv_cow_child(BlockDriverState *bs)
+{
+    if (!bs || !bs->drv) {
+        return NULL;
+    }
+
+    if (bs->drv->is_filter) {
+        return NULL;
+    }
+
+    if (!bs->backing) {
+        return NULL;
+    }
+
+    assert(bs->backing->role & BDRV_CHILD_COW);
+    return bs->backing;
+}
+
+/*
+ * If @bs acts as a filter for exactly one of its children, return
+ * that child.
+ */
+BdrvChild *bdrv_filter_child(BlockDriverState *bs)
+{
+    BdrvChild *c;
+
+    if (!bs || !bs->drv) {
+        return NULL;
+    }
+
+    if (!bs->drv->is_filter) {
+        return NULL;
+    }
+
+    /* Only one of @backing or @file may be used */
+    assert(!(bs->backing && bs->file));
+
+    c = bs->backing ?: bs->file;
+    if (!c) {
+        return NULL;
+    }
+
+    assert(c->role & BDRV_CHILD_FILTERED);
+    return c;
+}
+
+/*
+ * Return either the result of bdrv_cow_child() or bdrv_filter_child(),
+ * whichever is non-NULL.
+ *
+ * Return NULL if both are NULL.
+ */
+BdrvChild *bdrv_filter_or_cow_child(BlockDriverState *bs)
+{
+    BdrvChild *cow_child = bdrv_cow_child(bs);
+    BdrvChild *filter_child = bdrv_filter_child(bs);
+
+    /* Filter nodes cannot have COW backing files */
+    assert(!(cow_child && filter_child));
+
+    return cow_child ?: filter_child;
+}
+
+/*
+ * Return the primary child of this node: For filters, that is the
+ * filtered child.  For other nodes, that is usually the child storing
+ * metadata.
+ * (A generally more helpful description is that this is (usually) the
+ * child that has the same filename as @bs.)
+ *
+ * Drivers do not necessarily have a primary child; for example quorum
+ * does not.
+ */
+BdrvChild *bdrv_primary_child(BlockDriverState *bs)
+{
+    BdrvChild *c, *found = NULL;
+
+    QLIST_FOREACH(c, &bs->children, next) {
+        if (c->role & BDRV_CHILD_PRIMARY) {
+            assert(!found);
+            found = c;
+        }
+    }
+
+    return found;
+}
+
+static BlockDriverState *bdrv_do_skip_filters(BlockDriverState *bs,
+                                              bool stop_on_explicit_filter)
+{
+    BdrvChild *c;
+
+    if (!bs) {
+        return NULL;
+    }
+
+    while (!(stop_on_explicit_filter && !bs->implicit)) {
+        c = bdrv_filter_child(bs);
+        if (!c) {
+            /*
+             * A filter that is embedded in a working block graph must
+             * have a child.  Assert this here so this function does
+             * not return a filter node that is not expected by the
+             * caller.
+             */
+            assert(!bs->drv || !bs->drv->is_filter);
+            break;
+        }
+        bs = c->bs;
+    }
+    /*
+     * Note that this treats nodes with bs->drv == NULL as not being
+     * filters (bs->drv == NULL should be replaced by something else
+     * anyway).
+     * The advantage of this behavior is that this function will thus
+     * always return a non-NULL value (given a non-NULL @bs).
+     */
+
+    return bs;
+}
+
+/*
+ * Return the first BDS that has not been added implicitly or that
+ * does not have a filtered child down the chain starting from @bs
+ * (including @bs itself).
+ */
+BlockDriverState *bdrv_skip_implicit_filters(BlockDriverState *bs)
+{
+    return bdrv_do_skip_filters(bs, true);
+}
+
+/*
+ * Return the first BDS that does not have a filtered child down the
+ * chain starting from @bs (including @bs itself).
+ */
+BlockDriverState *bdrv_skip_filters(BlockDriverState *bs)
+{
+    return bdrv_do_skip_filters(bs, false);
+}
+
+/*
+ * For a backing chain, return the first non-filter backing image of
+ * the first non-filter image.
+ */
+BlockDriverState *bdrv_backing_chain_next(BlockDriverState *bs)
+{
+    return bdrv_skip_filters(bdrv_cow_bs(bdrv_skip_filters(bs)));
+}

block/backup-top.c

@@ -175,8 +175,6 @@ BlockDriver bdrv_backup_top_filter = {
     .bdrv_co_pdiscard           = backup_top_co_pdiscard,
     .bdrv_co_flush              = backup_top_co_flush,
 
-    .bdrv_co_block_status       = bdrv_co_block_status_from_backing,
-
     .bdrv_refresh_filename      = backup_top_refresh_filename,
 
     .bdrv_child_perm            = backup_top_child_perm,
@@ -281,7 +279,7 @@ void bdrv_backup_top_drop(BlockDriverState *bs)
 
     s->active = false;
     bdrv_child_refresh_perms(bs, bs->backing, &error_abort);
-    bdrv_replace_node(bs, backing_bs(bs), &error_abort);
+    bdrv_replace_node(bs, bs->backing->bs, &error_abort);
     bdrv_set_backing_hd(bs, NULL, &error_abort);
 
     bdrv_drained_end(bs);

block/backup.c

@@ -297,6 +297,7 @@ static int64_t backup_calculate_cluster_size(BlockDriverState *target,
 {
     int ret;
     BlockDriverInfo bdi;
+    bool target_does_cow = bdrv_backing_chain_next(target);
 
     /*
      * If there is no backing file on the target, we cannot rely on COW if our
@@ -304,7 +305,7 @@ static int64_t backup_calculate_cluster_size(BlockDriverState *target,
      * targets with a backing file, try to avoid COW if possible.
      */
     ret = bdrv_get_info(target, &bdi);
-    if (ret == -ENOTSUP && !target->backing) {
+    if (ret == -ENOTSUP && !target_does_cow) {
         /* Cluster size is not defined */
         warn_report("The target block device doesn't provide "
                     "information about the block size and it doesn't have a "
@@ -313,14 +314,14 @@ static int64_t backup_calculate_cluster_size(BlockDriverState *target,
                     "this default, the backup may be unusable",
                     BACKUP_CLUSTER_SIZE_DEFAULT);
         return BACKUP_CLUSTER_SIZE_DEFAULT;
-    } else if (ret < 0 && !target->backing) {
+    } else if (ret < 0 && !target_does_cow) {
         error_setg_errno(errp, -ret,
             "Couldn't determine the cluster size of the target image, "
             "which has no backing file");
         error_append_hint(errp,
             "Aborting, since this may create an unusable destination image\n");
         return ret;
-    } else if (ret < 0 && target->backing) {
+    } else if (ret < 0 && target_does_cow) {
         /* Not fatal; just trudge on ahead. */
         return BACKUP_CLUSTER_SIZE_DEFAULT;
     }
@@ -371,7 +372,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
         return NULL;
     }
 
-    if (compress && !block_driver_can_compress(target->drv)) {
+    if (compress && !bdrv_supports_compressed_writes(target)) {
         error_setg(errp, "Compression is not supported for this drive %s",
                    bdrv_get_device_name(target));
         return NULL;

block/blkdebug.c

@@ -752,8 +752,11 @@ static int coroutine_fn blkdebug_co_block_status(BlockDriverState *bs,
         return err;
     }
 
-    return bdrv_co_block_status_from_file(bs, want_zero, offset, bytes,
+    assert(bs->file && bs->file->bs);
-                                          pnum, map, file);
+    *pnum = bytes;
+    *map = offset;
+    *file = bs->file->bs;
+    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID;
 }
 
 static void blkdebug_close(BlockDriverState *bs)

block/blklogwrites.c

@@ -515,7 +515,6 @@ static BlockDriver bdrv_blk_log_writes = {
     .bdrv_co_pwrite_zeroes  = blk_log_writes_co_pwrite_zeroes,
     .bdrv_co_flush_to_disk  = blk_log_writes_co_flush_to_disk,
     .bdrv_co_pdiscard       = blk_log_writes_co_pdiscard,
-    .bdrv_co_block_status   = bdrv_co_block_status_from_file,
 
     .is_filter              = true,
     .strong_runtime_opts    = blk_log_writes_strong_runtime_opts,

block/block-backend.c

@@ -2279,10 +2279,13 @@ int blk_commit_all(void)
 
     while ((blk = blk_all_next(blk)) != NULL) {
         AioContext *aio_context = blk_get_aio_context(blk);
+        BlockDriverState *unfiltered_bs = bdrv_skip_filters(blk_bs(blk));
 
         aio_context_acquire(aio_context);
-        if (blk_is_inserted(blk) && blk->root->bs->backing) {
+        if (blk_is_inserted(blk) && bdrv_cow_child(unfiltered_bs)) {
-            int ret = bdrv_commit(blk->root->bs);
+            int ret;
+
+            ret = bdrv_commit(unfiltered_bs);
             if (ret < 0) {
                 aio_context_release(aio_context);
                 return ret;

block/block-copy.c

@@ -440,8 +440,8 @@ static int block_copy_block_status(BlockCopyState *s, int64_t offset,
     BlockDriverState *base;
     int ret;
 
-    if (s->skip_unallocated && s->source->bs->backing) {
+    if (s->skip_unallocated) {
-        base = s->source->bs->backing->bs;
+        base = bdrv_backing_chain_next(s->source->bs);
     } else {
         base = NULL;
     }

block/commit.c

@@ -37,6 +37,7 @@ typedef struct CommitBlockJob {
     BlockBackend *top;
     BlockBackend *base;
     BlockDriverState *base_bs;
+    BlockDriverState *base_overlay;
     BlockdevOnError on_error;
     bool base_read_only;
     bool chain_frozen;
@@ -89,7 +90,7 @@ static void commit_abort(Job *job)
      * 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. */
-    bdrv_replace_node(s->commit_top_bs, backing_bs(s->commit_top_bs),
+    bdrv_replace_node(s->commit_top_bs, s->commit_top_bs->backing->bs,
                       &error_abort);
 
     bdrv_unref(s->commit_top_bs);
@@ -153,7 +154,7 @@ static int coroutine_fn commit_run(Job *job, Error **errp)
             break;
         }
         /* Copy if allocated above the base */
-        ret = bdrv_is_allocated_above(blk_bs(s->top), blk_bs(s->base), false,
+        ret = bdrv_is_allocated_above(blk_bs(s->top), s->base_overlay, true,
                                       offset, COMMIT_BUFFER_SIZE, &n);
         copy = (ret == 1);
         trace_commit_one_iteration(s, offset, n, ret);
@@ -237,7 +238,6 @@ static void bdrv_commit_top_child_perm(BlockDriverState *bs, BdrvChild *c,
 static BlockDriver bdrv_commit_top = {
     .format_name                = "commit_top",
     .bdrv_co_preadv             = bdrv_commit_top_preadv,
-    .bdrv_co_block_status       = bdrv_co_block_status_from_backing,
     .bdrv_refresh_filename      = bdrv_commit_top_refresh_filename,
     .bdrv_child_perm            = bdrv_commit_top_child_perm,
 
@@ -253,15 +253,35 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     CommitBlockJob *s;
     BlockDriverState *iter;
     BlockDriverState *commit_top_bs = NULL;
+    BlockDriverState *filtered_base;
     Error *local_err = NULL;
+    int64_t base_size, top_size;
+    uint64_t base_perms, iter_shared_perms;
     int ret;
 
     assert(top != bs);
-    if (top == base) {
+    if (bdrv_skip_filters(top) == bdrv_skip_filters(base)) {
         error_setg(errp, "Invalid files for merge: top and base are the same");
         return;
     }
 
+    base_size = bdrv_getlength(base);
+    if (base_size < 0) {
+        error_setg_errno(errp, -base_size, "Could not inquire base image size");
+        return;
+    }
+
+    top_size = bdrv_getlength(top);
+    if (top_size < 0) {
+        error_setg_errno(errp, -top_size, "Could not inquire top image size");
+        return;
+    }
+
+    base_perms = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE;
+    if (base_size < top_size) {
+        base_perms |= BLK_PERM_RESIZE;
+    }
+
     s = block_job_create(job_id, &commit_job_driver, NULL, bs, 0, BLK_PERM_ALL,
                          speed, creation_flags, NULL, NULL, errp);
     if (!s) {
@@ -301,17 +321,43 @@ void commit_start(const char *job_id, BlockDriverState *bs,
 
     s->commit_top_bs = commit_top_bs;
 
-    /* Block all nodes between top and base, because they will
+    /*
-     * disappear from the chain after this operation. */
+     * Block all nodes between top and base, because they will
-    assert(bdrv_chain_contains(top, base));
+     * disappear from the chain after this operation.
-    for (iter = top; iter != base; iter = backing_bs(iter)) {
+     * Note that this assumes that the user is fine with removing all
-        /* XXX BLK_PERM_WRITE needs to be allowed so we don't block ourselves
+     * nodes (including R/W filters) between top and base.  Assuring
+     * this is the responsibility of the interface (i.e. whoever calls
+     * commit_start()).
+     */
+    s->base_overlay = bdrv_find_overlay(top, base);
+    assert(s->base_overlay);
+
+    /*
+     * The topmost node with
+     * bdrv_skip_filters(filtered_base) == bdrv_skip_filters(base)
+     */
+    filtered_base = bdrv_cow_bs(s->base_overlay);
+    assert(bdrv_skip_filters(filtered_base) == bdrv_skip_filters(base));
+
+    /*
+     * 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. */
+     * driver above s->base.
+     */
+    iter_shared_perms = BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE;
+
+    for (iter = top; iter != base; iter = bdrv_filter_or_cow_bs(iter)) {
+        if (iter == filtered_base) {
+            /*
+             * From here on, all nodes are filters on the base.  This
+             * allows us to share BLK_PERM_CONSISTENT_READ.
+             */
+            iter_shared_perms |= BLK_PERM_CONSISTENT_READ;
+        }
+
         ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
-                                 BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
+                                 iter_shared_perms, errp);
-                                 errp);
         if (ret < 0) {
             goto fail;
         }
@@ -328,9 +374,7 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     }
 
     s->base = blk_new(s->common.job.aio_context,
-                      BLK_PERM_CONSISTENT_READ
+                      base_perms,
-                      | BLK_PERM_WRITE
-                      | BLK_PERM_RESIZE,
                       BLK_PERM_CONSISTENT_READ
                       | BLK_PERM_GRAPH_MOD
                       | BLK_PERM_WRITE_UNCHANGED);
@@ -398,19 +442,22 @@ int bdrv_commit(BlockDriverState *bs)
     if (!drv)
         return -ENOMEDIUM;
 
-    if (!bs->backing) {
+    backing_file_bs = bdrv_cow_bs(bs);
+
+    if (!backing_file_bs) {
         return -ENOTSUP;
     }
 
     if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_COMMIT_SOURCE, NULL) ||
-        bdrv_op_is_blocked(bs->backing->bs, BLOCK_OP_TYPE_COMMIT_TARGET, NULL)) {
+        bdrv_op_is_blocked(backing_file_bs, BLOCK_OP_TYPE_COMMIT_TARGET, NULL))
+    {
         return -EBUSY;
     }
 
-    ro = bs->backing->bs->read_only;
+    ro = backing_file_bs->read_only;
 
     if (ro) {
-        if (bdrv_reopen_set_read_only(bs->backing->bs, false, NULL)) {
+        if (bdrv_reopen_set_read_only(backing_file_bs, false, NULL)) {
             return -EACCES;
         }
     }
@@ -428,8 +475,6 @@ int bdrv_commit(BlockDriverState *bs)
     }
 
     /* 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) {
@@ -515,7 +560,7 @@ ro_cleanup:
     qemu_vfree(buf);
 
     blk_unref(backing);
-    if (backing_file_bs) {
+    if (bdrv_cow_bs(bs) != backing_file_bs) {
         bdrv_set_backing_hd(bs, backing_file_bs, &error_abort);
     }
     bdrv_unref(commit_top_bs);
@@ -523,7 +568,7 @@ ro_cleanup:
 
     if (ro) {
         /* ignoring error return here */
-        bdrv_reopen_set_read_only(bs->backing->bs, true, NULL);
+        bdrv_reopen_set_read_only(backing_file_bs, true, NULL);
     }
 
     return ret;

block/copy-on-read.c

@@ -107,6 +107,16 @@ static int coroutine_fn cor_co_pdiscard(BlockDriverState *bs,
 }
 
 
+static int coroutine_fn cor_co_pwritev_compressed(BlockDriverState *bs,
+                                                  uint64_t offset,
+                                                  uint64_t bytes,
+                                                  QEMUIOVector *qiov)
+{
+    return bdrv_co_pwritev(bs->file, offset, bytes, qiov,
+                           BDRV_REQ_WRITE_COMPRESSED);
+}
+
+
 static void cor_eject(BlockDriverState *bs, bool eject_flag)
 {
     bdrv_eject(bs->file->bs, eject_flag);
@@ -131,12 +141,11 @@ static BlockDriver bdrv_copy_on_read = {
     .bdrv_co_pwritev                    = cor_co_pwritev,
     .bdrv_co_pwrite_zeroes              = cor_co_pwrite_zeroes,
     .bdrv_co_pdiscard                   = cor_co_pdiscard,
+    .bdrv_co_pwritev_compressed         = cor_co_pwritev_compressed,
 
     .bdrv_eject                         = cor_eject,
     .bdrv_lock_medium                   = cor_lock_medium,
 
-    .bdrv_co_block_status               = bdrv_co_block_status_from_file,
-
     .has_variable_length                = true,
     .is_filter                          = true,
 };

block/file-win32.c

@@ -299,6 +299,11 @@ static QemuOptsList raw_runtime_opts = {
             .type = QEMU_OPT_STRING,
             .help = "host AIO implementation (threads, native)",
         },
+        {
+            .name = "locking",
+            .type = QEMU_OPT_STRING,
+            .help = "file locking mode (on/off/auto, default: auto)",
+        },
         { /* end of list */ }
     },
 };
@@ -333,6 +338,7 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
     Error *local_err = NULL;
     const char *filename;
     bool use_aio;
+    OnOffAuto locking;
     int ret;
 
     s->type = FTYPE_FILE;
@@ -343,10 +349,24 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    if (qdict_get_try_bool(options, "locking", false)) {
+    locking = qapi_enum_parse(&OnOffAuto_lookup,
+                              qemu_opt_get(opts, "locking"),
+                              ON_OFF_AUTO_AUTO, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto fail;
+    }
+    switch (locking) {
+    case ON_OFF_AUTO_ON:
         error_setg(errp, "locking=on is not supported on Windows");
         ret = -EINVAL;
         goto fail;
+    case ON_OFF_AUTO_OFF:
+    case ON_OFF_AUTO_AUTO:
+        break;
+    default:
+        g_assert_not_reached();
     }
 
     filename = qemu_opt_get(opts, "filename");

block/filter-compress.c

@@ -146,8 +146,6 @@ static BlockDriver bdrv_compress = {
     .bdrv_eject                         = compress_eject,
     .bdrv_lock_medium                   = compress_lock_medium,
 
-    .bdrv_co_block_status               = bdrv_co_block_status_from_file,
-
     .has_variable_length                = true,
     .is_filter                          = true,
 };

block/io.c

@@ -135,6 +135,8 @@ static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src)
 void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
 {
     BlockDriver *drv = bs->drv;
+    BdrvChild *c;
+    bool have_limits;
     Error *local_err = NULL;
 
     memset(&bs->bl, 0, sizeof(bs->bl));
@@ -149,14 +151,21 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
                                 drv->bdrv_co_preadv_part) ? 1 : 512;
 
     /* Take some limits from the children as a default */
-    if (bs->file) {
+    have_limits = false;
-        bdrv_refresh_limits(bs->file->bs, &local_err);
+    QLIST_FOREACH(c, &bs->children, next) {
+        if (c->role & (BDRV_CHILD_DATA | BDRV_CHILD_FILTERED | BDRV_CHILD_COW))
+        {
+            bdrv_refresh_limits(c->bs, &local_err);
             if (local_err) {
                 error_propagate(errp, local_err);
                 return;
             }
-        bdrv_merge_limits(&bs->bl, &bs->file->bs->bl);
+            bdrv_merge_limits(&bs->bl, &c->bs->bl);
-    } else {
+            have_limits = true;
+        }
+    }
+
+    if (!have_limits) {
         bs->bl.min_mem_alignment = 512;
         bs->bl.opt_mem_alignment = qemu_real_host_page_size;
 
@@ -164,15 +173,6 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
         bs->bl.max_iov = IOV_MAX;
     }
 
-    if (bs->backing) {
-        bdrv_refresh_limits(bs->backing->bs, &local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
-            return;
-        }
-        bdrv_merge_limits(&bs->bl, &bs->backing->bs->bl);
-    }
-
     /* Then let the driver override it */
     if (drv->bdrv_refresh_limits) {
         drv->bdrv_refresh_limits(bs, errp);
@@ -2255,36 +2255,6 @@ typedef struct BdrvCoBlockStatusData {
     BlockDriverState **file;
 } BdrvCoBlockStatusData;
 
-int coroutine_fn bdrv_co_block_status_from_file(BlockDriverState *bs,
-                                                bool want_zero,
-                                                int64_t offset,
-                                                int64_t bytes,
-                                                int64_t *pnum,
-                                                int64_t *map,
-                                                BlockDriverState **file)
-{
-    assert(bs->file && bs->file->bs);
-    *pnum = bytes;
-    *map = offset;
-    *file = bs->file->bs;
-    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID;
-}
-
-int coroutine_fn bdrv_co_block_status_from_backing(BlockDriverState *bs,
-                                                   bool want_zero,
-                                                   int64_t offset,
-                                                   int64_t bytes,
-                                                   int64_t *pnum,
-                                                   int64_t *map,
-                                                   BlockDriverState **file)
-{
-    assert(bs->backing && bs->backing->bs);
-    *pnum = bytes;
-    *map = offset;
-    *file = bs->backing->bs;
-    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID;
-}
-
 /*
  * Returns the allocation status of the specified sectors.
  * Drivers not implementing the functionality are assumed to not support
@@ -2325,6 +2295,7 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
     BlockDriverState *local_file = NULL;
     int64_t aligned_offset, aligned_bytes;
     uint32_t align;
+    bool has_filtered_child;
 
     assert(pnum);
     *pnum = 0;
@@ -2350,7 +2321,8 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
 
     /* Must be non-NULL or bdrv_getlength() would have failed */
     assert(bs->drv);
-    if (!bs->drv->bdrv_co_block_status) {
+    has_filtered_child = bdrv_filter_child(bs);
+    if (!bs->drv->bdrv_co_block_status && !has_filtered_child) {
         *pnum = bytes;
         ret = BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED;
         if (offset + bytes == total_size) {
@@ -2371,9 +2343,20 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
     aligned_offset = QEMU_ALIGN_DOWN(offset, align);
     aligned_bytes = ROUND_UP(offset + bytes, align) - aligned_offset;
 
+    if (bs->drv->bdrv_co_block_status) {
         ret = bs->drv->bdrv_co_block_status(bs, want_zero, aligned_offset,
                                             aligned_bytes, pnum, &local_map,
                                             &local_file);
+    } else {
+        /* Default code for filters */
+
+        local_file = bdrv_filter_bs(bs);
+        assert(local_file);
+
+        *pnum = aligned_bytes;
+        local_map = aligned_offset;
+        ret = BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID;
+    }
     if (ret < 0) {
         *pnum = 0;
         goto out;
@@ -2409,9 +2392,10 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
     if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) {
         ret |= BDRV_BLOCK_ALLOCATED;
     } else if (want_zero && bs->drv->supports_backing) {
-        if (bs->backing) {
+        BlockDriverState *cow_bs = bdrv_cow_bs(bs);
-            BlockDriverState *bs2 = bs->backing->bs;
+
-            int64_t size2 = bdrv_getlength(bs2);
+        if (cow_bs) {
+            int64_t size2 = bdrv_getlength(cow_bs);
 
             if (size2 >= 0 && offset >= size2) {
                 ret |= BDRV_BLOCK_ZERO;
@@ -2479,7 +2463,7 @@ static int coroutine_fn bdrv_co_block_status_above(BlockDriverState *bs,
     bool first = true;
 
     assert(bs != base);
-    for (p = bs; p != base; p = backing_bs(p)) {
+    for (p = bs; p != base; p = bdrv_filter_or_cow_bs(p)) {
         ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map,
                                    file);
         if (ret < 0) {
@@ -2553,7 +2537,7 @@ int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base,
 int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes,
                       int64_t *pnum, int64_t *map, BlockDriverState **file)
 {
-    return bdrv_block_status_above(bs, backing_bs(bs),
+    return bdrv_block_status_above(bs, bdrv_filter_or_cow_bs(bs),
                                    offset, bytes, pnum, map, file);
 }
 
@@ -2563,9 +2547,9 @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset,
     int ret;
     int64_t dummy;
 
-    ret = bdrv_common_block_status_above(bs, backing_bs(bs), false, offset,
+    ret = bdrv_common_block_status_above(bs, bdrv_filter_or_cow_bs(bs), false,
-                                         bytes, pnum ? pnum : &dummy, NULL,
+                                         offset, bytes, pnum ? pnum : &dummy,
-                                         NULL);
+                                         NULL, NULL);
     if (ret < 0) {
         return ret;
     }
@@ -2628,7 +2612,7 @@ int bdrv_is_allocated_above(BlockDriverState *top,
             break;
         }
 
-        intermediate = backing_bs(intermediate);
+        intermediate = bdrv_filter_or_cow_bs(intermediate);
     }
 
     *pnum = n;
@@ -2647,6 +2631,7 @@ bdrv_co_rw_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos,
                    bool is_read)
 {
     BlockDriver *drv = bs->drv;
+    BlockDriverState *child_bs = bdrv_primary_bs(bs);
     int ret = -ENOTSUP;
 
     bdrv_inc_in_flight(bs);
@@ -2659,8 +2644,8 @@ bdrv_co_rw_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos,
         } else {
             ret = drv->bdrv_save_vmstate(bs, qiov, pos);
         }
-    } else if (bs->file) {
+    } else if (child_bs) {
-        ret = bdrv_co_rw_vmstate(bs->file->bs, qiov, pos, is_read);
+        ret = bdrv_co_rw_vmstate(child_bs, qiov, pos, is_read);
     }
 
     bdrv_dec_in_flight(bs);
@@ -2770,6 +2755,8 @@ static int coroutine_fn bdrv_flush_co_entry(void *opaque)
 
 int coroutine_fn bdrv_co_flush(BlockDriverState *bs)
 {
+    BdrvChild *primary_child = bdrv_primary_child(bs);
+    BdrvChild *child;
     int current_gen;
     int ret = 0;
 
@@ -2799,7 +2786,7 @@ int coroutine_fn bdrv_co_flush(BlockDriverState *bs)
     }
 
     /* Write back cached data to the OS even with cache=unsafe */
-    BLKDBG_EVENT(bs->file, BLKDBG_FLUSH_TO_OS);
+    BLKDBG_EVENT(primary_child, BLKDBG_FLUSH_TO_OS);
     if (bs->drv->bdrv_co_flush_to_os) {
         ret = bs->drv->bdrv_co_flush_to_os(bs);
         if (ret < 0) {
@@ -2809,15 +2796,15 @@ int coroutine_fn bdrv_co_flush(BlockDriverState *bs)
 
     /* But don't actually force it to the disk with cache=unsafe */
     if (bs->open_flags & BDRV_O_NO_FLUSH) {
-        goto flush_parent;
+        goto flush_children;
     }
 
     /* Check if we really need to flush anything */
     if (bs->flushed_gen == current_gen) {
-        goto flush_parent;
+        goto flush_children;
     }
 
-    BLKDBG_EVENT(bs->file, BLKDBG_FLUSH_TO_DISK);
+    BLKDBG_EVENT(primary_child, BLKDBG_FLUSH_TO_DISK);
     if (!bs->drv) {
         /* bs->drv->bdrv_co_flush() might have ejected the BDS
          * (even in case of apparent success) */
@@ -2861,8 +2848,17 @@ int coroutine_fn bdrv_co_flush(BlockDriverState *bs)
     /* Now flush the underlying protocol.  It will also have BDRV_O_NO_FLUSH
      * in the case of cache=unsafe, so there are no useless flushes.
      */
-flush_parent:
+flush_children:
-    ret = bs->file ? bdrv_co_flush(bs->file->bs) : 0;
+    ret = 0;
+    QLIST_FOREACH(child, &bs->children, next) {
+        if (child->perm & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) {
+            int this_child_ret = bdrv_co_flush(child->bs);
+            if (!ret) {
+                ret = this_child_ret;
+            }
+        }
+    }
+
 out:
     /* Notify any pending flushes that we have completed */
     if (ret == 0) {
@@ -3309,6 +3305,7 @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact,
                                   Error **errp)
 {
     BlockDriverState *bs = child->bs;
+    BdrvChild *filtered, *backing;
     BlockDriver *drv = bs->drv;
     BdrvTrackedRequest req;
     int64_t old_size, new_bytes;
@@ -3360,6 +3357,9 @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact,
         goto out;
     }
 
+    filtered = bdrv_filter_child(bs);
+    backing = bdrv_cow_child(bs);
+
     /*
      * If the image has a backing file that is large enough that it would
      * provide data for the new area, we cannot leave it unallocated because
@@ -3370,10 +3370,10 @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact,
      * backing file, taking care of keeping things consistent with that backing
      * file is the user's responsibility.
      */
-    if (new_bytes && bs->backing) {
+    if (new_bytes && backing) {
         int64_t backing_len;
 
-        backing_len = bdrv_getlength(backing_bs(bs));
+        backing_len = bdrv_getlength(backing->bs);
         if (backing_len < 0) {
             ret = backing_len;
             error_setg_errno(errp, -ret, "Could not get backing file size");
@@ -3392,8 +3392,8 @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact,
             goto out;
         }
         ret = drv->bdrv_co_truncate(bs, offset, exact, prealloc, flags, errp);
-    } else if (bs->file && drv->is_filter) {
+    } else if (filtered) {
-        ret = bdrv_co_truncate(bs->file, offset, exact, prealloc, flags, errp);
+        ret = bdrv_co_truncate(filtered, offset, exact, prealloc, flags, errp);
     } else {
         error_setg(errp, "Image format driver does not support resize");
         ret = -ENOTSUP;

block/mirror.c

@@ -42,6 +42,7 @@ typedef struct MirrorBlockJob {
     BlockBackend *target;
     BlockDriverState *mirror_top_bs;
     BlockDriverState *base;
+    BlockDriverState *base_overlay;
 
     /* The name of the graph node to replace */
     char *replaces;
@@ -677,8 +678,10 @@ static int mirror_exit_common(Job *job)
                              &error_abort);
     if (!abort && s->backing_mode == MIRROR_SOURCE_BACKING_CHAIN) {
         BlockDriverState *backing = s->is_none_mode ? src : s->base;
-        if (backing_bs(target_bs) != backing) {
+        BlockDriverState *unfiltered_target = bdrv_skip_filters(target_bs);
-            bdrv_set_backing_hd(target_bs, backing, &local_err);
+
+        if (bdrv_cow_bs(unfiltered_target) != backing) {
+            bdrv_set_backing_hd(unfiltered_target, backing, &local_err);
             if (local_err) {
                 error_report_err(local_err);
                 local_err = NULL;
@@ -740,7 +743,7 @@ static int mirror_exit_common(Job *job)
      * valid.
      */
     block_job_remove_all_bdrv(bjob);
-    bdrv_replace_node(mirror_top_bs, backing_bs(mirror_top_bs), &error_abort);
+    bdrv_replace_node(mirror_top_bs, mirror_top_bs->backing->bs, &error_abort);
 
     /* We just changed the BDS the job BB refers to (with either or both of the
      * bdrv_replace_node() calls), so switch the BB back so the cleanup does
@@ -786,7 +789,6 @@ static void coroutine_fn mirror_throttle(MirrorBlockJob *s)
 static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s)
 {
     int64_t offset;
-    BlockDriverState *base = s->base;
     BlockDriverState *bs = s->mirror_top_bs->backing->bs;
     BlockDriverState *target_bs = blk_bs(s->target);
     int ret;
@@ -837,7 +839,8 @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s)
             return 0;
         }
 
-        ret = bdrv_is_allocated_above(bs, base, false, offset, bytes, &count);
+        ret = bdrv_is_allocated_above(bs, s->base_overlay, true, offset, bytes,
+                                      &count);
         if (ret < 0) {
             return ret;
         }
@@ -936,7 +939,7 @@ static int coroutine_fn mirror_run(Job *job, Error **errp)
     } else {
         s->target_cluster_size = BDRV_SECTOR_SIZE;
     }
-    if (backing_filename[0] && !target_bs->backing &&
+    if (backing_filename[0] && !bdrv_backing_chain_next(target_bs) &&
         s->granularity < s->target_cluster_size) {
         s->buf_size = MAX(s->buf_size, s->target_cluster_size);
         s->cow_bitmap = bitmap_new(length);
@@ -1116,8 +1119,9 @@ static void mirror_complete(Job *job, Error **errp)
     if (s->backing_mode == MIRROR_OPEN_BACKING_CHAIN) {
         int ret;
 
-        assert(!target->backing);
+        assert(!bdrv_backing_chain_next(target));
-        ret = bdrv_open_backing_file(target, NULL, "backing", errp);
+        ret = bdrv_open_backing_file(bdrv_skip_filters(target), NULL,
+                                     "backing", errp);
         if (ret < 0) {
             return;
         }
@@ -1527,7 +1531,6 @@ static BlockDriver bdrv_mirror_top = {
     .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_block_status       = bdrv_co_block_status_from_backing,
     .bdrv_refresh_filename      = bdrv_mirror_top_refresh_filename,
     .bdrv_child_perm            = bdrv_mirror_top_child_perm,
 
@@ -1555,8 +1558,8 @@ static BlockJob *mirror_start_job(
     MirrorBlockJob *s;
     MirrorBDSOpaque *bs_opaque;
     BlockDriverState *mirror_top_bs;
-    bool target_graph_mod;
     bool target_is_backing;
+    uint64_t target_perms, target_shared_perms;
     Error *local_err = NULL;
     int ret;
 
@@ -1575,7 +1578,7 @@ static BlockJob *mirror_start_job(
         buf_size = DEFAULT_MIRROR_BUF_SIZE;
     }
 
-    if (bs == target) {
+    if (bdrv_skip_filters(bs) == bdrv_skip_filters(target)) {
         error_setg(errp, "Can't mirror node into itself");
         return NULL;
     }
@@ -1639,15 +1642,50 @@ static BlockJob *mirror_start_job(
      * 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_perms = BLK_PERM_WRITE;
+    target_shared_perms = BLK_PERM_WRITE_UNCHANGED;
+
     target_is_backing = bdrv_chain_contains(bs, target);
-    target_graph_mod = (backing_mode != MIRROR_LEAVE_BACKING_CHAIN);
+    if (target_is_backing) {
+        int64_t bs_size, target_size;
+        bs_size = bdrv_getlength(bs);
+        if (bs_size < 0) {
+            error_setg_errno(errp, -bs_size,
+                             "Could not inquire top image size");
+            goto fail;
+        }
+
+        target_size = bdrv_getlength(target);
+        if (target_size < 0) {
+            error_setg_errno(errp, -target_size,
+                             "Could not inquire base image size");
+            goto fail;
+        }
+
+        if (target_size < bs_size) {
+            target_perms |= BLK_PERM_RESIZE;
+        }
+
+        target_shared_perms |= BLK_PERM_CONSISTENT_READ
+                            |  BLK_PERM_WRITE
+                            |  BLK_PERM_GRAPH_MOD;
+    } else if (bdrv_chain_contains(bs, bdrv_skip_filters(target))) {
+        /*
+         * We may want to allow this in the future, but it would
+         * require taking some extra care.
+         */
+        error_setg(errp, "Cannot mirror to a filter on top of a node in the "
+                   "source's backing chain");
+        goto fail;
+    }
+
+    if (backing_mode != MIRROR_LEAVE_BACKING_CHAIN) {
+        target_perms |= BLK_PERM_GRAPH_MOD;
+    }
+
     s->target = blk_new(s->common.job.aio_context,
-                        BLK_PERM_WRITE | BLK_PERM_RESIZE |
+                        target_perms, target_shared_perms);
-                        (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;
@@ -1672,6 +1710,7 @@ static BlockJob *mirror_start_job(
     s->zero_target = zero_target;
     s->copy_mode = copy_mode;
     s->base = base;
+    s->base_overlay = bdrv_find_overlay(bs, base);
     s->granularity = granularity;
     s->buf_size = ROUND_UP(buf_size, granularity);
     s->unmap = unmap;
@@ -1702,15 +1741,39 @@ static BlockJob *mirror_start_job(
     /* In commit_active_start() all intermediate nodes disappear, so
      * any jobs in them must be blocked */
     if (target_is_backing) {
-        BlockDriverState *iter;
+        BlockDriverState *iter, *filtered_target;
-        for (iter = backing_bs(bs); iter != target; iter = backing_bs(iter)) {
+        uint64_t iter_shared_perms;
-            /* XXX BLK_PERM_WRITE needs to be allowed so we don't block
+
+        /*
+         * The topmost node with
+         * bdrv_skip_filters(filtered_target) == bdrv_skip_filters(target)
+         */
+        filtered_target = bdrv_cow_bs(bdrv_find_overlay(bs, target));
+
+        assert(bdrv_skip_filters(filtered_target) ==
+               bdrv_skip_filters(target));
+
+        /*
+         * 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). */
+         * second filter driver above s->base (== target).
+         */
+        iter_shared_perms = BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE;
+
+        for (iter = bdrv_filter_or_cow_bs(bs); iter != target;
+             iter = bdrv_filter_or_cow_bs(iter))
+        {
+            if (iter == filtered_target) {
+                /*
+                 * From here on, all nodes are filters on the base.
+                 * This allows us to share BLK_PERM_CONSISTENT_READ.
+                 */
+                iter_shared_perms |= BLK_PERM_CONSISTENT_READ;
+            }
+
             ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
-                                     BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
+                                     iter_shared_perms, errp);
-                                     errp);
             if (ret < 0) {
                 goto fail;
             }
@@ -1746,7 +1809,7 @@ fail:
     bs_opaque->stop = true;
     bdrv_child_refresh_perms(mirror_top_bs, mirror_top_bs->backing,
                              &error_abort);
-    bdrv_replace_node(mirror_top_bs, backing_bs(mirror_top_bs), &error_abort);
+    bdrv_replace_node(mirror_top_bs, mirror_top_bs->backing->bs, &error_abort);
 
     bdrv_unref(mirror_top_bs);
 
@@ -1774,7 +1837,7 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
         return;
     }
     is_none_mode = mode == MIRROR_SYNC_MODE_NONE;
-    base = mode == MIRROR_SYNC_MODE_TOP ? backing_bs(bs) : NULL;
+    base = mode == MIRROR_SYNC_MODE_TOP ? bdrv_backing_chain_next(bs) : NULL;
     mirror_start_job(job_id, bs, creation_flags, target, replaces,
                      speed, granularity, buf_size, backing_mode, zero_target,
                      on_source_error, on_target_error, unmap, NULL, NULL,

block/monitor/block-hmp-cmds.c

@@ -217,7 +217,7 @@ void hmp_commit(Monitor *mon, const QDict *qdict)
             return;
         }
 
-        bs = blk_bs(blk);
+        bs = bdrv_skip_implicit_filters(blk_bs(blk));
         aio_context = bdrv_get_aio_context(bs);
         aio_context_acquire(aio_context);
 

block/null.c

@@ -262,6 +262,11 @@ static void null_refresh_filename(BlockDriverState *bs)
              bs->drv->format_name);
 }
 
+static int64_t null_allocated_file_size(BlockDriverState *bs)
+{
+    return 0;
+}
+
 static const char *const null_strong_runtime_opts[] = {
     BLOCK_OPT_SIZE,
     NULL_OPT_ZEROES,
@@ -277,6 +282,7 @@ static BlockDriver bdrv_null_co = {
     .bdrv_file_open         = null_file_open,
     .bdrv_parse_filename    = null_co_parse_filename,
     .bdrv_getlength         = null_getlength,
+    .bdrv_get_allocated_file_size = null_allocated_file_size,
 
     .bdrv_co_preadv         = null_co_preadv,
     .bdrv_co_pwritev        = null_co_pwritev,
@@ -297,6 +303,7 @@ static BlockDriver bdrv_null_aio = {
     .bdrv_file_open         = null_file_open,
     .bdrv_parse_filename    = null_aio_parse_filename,
     .bdrv_getlength         = null_getlength,
+    .bdrv_get_allocated_file_size = null_allocated_file_size,
 
     .bdrv_aio_preadv        = null_aio_preadv,
     .bdrv_aio_pwritev       = null_aio_pwritev,

block/nvme.c

@@ -83,25 +83,21 @@ typedef struct {
 
 /* Memory mapped registers */
 typedef volatile struct {
-    uint64_t cap;
+    NvmeBar ctrl;
-    uint32_t vs;
+    struct {
-    uint32_t intms;
+        uint32_t sq_tail;
-    uint32_t intmc;
+        uint32_t cq_head;
-    uint32_t cc;
+    } doorbells[];
-    uint32_t reserved0;
-    uint32_t csts;
-    uint32_t nssr;
-    uint32_t aqa;
-    uint64_t asq;
-    uint64_t acq;
-    uint32_t cmbloc;
-    uint32_t cmbsz;
-    uint8_t  reserved1[0xec0];
-    uint8_t  cmd_set_specfic[0x100];
-    uint32_t doorbells[];
 } NVMeRegs;
 
-QEMU_BUILD_BUG_ON(offsetof(NVMeRegs, doorbells) != 0x1000);
+#define INDEX_ADMIN     0
+#define INDEX_IO(n)     (1 + n)
+
+/* This driver shares a single MSIX IRQ for the admin and I/O queues */
+enum {
+    MSIX_SHARED_IRQ_IDX = 0,
+    MSIX_IRQ_COUNT = 1
+};
 
 struct BDRVNVMeState {
     AioContext *aio_context;
@@ -117,7 +113,7 @@ struct BDRVNVMeState {
     /* How many uint32_t elements does each doorbell entry take. */
     size_t doorbell_scale;
     bool write_cache_supported;
-    EventNotifier irq_notifier;
+    EventNotifier irq_notifier[MSIX_IRQ_COUNT];
 
     uint64_t nsze; /* Namespace size reported by identify command */
     int nsid;      /* The namespace id to read/write data. */
@@ -162,21 +158,20 @@ static QemuOptsList runtime_opts = {
     },
 };
 
-static void nvme_init_queue(BlockDriverState *bs, NVMeQueue *q,
+static void nvme_init_queue(BDRVNVMeState *s, NVMeQueue *q,
                             int nentries, int entry_bytes, Error **errp)
 {
-    BDRVNVMeState *s = bs->opaque;
     size_t bytes;
     int r;
 
     bytes = ROUND_UP(nentries * entry_bytes, s->page_size);
     q->head = q->tail = 0;
-    q->queue = qemu_try_blockalign0(bs, bytes);
+    q->queue = qemu_try_memalign(s->page_size, bytes);
-
     if (!q->queue) {
         error_setg(errp, "Cannot allocate queue");
         return;
     }
+    memset(q->queue, 0, bytes);
     r = qemu_vfio_dma_map(s->vfio, q->queue, bytes, false, &q->iova);
     if (r) {
         error_setg(errp, "Cannot map queue");
@@ -206,23 +201,31 @@ static void nvme_free_req_queue_cb(void *opaque)
     qemu_mutex_unlock(&q->lock);
 }
 
-static NVMeQueuePair *nvme_create_queue_pair(BlockDriverState *bs,
+static NVMeQueuePair *nvme_create_queue_pair(BDRVNVMeState *s,
+                                             AioContext *aio_context,
                                              int idx, int size,
                                              Error **errp)
 {
     int i, r;
-    BDRVNVMeState *s = bs->opaque;
     Error *local_err = NULL;
-    NVMeQueuePair *q = g_new0(NVMeQueuePair, 1);
+    NVMeQueuePair *q;
     uint64_t prp_list_iova;
 
+    q = g_try_new0(NVMeQueuePair, 1);
+    if (!q) {
+        return NULL;
+    }
+    q->prp_list_pages = qemu_try_memalign(s->page_size,
+                                          s->page_size * NVME_NUM_REQS);
+    if (!q->prp_list_pages) {
+        goto fail;
+    }
+    memset(q->prp_list_pages, 0, s->page_size * NVME_NUM_REQS);
     qemu_mutex_init(&q->lock);
     q->s = s;
     q->index = idx;
     qemu_co_queue_init(&q->free_req_queue);
-    q->prp_list_pages = qemu_blockalign0(bs, s->page_size * NVME_NUM_REQS);
+    q->completion_bh = aio_bh_new(aio_context, nvme_process_completion_bh, q);
-    q->completion_bh = aio_bh_new(bdrv_get_aio_context(bs),
-                                  nvme_process_completion_bh, q);
     r = qemu_vfio_dma_map(s->vfio, q->prp_list_pages,
                           s->page_size * NVME_NUM_REQS,
                           false, &prp_list_iova);
@@ -239,19 +242,19 @@ static NVMeQueuePair *nvme_create_queue_pair(BlockDriverState *bs,
         req->prp_list_iova = prp_list_iova + i * s->page_size;
     }
 
-    nvme_init_queue(bs, &q->sq, size, NVME_SQ_ENTRY_BYTES, &local_err);
+    nvme_init_queue(s, &q->sq, size, NVME_SQ_ENTRY_BYTES, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         goto fail;
     }
-    q->sq.doorbell = &s->regs->doorbells[idx * 2 * s->doorbell_scale];
+    q->sq.doorbell = &s->regs->doorbells[idx * s->doorbell_scale].sq_tail;
 
-    nvme_init_queue(bs, &q->cq, size, NVME_CQ_ENTRY_BYTES, &local_err);
+    nvme_init_queue(s, &q->cq, size, NVME_CQ_ENTRY_BYTES, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         goto fail;
     }
-    q->cq.doorbell = &s->regs->doorbells[(idx * 2 + 1) * s->doorbell_scale];
+    q->cq.doorbell = &s->regs->doorbells[idx * s->doorbell_scale].cq_head;
 
     return q;
 fail:
@@ -441,6 +444,9 @@ static void nvme_trace_command(const NvmeCmd *cmd)
 {
     int i;
 
+    if (!trace_event_get_state_backends(TRACE_NVME_SUBMIT_COMMAND_RAW)) {
+        return;
+    }
     for (i = 0; i < 8; ++i) {
         uint8_t *cmdp = (uint8_t *)cmd + i * 8;
         trace_nvme_submit_command_raw(cmdp[0], cmdp[1], cmdp[2], cmdp[3],
@@ -479,6 +485,7 @@ static void nvme_cmd_sync_cb(void *opaque, int ret)
 static int nvme_cmd_sync(BlockDriverState *bs, NVMeQueuePair *q,
                          NvmeCmd *cmd)
 {
+    AioContext *aio_context = bdrv_get_aio_context(bs);
     NVMeRequest *req;
     int ret = -EINPROGRESS;
     req = nvme_get_free_req(q);
@@ -487,17 +494,18 @@ static int nvme_cmd_sync(BlockDriverState *bs, NVMeQueuePair *q,
     }
     nvme_submit_command(q, req, cmd, nvme_cmd_sync_cb, &ret);
 
-    BDRV_POLL_WHILE(bs, ret == -EINPROGRESS);
+    AIO_WAIT_WHILE(aio_context, ret == -EINPROGRESS);
     return ret;
 }
 
 static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
 {
     BDRVNVMeState *s = bs->opaque;
-    NvmeIdCtrl *idctrl;
+    union {
-    NvmeIdNs *idns;
+        NvmeIdCtrl ctrl;
+        NvmeIdNs ns;
+    } *id;
     NvmeLBAF *lbaf;
-    uint8_t *resp;
     uint16_t oncs;
     int r;
     uint64_t iova;
@@ -506,54 +514,52 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
         .cdw10 = cpu_to_le32(0x1),
     };
 
-    resp = qemu_try_blockalign0(bs, sizeof(NvmeIdCtrl));
+    id = qemu_try_memalign(s->page_size, sizeof(*id));
-    if (!resp) {
+    if (!id) {
         error_setg(errp, "Cannot allocate buffer for identify response");
         goto out;
     }
-    idctrl = (NvmeIdCtrl *)resp;
+    r = qemu_vfio_dma_map(s->vfio, id, sizeof(*id), true, &iova);
-    idns = (NvmeIdNs *)resp;
-    r = qemu_vfio_dma_map(s->vfio, resp, sizeof(NvmeIdCtrl), true, &iova);
     if (r) {
         error_setg(errp, "Cannot map buffer for DMA");
         goto out;
     }
-    cmd.dptr.prp1 = cpu_to_le64(iova);
 
-    if (nvme_cmd_sync(bs, s->queues[0], &cmd)) {
+    memset(id, 0, sizeof(*id));
+    cmd.dptr.prp1 = cpu_to_le64(iova);
+    if (nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd)) {
         error_setg(errp, "Failed to identify controller");
         goto out;
     }
 
-    if (le32_to_cpu(idctrl->nn) < namespace) {
+    if (le32_to_cpu(id->ctrl.nn) < namespace) {
         error_setg(errp, "Invalid namespace");
         goto out;
     }
-    s->write_cache_supported = le32_to_cpu(idctrl->vwc) & 0x1;
+    s->write_cache_supported = le32_to_cpu(id->ctrl.vwc) & 0x1;
-    s->max_transfer = (idctrl->mdts ? 1 << idctrl->mdts : 0) * s->page_size;
+    s->max_transfer = (id->ctrl.mdts ? 1 << id->ctrl.mdts : 0) * s->page_size;
     /* For now the page list buffer per command is one page, to hold at most
      * s->page_size / sizeof(uint64_t) entries. */
     s->max_transfer = MIN_NON_ZERO(s->max_transfer,
                           s->page_size / sizeof(uint64_t) * s->page_size);
 
-    oncs = le16_to_cpu(idctrl->oncs);
+    oncs = le16_to_cpu(id->ctrl.oncs);
     s->supports_write_zeroes = !!(oncs & NVME_ONCS_WRITE_ZEROES);
     s->supports_discard = !!(oncs & NVME_ONCS_DSM);
 
-    memset(resp, 0, 4096);
+    memset(id, 0, sizeof(*id));
-
     cmd.cdw10 = 0;
     cmd.nsid = cpu_to_le32(namespace);
-    if (nvme_cmd_sync(bs, s->queues[0], &cmd)) {
+    if (nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd)) {
         error_setg(errp, "Failed to identify namespace");
         goto out;
     }
 
-    s->nsze = le64_to_cpu(idns->nsze);
+    s->nsze = le64_to_cpu(id->ns.nsze);
-    lbaf = &idns->lbaf[NVME_ID_NS_FLBAS_INDEX(idns->flbas)];
+    lbaf = &id->ns.lbaf[NVME_ID_NS_FLBAS_INDEX(id->ns.flbas)];
 
-    if (NVME_ID_NS_DLFEAT_WRITE_ZEROES(idns->dlfeat) &&
+    if (NVME_ID_NS_DLFEAT_WRITE_ZEROES(id->ns.dlfeat) &&
-            NVME_ID_NS_DLFEAT_READ_BEHAVIOR(idns->dlfeat) ==
+            NVME_ID_NS_DLFEAT_READ_BEHAVIOR(id->ns.dlfeat) ==
                     NVME_ID_NS_DLFEAT_READ_BEHAVIOR_ZEROES) {
         bs->supported_write_flags |= BDRV_REQ_MAY_UNMAP;
     }
@@ -573,17 +579,14 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
 
     s->blkshift = lbaf->ds;
 out:
-    qemu_vfio_dma_unmap(s->vfio, resp);
+    qemu_vfio_dma_unmap(s->vfio, id);
-    qemu_vfree(resp);
+    qemu_vfree(id);
 }
 
-static bool nvme_poll_queues(BDRVNVMeState *s)
+static bool nvme_poll_queue(NVMeQueuePair *q)
 {
     bool progress = false;
-    int i;
 
-    for (i = 0; i < s->nr_queues; i++) {
-        NVMeQueuePair *q = s->queues[i];
     const size_t cqe_offset = q->cq.head * NVME_CQ_ENTRY_BYTES;
     NvmeCqe *cqe = (NvmeCqe *)&q->cq.queue[cqe_offset];
 
@@ -593,7 +596,7 @@ static bool nvme_poll_queues(BDRVNVMeState *s)
      * cannot race with itself.
      */
     if ((le16_to_cpu(cqe->status) & 0x1) == q->cq_phase) {
-            continue;
+        return false;
     }
 
     qemu_mutex_lock(&q->lock);
@@ -602,13 +605,27 @@ static bool nvme_poll_queues(BDRVNVMeState *s)
         progress = true;
     }
     qemu_mutex_unlock(&q->lock);
+
+    return progress;
+}
+
+static bool nvme_poll_queues(BDRVNVMeState *s)
+{
+    bool progress = false;
+    int i;
+
+    for (i = 0; i < s->nr_queues; i++) {
+        if (nvme_poll_queue(s->queues[i])) {
+            progress = true;
+        }
     }
     return progress;
 }
 
 static void nvme_handle_event(EventNotifier *n)
 {
-    BDRVNVMeState *s = container_of(n, BDRVNVMeState, irq_notifier);
+    BDRVNVMeState *s = container_of(n, BDRVNVMeState,
+                                    irq_notifier[MSIX_SHARED_IRQ_IDX]);
 
     trace_nvme_handle_event(s);
     event_notifier_test_and_clear(n);
@@ -623,7 +640,8 @@ static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp)
     NvmeCmd cmd;
     int queue_size = NVME_QUEUE_SIZE;
 
-    q = nvme_create_queue_pair(bs, n, queue_size, errp);
+    q = nvme_create_queue_pair(s, bdrv_get_aio_context(bs),
+                               n, queue_size, errp);
     if (!q) {
         return false;
     }
@@ -633,10 +651,9 @@ static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp)
         .cdw10 = cpu_to_le32(((queue_size - 1) << 16) | (n & 0xFFFF)),
         .cdw11 = cpu_to_le32(0x3),
     };
-    if (nvme_cmd_sync(bs, s->queues[0], &cmd)) {
+    if (nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd)) {
-        error_setg(errp, "Failed to create io queue [%d]", n);
+        error_setg(errp, "Failed to create CQ io queue [%d]", n);
-        nvme_free_queue_pair(q);
+        goto out_error;
-        return false;
     }
     cmd = (NvmeCmd) {
         .opcode = NVME_ADM_CMD_CREATE_SQ,
@@ -644,21 +661,24 @@ static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp)
         .cdw10 = cpu_to_le32(((queue_size - 1) << 16) | (n & 0xFFFF)),
         .cdw11 = cpu_to_le32(0x1 | (n << 16)),
     };
-    if (nvme_cmd_sync(bs, s->queues[0], &cmd)) {
+    if (nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd)) {
-        error_setg(errp, "Failed to create io queue [%d]", n);
+        error_setg(errp, "Failed to create SQ io queue [%d]", n);
-        nvme_free_queue_pair(q);
+        goto out_error;
-        return false;
     }
     s->queues = g_renew(NVMeQueuePair *, s->queues, n + 1);
     s->queues[n] = q;
     s->nr_queues++;
     return true;
+out_error:
+    nvme_free_queue_pair(q);
+    return false;
 }
 
 static bool nvme_poll_cb(void *opaque)
 {
     EventNotifier *e = opaque;
-    BDRVNVMeState *s = container_of(e, BDRVNVMeState, irq_notifier);
+    BDRVNVMeState *s = container_of(e, BDRVNVMeState,
+                                    irq_notifier[MSIX_SHARED_IRQ_IDX]);
 
     trace_nvme_poll_cb(s);
     return nvme_poll_queues(s);
@@ -668,6 +688,7 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace,
                      Error **errp)
 {
     BDRVNVMeState *s = bs->opaque;
+    AioContext *aio_context = bdrv_get_aio_context(bs);
     int ret;
     uint64_t cap;
     uint64_t timeout_ms;
@@ -679,7 +700,7 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace,
     s->device = g_strdup(device);
     s->nsid = namespace;
     s->aio_context = bdrv_get_aio_context(bs);
-    ret = event_notifier_init(&s->irq_notifier, 0);
+    ret = event_notifier_init(&s->irq_notifier[MSIX_SHARED_IRQ_IDX], 0);
     if (ret) {
         error_setg(errp, "Failed to init event notifier");
         return ret;
@@ -700,7 +721,7 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace,
     /* Perform initialize sequence as described in NVMe spec "7.6.1
      * Initialization". */
 
-    cap = le64_to_cpu(s->regs->cap);
+    cap = le64_to_cpu(s->regs->ctrl.cap);
     if (!(cap & (1ULL << 37))) {
         error_setg(errp, "Device doesn't support NVMe command set");
         ret = -EINVAL;
@@ -713,10 +734,10 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace,
     timeout_ms = MIN(500 * ((cap >> 24) & 0xFF), 30000);
 
     /* Reset device to get a clean state. */
-    s->regs->cc = cpu_to_le32(le32_to_cpu(s->regs->cc) & 0xFE);
+    s->regs->ctrl.cc = cpu_to_le32(le32_to_cpu(s->regs->ctrl.cc) & 0xFE);
     /* Wait for CSTS.RDY = 0. */
-    deadline = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + timeout_ms * 1000000ULL;
+    deadline = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + timeout_ms * SCALE_MS;
-    while (le32_to_cpu(s->regs->csts) & 0x1) {
+    while (le32_to_cpu(s->regs->ctrl.csts) & 0x1) {
         if (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) > deadline) {
             error_setg(errp, "Timeout while waiting for device to reset (%"
                              PRId64 " ms)",
@@ -728,25 +749,27 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace,
 
     /* Set up admin queue. */
     s->queues = g_new(NVMeQueuePair *, 1);
-    s->queues[0] = nvme_create_queue_pair(bs, 0, NVME_QUEUE_SIZE, errp);
+    s->queues[INDEX_ADMIN] = nvme_create_queue_pair(s, aio_context, 0,
-    if (!s->queues[0]) {
+                                                          NVME_QUEUE_SIZE,
+                                                          errp);
+    if (!s->queues[INDEX_ADMIN]) {
         ret = -EINVAL;
         goto out;
     }
     s->nr_queues = 1;
     QEMU_BUILD_BUG_ON(NVME_QUEUE_SIZE & 0xF000);
-    s->regs->aqa = cpu_to_le32((NVME_QUEUE_SIZE << 16) | NVME_QUEUE_SIZE);
+    s->regs->ctrl.aqa = cpu_to_le32((NVME_QUEUE_SIZE << 16) | NVME_QUEUE_SIZE);
-    s->regs->asq = cpu_to_le64(s->queues[0]->sq.iova);
+    s->regs->ctrl.asq = cpu_to_le64(s->queues[INDEX_ADMIN]->sq.iova);
-    s->regs->acq = cpu_to_le64(s->queues[0]->cq.iova);
+    s->regs->ctrl.acq = cpu_to_le64(s->queues[INDEX_ADMIN]->cq.iova);
 
     /* After setting up all control registers we can enable device now. */
-    s->regs->cc = cpu_to_le32((ctz32(NVME_CQ_ENTRY_BYTES) << 20) |
+    s->regs->ctrl.cc = cpu_to_le32((ctz32(NVME_CQ_ENTRY_BYTES) << 20) |
                               (ctz32(NVME_SQ_ENTRY_BYTES) << 16) |
                               0x1);
     /* Wait for CSTS.RDY = 1. */
     now = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
     deadline = now + timeout_ms * 1000000;
-    while (!(le32_to_cpu(s->regs->csts) & 0x1)) {
+    while (!(le32_to_cpu(s->regs->ctrl.csts) & 0x1)) {
         if (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) > deadline) {
             error_setg(errp, "Timeout while waiting for device to start (%"
                              PRId64 " ms)",
@@ -756,12 +779,13 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace,
         }
     }
 
-    ret = qemu_vfio_pci_init_irq(s->vfio, &s->irq_notifier,
+    ret = qemu_vfio_pci_init_irq(s->vfio, s->irq_notifier,
                                  VFIO_PCI_MSIX_IRQ_INDEX, errp);
     if (ret) {
         goto out;
     }
-    aio_set_event_notifier(bdrv_get_aio_context(bs), &s->irq_notifier,
+    aio_set_event_notifier(bdrv_get_aio_context(bs),
+                           &s->irq_notifier[MSIX_SHARED_IRQ_IDX],
                            false, nvme_handle_event, nvme_poll_cb);
 
     nvme_identify(bs, namespace, &local_err);
@@ -828,7 +852,7 @@ static int nvme_enable_disable_write_cache(BlockDriverState *bs, bool enable,
         .cdw11 = cpu_to_le32(enable ? 0x01 : 0x00),
     };
 
-    ret = nvme_cmd_sync(bs, s->queues[0], &cmd);
+    ret = nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd);
     if (ret) {
         error_setg(errp, "Failed to configure NVMe write cache");
     }
@@ -844,9 +868,10 @@ static void nvme_close(BlockDriverState *bs)
         nvme_free_queue_pair(s->queues[i]);
     }
     g_free(s->queues);
-    aio_set_event_notifier(bdrv_get_aio_context(bs), &s->irq_notifier,
+    aio_set_event_notifier(bdrv_get_aio_context(bs),
+                           &s->irq_notifier[MSIX_SHARED_IRQ_IDX],
                            false, NULL, NULL);
-    event_notifier_cleanup(&s->irq_notifier);
+    event_notifier_cleanup(&s->irq_notifier[MSIX_SHARED_IRQ_IDX]);
     qemu_vfio_pci_unmap_bar(s->vfio, 0, (void *)s->regs, 0, NVME_BAR_SIZE);
     qemu_vfio_close(s->vfio);
 
@@ -1045,7 +1070,7 @@ static coroutine_fn int nvme_co_prw_aligned(BlockDriverState *bs,
 {
     int r;
     BDRVNVMeState *s = bs->opaque;
-    NVMeQueuePair *ioq = s->queues[1];
+    NVMeQueuePair *ioq = s->queues[INDEX_IO(0)];
     NVMeRequest *req;
 
     uint32_t cdw12 = (((bytes >> s->blkshift) - 1) & 0xFFFF) |
@@ -1124,7 +1149,7 @@ static int nvme_co_prw(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
         return nvme_co_prw_aligned(bs, offset, bytes, qiov, is_write, flags);
     }
     trace_nvme_prw_buffered(s, offset, bytes, qiov->niov, is_write);
-    buf = qemu_try_blockalign(bs, bytes);
+    buf = qemu_try_memalign(s->page_size, bytes);
 
     if (!buf) {
         return -ENOMEM;
@@ -1160,7 +1185,7 @@ static coroutine_fn int nvme_co_pwritev(BlockDriverState *bs,
 static coroutine_fn int nvme_co_flush(BlockDriverState *bs)
 {
     BDRVNVMeState *s = bs->opaque;
-    NVMeQueuePair *ioq = s->queues[1];
+    NVMeQueuePair *ioq = s->queues[INDEX_IO(0)];
     NVMeRequest *req;
     NvmeCmd cmd = {
         .opcode = NVME_CMD_FLUSH,
@@ -1191,7 +1216,7 @@ static coroutine_fn int nvme_co_pwrite_zeroes(BlockDriverState *bs,
                                               BdrvRequestFlags flags)
 {
     BDRVNVMeState *s = bs->opaque;
-    NVMeQueuePair *ioq = s->queues[1];
+    NVMeQueuePair *ioq = s->queues[INDEX_IO(0)];
     NVMeRequest *req;
 
     uint32_t cdw12 = ((bytes >> s->blkshift) - 1) & 0xFFFF;
@@ -1244,7 +1269,7 @@ static int coroutine_fn nvme_co_pdiscard(BlockDriverState *bs,
                                          int bytes)
 {
     BDRVNVMeState *s = bs->opaque;
-    NVMeQueuePair *ioq = s->queues[1];
+    NVMeQueuePair *ioq = s->queues[INDEX_IO(0)];
     NVMeRequest *req;
     NvmeDsmRange *buf;
     QEMUIOVector local_qiov;
@@ -1268,11 +1293,11 @@ static int coroutine_fn nvme_co_pdiscard(BlockDriverState *bs,
 
     assert(s->nr_queues > 1);
 
-    buf = qemu_try_blockalign0(bs, s->page_size);
+    buf = qemu_try_memalign(s->page_size, s->page_size);
     if (!buf) {
         return -ENOMEM;
     }
-
+    memset(buf, 0, s->page_size);
     buf->nlb = cpu_to_le32(bytes >> s->blkshift);
     buf->slba = cpu_to_le64(offset >> s->blkshift);
     buf->cattr = 0;
@@ -1353,7 +1378,8 @@ static void nvme_detach_aio_context(BlockDriverState *bs)
         q->completion_bh = NULL;
     }
 
-    aio_set_event_notifier(bdrv_get_aio_context(bs), &s->irq_notifier,
+    aio_set_event_notifier(bdrv_get_aio_context(bs),
+                           &s->irq_notifier[MSIX_SHARED_IRQ_IDX],
                            false, NULL, NULL);
 }
 
@@ -1363,7 +1389,7 @@ static void nvme_attach_aio_context(BlockDriverState *bs,
     BDRVNVMeState *s = bs->opaque;
 
     s->aio_context = new_context;
-    aio_set_event_notifier(new_context, &s->irq_notifier,
+    aio_set_event_notifier(new_context, &s->irq_notifier[MSIX_SHARED_IRQ_IDX],
                            false, nvme_handle_event, nvme_poll_cb);
 
     for (int i = 0; i < s->nr_queues; i++) {
@@ -1387,7 +1413,7 @@ static void nvme_aio_unplug(BlockDriverState *bs)
     BDRVNVMeState *s = bs->opaque;
     assert(s->plugged);
     s->plugged = false;
-    for (i = 1; i < s->nr_queues; i++) {
+    for (i = INDEX_IO(0); i < s->nr_queues; i++) {
         NVMeQueuePair *q = s->queues[i];
         qemu_mutex_lock(&q->lock);
         nvme_kick(q);

block/qapi.c

@@ -47,7 +47,7 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
                                         Error **errp)
 {
     ImageInfo **p_image_info;
-    BlockDriverState *bs0;
+    BlockDriverState *bs0, *backing;
     BlockDeviceInfo *info;
 
     if (!bs->drv) {
@@ -76,9 +76,10 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
         info->node_name = g_strdup(bs->node_name);
     }
 
-    if (bs->backing_file[0]) {
+    backing = bdrv_cow_bs(bs);
+    if (backing) {
         info->has_backing_file = true;
-        info->backing_file = g_strdup(bs->backing_file);
+        info->backing_file = g_strdup(backing->filename);
     }
 
     if (!QLIST_EMPTY(&bs->dirty_bitmaps)) {
@@ -163,9 +164,13 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
             break;
         }
 
-        if (bs0->drv && bs0->backing) {
+        if (bs0->drv && bdrv_filter_or_cow_child(bs0)) {
+            /*
+             * Put any filtered child here (for backwards compatibility to when
+             * we put bs0->backing here, which might be any filtered child).
+             */
             info->backing_file_depth++;
-            bs0 = bs0->backing->bs;
+            bs0 = bdrv_filter_or_cow_bs(bs0);
             (*p_image_info)->has_backing_image = true;
             p_image_info = &((*p_image_info)->backing_image);
         } else {
@@ -174,9 +179,8 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
 
         /* Skip automatically inserted nodes that the user isn't aware of for
          * query-block (blk != NULL), but not for query-named-block-nodes */
-        while (blk && bs0->drv && bs0->implicit) {
+        if (blk) {
-            bs0 = backing_bs(bs0);
+            bs0 = bdrv_skip_implicit_filters(bs0);
-            assert(bs0);
         }
     }
 
@@ -288,7 +292,7 @@ void bdrv_query_image_info(BlockDriverState *bs,
     info->virtual_size    = size;
     info->actual_size     = bdrv_get_allocated_file_size(bs);
     info->has_actual_size = info->actual_size >= 0;
-    if (bdrv_is_encrypted(bs)) {
+    if (bs->encrypted) {
         info->encrypted = true;
         info->has_encrypted = true;
     }
@@ -311,6 +315,7 @@ void bdrv_query_image_info(BlockDriverState *bs,
     backing_filename = bs->backing_file;
     if (backing_filename[0] != '\0') {
         char *backing_filename2;
+
         info->backing_filename = g_strdup(backing_filename);
         info->has_backing_filename = true;
         backing_filename2 = bdrv_get_full_backing_filename(bs, NULL);
@@ -362,9 +367,7 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
     char *qdev;
 
     /* Skip automatically inserted nodes that the user isn't aware of */
-    while (bs && bs->drv && bs->implicit) {
+    bs = bdrv_skip_implicit_filters(bs);
-        bs = backing_bs(bs);
-    }
 
     info->device = g_strdup(blk_name(blk));
     info->type = g_strdup("unknown");
@@ -526,6 +529,8 @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
 static BlockStats *bdrv_query_bds_stats(BlockDriverState *bs,
                                         bool blk_level)
 {
+    BdrvChild *parent_child;
+    BlockDriverState *filter_or_cow_bs;
     BlockStats *s = NULL;
 
     s = g_malloc0(sizeof(*s));
@@ -538,9 +543,8 @@ static BlockStats *bdrv_query_bds_stats(BlockDriverState *bs,
     /* Skip automatically inserted nodes that the user isn't aware of in
      * a BlockBackend-level command. Stay at the exact node for a node-level
      * command. */
-    while (blk_level && bs->drv && bs->implicit) {
+    if (blk_level) {
-        bs = backing_bs(bs);
+        bs = bdrv_skip_implicit_filters(bs);
-        assert(bs);
     }
 
     if (bdrv_get_node_name(bs)[0]) {
@@ -555,14 +559,46 @@ static BlockStats *bdrv_query_bds_stats(BlockDriverState *bs,
         s->has_driver_specific = true;
     }
 
-    if (bs->file) {
+    parent_child = bdrv_primary_child(bs);
+    if (!parent_child ||
+        !(parent_child->role & (BDRV_CHILD_DATA | BDRV_CHILD_FILTERED)))
+    {
+        BdrvChild *c;
+
+        /*
+         * Look for a unique data-storing child.  We do not need to look for
+         * filtered children, as there would be only one and it would have been
+         * the primary child.
+         */
+        parent_child = NULL;
+        QLIST_FOREACH(c, &bs->children, next) {
+            if (c->role & BDRV_CHILD_DATA) {
+                if (parent_child) {
+                    /*
+                     * There are multiple data-storing children and we cannot
+                     * choose between them.
+                     */
+                    parent_child = NULL;
+                    break;
+                }
+                parent_child = c;
+            }
+        }
+    }
+    if (parent_child) {
         s->has_parent = true;
-        s->parent = bdrv_query_bds_stats(bs->file->bs, blk_level);
+        s->parent = bdrv_query_bds_stats(parent_child->bs, blk_level);
     }
 
-    if (blk_level && bs->backing) {
+    filter_or_cow_bs = bdrv_filter_or_cow_bs(bs);
+    if (blk_level && filter_or_cow_bs) {
+        /*
+         * Put any filtered or COW child here (for backwards
+         * compatibility to when we put bs0->backing here, which might
+         * be either)
+         */
         s->has_backing = true;
-        s->backing = bdrv_query_bds_stats(bs->backing->bs, blk_level);
+        s->backing = bdrv_query_bds_stats(filter_or_cow_bs, blk_level);
     }
 
     return s;

block/qcow2-cluster.c

@@ -1320,6 +1320,7 @@ static bool cluster_needs_new_alloc(BlockDriverState *bs, uint64_t l2_entry)
         if (l2_entry & QCOW_OFLAG_COPIED) {
             return false;
         }
+        /* fallthrough */
     case QCOW2_CLUSTER_UNALLOCATED:
     case QCOW2_CLUSTER_COMPRESSED:
     case QCOW2_CLUSTER_ZERO_PLAIN:

block/snapshot.c

@@ -147,6 +147,56 @@ bool bdrv_snapshot_find_by_id_and_name(BlockDriverState *bs,
     return ret;
 }
 
+/**
+ * Return a pointer to the child BDS pointer to which we can fall
+ * back if the given BDS does not support snapshots.
+ * Return NULL if there is no BDS to (safely) fall back to.
+ *
+ * We need to return an indirect pointer because bdrv_snapshot_goto()
+ * has to modify the BdrvChild pointer.
+ */
+static BdrvChild **bdrv_snapshot_fallback_ptr(BlockDriverState *bs)
+{
+    BdrvChild **fallback;
+    BdrvChild *child;
+
+    /*
+     * The only BdrvChild pointers that are safe to modify (and which
+     * we can thus return a reference to) are bs->file and
+     * bs->backing.
+     */
+    fallback = &bs->file;
+    if (!*fallback && bs->drv && bs->drv->is_filter) {
+        fallback = &bs->backing;
+    }
+
+    if (!*fallback) {
+        return NULL;
+    }
+
+    /*
+     * Check that there are no other children that would need to be
+     * snapshotted.  If there are, it is not safe to fall back to
+     * *fallback.
+     */
+    QLIST_FOREACH(child, &bs->children, next) {
+        if (child->role & (BDRV_CHILD_DATA | BDRV_CHILD_METADATA |
+                           BDRV_CHILD_FILTERED) &&
+            child != *fallback)
+        {
+            return NULL;
+        }
+    }
+
+    return fallback;
+}
+
+static BlockDriverState *bdrv_snapshot_fallback(BlockDriverState *bs)
+{
+    BdrvChild **child_ptr = bdrv_snapshot_fallback_ptr(bs);
+    return child_ptr ? (*child_ptr)->bs : NULL;
+}
+
 int bdrv_can_snapshot(BlockDriverState *bs)
 {
     BlockDriver *drv = bs->drv;
@@ -155,8 +205,9 @@ int bdrv_can_snapshot(BlockDriverState *bs)
     }
 
     if (!drv->bdrv_snapshot_create) {
-        if (bs->file != NULL) {
+        BlockDriverState *fallback_bs = bdrv_snapshot_fallback(bs);
-            return bdrv_can_snapshot(bs->file->bs);
+        if (fallback_bs) {
+            return bdrv_can_snapshot(fallback_bs);
         }
         return 0;
     }
@@ -168,14 +219,15 @@ int bdrv_snapshot_create(BlockDriverState *bs,
                          QEMUSnapshotInfo *sn_info)
 {
     BlockDriver *drv = bs->drv;
+    BlockDriverState *fallback_bs = bdrv_snapshot_fallback(bs);
     if (!drv) {
         return -ENOMEDIUM;
     }
     if (drv->bdrv_snapshot_create) {
         return drv->bdrv_snapshot_create(bs, sn_info);
     }
-    if (bs->file) {
+    if (fallback_bs) {
-        return bdrv_snapshot_create(bs->file->bs, sn_info);
+        return bdrv_snapshot_create(fallback_bs, sn_info);
     }
     return -ENOTSUP;
 }
@@ -185,6 +237,7 @@ int bdrv_snapshot_goto(BlockDriverState *bs,
                        Error **errp)
 {
     BlockDriver *drv = bs->drv;
+    BdrvChild **fallback_ptr;
     int ret, open_ret;
 
     if (!drv) {
@@ -205,39 +258,46 @@ int bdrv_snapshot_goto(BlockDriverState *bs,
         return ret;
     }
 
-    if (bs->file) {
+    fallback_ptr = bdrv_snapshot_fallback_ptr(bs);
-        BlockDriverState *file;
+    if (fallback_ptr) {
-        QDict *options = qdict_clone_shallow(bs->options);
+        QDict *options;
         QDict *file_options;
         Error *local_err = NULL;
+        BlockDriverState *fallback_bs = (*fallback_ptr)->bs;
+        char *subqdict_prefix = g_strdup_printf("%s.", (*fallback_ptr)->name);
+
+        options = qdict_clone_shallow(bs->options);
 
-        file = bs->file->bs;
         /* Prevent it from getting deleted when detached from bs */
-        bdrv_ref(file);
+        bdrv_ref(fallback_bs);
 
-        qdict_extract_subqdict(options, &file_options, "file.");
+        qdict_extract_subqdict(options, &file_options, subqdict_prefix);
         qobject_unref(file_options);
-        qdict_put_str(options, "file", bdrv_get_node_name(file));
+        g_free(subqdict_prefix);
+
+        qdict_put_str(options, (*fallback_ptr)->name,
+                      bdrv_get_node_name(fallback_bs));
 
         if (drv->bdrv_close) {
             drv->bdrv_close(bs);
         }
-        bdrv_unref_child(bs, bs->file);
-        bs->file = NULL;
 
-        ret = bdrv_snapshot_goto(file, snapshot_id, errp);
+        bdrv_unref_child(bs, *fallback_ptr);
+        *fallback_ptr = NULL;
+
+        ret = bdrv_snapshot_goto(fallback_bs, snapshot_id, errp);
         open_ret = drv->bdrv_open(bs, options, bs->open_flags, &local_err);
         qobject_unref(options);
         if (open_ret < 0) {
-            bdrv_unref(file);
+            bdrv_unref(fallback_bs);
             bs->drv = NULL;
             /* A bdrv_snapshot_goto() error takes precedence */
             error_propagate(errp, local_err);
             return ret < 0 ? ret : open_ret;
         }
 
-        assert(bs->file->bs == file);
+        assert(fallback_bs == (*fallback_ptr)->bs);
-        bdrv_unref(file);
+        bdrv_unref(fallback_bs);
         return ret;
     }
 
@@ -273,6 +333,7 @@ int bdrv_snapshot_delete(BlockDriverState *bs,
                          Error **errp)
 {
     BlockDriver *drv = bs->drv;
+    BlockDriverState *fallback_bs = bdrv_snapshot_fallback(bs);
     int ret;
 
     if (!drv) {
@@ -289,8 +350,8 @@ int bdrv_snapshot_delete(BlockDriverState *bs,
 
     if (drv->bdrv_snapshot_delete) {
         ret = drv->bdrv_snapshot_delete(bs, snapshot_id, name, errp);
-    } else if (bs->file) {
+    } else if (fallback_bs) {
-        ret = bdrv_snapshot_delete(bs->file->bs, snapshot_id, name, errp);
+        ret = bdrv_snapshot_delete(fallback_bs, snapshot_id, name, errp);
     } else {
         error_setg(errp, "Block format '%s' used by device '%s' "
                    "does not support internal snapshot deletion",
@@ -306,14 +367,15 @@ int bdrv_snapshot_list(BlockDriverState *bs,
                        QEMUSnapshotInfo **psn_info)
 {
     BlockDriver *drv = bs->drv;
+    BlockDriverState *fallback_bs = bdrv_snapshot_fallback(bs);
     if (!drv) {
         return -ENOMEDIUM;
     }
     if (drv->bdrv_snapshot_list) {
         return drv->bdrv_snapshot_list(bs, psn_info);
     }
-    if (bs->file) {
+    if (fallback_bs) {
-        return bdrv_snapshot_list(bs->file->bs, psn_info);
+        return bdrv_snapshot_list(fallback_bs, psn_info);
     }
     return -ENOTSUP;
 }

block/stream.c

@@ -31,7 +31,8 @@ enum {
 
 typedef struct StreamBlockJob {
     BlockJob common;
-    BlockDriverState *bottom;
+    BlockDriverState *base_overlay; /* COW overlay (stream from this) */
+    BlockDriverState *above_base;   /* Node directly above the base */
     BlockdevOnError on_error;
     char *backing_file_str;
     bool bs_read_only;
@@ -53,7 +54,7 @@ static void stream_abort(Job *job)
 
     if (s->chain_frozen) {
         BlockJob *bjob = &s->common;
-        bdrv_unfreeze_backing_chain(blk_bs(bjob->blk), s->bottom);
+        bdrv_unfreeze_backing_chain(blk_bs(bjob->blk), s->above_base);
     }
 }
 
@@ -62,14 +63,15 @@ static int stream_prepare(Job *job)
     StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
     BlockJob *bjob = &s->common;
     BlockDriverState *bs = blk_bs(bjob->blk);
-    BlockDriverState *base = backing_bs(s->bottom);
+    BlockDriverState *unfiltered_bs = bdrv_skip_filters(bs);
+    BlockDriverState *base = bdrv_filter_or_cow_bs(s->above_base);
     Error *local_err = NULL;
     int ret = 0;
 
-    bdrv_unfreeze_backing_chain(bs, s->bottom);
+    bdrv_unfreeze_backing_chain(bs, s->above_base);
     s->chain_frozen = false;
 
-    if (bs->backing) {
+    if (bdrv_cow_child(unfiltered_bs)) {
         const char *base_id = NULL, *base_fmt = NULL;
         if (base) {
             base_id = s->backing_file_str;
@@ -77,8 +79,8 @@ static int stream_prepare(Job *job)
                 base_fmt = base->drv->format_name;
             }
         }
-        bdrv_set_backing_hd(bs, base, &local_err);
+        bdrv_set_backing_hd(unfiltered_bs, base, &local_err);
-        ret = bdrv_change_backing_file(bs, base_id, base_fmt, false);
+        ret = bdrv_change_backing_file(unfiltered_bs, base_id, base_fmt, false);
         if (local_err) {
             error_report_err(local_err);
             return -EPERM;
@@ -109,14 +111,15 @@ static int coroutine_fn stream_run(Job *job, Error **errp)
     StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
     BlockBackend *blk = s->common.blk;
     BlockDriverState *bs = blk_bs(blk);
-    bool enable_cor = !backing_bs(s->bottom);
+    BlockDriverState *unfiltered_bs = bdrv_skip_filters(bs);
+    bool enable_cor = !bdrv_cow_child(s->base_overlay);
     int64_t len;
     int64_t offset = 0;
     uint64_t delay_ns = 0;
     int error = 0;
     int64_t n = 0; /* bytes */
 
-    if (bs == s->bottom) {
+    if (unfiltered_bs == s->base_overlay) {
         /* Nothing to stream */
         return 0;
     }
@@ -150,13 +153,14 @@ static int coroutine_fn stream_run(Job *job, Error **errp)
 
         copy = false;
 
-        ret = bdrv_is_allocated(bs, offset, STREAM_CHUNK, &n);
+        ret = bdrv_is_allocated(unfiltered_bs, offset, STREAM_CHUNK, &n);
         if (ret == 1) {
             /* Allocated in the top, no need to copy.  */
         } else if (ret >= 0) {
             /* Copy if allocated in the intermediate images.  Limit to the
              * known-unallocated area [offset, offset+n*BDRV_SECTOR_SIZE).  */
-            ret = bdrv_is_allocated_above(backing_bs(bs), s->bottom, true,
+            ret = bdrv_is_allocated_above(bdrv_cow_bs(unfiltered_bs),
+                                          s->base_overlay, true,
                                           offset, n, &n);
             /* Finish early if end of backing file has been reached */
             if (ret == 0 && n == 0) {
@@ -223,9 +227,29 @@ void stream_start(const char *job_id, BlockDriverState *bs,
     BlockDriverState *iter;
     bool bs_read_only;
     int basic_flags = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED;
-    BlockDriverState *bottom = bdrv_find_overlay(bs, base);
+    BlockDriverState *base_overlay = bdrv_find_overlay(bs, base);
+    BlockDriverState *above_base;
 
-    if (bdrv_freeze_backing_chain(bs, bottom, errp) < 0) {
+    if (!base_overlay) {
+        error_setg(errp, "'%s' is not in the backing chain of '%s'",
+                   base->node_name, bs->node_name);
+        return;
+    }
+
+    /*
+     * Find the node directly above @base.  @base_overlay is a COW overlay, so
+     * it must have a bdrv_cow_child(), but it is the immediate overlay of
+     * @base, so between the two there can only be filters.
+     */
+    above_base = base_overlay;
+    if (bdrv_cow_bs(above_base) != base) {
+        above_base = bdrv_cow_bs(above_base);
+        while (bdrv_filter_bs(above_base) != base) {
+            above_base = bdrv_filter_bs(above_base);
+        }
+    }
+
+    if (bdrv_freeze_backing_chain(bs, above_base, errp) < 0) {
         return;
     }
 
@@ -255,14 +279,19 @@ void stream_start(const char *job_id, BlockDriverState *bs,
      * and resizes. Reassign the base node pointer because the backing BS of the
      * bottom node might change after the call to bdrv_reopen_set_read_only()
      * due to parallel block jobs running.
+     * above_base node might change after the call to
+     * bdrv_reopen_set_read_only() due to parallel block jobs running.
      */
-    base = backing_bs(bottom);
+    base = bdrv_filter_or_cow_bs(above_base);
-    for (iter = backing_bs(bs); iter && iter != base; iter = backing_bs(iter)) {
+    for (iter = bdrv_filter_or_cow_bs(bs); iter != base;
+         iter = bdrv_filter_or_cow_bs(iter))
+    {
         block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
                            basic_flags, &error_abort);
     }
 
-    s->bottom = bottom;
+    s->base_overlay = base_overlay;
+    s->above_base = above_base;
     s->backing_file_str = g_strdup(backing_file_str);
     s->bs_read_only = bs_read_only;
     s->chain_frozen = true;
@@ -276,5 +305,5 @@ fail:
     if (bs_read_only) {
         bdrv_reopen_set_read_only(bs, true, NULL);
     }
-    bdrv_unfreeze_backing_chain(bs, bottom);
+    bdrv_unfreeze_backing_chain(bs, above_base);
 }

block/throttle.c

@@ -151,6 +151,15 @@ static int coroutine_fn throttle_co_pdiscard(BlockDriverState *bs,
     return bdrv_co_pdiscard(bs->file, offset, bytes);
 }
 
+static int coroutine_fn throttle_co_pwritev_compressed(BlockDriverState *bs,
+                                                       uint64_t offset,
+                                                       uint64_t bytes,
+                                                       QEMUIOVector *qiov)
+{
+    return throttle_co_pwritev(bs, offset, bytes, qiov,
+                               BDRV_REQ_WRITE_COMPRESSED);
+}
+
 static int throttle_co_flush(BlockDriverState *bs)
 {
     return bdrv_co_flush(bs->file->bs);
@@ -243,6 +252,7 @@ static BlockDriver bdrv_throttle = {
 
     .bdrv_co_pwrite_zeroes              =   throttle_co_pwrite_zeroes,
     .bdrv_co_pdiscard                   =   throttle_co_pdiscard,
+    .bdrv_co_pwritev_compressed         =   throttle_co_pwritev_compressed,
 
     .bdrv_attach_aio_context            =   throttle_attach_aio_context,
     .bdrv_detach_aio_context            =   throttle_detach_aio_context,
@@ -250,7 +260,6 @@ static BlockDriver bdrv_throttle = {
     .bdrv_reopen_prepare                =   throttle_reopen_prepare,
     .bdrv_reopen_commit                 =   throttle_reopen_commit,
     .bdrv_reopen_abort                  =   throttle_reopen_abort,
-    .bdrv_co_block_status               =   bdrv_co_block_status_from_file,
 
     .bdrv_co_drain_begin                =   throttle_co_drain_begin,
     .bdrv_co_drain_end                  =   throttle_co_drain_end,

block/vmdk.c

@@ -2803,21 +2803,6 @@ static void vmdk_close(BlockDriverState *bs)
     error_free(s->migration_blocker);
 }
 
-static coroutine_fn int vmdk_co_flush(BlockDriverState *bs)
-{
-    BDRVVmdkState *s = bs->opaque;
-    int i, err;
-    int ret = 0;
-
-    for (i = 0; i < s->num_extents; i++) {
-        err = bdrv_co_flush(s->extents[i].file->bs);
-        if (err < 0) {
-            ret = err;
-        }
-    }
-    return ret;
-}
-
 static int64_t vmdk_get_allocated_file_size(BlockDriverState *bs)
 {
     int i;
@@ -3081,7 +3066,6 @@ static BlockDriver bdrv_vmdk = {
     .bdrv_close                   = vmdk_close,
     .bdrv_co_create_opts          = vmdk_co_create_opts,
     .bdrv_co_create               = vmdk_co_create,
-    .bdrv_co_flush_to_disk        = vmdk_co_flush,
     .bdrv_co_block_status         = vmdk_co_block_status,
     .bdrv_get_allocated_file_size = vmdk_get_allocated_file_size,
     .bdrv_has_zero_init           = vmdk_has_zero_init,

blockdev.c

@@ -1562,7 +1562,12 @@ static void external_snapshot_prepare(BlkActionState *common,
         goto out;
     }
 
-    if (state->new_bs->backing != NULL) {
+    if (state->new_bs->drv->is_filter) {
+        error_setg(errp, "Filters cannot be used as overlays");
+        goto out;
+    }
+
+    if (bdrv_cow_child(state->new_bs)) {
         error_setg(errp, "The overlay already has a backing image");
         goto out;
     }
@@ -1736,7 +1741,13 @@ static void drive_backup_prepare(BlkActionState *common, Error **errp)
      * on top of.
      */
     if (backup->sync == MIRROR_SYNC_MODE_TOP) {
-        source = backing_bs(bs);
+        /*
+         * Backup will not replace the source by the target, so none
+         * of the filters skipped here will be removed (in contrast to
+         * mirror).  Therefore, we can skip all of them when looking
+         * for the first COW relationship.
+         */
+        source = bdrv_cow_bs(bdrv_skip_filters(bs));
         if (!source) {
             backup->sync = MIRROR_SYNC_MODE_FULL;
         }
@@ -1756,9 +1767,14 @@ static void drive_backup_prepare(BlkActionState *common, Error **errp)
     if (backup->mode != NEW_IMAGE_MODE_EXISTING) {
         assert(backup->format);
         if (source) {
-            bdrv_refresh_filename(source);
+            /* Implicit filters should not appear in the filename */
-            bdrv_img_create(backup->target, backup->format, source->filename,
+            BlockDriverState *explicit_backing =
-                            source->drv->format_name, NULL,
+                bdrv_skip_implicit_filters(source);
+
+            bdrv_refresh_filename(explicit_backing);
+            bdrv_img_create(backup->target, backup->format,
+                            explicit_backing->filename,
+                            explicit_backing->drv->format_name, NULL,
                             size, flags, false, &local_err);
         } else {
             bdrv_img_create(backup->target, backup->format, NULL, NULL, NULL,
@@ -2528,7 +2544,9 @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device,
     }
 
     /* Check for op blockers in the whole chain between bs and base */
-    for (iter = bs; iter && iter != base_bs; iter = backing_bs(iter)) {
+    for (iter = bs; iter && iter != base_bs;
+         iter = bdrv_filter_or_cow_bs(iter))
+    {
         if (bdrv_op_is_blocked(iter, BLOCK_OP_TYPE_STREAM, errp)) {
             goto out;
         }
@@ -2584,6 +2602,7 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
     AioContext *aio_context;
     Error *local_err = NULL;
     int job_flags = JOB_DEFAULT;
+    uint64_t top_perm, top_shared;
 
     if (!has_speed) {
         speed = 0;
@@ -2685,7 +2704,9 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
 
     assert(bdrv_get_aio_context(base_bs) == aio_context);
 
-    for (iter = top_bs; iter != backing_bs(base_bs); iter = backing_bs(iter)) {
+    for (iter = top_bs; iter != bdrv_filter_or_cow_bs(base_bs);
+         iter = bdrv_filter_or_cow_bs(iter))
+    {
         if (bdrv_op_is_blocked(iter, BLOCK_OP_TYPE_COMMIT_TARGET, errp)) {
             goto out;
         }
@@ -2697,14 +2718,38 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
         goto out;
     }
 
-    if (top_bs == bs) {
+    /*
+     * Active commit is required if and only if someone has taken a
+     * WRITE permission on the top node.  Historically, we have always
+     * used active commit for top nodes, so continue that practice
+     * lest we possibly break clients that rely on this behavior, e.g.
+     * to later attach this node to a writing parent.
+     * (Active commit is never really wrong.)
+     */
+    bdrv_get_cumulative_perm(top_bs, &top_perm, &top_shared);
+    if (top_perm & BLK_PERM_WRITE ||
+        bdrv_skip_filters(top_bs) == bdrv_skip_filters(bs))
+    {
         if (has_backing_file) {
+            if (bdrv_skip_filters(top_bs) == bdrv_skip_filters(bs)) {
                 error_setg(errp, "'backing-file' specified,"
                                  " but 'top' is the active layer");
+            } else {
+                error_setg(errp, "'backing-file' specified, but 'top' has a "
+                                 "writer on it");
+            }
             goto out;
         }
-        commit_active_start(has_job_id ? job_id : NULL, bs, base_bs,
+        if (!has_job_id) {
-                            job_flags, speed, on_error,
+            /*
+             * Emulate here what block_job_create() does, because it
+             * is possible that @bs != @top_bs (the block job should
+             * be named after @bs, even if @top_bs is the actual
+             * source)
+             */
+            job_id = bdrv_get_device_name(bs);
+        }
+        commit_active_start(job_id, top_bs, base_bs, job_flags, speed, on_error,
                             filter_node_name, NULL, NULL, false, &local_err);
     } else {
         BlockDriverState *overlay_bs = bdrv_find_overlay(bs, top_bs);
@@ -2892,6 +2937,7 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
                                    bool has_auto_dismiss, bool auto_dismiss,
                                    Error **errp)
 {
+    BlockDriverState *unfiltered_bs;
     int job_flags = JOB_DEFAULT;
 
     if (!has_speed) {
@@ -2943,10 +2989,19 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
         return;
     }
 
-    if (!bs->backing && sync == MIRROR_SYNC_MODE_TOP) {
+    if (!bdrv_backing_chain_next(bs) && sync == MIRROR_SYNC_MODE_TOP) {
         sync = MIRROR_SYNC_MODE_FULL;
     }
 
+    if (!has_replaces) {
+        /* We want to mirror from @bs, but keep implicit filters on top */
+        unfiltered_bs = bdrv_skip_implicit_filters(bs);
+        if (unfiltered_bs != bs) {
+            replaces = unfiltered_bs->node_name;
+            has_replaces = true;
+        }
+    }
+
     if (has_replaces) {
         BlockDriverState *to_replace_bs;
         AioContext *replace_aio_context;
@@ -2993,7 +3048,7 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
 void qmp_drive_mirror(DriveMirror *arg, Error **errp)
 {
     BlockDriverState *bs;
-    BlockDriverState *source, *target_bs;
+    BlockDriverState *target_backing_bs, *target_bs;
     AioContext *aio_context;
     AioContext *old_context;
     BlockMirrorBackingMode backing_mode;
@@ -3028,12 +3083,12 @@ void qmp_drive_mirror(DriveMirror *arg, Error **errp)
     }
 
     flags = bs->open_flags | BDRV_O_RDWR;
-    source = backing_bs(bs);
+    target_backing_bs = bdrv_cow_bs(bdrv_skip_filters(bs));
-    if (!source && arg->sync == MIRROR_SYNC_MODE_TOP) {
+    if (!target_backing_bs && arg->sync == MIRROR_SYNC_MODE_TOP) {
         arg->sync = MIRROR_SYNC_MODE_FULL;
     }
     if (arg->sync == MIRROR_SYNC_MODE_NONE) {
-        source = bs;
+        target_backing_bs = bs;
     }
 
     size = bdrv_getlength(bs);
@@ -3059,7 +3114,7 @@ void qmp_drive_mirror(DriveMirror *arg, Error **errp)
     /* Don't open backing image in create() */
     flags |= BDRV_O_NO_BACKING;
 
-    if ((arg->sync == MIRROR_SYNC_MODE_FULL || !source)
+    if ((arg->sync == MIRROR_SYNC_MODE_FULL || !target_backing_bs)
         && arg->mode != NEW_IMAGE_MODE_EXISTING)
     {
         /* create new image w/o backing file */
@@ -3067,15 +3122,19 @@ void qmp_drive_mirror(DriveMirror *arg, Error **errp)
         bdrv_img_create(arg->target, format,
                         NULL, NULL, NULL, size, flags, false, &local_err);
     } else {
+        /* Implicit filters should not appear in the filename */
+        BlockDriverState *explicit_backing =
+            bdrv_skip_implicit_filters(target_backing_bs);
+
         switch (arg->mode) {
         case NEW_IMAGE_MODE_EXISTING:
             break;
         case NEW_IMAGE_MODE_ABSOLUTE_PATHS:
             /* create new image with backing file */
-            bdrv_refresh_filename(source);
+            bdrv_refresh_filename(explicit_backing);
             bdrv_img_create(arg->target, format,
-                            source->filename,
+                            explicit_backing->filename,
-                            source->drv->format_name,
+                            explicit_backing->drv->format_name,
                             NULL, size, flags, false, &local_err);
             break;
         default:

include/block/block.h

@@ -532,7 +532,7 @@ BlockDriverState *bdrv_next(BdrvNextIterator *it);
 void bdrv_next_cleanup(BdrvNextIterator *it);
 
 BlockDriverState *bdrv_next_monitor_owned(BlockDriverState *bs);
-bool bdrv_is_encrypted(BlockDriverState *bs);
+bool bdrv_supports_compressed_writes(BlockDriverState *bs);
 void bdrv_iterate_format(void (*it)(void *opaque, const char *name),
                          void *opaque, bool read_only);
 const char *bdrv_get_node_name(const BlockDriverState *bs);

include/block/block_int.h

@@ -92,9 +92,17 @@ struct BlockDriver {
     int instance_size;
 
     /* set to true if the BlockDriver is a block filter. Block filters pass
-     * certain callbacks that refer to data (see block.c) to their bs->file if
+     * certain callbacks that refer to data (see block.c) to their bs->file
-     * the driver doesn't implement them. Drivers that do not wish to forward
+     * or bs->backing (whichever one exists) if the driver doesn't implement
-     * must implement them and return -ENOTSUP.
+     * them. Drivers that do not wish to forward must implement them and return
+     * -ENOTSUP.
+     * Note that filters are not allowed to modify data.
+     *
+     * Filters generally cannot have more than a single filtered child,
+     * because the data they present must at all times be the same as
+     * that on their filtered child.  That would be impossible to
+     * achieve for multiple filtered children.
+     * (And this filtered child must then be bs->file or bs->backing.)
      */
     bool is_filter;
     /*
@@ -839,11 +847,20 @@ struct BlockDriverState {
     bool walking_aio_notifiers; /* to make removal during iteration safe */
 
     char filename[PATH_MAX];
-    char backing_file[PATH_MAX]; /* if non zero, the image is a diff of
+    /*
-                                    this file image */
+     * If not empty, this image is a diff in relation to backing_file.
-    /* The backing filename indicated by the image header; if we ever
+     * Note that this is the name given in the image header and
-     * open this file, then this is replaced by the resulting BDS's
+     * therefore may or may not be equal to .backing->bs->filename.
-     * filename (i.e. after a bdrv_refresh_filename() run). */
+     * If this field contains a relative path, it is to be resolved
+     * relatively to the overlay's location.
+     */
+    char backing_file[PATH_MAX];
+    /*
+     * The backing filename indicated by the image header.  Contrary
+     * to backing_file, if we ever open this file, auto_backing_file
+     * is replaced by the resulting BDS's filename (i.e. after a
+     * bdrv_refresh_filename() run).
+     */
     char auto_backing_file[PATH_MAX];
     char backing_format[16]; /* if non-zero and backing_file exists */
 
@@ -995,11 +1012,6 @@ typedef enum BlockMirrorBackingMode {
     MIRROR_LEAVE_BACKING_CHAIN,
 } BlockMirrorBackingMode;
 
-static inline BlockDriverState *backing_bs(BlockDriverState *bs)
-{
-    return bs->backing ? bs->backing->bs : NULL;
-}
-
 
 /* Essential block drivers which must always be statically linked into qemu, and
  * which therefore can be accessed without using bdrv_find_format() */
@@ -1050,6 +1062,8 @@ BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size,
 void bdrv_parse_filename_strip_prefix(const char *filename, const char *prefix,
                                       QDict *options);
 
+bool bdrv_backing_overridden(BlockDriverState *bs);
+
 
 /**
  * bdrv_add_before_write_notifier:
@@ -1300,28 +1314,6 @@ void bdrv_default_perms(BlockDriverState *bs, BdrvChild *c,
                         uint64_t perm, uint64_t shared,
                         uint64_t *nperm, uint64_t *nshared);
 
-/*
- * Default implementation for drivers to pass bdrv_co_block_status() to
- * their file.
- */
-int coroutine_fn bdrv_co_block_status_from_file(BlockDriverState *bs,
-                                                bool want_zero,
-                                                int64_t offset,
-                                                int64_t bytes,
-                                                int64_t *pnum,
-                                                int64_t *map,
-                                                BlockDriverState **file);
-/*
- * Default implementation for drivers to pass bdrv_co_block_status() to
- * their backing file.
- */
-int coroutine_fn bdrv_co_block_status_from_backing(BlockDriverState *bs,
-                                                   bool want_zero,
-                                                   int64_t offset,
-                                                   int64_t bytes,
-                                                   int64_t *pnum,
-                                                   int64_t *map,
-                                                   BlockDriverState **file);
 const char *bdrv_get_parent_name(const BlockDriverState *bs);
 void blk_dev_change_media_cb(BlockBackend *blk, bool load, Error **errp);
 bool blk_dev_has_removable_media(BlockBackend *blk);
@@ -1382,4 +1374,37 @@ BdrvDirtyBitmap *block_dirty_bitmap_remove(const char *node, const char *name,
                                            BlockDriverState **bitmap_bs,
                                            Error **errp);
 
+BdrvChild *bdrv_cow_child(BlockDriverState *bs);
+BdrvChild *bdrv_filter_child(BlockDriverState *bs);
+BdrvChild *bdrv_filter_or_cow_child(BlockDriverState *bs);
+BdrvChild *bdrv_primary_child(BlockDriverState *bs);
+BlockDriverState *bdrv_skip_implicit_filters(BlockDriverState *bs);
+BlockDriverState *bdrv_skip_filters(BlockDriverState *bs);
+BlockDriverState *bdrv_backing_chain_next(BlockDriverState *bs);
+
+static inline BlockDriverState *child_bs(BdrvChild *child)
+{
+    return child ? child->bs : NULL;
+}
+
+static inline BlockDriverState *bdrv_cow_bs(BlockDriverState *bs)
+{
+    return child_bs(bdrv_cow_child(bs));
+}
+
+static inline BlockDriverState *bdrv_filter_bs(BlockDriverState *bs)
+{
+    return child_bs(bdrv_filter_child(bs));
+}
+
+static inline BlockDriverState *bdrv_filter_or_cow_bs(BlockDriverState *bs)
+{
+    return child_bs(bdrv_filter_or_cow_child(bs));
+}
+
+static inline BlockDriverState *bdrv_primary_bs(BlockDriverState *bs)
+{
+    return child_bs(bdrv_primary_child(bs));
+}
+
 #endif /* BLOCK_INT_H */

migration/block-dirty-bitmap.c

@@ -615,13 +615,7 @@ static int init_dirty_bitmap_migration(DBMSaveState *s)
             while (bs && bs->drv && bs->drv->is_filter &&
                    !bdrv_has_named_bitmaps(bs))
             {
-                if (bs->backing) {
+                bs = bdrv_filter_bs(bs);
-                    bs = bs->backing->bs;
-                } else if (bs->file) {
-                    bs = bs->file->bs;
-                } else {
-                    bs = NULL;
-                }
             }
 
             if (bs && bs->drv && !bs->drv->is_filter) {

nbd/server.c

@@ -1567,13 +1567,13 @@ NBDExport *nbd_export_new(BlockDriverState *bs, uint64_t dev_offset,
     if (bitmap) {
         BdrvDirtyBitmap *bm = NULL;
 
-        while (true) {
+        while (bs) {
             bm = bdrv_find_dirty_bitmap(bs, bitmap);
-            if (bm != NULL || bs->backing == NULL) {
+            if (bm != NULL) {
                 break;
             }
 
-            bs = bs->backing->bs;
+            bs = bdrv_filter_or_cow_bs(bs);
         }
 
         if (bm == NULL) {

qapi/block-core.json

@@ -1569,6 +1569,18 @@
 # Live commit of data from overlay image nodes into backing nodes - i.e.,
 # writes data between 'top' and 'base' into 'base'.
 #
+# If top == base, that is an error.
+# If top has no overlays on top of it, or if it is in use by a writer,
+# the job will not be completed by itself.  The user needs to complete
+# the job with the block-job-complete command after getting the ready
+# event. (Since 2.0)
+#
+# If the base image is smaller than top, then the base image will be
+# resized to be the same size as top.  If top is smaller than the base
+# image, the base will not be truncated.  If you want the base image
+# size to match the size of the smaller top, you can safely truncate
+# it yourself once the commit operation successfully completes.
+#
 # @job-id: identifier for the newly-created block job. If
 #          omitted, the device name will be used. (Since 2.7)
 #
@@ -1593,14 +1605,15 @@
 #       accepted
 #
 # @backing-file: The backing file string to write into the overlay
-#                image of 'top'.  If 'top' is the active layer,
+#                image of 'top'.  If 'top' does not have an overlay
-#                specifying a backing file string is an error. This
+#                image, or if 'top' is in use by a writer, specifying
-#                filename is not validated.
+#                a backing file string is an error.
 #
-#                If a pathname string is such that it cannot be
+#                This filename is not validated.  If a pathname string
-#                resolved by QEMU, that means that subsequent QMP or
+#                is such that it cannot be resolved by QEMU, that
-#                HMP commands must use node-names for the image in
+#                means that subsequent QMP or HMP commands must use
-#                question, as filename lookup methods will fail.
+#                node-names for the image in question, as filename
+#                lookup methods will fail.
 #
 #                If not specified, QEMU will automatically determine
 #                the backing file string to use, or error out if
@@ -1609,18 +1622,6 @@
 #                filename or protocol.
 #                (Since 2.1)
 #
-#                If top == base, that is an error.
-#                If top == active, the job will not be completed by itself,
-#                user needs to complete the job with the block-job-complete
-#                command after getting the ready event. (Since 2.0)
-#
-#                If the base image is smaller than top, then the base image
-#                will be resized to be the same size as top.  If top is
-#                smaller than the base image, the base will not be
-#                truncated.  If you want the base image size to match the
-#                size of the smaller top, you can safely truncate it
-#                yourself once the commit operation successfully completes.
-#
 # @speed: the maximum speed, in bytes per second
 #
 # @on-error: the action to take on an error. 'ignore' means that the request
@@ -1948,7 +1949,8 @@
 #
 # @replaces: with sync=full graph node name to be replaced by the new
 #            image when a whole image copy is done. This can be used to repair
-#            broken Quorum files. (Since 2.1)
+#            broken Quorum files.  By default, @device is replaced, although
+#            implicitly created filters on it are kept. (Since 2.1)
 #
 # @mode: whether and how QEMU should create a new image, default is
 #        'absolute-paths'.
@@ -2259,7 +2261,8 @@
 #
 # @replaces: with sync=full graph node name to be replaced by the new
 #            image when a whole image copy is done. This can be used to repair
-#            broken Quorum files.
+#            broken Quorum files.  By default, @device is replaced, although
+#            implicitly created filters on it are kept.
 #
 # @speed:  the maximum speed, in bytes per second
 #
@@ -2484,13 +2487,20 @@
 # of 'device'.
 #
 # If a base file is specified then sectors are not copied from that base file and
-# its backing chain.  When streaming completes the image file will have the base
+# its backing chain.  This can be used to stream a subset of the backing file
-# file as its backing file.  This can be used to stream a subset of the backing
+# chain instead of flattening the entire image.
-# file chain instead of flattening the entire image.
+# When streaming completes the image file will have the base file as its backing
+# file, unless that node was changed while the job was running.  In that case,
+# base's parent's backing (or filtered, whichever exists) child (i.e., base at
+# the beginning of the job) will be the new backing file.
 #
 # On successful completion the image file is updated to drop the backing file
 # and the BLOCK_JOB_COMPLETED event is emitted.
 #
+# In case @device is a filter node, block-stream modifies the first non-filter
+# overlay node below it to point to the new backing node instead of modifying
+# @device itself.
+#
 # @job-id: identifier for the newly-created block job. If
 #          omitted, the device name will be used. (Since 2.7)
 #

qemu-img.c

@@ -1085,7 +1085,7 @@ static int img_commit(int argc, char **argv)
         /* This is different from QMP, which by default uses the deepest file in
          * the backing chain (i.e., the very base); however, the traditional
          * behavior of qemu-img commit is using the immediate backing file. */
-        base_bs = backing_bs(bs);
+        base_bs = bdrv_backing_chain_next(bs);
         if (!base_bs) {
             error_setg(&local_err, "Image does not have a backing file");
             goto done;
@@ -1732,18 +1732,20 @@ static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num)
     if (s->sector_next_status <= sector_num) {
         uint64_t offset = (sector_num - src_cur_offset) * BDRV_SECTOR_SIZE;
         int64_t count;
+        BlockDriverState *src_bs = blk_bs(s->src[src_cur]);
+        BlockDriverState *base;
+
+        if (s->target_has_backing) {
+            base = bdrv_cow_bs(bdrv_skip_filters(src_bs));
+        } else {
+            base = NULL;
+        }
 
         do {
             count = n * BDRV_SECTOR_SIZE;
 
-            if (s->target_has_backing) {
+            ret = bdrv_block_status_above(src_bs, base, offset, count, &count,
-                ret = bdrv_block_status(blk_bs(s->src[src_cur]), offset,
+                                          NULL, NULL);
-                                        count, &count, NULL, NULL);
-            } else {
-                ret = bdrv_block_status_above(blk_bs(s->src[src_cur]), NULL,
-                                              offset, count, &count, NULL,
-                                              NULL);
-            }
 
             if (ret < 0) {
                 if (s->salvage) {
@@ -2665,7 +2667,8 @@ static int img_convert(int argc, char **argv)
          * s.target_backing_sectors has to be negative, which it will
          * be automatically).  The backing file length is used only
          * for optimizations, so such a case is not fatal. */
-        s.target_backing_sectors = bdrv_nb_sectors(out_bs->backing->bs);
+        s.target_backing_sectors =
+            bdrv_nb_sectors(bdrv_backing_chain_next(out_bs));
     } else {
         s.target_backing_sectors = -1;
     }
@@ -3035,6 +3038,7 @@ static int get_block_status(BlockDriverState *bs, int64_t offset,
 
     depth = 0;
     for (;;) {
+        bs = bdrv_skip_filters(bs);
         ret = bdrv_block_status(bs, offset, bytes, &bytes, &map, &file);
         if (ret < 0) {
             return ret;
@@ -3043,7 +3047,7 @@ static int get_block_status(BlockDriverState *bs, int64_t offset,
         if (ret & (BDRV_BLOCK_ZERO|BDRV_BLOCK_DATA)) {
             break;
         }
-        bs = backing_bs(bs);
+        bs = bdrv_cow_bs(bs);
         if (bs == NULL) {
             ret = 0;
             break;
@@ -3425,6 +3429,7 @@ static int img_rebase(int argc, char **argv)
     uint8_t *buf_old = NULL;
     uint8_t *buf_new = NULL;
     BlockDriverState *bs = NULL, *prefix_chain_bs = NULL;
+    BlockDriverState *unfiltered_bs;
     char *filename;
     const char *fmt, *cache, *src_cache, *out_basefmt, *out_baseimg;
     int c, flags, src_flags, ret;
@@ -3559,6 +3564,8 @@ static int img_rebase(int argc, char **argv)
     }
     bs = blk_bs(blk);
 
+    unfiltered_bs = bdrv_skip_filters(bs);
+
     if (out_basefmt != NULL) {
         if (bdrv_find_format(out_basefmt) == NULL) {
             error_report("Invalid format name: '%s'", out_basefmt);
@@ -3570,7 +3577,7 @@ static int img_rebase(int argc, char **argv)
     /* For safe rebasing we need to compare old and new backing file */
     if (!unsafe) {
         QDict *options = NULL;
-        BlockDriverState *base_bs = backing_bs(bs);
+        BlockDriverState *base_bs = bdrv_cow_bs(unfiltered_bs);
 
         if (base_bs) {
             blk_old_backing = blk_new(qemu_get_aio_context(),
@@ -3711,7 +3718,7 @@ static int img_rebase(int argc, char **argv)
             n = MIN(IO_BUF_SIZE, size - offset);
 
             /* If the cluster is allocated, we don't need to take action */
-            ret = bdrv_is_allocated(bs, offset, n, &n);
+            ret = bdrv_is_allocated(unfiltered_bs, offset, n, &n);
             if (ret < 0) {
                 error_report("error while reading image metadata: %s",
                              strerror(-ret));
@@ -3726,8 +3733,9 @@ static int img_rebase(int argc, char **argv)
                  * If cluster wasn't changed since prefix_chain, we don't need
                  * to take action
                  */
-                ret = bdrv_is_allocated_above(backing_bs(bs), prefix_chain_bs,
+                ret = bdrv_is_allocated_above(bdrv_cow_bs(unfiltered_bs),
-                                              false, offset, n, &n);
+                                              prefix_chain_bs, false,
+                                              offset, n, &n);
                 if (ret < 0) {
                     error_report("error while reading image metadata: %s",
                                  strerror(-ret));
@@ -3805,9 +3813,10 @@ static int img_rebase(int argc, char **argv)
      * doesn't change when we switch the backing file.
      */
     if (out_baseimg && *out_baseimg) {
-        ret = bdrv_change_backing_file(bs, out_baseimg, out_basefmt, true);
+        ret = bdrv_change_backing_file(unfiltered_bs, out_baseimg, out_basefmt,
+                                       true);
     } else {
-        ret = bdrv_change_backing_file(bs, NULL, NULL, false);
+        ret = bdrv_change_backing_file(unfiltered_bs, NULL, NULL, false);
     }
 
     if (ret == -ENOSPC) {

tests/qemu-iotests/020

@@ -31,6 +31,11 @@ _cleanup()
     _cleanup_test_img
     _rm_test_img "$TEST_IMG.base"
     _rm_test_img "$TEST_IMG.orig"
+
+    _rm_test_img "$TEST_DIR/subdir/t.$IMGFMT.base"
+    _rm_test_img "$TEST_DIR/subdir/t.$IMGFMT.mid"
+    _rm_test_img "$TEST_DIR/subdir/t.$IMGFMT"
+    rmdir "$TEST_DIR/subdir" &> /dev/null
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
@@ -139,6 +144,45 @@ $QEMU_IO -c 'writev 0 64k' "$TEST_IMG" | _filter_qemu_io
 $QEMU_IMG commit "$TEST_IMG"
 _cleanup
 
+
+echo
+echo 'Testing commit in sub-directory with relative filenames'
+echo
+
+pushd "$TEST_DIR" > /dev/null
+
+mkdir subdir
+
+TEST_IMG="subdir/t.$IMGFMT.base" _make_test_img 1M
+TEST_IMG="subdir/t.$IMGFMT.mid" _make_test_img -b "t.$IMGFMT.base" -F $IMGFMT
+TEST_IMG="subdir/t.$IMGFMT" _make_test_img -b "t.$IMGFMT.mid" -F $IMGFMT
+
+# Should work
+$QEMU_IMG commit -b "t.$IMGFMT.mid" "subdir/t.$IMGFMT"
+
+# Might theoretically work, but does not in practice (we have to
+# decide between this and the above; and since we always represent
+# backing file names as relative to the overlay, we go for the above)
+$QEMU_IMG commit -b "subdir/t.$IMGFMT.mid" "subdir/t.$IMGFMT" 2>&1 | \
+    _filter_imgfmt
+
+# This should work as well
+$QEMU_IMG commit -b "$TEST_DIR/subdir/t.$IMGFMT.mid" "subdir/t.$IMGFMT"
+
+popd > /dev/null
+
+# Now let's try with just absolute filenames
+# (This will not work with external data files, though, because when
+# using relative paths for those, qemu will always resolve them
+# relative to its CWD.  Therefore, it cannot find those data files now
+# that we left $TEST_DIR.)
+if _get_data_file '' > /dev/null; then
+    echo 'Image committed.' # Skip test
+else
+    $QEMU_IMG commit -b "$TEST_DIR/subdir/t.$IMGFMT.mid" \
+        "$TEST_DIR/subdir/t.$IMGFMT"
+fi
+
 # success, all done
 echo "*** done"
 rm -f $seq.full

tests/qemu-iotests/020.out

@@ -1083,4 +1083,14 @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=json:{'driv
 wrote 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 qemu-img: Block job failed: No space left on device
+
+Testing commit in sub-directory with relative filenames
+
+Formatting 'subdir/t.IMGFMT.base', fmt=IMGFMT size=1048576
+Formatting 'subdir/t.IMGFMT.mid', fmt=IMGFMT size=1048576 backing_file=t.IMGFMT.base backing_fmt=IMGFMT
+Formatting 'subdir/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=t.IMGFMT.mid backing_fmt=IMGFMT
+Image committed.
+qemu-img: Did not find 'subdir/t.IMGFMT.mid' in the backing chain of 'subdir/t.IMGFMT'
+Image committed.
+Image committed.
 *** done

tests/qemu-iotests/040

@@ -734,6 +734,244 @@ class TestErrorHandling(iotests.QMPTestCase):
         self.assertTrue(iotests.compare_images(mid_img, backing_img, fmt2='raw'),
                         'target image does not match source after commit')
 
+class TestCommitWithFilters(iotests.QMPTestCase):
+    img0 = os.path.join(iotests.test_dir, '0.img')
+    img1 = os.path.join(iotests.test_dir, '1.img')
+    img2 = os.path.join(iotests.test_dir, '2.img')
+    img3 = os.path.join(iotests.test_dir, '3.img')
+
+    def do_test_io(self, read_or_write):
+        for index, pattern_file in enumerate(self.pattern_files):
+            result = qemu_io('-f', iotests.imgfmt,
+                             '-c',
+                             f'{read_or_write} -P {index + 1} {index}M 1M',
+                             pattern_file)
+            self.assertFalse('Pattern verification failed' in result)
+
+    def setUp(self):
+        qemu_img('create', '-f', iotests.imgfmt, self.img0, '64M')
+        qemu_img('create', '-f', iotests.imgfmt, self.img1, '64M')
+        qemu_img('create', '-f', iotests.imgfmt, self.img2, '64M')
+        qemu_img('create', '-f', iotests.imgfmt, self.img3, '64M')
+
+        # Distributions of the patterns in the files; this is checked
+        # by tearDown() and should be changed by the test cases as is
+        # necessary
+        self.pattern_files = [self.img0, self.img1, self.img2, self.img3]
+
+        self.do_test_io('write')
+
+        self.vm = iotests.VM().add_device('virtio-scsi,id=vio-scsi')
+        self.vm.launch()
+
+        result = self.vm.qmp('object-add', qom_type='throttle-group', id='tg')
+        self.assert_qmp(result, 'return', {})
+
+        result = self.vm.qmp('blockdev-add', **{
+                'node-name': 'top-filter',
+                'driver': 'throttle',
+                'throttle-group': 'tg',
+                'file': {
+                    'node-name': 'cow-3',
+                    'driver': iotests.imgfmt,
+                    'file': {
+                        'driver': 'file',
+                        'filename': self.img3
+                    },
+                    'backing': {
+                        'node-name': 'cow-2',
+                        'driver': iotests.imgfmt,
+                        'file': {
+                            'driver': 'file',
+                            'filename': self.img2
+                        },
+                        'backing': {
+                            'node-name': 'cow-1',
+                            'driver': iotests.imgfmt,
+                            'file': {
+                                'driver': 'file',
+                                'filename': self.img1
+                            },
+                            'backing': {
+                                'node-name': 'bottom-filter',
+                                'driver': 'throttle',
+                                'throttle-group': 'tg',
+                                'file': {
+                                    'node-name': 'cow-0',
+                                    'driver': iotests.imgfmt,
+                                    'file': {
+                                        'driver': 'file',
+                                        'filename': self.img0
+                                    }
+                                }
+                            }
+                        }
+                    }
+                }
+            })
+        self.assert_qmp(result, 'return', {})
+
+    def tearDown(self):
+        self.vm.shutdown()
+        self.do_test_io('read')
+
+        os.remove(self.img3)
+        os.remove(self.img2)
+        os.remove(self.img1)
+        os.remove(self.img0)
+
+    # Filters make for funny filenames, so we cannot just use
+    # self.imgX to get them
+    def get_filename(self, node):
+        return self.vm.node_info(node)['image']['filename']
+
+    def test_filterless_commit(self):
+        result = self.vm.qmp('block-commit',
+                             job_id='commit',
+                             device='top-filter',
+                             top_node='cow-2',
+                             base_node='cow-1')
+        self.assert_qmp(result, 'return', {})
+        self.wait_until_completed(drive='commit')
+
+        self.assertIsNotNone(self.vm.node_info('cow-3'))
+        self.assertIsNone(self.vm.node_info('cow-2'))
+        self.assertIsNotNone(self.vm.node_info('cow-1'))
+
+        # 2 has been comitted into 1
+        self.pattern_files[2] = self.img1
+
+    def test_commit_through_filter(self):
+        result = self.vm.qmp('block-commit',
+                             job_id='commit',
+                             device='top-filter',
+                             top_node='cow-1',
+                             base_node='cow-0')
+        self.assert_qmp(result, 'return', {})
+        self.wait_until_completed(drive='commit')
+
+        self.assertIsNotNone(self.vm.node_info('cow-2'))
+        self.assertIsNone(self.vm.node_info('cow-1'))
+        self.assertIsNone(self.vm.node_info('bottom-filter'))
+        self.assertIsNotNone(self.vm.node_info('cow-0'))
+
+        # 1 has been comitted into 0
+        self.pattern_files[1] = self.img0
+
+    def test_filtered_active_commit_with_filter(self):
+        # Add a device, so the commit job finds a parent it can change
+        # to point to the base node (so we can test that top-filter is
+        # dropped from the graph)
+        result = self.vm.qmp('device_add', id='drv0', driver='scsi-hd',
+                             bus='vio-scsi.0', drive='top-filter')
+        self.assert_qmp(result, 'return', {})
+
+        # Try to release our reference to top-filter; that should not
+        # work because drv0 uses it
+        result = self.vm.qmp('blockdev-del', node_name='top-filter')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+        self.assert_qmp(result, 'error/desc', 'Node top-filter is in use')
+
+        result = self.vm.qmp('block-commit',
+                             job_id='commit',
+                             device='top-filter',
+                             base_node='cow-2')
+        self.assert_qmp(result, 'return', {})
+        self.complete_and_wait(drive='commit')
+
+        # Try to release our reference to top-filter again
+        result = self.vm.qmp('blockdev-del', node_name='top-filter')
+        self.assert_qmp(result, 'return', {})
+
+        self.assertIsNone(self.vm.node_info('top-filter'))
+        self.assertIsNone(self.vm.node_info('cow-3'))
+        self.assertIsNotNone(self.vm.node_info('cow-2'))
+
+        # Check that drv0 is now connected to cow-2
+        blockdevs = self.vm.qmp('query-block')['return']
+        drv0 = next(dev for dev in blockdevs if dev['qdev'] == 'drv0')
+        self.assertEqual(drv0['inserted']['node-name'], 'cow-2')
+
+        # 3 has been comitted into 2
+        self.pattern_files[3] = self.img2
+
+    def test_filtered_active_commit_without_filter(self):
+        result = self.vm.qmp('block-commit',
+                             job_id='commit',
+                             device='top-filter',
+                             top_node='cow-3',
+                             base_node='cow-2')
+        self.assert_qmp(result, 'return', {})
+        self.complete_and_wait(drive='commit')
+
+        self.assertIsNotNone(self.vm.node_info('top-filter'))
+        self.assertIsNone(self.vm.node_info('cow-3'))
+        self.assertIsNotNone(self.vm.node_info('cow-2'))
+
+        # 3 has been comitted into 2
+        self.pattern_files[3] = self.img2
+
+class TestCommitWithOverriddenBacking(iotests.QMPTestCase):
+    img_base_a = os.path.join(iotests.test_dir, 'base_a.img')
+    img_base_b = os.path.join(iotests.test_dir, 'base_b.img')
+    img_top = os.path.join(iotests.test_dir, 'top.img')
+
+    def setUp(self):
+        qemu_img('create', '-f', iotests.imgfmt, self.img_base_a, '1M')
+        qemu_img('create', '-f', iotests.imgfmt, self.img_base_b, '1M')
+        qemu_img('create', '-f', iotests.imgfmt, '-b', self.img_base_a, \
+                 self.img_top)
+
+        self.vm = iotests.VM()
+        self.vm.launch()
+
+        # Use base_b instead of base_a as the backing of top
+        result = self.vm.qmp('blockdev-add', **{
+                                'node-name': 'top',
+                                'driver': iotests.imgfmt,
+                                'file': {
+                                    'driver': 'file',
+                                    'filename': self.img_top
+                                },
+                                'backing': {
+                                    'node-name': 'base',
+                                    'driver': iotests.imgfmt,
+                                    'file': {
+                                        'driver': 'file',
+                                        'filename': self.img_base_b
+                                    }
+                                }
+                            })
+        self.assert_qmp(result, 'return', {})
+
+    def tearDown(self):
+        self.vm.shutdown()
+        os.remove(self.img_top)
+        os.remove(self.img_base_a)
+        os.remove(self.img_base_b)
+
+    def test_commit_to_a(self):
+        # Try committing to base_a (which should fail, as top's
+        # backing image is base_b instead)
+        result = self.vm.qmp('block-commit',
+                             job_id='commit',
+                             device='top',
+                             base=self.img_base_a)
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+    def test_commit_to_b(self):
+        # Try committing to base_b (which should work, since that is
+        # actually top's backing image)
+        result = self.vm.qmp('block-commit',
+                             job_id='commit',
+                             device='top',
+                             base=self.img_base_b)
+        self.assert_qmp(result, 'return', {})
+
+        self.vm.event_wait('BLOCK_JOB_READY')
+        self.vm.qmp('block-job-complete', device='commit')
+        self.vm.event_wait('BLOCK_JOB_COMPLETED')
+
 if __name__ == '__main__':
     iotests.main(supported_fmts=['qcow2', 'qed'],
                  supported_protocols=['file'])

tests/qemu-iotests/040.out

@@ -1,5 +1,5 @@
-...........................................................
+.................................................................
 ----------------------------------------------------------------------
-Ran 59 tests
+Ran 65 tests
 
 OK

tests/qemu-iotests/041

@@ -21,8 +21,9 @@
 import time
 import os
 import re
+import json
 import iotests
-from iotests import qemu_img, qemu_io
+from iotests import qemu_img, qemu_img_pipe, qemu_io
 
 backing_img = os.path.join(iotests.test_dir, 'backing.img')
 target_backing_img = os.path.join(iotests.test_dir, 'target-backing.img')
@@ -1288,6 +1289,149 @@ class TestReplaces(iotests.QMPTestCase):
 
         self.vm.assert_block_path('filter0', '/file', 'target')
 
+# Tests for mirror with filters (and how the mirror filter behaves, as
+# an example for an implicit filter)
+class TestFilters(iotests.QMPTestCase):
+    def setUp(self):
+        qemu_img('create', '-f', iotests.imgfmt, backing_img, '1M')
+        qemu_img('create', '-f', iotests.imgfmt, '-b', backing_img, test_img)
+        qemu_img('create', '-f', iotests.imgfmt, '-b', backing_img, target_img)
+
+        qemu_io('-c', 'write -P 1 0 512k', backing_img)
+        qemu_io('-c', 'write -P 2 512k 512k', test_img)
+
+        self.vm = iotests.VM().add_device('virtio-scsi,id=vio-scsi')
+        self.vm.launch()
+
+        result = self.vm.qmp('blockdev-add', **{
+                                'node-name': 'target',
+                                'driver': iotests.imgfmt,
+                                'file': {
+                                    'driver': 'file',
+                                    'filename': target_img
+                                },
+                                'backing': None
+                            })
+        self.assert_qmp(result, 'return', {})
+
+        self.filterless_chain = {
+                'node-name': 'source',
+                'driver': iotests.imgfmt,
+                'file': {
+                    'driver': 'file',
+                    'filename': test_img
+                },
+                'backing': {
+                    'node-name': 'backing',
+                    'driver': iotests.imgfmt,
+                    'file': {
+                        'driver': 'file',
+                        'filename': backing_img
+                    }
+                }
+            }
+
+    def tearDown(self):
+        self.vm.shutdown()
+
+        os.remove(test_img)
+        os.remove(target_img)
+        os.remove(backing_img)
+
+    def test_cor(self):
+        result = self.vm.qmp('blockdev-add', **{
+                                'node-name': 'filter',
+                                'driver': 'copy-on-read',
+                                'file': self.filterless_chain
+                            })
+        self.assert_qmp(result, 'return', {})
+
+        result = self.vm.qmp('blockdev-mirror',
+                             job_id='mirror',
+                             device='filter',
+                             target='target',
+                             sync='top')
+        self.assert_qmp(result, 'return', {})
+
+        self.complete_and_wait('mirror')
+
+        self.vm.qmp('blockdev-del', node_name='target')
+
+        target_map = qemu_img_pipe('map', '--output=json', target_img)
+        target_map = json.loads(target_map)
+
+        assert target_map[0]['start'] == 0
+        assert target_map[0]['length'] == 512 * 1024
+        assert target_map[0]['depth'] == 1
+
+        assert target_map[1]['start'] == 512 * 1024
+        assert target_map[1]['length'] == 512 * 1024
+        assert target_map[1]['depth'] == 0
+
+    def test_implicit_mirror_filter(self):
+        result = self.vm.qmp('blockdev-add', **self.filterless_chain)
+        self.assert_qmp(result, 'return', {})
+
+        # We need this so we can query from above the mirror node
+        result = self.vm.qmp('device_add',
+                             driver='scsi-hd',
+                             id='virtio',
+                             bus='vio-scsi.0',
+                             drive='source')
+        self.assert_qmp(result, 'return', {})
+
+        result = self.vm.qmp('blockdev-mirror',
+                             job_id='mirror',
+                             device='source',
+                             target='target',
+                             sync='top')
+        self.assert_qmp(result, 'return', {})
+
+        # The mirror filter is now an implicit node, so it should be
+        # invisible when querying the backing chain
+        blockdevs = self.vm.qmp('query-block')['return']
+        device_info = next(dev for dev in blockdevs if dev['qdev'] == 'virtio')
+
+        assert device_info['inserted']['node-name'] == 'source'
+
+        image_info = device_info['inserted']['image']
+        assert image_info['filename'] == test_img
+        assert image_info['backing-image']['filename'] == backing_img
+
+        self.complete_and_wait('mirror')
+
+    def test_explicit_mirror_filter(self):
+        # Same test as above, but this time we give the mirror filter
+        # a node-name so it will not be invisible
+        result = self.vm.qmp('blockdev-add', **self.filterless_chain)
+        self.assert_qmp(result, 'return', {})
+
+        # We need this so we can query from above the mirror node
+        result = self.vm.qmp('device_add',
+                             driver='scsi-hd',
+                             id='virtio',
+                             bus='vio-scsi.0',
+                             drive='source')
+        self.assert_qmp(result, 'return', {})
+
+        result = self.vm.qmp('blockdev-mirror',
+                             job_id='mirror',
+                             device='source',
+                             target='target',
+                             sync='top',
+                             filter_node_name='mirror-filter')
+        self.assert_qmp(result, 'return', {})
+
+        # With a node-name given to it, the mirror filter should now
+        # be visible
+        blockdevs = self.vm.qmp('query-block')['return']
+        device_info = next(dev for dev in blockdevs if dev['qdev'] == 'virtio')
+
+        assert device_info['inserted']['node-name'] == 'mirror-filter'
+
+        self.complete_and_wait('mirror')
+
+
 if __name__ == '__main__':
     iotests.main(supported_fmts=['qcow2', 'qed'],
                  supported_protocols=['file'],

tests/qemu-iotests/041.out

@@ -1,5 +1,5 @@
-........................................................................................................
+...........................................................................................................
 ----------------------------------------------------------------------
-Ran 104 tests
+Ran 107 tests
 
 OK

tests/qemu-iotests/049

@@ -119,6 +119,10 @@ test_qemu_img create -f $IMGFMT -o compat=1.1,lazy_refcounts=on "$TEST_IMG" 64M
 test_qemu_img create -f $IMGFMT -o compat=0.10,lazy_refcounts=off "$TEST_IMG" 64M
 test_qemu_img create -f $IMGFMT -o compat=0.10,lazy_refcounts=on "$TEST_IMG" 64M
 
+echo "== Expect error when backing file name is empty string =="
+echo
+test_qemu_img create -f $IMGFMT -b '' $TEST_IMG 1M
+
 # success, all done
 echo "*** done"
 rm -f $seq.full

tests/qemu-iotests/049.out

@@ -209,4 +209,9 @@ qemu-img create -f qcow2 -o compat=0.10,lazy_refcounts=on TEST_DIR/t.qcow2 64M
 Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=67108864 compat=0.10 lazy_refcounts=on refcount_bits=16
 qemu-img: TEST_DIR/t.qcow2: Lazy refcounts only supported with compatibility level 1.1 and above (use version=v3 or greater)
 
+== Expect error when backing file name is empty string ==
+
+qemu-img create -f qcow2 -b  TEST_DIR/t.qcow2 1M
+qemu-img: TEST_DIR/t.qcow2: Expected backing file name, got empty string
+
 *** done

tests/qemu-iotests/153.out

@@ -464,7 +464,7 @@ No conflict:
 image: null-co://
 file format: null-co
 virtual size: 1 GiB (1073741824 bytes)
-disk size: unavailable
+disk size: 0 B
 
 Conflict:
 qemu-img: --force-share/-U conflicts with image options

tests/qemu-iotests/184

@@ -45,8 +45,7 @@ do_run_qemu()
 run_qemu()
 {
     do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_qemu | _filter_qmp\
-                          | _filter_qemu_io | _filter_generated_node_ids \
+                          | _filter_qemu_io | _filter_generated_node_ids
-                          | _filter_actual_image_size
 }
 
 test_throttle=$($QEMU_IMG --help|grep throttle)

tests/qemu-iotests/184.out

@@ -27,14 +27,21 @@ Testing:
             "iops_rd": 0,
             "detect_zeroes": "off",
             "image": {
+                "backing-image": {
+                    "virtual-size": 1073741824,
+                    "filename": "null-co://",
+                    "format": "null-co",
+                    "actual-size": 0
+                },
                 "virtual-size": 1073741824,
                 "filename": "json:{\"throttle-group\": \"group0\", \"driver\": \"throttle\", \"file\": {\"driver\": \"null-co\"}}",
-                "format": "throttle"
+                "format": "throttle",
+                "actual-size": 0
             },
             "iops_wr": 0,
             "ro": false,
             "node-name": "throttle0",
-            "backing_file_depth": 0,
+            "backing_file_depth": 1,
             "drv": "throttle",
             "iops": 0,
             "bps_wr": 0,
@@ -56,7 +63,8 @@ Testing:
             "image": {
                 "virtual-size": 1073741824,
                 "filename": "null-co://",
-                "format": "null-co"
+                "format": "null-co",
+                "actual-size": 0
             },
             "iops_wr": 0,
             "ro": false,

tests/qemu-iotests/204.out

@@ -59,5 +59,6 @@ Offset          Length          File
 0x900000        0x2400000       TEST_DIR/t.IMGFMT
 0x3c00000       0x1100000       TEST_DIR/t.IMGFMT
 0x6a00000       0x400000        TEST_DIR/t.IMGFMT
+0x6e00000       0x1200000       TEST_DIR/t.IMGFMT.base
 No errors were found on the image.
 *** done

tests/qemu-iotests/228

@@ -36,7 +36,7 @@ def log_node_info(node):
 
     log('bs->filename: ' + node['image']['filename'],
         filters=[filter_testfiles, filter_imgfmt])
-    log('bs->backing_file: ' + node['backing_file'],
+    log('bs->backing_file: ' + node['image']['full-backing-filename'],
         filters=[filter_testfiles, filter_imgfmt])
 
     if 'backing-image' in node['image']:
@@ -73,8 +73,8 @@ with iotests.FilePath('base.img') as base_img_path, \
                 },
                 filters=[filter_qmp_testfiles, filter_qmp_imgfmt])
 
-    # Filename should be plain, and the backing filename should not
+    # Filename should be plain, and the backing node filename should
-    # contain the "file:" prefix
+    # not contain the "file:" prefix
     log_node_info(vm.node_info('node0'))
 
     vm.qmp_log('blockdev-del', node_name='node0')

tests/qemu-iotests/228.out

@@ -4,7 +4,7 @@
 {"return": {}}
 
 bs->filename: TEST_DIR/PID-top.img
-bs->backing_file: TEST_DIR/PID-base.img
+bs->backing_file: file:TEST_DIR/PID-base.img
 bs->backing->bs->filename: TEST_DIR/PID-base.img
 
 {"execute": "blockdev-del", "arguments": {"node-name": "node0"}}
@@ -41,7 +41,7 @@ bs->backing->bs->filename: TEST_DIR/PID-base.img
 {"return": {}}
 
 bs->filename: TEST_DIR/PID-top.img
-bs->backing_file: TEST_DIR/PID-base.img
+bs->backing_file: file:TEST_DIR/PID-base.img
 bs->backing->bs->filename: TEST_DIR/PID-base.img
 
 {"execute": "blockdev-del", "arguments": {"node-name": "node0"}}
@@ -55,7 +55,7 @@ bs->backing->bs->filename: TEST_DIR/PID-base.img
 {"return": {}}
 
 bs->filename: json:{"backing": {"driver": "null-co"}, "driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-top.img"}}
-bs->backing_file: null-co://
+bs->backing_file: TEST_DIR/PID-base.img
 bs->backing->bs->filename: null-co://
 
 {"execute": "blockdev-del", "arguments": {"node-name": "node0"}}

tests/qemu-iotests/244

@@ -217,6 +217,55 @@ $QEMU_IMG amend -f $IMGFMT -o "data_file=blkdebug::$TEST_IMG.data" "$TEST_IMG"
 $QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n -C "$TEST_IMG.src" "$TEST_IMG"
 $QEMU_IMG compare -f $IMGFMT -F $IMGFMT "$TEST_IMG.src" "$TEST_IMG"
 
+echo
+echo "=== Flushing should flush the data file ==="
+echo
+
+# We are going to flush a qcow2 file with a blkdebug node inserted
+# between the qcow2 node and its data file node.  The blkdebug node
+# will return an error for all flushes and so we if the data file is
+# flushed, we will see qemu-io return an error.
+
+# We need to write something or the flush will not do anything; we
+# also need -t writeback so the write is not done as a FUA write
+# (which would then fail thanks to the implicit flush)
+$QEMU_IO -c 'write 0 512' -c flush \
+    -t writeback \
+    "json:{
+         'driver': 'qcow2',
+         'file': {
+             'driver': 'file',
+             'filename': '$TEST_IMG'
+         },
+         'data-file': {
+             'driver': 'blkdebug',
+             'inject-error': [{
+                 'event': 'none',
+                 'iotype': 'flush'
+             }],
+             'image': {
+                 'driver': 'file',
+                 'filename': '$TEST_IMG.data'
+             }
+         }
+     }" \
+    | _filter_qemu_io
+
+result=${PIPESTATUS[0]}
+echo
+
+case $result in
+    0)
+        echo "ERROR: qemu-io succeeded, so the data file was not flushed"
+        ;;
+    1)
+        echo "Success: qemu-io failed, so the data file was flushed"
+        ;;
+    *)
+        echo "ERROR: qemu-io returned unknown exit code $result"
+        ;;
+esac
+
 # success, all done
 echo "*** done"
 rm -f $seq.full

tests/qemu-iotests/244.out

@@ -131,4 +131,11 @@ Offset          Length          Mapped to       File
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 data_file=TEST_DIR/t.IMGFMT.data
 Images are identical.
 Images are identical.
+
+=== Flushing should flush the data file ===
+
+wrote 512/512 bytes at offset 0
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+Success: qemu-io failed, so the data file was flushed
 *** done

tests/qemu-iotests/245

@@ -725,7 +725,9 @@ class TestBlockdevReopen(iotests.QMPTestCase):
 
         # Detach hd2 from hd0.
         self.reopen(opts, {'backing': None})
-        self.reopen(opts, {}, "backing is missing for 'hd0'")
+
+        # Without a backing file, we can omit 'backing' again
+        self.reopen(opts)
 
         # Remove both hd0 and hd2
         result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'hd0')

tests/qemu-iotests/273.out

@@ -32,7 +32,7 @@ Testing: -blockdev file,node-name=base,filename=TEST_DIR/t.IMGFMT.base -blockdev
                         "actual-size": SIZE,
                         "dirty-flag": false
                     },
-                    "backing-filename-format": "file",
+                    "backing-filename-format": "IMGFMT",
                     "virtual-size": 67108864,
                     "filename": "TEST_DIR/t.IMGFMT.mid",
                     "cluster-size": 65536,
@@ -112,7 +112,7 @@ Testing: -blockdev file,node-name=base,filename=TEST_DIR/t.IMGFMT.base -blockdev
                     "actual-size": SIZE,
                     "dirty-flag": false
                 },
-                "backing-filename-format": "file",
+                "backing-filename-format": "IMGFMT",
                 "virtual-size": 67108864,
                 "filename": "TEST_DIR/t.IMGFMT.mid",
                 "cluster-size": 65536,

tests/qemu-iotests/check

@@ -44,7 +44,7 @@ then
         _init_error "failed to obtain source tree name from check symlink"
     fi
     source_iotests=$(cd "$source_iotests"; pwd) || _init_error "failed to enter source tree"
-    build_iotests=$PWD
+    build_iotests=$(readlink -f $(dirname "$0"))
 else
     # called from the source tree
     source_iotests=$PWD

tests/qemu-iotests/iotests.py

@@ -972,8 +972,12 @@ class QMPTestCase(unittest.TestCase):
 
     def wait_ready(self, drive='drive0'):
         """Wait until a BLOCK_JOB_READY event, and return the event."""
-        f = {'data': {'type': 'mirror', 'device': drive}}
+        return self.vm.events_wait([
-        return self.vm.event_wait(name='BLOCK_JOB_READY', match=f)
+            ('BLOCK_JOB_READY',
+             {'data': {'type': 'mirror', 'device': drive}}),
+            ('BLOCK_JOB_READY',
+             {'data': {'type': 'commit', 'device': drive}})
+        ])
 
     def wait_ready_and_cancel(self, drive='drive0'):
         self.wait_ready(drive=drive)
@@ -992,7 +996,7 @@ class QMPTestCase(unittest.TestCase):
         self.assert_qmp(result, 'return', {})
 
         event = self.wait_until_completed(drive=drive, error=completion_error)
-        self.assert_qmp(event, 'data/type', 'mirror')
+        self.assertTrue(event['data']['type'] in ['mirror', 'commit'])
 
     def pause_wait(self, job_id='job0'):
         with Timeout(3, "Timeout waiting for job to pause"):