block: add zoned BlockDriver check to block layer

Putting zoned/non-zoned BlockDrivers on top of each other is not
allowed.

Signed-off-by: Sam Li <faithilikerun@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
Acked-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20230508045533.175575-6-faithilikerun@gmail.com
Message-id: 20230324090605.28361-6-faithilikerun@gmail.com
[Adjust commit message prefix as suggested by Philippe Mathieu-Daudé
<philmd@linaro.org> and clarify that the check is about zoned
BlockDrivers.
--Stefan]
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

4 files changed, 37 insertions, 0 deletions

diff --git a/block.c b/block.c
index dad9a4f..f04a6ad 100644
--- a/block.c
+++ b/block.c
@@ -7982,6 +7982,25 @@ void bdrv_add_child(BlockDriverState *parent_bs, BlockDriverState *child_bs,
         return;
     }
 
+    /*
+     * Non-zoned block drivers do not follow zoned storage constraints
+     * (i.e. sequential writes to zones). Refuse mixing zoned and non-zoned
+     * drivers in a graph.
+     */
+    if (!parent_bs->drv->supports_zoned_children &&
+        child_bs->bl.zoned == BLK_Z_HM) {
+        /*
+         * The host-aware model allows zoned storage constraints and random
+         * write. Allow mixing host-aware and non-zoned drivers. Using
+         * host-aware device as a regular device.
+         */
+        error_setg(errp, "Cannot add a %s child to a %s parent",
+                   child_bs->bl.zoned == BLK_Z_HM ? "zoned" : "non-zoned",
+                   parent_bs->drv->supports_zoned_children ?
+                   "support zoned children" : "not support zoned children");
+        return;
+    }
+
     if (!QLIST_EMPTY(&child_bs->parents)) {
         error_setg(errp, "The node %s already has a parent",
                    child_bs->node_name);
diff --git a/block/file-posix.c b/block/file-posix.c
index 11eaa78..9a52ad4 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -776,6 +776,18 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
             goto fail;
         }
     }
+#ifdef CONFIG_BLKZONED
+    /*
+     * The kernel page cache does not reliably work for writes to SWR zones
+     * of zoned block device because it can not guarantee the order of writes.
+     */
+    if ((bs->bl.zoned != BLK_Z_NONE) &&
+        (!(s->open_flags & O_DIRECT))) {
+        error_setg(errp, "The driver supports zoned devices, and it requires "
+                         "cache.direct=on, which was not specified.");
+        return -EINVAL; /* No host kernel page cache */
+    }
+#endif
 
     if (S_ISBLK(st.st_mode)) {
 #ifdef __linux__
diff --git a/block/raw-format.c b/block/raw-format.c
index 6c11b72..bbb644c 100644
--- a/block/raw-format.c
+++ b/block/raw-format.c
@@ -623,6 +623,7 @@ static void raw_child_perm(BlockDriverState *bs, BdrvChild *c,
 BlockDriver bdrv_raw = {
     .format_name          = "raw",
     .instance_size        = sizeof(BDRVRawState),
+    .supports_zoned_children = true,
     .bdrv_probe           = &raw_probe,
     .bdrv_reopen_prepare  = &raw_reopen_prepare,
     .bdrv_reopen_commit   = &raw_reopen_commit,
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index b2612f0..e6975d3 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -138,6 +138,11 @@ struct BlockDriver {
     bool is_format;
 
     /*
+     * Set to true if the BlockDriver supports zoned children.
+     */
+    bool supports_zoned_children;
+
+    /*
      * Drivers not implementing bdrv_parse_filename nor bdrv_open should have
      * this field set to true, except ones that are defined only by their
      * child's bs.