block/block-backend: add block layer APIs resembling Linux ZonedBlockDevice ioctls

Add zoned device option to host_device BlockDriver. It will be presented only
for zoned host block devices. By adding zone management operations to the
host_block_device BlockDriver, users can use the new block layer APIs
including Report Zone and four zone management operations
(open, close, finish, reset, reset_all).

Qemu-io uses the new APIs to perform zoned storage commands of the device:
zone_report(zrp), zone_open(zo), zone_close(zc), zone_reset(zrs),
zone_finish(zf).

For example, to test zone_report, use following command:
$ ./build/qemu-io --image-opts -n driver=host_device, filename=/dev/nullb0
-c "zrp offset nr_zones"

Signed-off-by: Sam Li <faithilikerun@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
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: 20230508045533.175575-4-faithilikerun@gmail.com
Message-id: 20230324090605.28361-4-faithilikerun@gmail.com
[Adjust commit message prefix as suggested by Philippe Mathieu-Daudé
<philmd@linaro.org> and remove spurious ret = -errno in
raw_co_zone_mgmt().
--Stefan]
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

4 files changed, 53 insertions, 1 deletions

diff --git a/include/block/block-io.h b/include/block/block-io.h
index 1f612ec..f099b20 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -114,6 +114,15 @@ int coroutine_fn GRAPH_RDLOCK bdrv_co_flush(BlockDriverState *bs);
 int coroutine_fn GRAPH_RDLOCK bdrv_co_pdiscard(BdrvChild *child, int64_t offset,
                                                int64_t bytes);
 
+/* Report zone information of zone block device. */
+int coroutine_fn GRAPH_RDLOCK bdrv_co_zone_report(BlockDriverState *bs,
+                                                  int64_t offset,
+                                                  unsigned int *nr_zones,
+                                                  BlockZoneDescriptor *zones);
+int coroutine_fn GRAPH_RDLOCK bdrv_co_zone_mgmt(BlockDriverState *bs,
+                                                BlockZoneOp op,
+                                                int64_t offset, int64_t len);
+
 bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs);
 int bdrv_block_status(BlockDriverState *bs, int64_t offset,
                       int64_t bytes, int64_t *pnum, int64_t *map,
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index c7ca5a8..b2612f0 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -713,6 +713,12 @@ struct BlockDriver {
     int coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_load_vmstate)(
         BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos);
 
+    int coroutine_fn (*bdrv_co_zone_report)(BlockDriverState *bs,
+            int64_t offset, unsigned int *nr_zones,
+            BlockZoneDescriptor *zones);
+    int coroutine_fn (*bdrv_co_zone_mgmt)(BlockDriverState *bs, BlockZoneOp op,
+            int64_t offset, int64_t len);
+
     /* removable device specific */
     bool coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_is_inserted)(
         BlockDriverState *bs);
@@ -865,6 +871,21 @@ typedef struct BlockLimits {
 
     /* device zone model */
     BlockZoneModel zoned;
+
+    /* zone size expressed in bytes */
+    uint32_t zone_size;
+
+    /* total number of zones */
+    uint32_t nr_zones;
+
+    /* maximum sectors of a zone append write operation */
+    uint32_t max_append_sectors;
+
+    /* maximum number of open zones */
+    uint32_t max_open_zones;
+
+    /* maximum number of active zones */
+    uint32_t max_active_zones;
 } BlockLimits;
 
 typedef struct BdrvOpBlocker BdrvOpBlocker;
diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h
index e46a29c..afb9bdf 100644
--- a/include/block/raw-aio.h
+++ b/include/block/raw-aio.h
@@ -28,6 +28,8 @@
 #define QEMU_AIO_WRITE_ZEROES 0x0020
 #define QEMU_AIO_COPY_RANGE   0x0040
 #define QEMU_AIO_TRUNCATE     0x0080
+#define QEMU_AIO_ZONE_REPORT  0x0100
+#define QEMU_AIO_ZONE_MGMT    0x0200
 #define QEMU_AIO_TYPE_MASK \
         (QEMU_AIO_READ | \
          QEMU_AIO_WRITE | \
@@ -36,7 +38,9 @@
          QEMU_AIO_DISCARD | \
          QEMU_AIO_WRITE_ZEROES | \
          QEMU_AIO_COPY_RANGE | \
-         QEMU_AIO_TRUNCATE)
+         QEMU_AIO_TRUNCATE | \
+         QEMU_AIO_ZONE_REPORT | \
+         QEMU_AIO_ZONE_MGMT)
 
 /* AIO flags */
 #define QEMU_AIO_MISALIGNED   0x1000
diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h
index 851a44d..eb1c1eb 100644
--- a/include/sysemu/block-backend-io.h
+++ b/include/sysemu/block-backend-io.h
@@ -46,6 +46,13 @@ BlockAIOCB *blk_aio_pwritev(BlockBackend *blk, int64_t offset,
                             BlockCompletionFunc *cb, void *opaque);
 BlockAIOCB *blk_aio_flush(BlockBackend *blk,
                           BlockCompletionFunc *cb, void *opaque);
+BlockAIOCB *blk_aio_zone_report(BlockBackend *blk, int64_t offset,
+                                unsigned int *nr_zones,
+                                BlockZoneDescriptor *zones,
+                                BlockCompletionFunc *cb, void *opaque);
+BlockAIOCB *blk_aio_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
+                              int64_t offset, int64_t len,
+                              BlockCompletionFunc *cb, void *opaque);
 BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes,
                              BlockCompletionFunc *cb, void *opaque);
 void blk_aio_cancel_async(BlockAIOCB *acb);
@@ -191,6 +198,17 @@ int co_wrapper_mixed blk_pwrite_zeroes(BlockBackend *blk, int64_t offset,
 int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset,
                                       int64_t bytes, BdrvRequestFlags flags);
 
+int coroutine_fn blk_co_zone_report(BlockBackend *blk, int64_t offset,
+                                    unsigned int *nr_zones,
+                                    BlockZoneDescriptor *zones);
+int co_wrapper_mixed blk_zone_report(BlockBackend *blk, int64_t offset,
+                                         unsigned int *nr_zones,
+                                         BlockZoneDescriptor *zones);
+int coroutine_fn blk_co_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
+                                  int64_t offset, int64_t len);
+int co_wrapper_mixed blk_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
+                                       int64_t offset, int64_t len);
+
 int co_wrapper_mixed blk_pdiscard(BlockBackend *blk, int64_t offset,
                                   int64_t bytes);
 int coroutine_fn blk_co_pdiscard(BlockBackend *blk, int64_t offset,