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

Block layer patches

# gpg: Signature made Mon 05 Mar 2018 17:45:51 GMT
# gpg:                using RSA key 7F09B272C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* remotes/kevin/tags/for-upstream: (38 commits)
  block: Fix NULL dereference on empty drive error
  qcow2: Replace align_offset() with ROUND_UP()
  block/ssh: Add basic .bdrv_truncate()
  block/ssh: Make ssh_grow_file() blocking
  block/ssh: Pull ssh_grow_file() from ssh_create()
  qemu-img: Make resize error message more general
  qcow2: make qcow2_co_create2() a coroutine_fn
  block: rename .bdrv_create() to .bdrv_co_create_opts()
  Revert "IDE: Do not flush empty CDROM drives"
  block: test blk_aio_flush() with blk->root == NULL
  block: add BlockBackend->in_flight counter
  block: extract AIO_WAIT_WHILE() from BlockDriverState
  aio: rename aio_context_in_iothread() to in_aio_context_home_thread()
  docs: document how to use the l2-cache-entry-size parameter
  specs/qcow2: Fix documentation of the compressed cluster descriptor
  iotest 033: add misaligned write-zeroes test via truncate
  block: fix write with zero flag set and iovector provided
  block: Drop unused .bdrv_co_get_block_status()
  vvfat: Switch to .bdrv_co_block_status()
  vpc: Switch to .bdrv_co_block_status()
  ...

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

# Conflicts:
#	include/block/block.h

32 files changed, 572 insertions, 521 deletions

diff --git a/block/blkdebug.c b/block/blkdebug.c
index d83f23febd..589712475a 100644
--- a/block/blkdebug.c
+++ b/block/blkdebug.c
@@ -627,15 +627,17 @@ static int coroutine_fn blkdebug_co_pdiscard(BlockDriverState *bs,
     return bdrv_co_pdiscard(bs->file->bs, offset, bytes);
 }
 
-static int64_t coroutine_fn blkdebug_co_get_block_status(
-    BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum,
-    BlockDriverState **file)
+static int coroutine_fn blkdebug_co_block_status(BlockDriverState *bs,
+                                                 bool want_zero,
+                                                 int64_t offset,
+                                                 int64_t bytes,
+                                                 int64_t *pnum,
+                                                 int64_t *map,
+                                                 BlockDriverState **file)
 {
-    assert(QEMU_IS_ALIGNED(sector_num | nb_sectors,
-                           DIV_ROUND_UP(bs->bl.request_alignment,
-                                        BDRV_SECTOR_SIZE)));
-    return bdrv_co_get_block_status_from_file(bs, sector_num, nb_sectors,
-                                              pnum, file);
+    assert(QEMU_IS_ALIGNED(offset | bytes, bs->bl.request_alignment));
+    return bdrv_co_block_status_from_file(bs, want_zero, offset, bytes,
+                                          pnum, map, file);
 }
 
 static void blkdebug_close(BlockDriverState *bs)
@@ -907,7 +909,7 @@ static BlockDriver bdrv_blkdebug = {
     .bdrv_co_flush_to_disk  = blkdebug_co_flush,
     .bdrv_co_pwrite_zeroes  = blkdebug_co_pwrite_zeroes,
     .bdrv_co_pdiscard       = blkdebug_co_pdiscard,
-    .bdrv_co_get_block_status = blkdebug_co_get_block_status,
+    .bdrv_co_block_status   = blkdebug_co_block_status,
 
     .bdrv_debug_event           = blkdebug_debug_event,
     .bdrv_debug_breakpoint      = blkdebug_debug_breakpoint,
diff --git a/block/block-backend.c b/block/block-backend.c
index 94ffbb6a60..b3c790e2bd 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -73,6 +73,14 @@ struct BlockBackend {
     int quiesce_counter;
     VMChangeStateEntry *vmsh;
     bool force_allow_inactivate;
+
+    /* Number of in-flight aio requests.  BlockDriverState also counts
+     * in-flight requests but aio requests can exist even when blk->root is
+     * NULL, so we cannot rely on its counter for that case.
+     * Accessed with atomic ops.
+     */
+    unsigned int in_flight;
+    AioWait wait;
 };
 
 typedef struct BlockBackendAIOCB {
@@ -1225,11 +1233,22 @@ int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags)
     return bdrv_make_zero(blk->root, flags);
 }
 
+static void blk_inc_in_flight(BlockBackend *blk)
+{
+    atomic_inc(&blk->in_flight);
+}
+
+static void blk_dec_in_flight(BlockBackend *blk)
+{
+    atomic_dec(&blk->in_flight);
+    aio_wait_kick(&blk->wait);
+}
+
 static void error_callback_bh(void *opaque)
 {
     struct BlockBackendAIOCB *acb = opaque;
 
-    bdrv_dec_in_flight(acb->common.bs);
+    blk_dec_in_flight(acb->blk);
     acb->common.cb(acb->common.opaque, acb->ret);
     qemu_aio_unref(acb);
 }
@@ -1240,7 +1259,7 @@ BlockAIOCB *blk_abort_aio_request(BlockBackend *blk,
 {
     struct BlockBackendAIOCB *acb;
 
-    bdrv_inc_in_flight(blk_bs(blk));
+    blk_inc_in_flight(blk);
     acb = blk_aio_get(&block_backend_aiocb_info, blk, cb, opaque);
     acb->blk = blk;
     acb->ret = ret;
@@ -1263,7 +1282,7 @@ static const AIOCBInfo blk_aio_em_aiocb_info = {
 static void blk_aio_complete(BlkAioEmAIOCB *acb)
 {
     if (acb->has_returned) {
-        bdrv_dec_in_flight(acb->common.bs);
+        blk_dec_in_flight(acb->rwco.blk);
         acb->common.cb(acb->common.opaque, acb->rwco.ret);
         qemu_aio_unref(acb);
     }
@@ -1284,7 +1303,7 @@ static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes,
     BlkAioEmAIOCB *acb;
     Coroutine *co;
 
-    bdrv_inc_in_flight(blk_bs(blk));
+    blk_inc_in_flight(blk);
     acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque);
     acb->rwco = (BlkRwCo) {
         .blk    = blk,
@@ -1521,14 +1540,41 @@ int blk_flush(BlockBackend *blk)
 
 void blk_drain(BlockBackend *blk)
 {
-    if (blk_bs(blk)) {
-        bdrv_drain(blk_bs(blk));
+    BlockDriverState *bs = blk_bs(blk);
+
+    if (bs) {
+        bdrv_drained_begin(bs);
+    }
+
+    /* We may have -ENOMEDIUM completions in flight */
+    AIO_WAIT_WHILE(&blk->wait,
+            blk_get_aio_context(blk),
+            atomic_mb_read(&blk->in_flight) > 0);
+
+    if (bs) {
+        bdrv_drained_end(bs);
     }
 }
 
 void blk_drain_all(void)
 {
-    bdrv_drain_all();
+    BlockBackend *blk = NULL;
+
+    bdrv_drain_all_begin();
+
+    while ((blk = blk_all_next(blk)) != NULL) {
+        AioContext *ctx = blk_get_aio_context(blk);
+
+        aio_context_acquire(ctx);
+
+        /* We may have -ENOMEDIUM completions in flight */
+        AIO_WAIT_WHILE(&blk->wait, ctx,
+                atomic_mb_read(&blk->in_flight) > 0);
+
+        aio_context_release(ctx);
+    }
+
+    bdrv_drain_all_end();
 }
 
 void blk_set_on_error(BlockBackend *blk, BlockdevOnError on_read_error,
@@ -1569,10 +1615,11 @@ static void send_qmp_error_event(BlockBackend *blk,
                                  bool is_read, int error)
 {
     IoOperationType optype;
+    BlockDriverState *bs = blk_bs(blk);
 
     optype = is_read ? IO_OPERATION_TYPE_READ : IO_OPERATION_TYPE_WRITE;
-    qapi_event_send_block_io_error(blk_name(blk),
-                                   bdrv_get_node_name(blk_bs(blk)), optype,
+    qapi_event_send_block_io_error(blk_name(blk), !!bs,
+                                   bs ? bdrv_get_node_name(bs) : NULL, optype,
                                    action, blk_iostatus_is_enabled(blk),
                                    error == ENOSPC, strerror(error),
                                    &error_abort);
diff --git a/block/commit.c b/block/commit.c
index bb6c904704..1943c9c3e1 100644
--- a/block/commit.c
+++ b/block/commit.c
@@ -265,7 +265,7 @@ 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_get_block_status   = bdrv_co_get_block_status_from_backing,
+    .bdrv_co_block_status       = bdrv_co_block_status_from_backing,
     .bdrv_refresh_filename      = bdrv_commit_top_refresh_filename,
     .bdrv_close                 = bdrv_commit_top_close,
     .bdrv_child_perm            = bdrv_commit_top_child_perm,
diff --git a/block/crypto.c b/block/crypto.c
index aeac482e7b..17b5c0abad 100644
--- a/block/crypto.c
+++ b/block/crypto.c
@@ -556,9 +556,9 @@ static int block_crypto_open_luks(BlockDriverState *bs,
                                      bs, options, flags, errp);
 }
 
-static int block_crypto_create_luks(const char *filename,
-                                    QemuOpts *opts,
-                                    Error **errp)
+static int coroutine_fn block_crypto_co_create_opts_luks(const char *filename,
+                                                         QemuOpts *opts,
+                                                         Error **errp)
 {
     return block_crypto_create_generic(Q_CRYPTO_BLOCK_FORMAT_LUKS,
                                        filename, opts, errp);
@@ -617,7 +617,7 @@ BlockDriver bdrv_crypto_luks = {
     .bdrv_open          = block_crypto_open_luks,
     .bdrv_close         = block_crypto_close,
     .bdrv_child_perm    = bdrv_format_default_perms,
-    .bdrv_create        = block_crypto_create_luks,
+    .bdrv_co_create_opts = block_crypto_co_create_opts_luks,
     .bdrv_truncate      = block_crypto_truncate,
     .create_opts        = &block_crypto_create_opts_luks,
 
diff --git a/block/file-posix.c b/block/file-posix.c
index ca49c1a98a..7f2cc63c60 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -1982,7 +1982,8 @@ static int64_t raw_get_allocated_file_size(BlockDriverState *bs)
     return (int64_t)st.st_blocks * 512;
 }
 
-static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
+static int coroutine_fn raw_co_create_opts(const char *filename, QemuOpts *opts,
+                                           Error **errp)
 {
     int fd;
     int result = 0;
@@ -2131,25 +2132,24 @@ static int find_allocation(BlockDriverState *bs, off_t start,
 }
 
 /*
- * Returns the allocation status of the specified sectors.
+ * Returns the allocation status of the specified offset.
  *
- * If 'sector_num' is beyond the end of the disk image the return value is 0
- * and 'pnum' is set to 0.
+ * The block layer guarantees 'offset' and 'bytes' are within bounds.
  *
- * 'pnum' is set to the number of sectors (including and immediately following
- * the specified sector) that are known to be in the same
+ * 'pnum' is set to the number of bytes (including and immediately following
+ * the specified offset) that are known to be in the same
  * allocated/unallocated state.
  *
- * 'nb_sectors' is the max value 'pnum' should be set to.  If nb_sectors goes
- * beyond the end of the disk image it will be clamped.
+ * 'bytes' is the max value 'pnum' should be set to.
  */
-static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
-                                                    int64_t sector_num,
-                                                    int nb_sectors, int *pnum,
-                                                    BlockDriverState **file)
-{
-    off_t start, data = 0, hole = 0;
-    int64_t total_size;
+static int coroutine_fn raw_co_block_status(BlockDriverState *bs,
+                                            bool want_zero,
+                                            int64_t offset,
+                                            int64_t bytes, int64_t *pnum,
+                                            int64_t *map,
+                                            BlockDriverState **file)
+{
+    off_t data = 0, hole = 0;
     int ret;
 
     ret = fd_open(bs);
@@ -2157,39 +2157,36 @@ static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
         return ret;
     }
 
-    start = sector_num * BDRV_SECTOR_SIZE;
-    total_size = bdrv_getlength(bs);
-    if (total_size < 0) {
-        return total_size;
-    } else if (start >= total_size) {
-        *pnum = 0;
-        return 0;
-    } else if (start + nb_sectors * BDRV_SECTOR_SIZE > total_size) {
-        nb_sectors = DIV_ROUND_UP(total_size - start, BDRV_SECTOR_SIZE);
+    if (!want_zero) {
+        *pnum = bytes;
+        *map = offset;
+        *file = bs;
+        return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
     }
 
-    ret = find_allocation(bs, start, &data, &hole);
+    ret = find_allocation(bs, offset, &data, &hole);
     if (ret == -ENXIO) {
         /* Trailing hole */
-        *pnum = nb_sectors;
+        *pnum = bytes;
         ret = BDRV_BLOCK_ZERO;
     } else if (ret < 0) {
         /* No info available, so pretend there are no holes */
-        *pnum = nb_sectors;
+        *pnum = bytes;
         ret = BDRV_BLOCK_DATA;
-    } else if (data == start) {
-        /* On a data extent, compute sectors to the end of the extent,
+    } else if (data == offset) {
+        /* On a data extent, compute bytes to the end of the extent,
          * possibly including a partial sector at EOF. */
-        *pnum = MIN(nb_sectors, DIV_ROUND_UP(hole - start, BDRV_SECTOR_SIZE));
+        *pnum = MIN(bytes, hole - offset);
         ret = BDRV_BLOCK_DATA;
     } else {
-        /* On a hole, compute sectors to the beginning of the next extent.  */
-        assert(hole == start);
-        *pnum = MIN(nb_sectors, (data - start) / BDRV_SECTOR_SIZE);
+        /* On a hole, compute bytes to the beginning of the next extent.  */
+        assert(hole == offset);
+        *pnum = MIN(bytes, data - offset);
         ret = BDRV_BLOCK_ZERO;
     }
+    *map = offset;
     *file = bs;
-    return ret | BDRV_BLOCK_OFFSET_VALID | start;
+    return ret | BDRV_BLOCK_OFFSET_VALID;
 }
 
 static coroutine_fn BlockAIOCB *raw_aio_pdiscard(BlockDriverState *bs,
@@ -2280,9 +2277,9 @@ BlockDriver bdrv_file = {
     .bdrv_reopen_commit = raw_reopen_commit,
     .bdrv_reopen_abort = raw_reopen_abort,
     .bdrv_close = raw_close,
-    .bdrv_create = raw_create,
+    .bdrv_co_create_opts = raw_co_create_opts,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
-    .bdrv_co_get_block_status = raw_co_get_block_status,
+    .bdrv_co_block_status = raw_co_block_status,
     .bdrv_co_pwrite_zeroes = raw_co_pwrite_zeroes,
 
     .bdrv_co_preadv         = raw_co_preadv,
@@ -2684,8 +2681,8 @@ static coroutine_fn int hdev_co_pwrite_zeroes(BlockDriverState *bs,
     return -ENOTSUP;
 }
 
-static int hdev_create(const char *filename, QemuOpts *opts,
-                       Error **errp)
+static int coroutine_fn hdev_co_create_opts(const char *filename, QemuOpts *opts,
+                                            Error **errp)
 {
     int fd;
     int ret = 0;
@@ -2758,7 +2755,7 @@ static BlockDriver bdrv_host_device = {
     .bdrv_reopen_prepare = raw_reopen_prepare,
     .bdrv_reopen_commit  = raw_reopen_commit,
     .bdrv_reopen_abort   = raw_reopen_abort,
-    .bdrv_create         = hdev_create,
+    .bdrv_co_create_opts = hdev_co_create_opts,
     .create_opts         = &raw_create_opts,
     .bdrv_co_pwrite_zeroes = hdev_co_pwrite_zeroes,
 
@@ -2880,7 +2877,7 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_reopen_prepare = raw_reopen_prepare,
     .bdrv_reopen_commit  = raw_reopen_commit,
     .bdrv_reopen_abort   = raw_reopen_abort,
-    .bdrv_create         = hdev_create,
+    .bdrv_co_create_opts = hdev_co_create_opts,
     .create_opts         = &raw_create_opts,
 
 
@@ -3011,7 +3008,7 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_reopen_prepare = raw_reopen_prepare,
     .bdrv_reopen_commit  = raw_reopen_commit,
     .bdrv_reopen_abort   = raw_reopen_abort,
-    .bdrv_create        = hdev_create,
+    .bdrv_co_create_opts = hdev_co_create_opts,
     .create_opts        = &raw_create_opts,
 
     .bdrv_co_preadv         = raw_co_preadv,
diff --git a/block/file-win32.c b/block/file-win32.c
index f24c7bb92c..4a430d45f1 100644
--- a/block/file-win32.c
+++ b/block/file-win32.c
@@ -553,7 +553,8 @@ static int64_t raw_get_allocated_file_size(BlockDriverState *bs)
     return st.st_size;
 }
 
-static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
+static int coroutine_fn raw_co_create_opts(const char *filename, QemuOpts *opts,
+                                           Error **errp)
 {
     int fd;
     int64_t total_size = 0;
@@ -599,7 +600,7 @@ BlockDriver bdrv_file = {
     .bdrv_file_open     = raw_open,
     .bdrv_refresh_limits = raw_probe_alignment,
     .bdrv_close         = raw_close,
-    .bdrv_create        = raw_create,
+    .bdrv_co_create_opts = raw_co_create_opts,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
 
     .bdrv_aio_readv     = raw_aio_readv,
diff --git a/block/gluster.c b/block/gluster.c
index 3f17b7819d..79b4cfdf74 100644
--- a/block/gluster.c
+++ b/block/gluster.c
@@ -1021,8 +1021,9 @@ static int qemu_gluster_do_truncate(struct glfs_fd *fd, int64_t offset,
     return 0;
 }
 
-static int qemu_gluster_create(const char *filename,
-                               QemuOpts *opts, Error **errp)
+static int coroutine_fn qemu_gluster_co_create_opts(const char *filename,
+                                                    QemuOpts *opts,
+                                                    Error **errp)
 {
     BlockdevOptionsGluster *gconf;
     struct glfs *glfs;
@@ -1362,68 +1363,66 @@ exit:
 }
 
 /*
- * Returns the allocation status of the specified sectors.
+ * Returns the allocation status of the specified offset.
  *
- * If 'sector_num' is beyond the end of the disk image the return value is 0
- * and 'pnum' is set to 0.
+ * The block layer guarantees 'offset' and 'bytes' are within bounds.
  *
- * 'pnum' is set to the number of sectors (including and immediately following
- * the specified sector) that are known to be in the same
+ * 'pnum' is set to the number of bytes (including and immediately following
+ * the specified offset) that are known to be in the same
  * allocated/unallocated state.
  *
- * 'nb_sectors' is the max value 'pnum' should be set to.  If nb_sectors goes
- * beyond the end of the disk image it will be clamped.
+ * 'bytes' is the max value 'pnum' should be set to.
  *
- * (Based on raw_co_get_block_status() from file-posix.c.)
+ * (Based on raw_co_block_status() from file-posix.c.)
  */
-static int64_t coroutine_fn qemu_gluster_co_get_block_status(
-        BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum,
-        BlockDriverState **file)
+static int coroutine_fn qemu_gluster_co_block_status(BlockDriverState *bs,
+                                                     bool want_zero,
+                                                     int64_t offset,
+                                                     int64_t bytes,
+                                                     int64_t *pnum,
+                                                     int64_t *map,
+                                                     BlockDriverState **file)
 {
     BDRVGlusterState *s = bs->opaque;
-    off_t start, data = 0, hole = 0;
-    int64_t total_size;
+    off_t data = 0, hole = 0;
     int ret = -EINVAL;
 
     if (!s->fd) {
         return ret;
     }
 
-    start = sector_num * BDRV_SECTOR_SIZE;
-    total_size = bdrv_getlength(bs);
-    if (total_size < 0) {
-        return total_size;
-    } else if (start >= total_size) {
-        *pnum = 0;
-        return 0;
-    } else if (start + nb_sectors * BDRV_SECTOR_SIZE > total_size) {
-        nb_sectors = DIV_ROUND_UP(total_size - start, BDRV_SECTOR_SIZE);
+    if (!want_zero) {
+        *pnum = bytes;
+        *map = offset;
+        *file = bs;
+        return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
     }
 
-    ret = find_allocation(bs, start, &data, &hole);
+    ret = find_allocation(bs, offset, &data, &hole);
     if (ret == -ENXIO) {
         /* Trailing hole */
-        *pnum = nb_sectors;
+        *pnum = bytes;
         ret = BDRV_BLOCK_ZERO;
     } else if (ret < 0) {
         /* No info available, so pretend there are no holes */
-        *pnum = nb_sectors;
+        *pnum = bytes;
         ret = BDRV_BLOCK_DATA;
-    } else if (data == start) {
-        /* On a data extent, compute sectors to the end of the extent,
+    } else if (data == offset) {
+        /* On a data extent, compute bytes to the end of the extent,
          * possibly including a partial sector at EOF. */
-        *pnum = MIN(nb_sectors, DIV_ROUND_UP(hole - start, BDRV_SECTOR_SIZE));
+        *pnum = MIN(bytes, hole - offset);
         ret = BDRV_BLOCK_DATA;
     } else {
-        /* On a hole, compute sectors to the beginning of the next extent.  */
-        assert(hole == start);
-        *pnum = MIN(nb_sectors, (data - start) / BDRV_SECTOR_SIZE);
+        /* On a hole, compute bytes to the beginning of the next extent.  */
+        assert(hole == offset);
+        *pnum = MIN(bytes, data - offset);
         ret = BDRV_BLOCK_ZERO;
     }
 
+    *map = offset;
     *file = bs;
 
-    return ret | BDRV_BLOCK_OFFSET_VALID | start;
+    return ret | BDRV_BLOCK_OFFSET_VALID;
 }
 
 
@@ -1437,7 +1436,7 @@ static BlockDriver bdrv_gluster = {
     .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
     .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
     .bdrv_close                   = qemu_gluster_close,
-    .bdrv_create                  = qemu_gluster_create,
+    .bdrv_co_create_opts          = qemu_gluster_co_create_opts,
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
     .bdrv_truncate                = qemu_gluster_truncate,
@@ -1451,7 +1450,7 @@ static BlockDriver bdrv_gluster = {
 #ifdef CONFIG_GLUSTERFS_ZEROFILL
     .bdrv_co_pwrite_zeroes        = qemu_gluster_co_pwrite_zeroes,
 #endif
-    .bdrv_co_get_block_status     = qemu_gluster_co_get_block_status,
+    .bdrv_co_block_status         = qemu_gluster_co_block_status,
     .create_opts                  = &qemu_gluster_create_opts,
 };
 
@@ -1465,7 +1464,7 @@ static BlockDriver bdrv_gluster_tcp = {
     .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
     .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
     .bdrv_close                   = qemu_gluster_close,
-    .bdrv_create                  = qemu_gluster_create,
+    .bdrv_co_create_opts          = qemu_gluster_co_create_opts,
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
     .bdrv_truncate                = qemu_gluster_truncate,
@@ -1479,7 +1478,7 @@ static BlockDriver bdrv_gluster_tcp = {
 #ifdef CONFIG_GLUSTERFS_ZEROFILL
     .bdrv_co_pwrite_zeroes        = qemu_gluster_co_pwrite_zeroes,
 #endif
-    .bdrv_co_get_block_status     = qemu_gluster_co_get_block_status,
+    .bdrv_co_block_status         = qemu_gluster_co_block_status,
     .create_opts                  = &qemu_gluster_create_opts,
 };
 
@@ -1493,7 +1492,7 @@ static BlockDriver bdrv_gluster_unix = {
     .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
     .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
     .bdrv_close                   = qemu_gluster_close,
-    .bdrv_create                  = qemu_gluster_create,
+    .bdrv_co_create_opts          = qemu_gluster_co_create_opts,
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
     .bdrv_truncate                = qemu_gluster_truncate,
@@ -1507,7 +1506,7 @@ static BlockDriver bdrv_gluster_unix = {
 #ifdef CONFIG_GLUSTERFS_ZEROFILL
     .bdrv_co_pwrite_zeroes        = qemu_gluster_co_pwrite_zeroes,
 #endif
-    .bdrv_co_get_block_status     = qemu_gluster_co_get_block_status,
+    .bdrv_co_block_status         = qemu_gluster_co_block_status,
     .create_opts                  = &qemu_gluster_create_opts,
 };
 
@@ -1527,7 +1526,7 @@ static BlockDriver bdrv_gluster_rdma = {
     .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
     .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
     .bdrv_close                   = qemu_gluster_close,
-    .bdrv_create                  = qemu_gluster_create,
+    .bdrv_co_create_opts          = qemu_gluster_co_create_opts,
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
     .bdrv_truncate                = qemu_gluster_truncate,
@@ -1541,7 +1540,7 @@ static BlockDriver bdrv_gluster_rdma = {
 #ifdef CONFIG_GLUSTERFS_ZEROFILL
     .bdrv_co_pwrite_zeroes        = qemu_gluster_co_pwrite_zeroes,
 #endif
-    .bdrv_co_get_block_status     = qemu_gluster_co_get_block_status,
+    .bdrv_co_block_status         = qemu_gluster_co_block_status,
     .create_opts                  = &qemu_gluster_create_opts,
 };
 
diff --git a/block/io.c b/block/io.c
index 89d0745e95..2b09c656d0 100644
--- a/block/io.c
+++ b/block/io.c
@@ -25,6 +25,7 @@
 #include "qemu/osdep.h"
 #include "trace.h"
 #include "sysemu/block-backend.h"
+#include "block/aio-wait.h"
 #include "block/blockjob.h"
 #include "block/blockjob_int.h"
 #include "block/block_int.h"
@@ -587,16 +588,9 @@ void bdrv_inc_in_flight(BlockDriverState *bs)
     atomic_inc(&bs->in_flight);
 }
 
-static void dummy_bh_cb(void *opaque)
-{
-}
-
 void bdrv_wakeup(BlockDriverState *bs)
 {
-    /* The barrier (or an atomic op) is in the caller.  */
-    if (atomic_read(&bs->wakeup)) {
-        aio_bh_schedule_oneshot(qemu_get_aio_context(), dummy_bh_cb, NULL);
-    }
+    aio_wait_kick(bdrv_get_aio_wait(bs));
 }
 
 void bdrv_dec_in_flight(BlockDriverState *bs)
@@ -1701,7 +1695,7 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
      */
     tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_WRITE);
 
-    if (!qiov) {
+    if (flags & BDRV_REQ_ZERO_WRITE) {
         ret = bdrv_co_do_zero_pwritev(child, offset, bytes, flags, &req);
         goto out;
     }
@@ -1868,30 +1862,34 @@ typedef struct BdrvCoBlockStatusData {
     bool done;
 } BdrvCoBlockStatusData;
 
-int64_t coroutine_fn bdrv_co_get_block_status_from_file(BlockDriverState *bs,
-                                                        int64_t sector_num,
-                                                        int nb_sectors,
-                                                        int *pnum,
-                                                        BlockDriverState **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)
 {
     assert(bs->file && bs->file->bs);
-    *pnum = nb_sectors;
+    *pnum = bytes;
+    *map = offset;
     *file = bs->file->bs;
-    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID |
-           (sector_num << BDRV_SECTOR_BITS);
+    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID;
 }
 
-int64_t coroutine_fn bdrv_co_get_block_status_from_backing(BlockDriverState *bs,
-                                                           int64_t sector_num,
-                                                           int nb_sectors,
-                                                           int *pnum,
-                                                           BlockDriverState **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)
 {
     assert(bs->backing && bs->backing->bs);
-    *pnum = nb_sectors;
+    *pnum = bytes;
+    *map = offset;
     *file = bs->backing->bs;
-    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID |
-           (sector_num << BDRV_SECTOR_BITS);
+    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID;
 }
 
 /*
@@ -1899,10 +1897,10 @@ int64_t coroutine_fn bdrv_co_get_block_status_from_backing(BlockDriverState *bs,
  * Drivers not implementing the functionality are assumed to not support
  * backing files, hence all their sectors are reported as allocated.
  *
- * If 'want_zero' is true, the caller is querying for mapping purposes,
- * and the result should include BDRV_BLOCK_OFFSET_VALID and
- * BDRV_BLOCK_ZERO where possible; otherwise, the result may omit those
- * bits particularly if it allows for a larger value in 'pnum'.
+ * If 'want_zero' is true, the caller is querying for mapping
+ * purposes, with a focus on valid BDRV_BLOCK_OFFSET_VALID, _DATA, and
+ * _ZERO where possible; otherwise, the result favors larger 'pnum',
+ * with a focus on accurate BDRV_BLOCK_ALLOCATED.
  *
  * If 'offset' is beyond the end of the disk image the return value is
  * BDRV_BLOCK_EOF and 'pnum' is set to 0.
@@ -1959,7 +1957,7 @@ 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_get_block_status) {
+    if (!bs->drv->bdrv_co_block_status) {
         *pnum = bytes;
         ret = BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED;
         if (offset + bytes == total_size) {
@@ -1976,44 +1974,24 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
     bdrv_inc_in_flight(bs);
 
     /* Round out to request_alignment boundaries */
-    /* TODO: until we have a byte-based driver callback, we also have to
-     * round out to sectors, even if that is bigger than request_alignment */
-    align = MAX(bs->bl.request_alignment, BDRV_SECTOR_SIZE);
+    align = bs->bl.request_alignment;
     aligned_offset = QEMU_ALIGN_DOWN(offset, align);
     aligned_bytes = ROUND_UP(offset + bytes, align) - aligned_offset;
 
-    {
-        int count; /* sectors */
-        int64_t longret;
-
-        assert(QEMU_IS_ALIGNED(aligned_offset | aligned_bytes,
-                               BDRV_SECTOR_SIZE));
-        /*
-         * The contract allows us to return pnum smaller than bytes, even
-         * if the next query would see the same status; we truncate the
-         * request to avoid overflowing the driver's 32-bit interface.
-         */
-        longret = bs->drv->bdrv_co_get_block_status(
-            bs, aligned_offset >> BDRV_SECTOR_BITS,
-            MIN(INT_MAX, aligned_bytes) >> BDRV_SECTOR_BITS, &count,
-            &local_file);
-        if (longret < 0) {
-            assert(INT_MIN <= longret);
-            ret = longret;
-            goto out;
-        }
-        if (longret & BDRV_BLOCK_OFFSET_VALID) {
-            local_map = longret & BDRV_BLOCK_OFFSET_MASK;
-        }
-        ret = longret & ~BDRV_BLOCK_OFFSET_MASK;
-        *pnum = count * BDRV_SECTOR_SIZE;
+    ret = bs->drv->bdrv_co_block_status(bs, want_zero, aligned_offset,
+                                        aligned_bytes, pnum, &local_map,
+                                        &local_file);
+    if (ret < 0) {
+        *pnum = 0;
+        goto out;
     }
 
     /*
-     * The driver's result must be a multiple of request_alignment.
+     * The driver's result must be a non-zero multiple of request_alignment.
      * Clamp pnum and adjust map to original request.
      */
-    assert(QEMU_IS_ALIGNED(*pnum, align) && align > offset - aligned_offset);
+    assert(*pnum && QEMU_IS_ALIGNED(*pnum, align) &&
+           align > offset - aligned_offset);
     *pnum -= offset - aligned_offset;
     if (*pnum > bytes) {
         *pnum = bytes;
diff --git a/block/iscsi.c b/block/iscsi.c
index d2b320ea41..8bf0e87244 100644
--- a/block/iscsi.c
+++ b/block/iscsi.c
@@ -86,7 +86,7 @@ typedef struct IscsiLun {
     unsigned long *allocmap;
     unsigned long *allocmap_valid;
     long allocmap_size;
-    int cluster_sectors;
+    int cluster_size;
     bool use_16_for_rw;
     bool write_protected;
     bool lbpme;
@@ -430,9 +430,10 @@ static int iscsi_allocmap_init(IscsiLun *iscsilun, int open_flags)
 {
     iscsi_allocmap_free(iscsilun);
 
+    assert(iscsilun->cluster_size);
     iscsilun->allocmap_size =
-        DIV_ROUND_UP(sector_lun2qemu(iscsilun->num_blocks, iscsilun),
-                     iscsilun->cluster_sectors);
+        DIV_ROUND_UP(iscsilun->num_blocks * iscsilun->block_size,
+                     iscsilun->cluster_size);
 
     iscsilun->allocmap = bitmap_try_new(iscsilun->allocmap_size);
     if (!iscsilun->allocmap) {
@@ -440,7 +441,7 @@ static int iscsi_allocmap_init(IscsiLun *iscsilun, int open_flags)
     }
 
     if (open_flags & BDRV_O_NOCACHE) {
-        /* in case that cache.direct = on all allocmap entries are
+        /* when cache.direct = on all allocmap entries are
          * treated as invalid to force a relookup of the block
          * status on every read request */
         return 0;
@@ -457,8 +458,8 @@ static int iscsi_allocmap_init(IscsiLun *iscsilun, int open_flags)
 }
 
 static void
-iscsi_allocmap_update(IscsiLun *iscsilun, int64_t sector_num,
-                      int nb_sectors, bool allocated, bool valid)
+iscsi_allocmap_update(IscsiLun *iscsilun, int64_t offset,
+                      int64_t bytes, bool allocated, bool valid)
 {
     int64_t cl_num_expanded, nb_cls_expanded, cl_num_shrunk, nb_cls_shrunk;
 
@@ -466,13 +467,13 @@ iscsi_allocmap_update(IscsiLun *iscsilun, int64_t sector_num,
         return;
     }
     /* expand to entirely contain all affected clusters */
-    cl_num_expanded = sector_num / iscsilun->cluster_sectors;
-    nb_cls_expanded = DIV_ROUND_UP(sector_num + nb_sectors,
-                                   iscsilun->cluster_sectors) - cl_num_expanded;
+    assert(iscsilun->cluster_size);
+    cl_num_expanded = offset / iscsilun->cluster_size;
+    nb_cls_expanded = DIV_ROUND_UP(offset + bytes,
+                                   iscsilun->cluster_size) - cl_num_expanded;
     /* shrink to touch only completely contained clusters */
-    cl_num_shrunk = DIV_ROUND_UP(sector_num, iscsilun->cluster_sectors);
-    nb_cls_shrunk = (sector_num + nb_sectors) / iscsilun->cluster_sectors
-                      - cl_num_shrunk;
+    cl_num_shrunk = DIV_ROUND_UP(offset, iscsilun->cluster_size);
+    nb_cls_shrunk = (offset + bytes) / iscsilun->cluster_size - cl_num_shrunk;
     if (allocated) {
         bitmap_set(iscsilun->allocmap, cl_num_expanded, nb_cls_expanded);
     } else {
@@ -495,26 +496,26 @@ iscsi_allocmap_update(IscsiLun *iscsilun, int64_t sector_num,
 }
 
 static void
-iscsi_allocmap_set_allocated(IscsiLun *iscsilun, int64_t sector_num,
-                             int nb_sectors)
+iscsi_allocmap_set_allocated(IscsiLun *iscsilun, int64_t offset,
+                             int64_t bytes)
 {
-    iscsi_allocmap_update(iscsilun, sector_num, nb_sectors, true, true);
+    iscsi_allocmap_update(iscsilun, offset, bytes, true, true);
 }
 
 static void
-iscsi_allocmap_set_unallocated(IscsiLun *iscsilun, int64_t sector_num,
-                               int nb_sectors)
+iscsi_allocmap_set_unallocated(IscsiLun *iscsilun, int64_t offset,
+                               int64_t bytes)
 {
     /* Note: if cache.direct=on the fifth argument to iscsi_allocmap_update
      * is ignored, so this will in effect be an iscsi_allocmap_set_invalid.
      */
-    iscsi_allocmap_update(iscsilun, sector_num, nb_sectors, false, true);
+    iscsi_allocmap_update(iscsilun, offset, bytes, false, true);
 }
 
-static void iscsi_allocmap_set_invalid(IscsiLun *iscsilun, int64_t sector_num,
-                                       int nb_sectors)
+static void iscsi_allocmap_set_invalid(IscsiLun *iscsilun, int64_t offset,
+                                       int64_t bytes)
 {
-    iscsi_allocmap_update(iscsilun, sector_num, nb_sectors, false, false);
+    iscsi_allocmap_update(iscsilun, offset, bytes, false, false);
 }
 
 static void iscsi_allocmap_invalidate(IscsiLun *iscsilun)
@@ -528,28 +529,30 @@ static void iscsi_allocmap_invalidate(IscsiLun *iscsilun)
 }
 
 static inline bool
-iscsi_allocmap_is_allocated(IscsiLun *iscsilun, int64_t sector_num,
-                            int nb_sectors)
+iscsi_allocmap_is_allocated(IscsiLun *iscsilun, int64_t offset,
+                            int64_t bytes)
 {
     unsigned long size;
     if (iscsilun->allocmap == NULL) {
         return true;
     }
-    size = DIV_ROUND_UP(sector_num + nb_sectors, iscsilun->cluster_sectors);
+    assert(iscsilun->cluster_size);
+    size = DIV_ROUND_UP(offset + bytes, iscsilun->cluster_size);
     return !(find_next_bit(iscsilun->allocmap, size,
-                           sector_num / iscsilun->cluster_sectors) == size);
+                           offset / iscsilun->cluster_size) == size);
 }
 
 static inline bool iscsi_allocmap_is_valid(IscsiLun *iscsilun,
-                                           int64_t sector_num, int nb_sectors)
+                                           int64_t offset, int64_t bytes)
 {
     unsigned long size;
     if (iscsilun->allocmap_valid == NULL) {
         return false;
     }
-    size = DIV_ROUND_UP(sector_num + nb_sectors, iscsilun->cluster_sectors);
+    assert(iscsilun->cluster_size);
+    size = DIV_ROUND_UP(offset + bytes, iscsilun->cluster_size);
     return (find_next_zero_bit(iscsilun->allocmap_valid, size,
-                               sector_num / iscsilun->cluster_sectors) == size);
+                               offset / iscsilun->cluster_size) == size);
 }
 
 static int coroutine_fn
@@ -631,14 +634,16 @@ retry:
     }
 
     if (iTask.status != SCSI_STATUS_GOOD) {
-        iscsi_allocmap_set_invalid(iscsilun, sector_num, nb_sectors);
+        iscsi_allocmap_set_invalid(iscsilun, sector_num * BDRV_SECTOR_SIZE,
+                                   nb_sectors * BDRV_SECTOR_SIZE);
         error_report("iSCSI WRITE10/16 failed at lba %" PRIu64 ": %s", lba,
                      iTask.err_str);
         r = iTask.err_code;
         goto out_unlock;
     }
 
-    iscsi_allocmap_set_allocated(iscsilun, sector_num, nb_sectors);
+    iscsi_allocmap_set_allocated(iscsilun, sector_num * BDRV_SECTOR_SIZE,
+                                 nb_sectors * BDRV_SECTOR_SIZE);
 
 out_unlock:
     qemu_mutex_unlock(&iscsilun->mutex);
@@ -648,36 +653,36 @@ out_unlock:
 
 
 
-static int64_t coroutine_fn iscsi_co_get_block_status(BlockDriverState *bs,
-                                                  int64_t sector_num,
-                                                  int nb_sectors, int *pnum,
-                                                  BlockDriverState **file)
+static int coroutine_fn iscsi_co_block_status(BlockDriverState *bs,
+                                              bool want_zero, int64_t offset,
+                                              int64_t bytes, int64_t *pnum,
+                                              int64_t *map,
+                                              BlockDriverState **file)
 {
     IscsiLun *iscsilun = bs->opaque;
     struct scsi_get_lba_status *lbas = NULL;
     struct scsi_lba_status_descriptor *lbasd = NULL;
     struct IscsiTask iTask;
     uint64_t lba;
-    int64_t ret;
+    int ret;
 
     iscsi_co_init_iscsitask(iscsilun, &iTask);
 
-    if (!is_sector_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
-        ret = -EINVAL;
-        goto out;
-    }
+    assert(QEMU_IS_ALIGNED(offset | bytes, iscsilun->block_size));
 
     /* default to all sectors allocated */
-    ret = BDRV_BLOCK_DATA;
-    ret |= (sector_num << BDRV_SECTOR_BITS) | BDRV_BLOCK_OFFSET_VALID;
-    *pnum = nb_sectors;
+    ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
+    if (map) {
+        *map = offset;
+    }
+    *pnum = bytes;
 
     /* LUN does not support logical block provisioning */
     if (!iscsilun->lbpme) {
         goto out;
     }
 
-    lba = sector_qemu2lun(sector_num, iscsilun);
+    lba = offset / iscsilun->block_size;
 
     qemu_mutex_lock(&iscsilun->mutex);
 retry:
@@ -722,12 +727,12 @@ retry:
 
     lbasd = &lbas->descriptors[0];
 
-    if (sector_qemu2lun(sector_num, iscsilun) != lbasd->lba) {
+    if (lba != lbasd->lba) {
         ret = -EIO;
         goto out_unlock;
     }
 
-    *pnum = sector_lun2qemu(lbasd->num_blocks, iscsilun);
+    *pnum = lbasd->num_blocks * iscsilun->block_size;
 
     if (lbasd->provisioning == SCSI_PROVISIONING_TYPE_DEALLOCATED ||
         lbasd->provisioning == SCSI_PROVISIONING_TYPE_ANCHORED) {
@@ -738,13 +743,13 @@ retry:
     }
 
     if (ret & BDRV_BLOCK_ZERO) {
-        iscsi_allocmap_set_unallocated(iscsilun, sector_num, *pnum);
+        iscsi_allocmap_set_unallocated(iscsilun, offset, *pnum);
     } else {
-        iscsi_allocmap_set_allocated(iscsilun, sector_num, *pnum);
+        iscsi_allocmap_set_allocated(iscsilun, offset, *pnum);
     }
 
-    if (*pnum > nb_sectors) {
-        *pnum = nb_sectors;
+    if (*pnum > bytes) {
+        *pnum = bytes;
     }
 out_unlock:
     qemu_mutex_unlock(&iscsilun->mutex);
@@ -753,7 +758,7 @@ out:
     if (iTask.task != NULL) {
         scsi_free_scsi_task(iTask.task);
     }
-    if (ret > 0 && ret & BDRV_BLOCK_OFFSET_VALID) {
+    if (ret > 0 && ret & BDRV_BLOCK_OFFSET_VALID && file) {
         *file = bs;
     }
     return ret;
@@ -780,29 +785,37 @@ static int coroutine_fn iscsi_co_readv(BlockDriverState *bs,
     /* if cache.direct is off and we have a valid entry in our allocation map
      * we can skip checking the block status and directly return zeroes if
      * the request falls within an unallocated area */
-    if (iscsi_allocmap_is_valid(iscsilun, sector_num, nb_sectors) &&
-        !iscsi_allocmap_is_allocated(iscsilun, sector_num, nb_sectors)) {
+    if (iscsi_allocmap_is_valid(iscsilun, sector_num * BDRV_SECTOR_SIZE,
+                                nb_sectors * BDRV_SECTOR_SIZE) &&
+        !iscsi_allocmap_is_allocated(iscsilun, sector_num * BDRV_SECTOR_SIZE,
+                                     nb_sectors * BDRV_SECTOR_SIZE)) {
             qemu_iovec_memset(iov, 0, 0x00, iov->size);
             return 0;
     }
 
     if (nb_sectors >= ISCSI_CHECKALLOC_THRES &&
-        !iscsi_allocmap_is_valid(iscsilun, sector_num, nb_sectors) &&
-        !iscsi_allocmap_is_allocated(iscsilun, sector_num, nb_sectors)) {
-        int pnum;
-        BlockDriverState *file;
+        !iscsi_allocmap_is_valid(iscsilun, sector_num * BDRV_SECTOR_SIZE,
+                                 nb_sectors * BDRV_SECTOR_SIZE) &&
+        !iscsi_allocmap_is_allocated(iscsilun, sector_num * BDRV_SECTOR_SIZE,
+                                     nb_sectors * BDRV_SECTOR_SIZE)) {
+        int64_t pnum;
         /* check the block status from the beginning of the cluster
          * containing the start sector */
-        int64_t ret = iscsi_co_get_block_status(bs,
-                          sector_num - sector_num % iscsilun->cluster_sectors,
-                          BDRV_REQUEST_MAX_SECTORS, &pnum, &file);
+        int64_t head;
+        int ret;
+
+        assert(iscsilun->cluster_size);
+        head = (sector_num * BDRV_SECTOR_SIZE) % iscsilun->cluster_size;
+        ret = iscsi_co_block_status(bs, true,
+                                    sector_num * BDRV_SECTOR_SIZE - head,
+                                    BDRV_REQUEST_MAX_BYTES, &pnum, NULL, NULL);
         if (ret < 0) {
             return ret;
         }
         /* if the whole request falls into an unallocated area we can avoid
-         * to read and directly return zeroes instead */
+         * reading and directly return zeroes instead */
         if (ret & BDRV_BLOCK_ZERO &&
-            pnum >= nb_sectors + sector_num % iscsilun->cluster_sectors) {
+            pnum >= nb_sectors * BDRV_SECTOR_SIZE + head) {
             qemu_iovec_memset(iov, 0, 0x00, iov->size);
             return 0;
         }
@@ -1146,8 +1159,7 @@ retry:
         goto retry;
     }
 
-    iscsi_allocmap_set_invalid(iscsilun, offset >> BDRV_SECTOR_BITS,
-                               bytes >> BDRV_SECTOR_BITS);
+    iscsi_allocmap_set_invalid(iscsilun, offset, bytes);
 
     if (iTask.status == SCSI_STATUS_CHECK_CONDITION) {
         /* the target might fail with a check condition if it
@@ -1260,8 +1272,7 @@ retry:
     }
 
     if (iTask.status != SCSI_STATUS_GOOD) {
-        iscsi_allocmap_set_invalid(iscsilun, offset >> BDRV_SECTOR_BITS,
-                                   bytes >> BDRV_SECTOR_BITS);
+        iscsi_allocmap_set_invalid(iscsilun, offset, bytes);
         error_report("iSCSI WRITESAME10/16 failed at lba %" PRIu64 ": %s",
                      lba, iTask.err_str);
         r = iTask.err_code;
@@ -1269,11 +1280,9 @@ retry:
     }
 
     if (flags & BDRV_REQ_MAY_UNMAP) {
-        iscsi_allocmap_set_invalid(iscsilun, offset >> BDRV_SECTOR_BITS,
-                                   bytes >> BDRV_SECTOR_BITS);
+        iscsi_allocmap_set_invalid(iscsilun, offset, bytes);
     } else {
-        iscsi_allocmap_set_allocated(iscsilun, offset >> BDRV_SECTOR_BITS,
-                                     bytes >> BDRV_SECTOR_BITS);
+        iscsi_allocmap_set_allocated(iscsilun, offset, bytes);
     }
 
 out_unlock:
@@ -1953,8 +1962,8 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
      * reasonable size */
     if (iscsilun->bl.opt_unmap_gran * iscsilun->block_size >= 4 * 1024 &&
         iscsilun->bl.opt_unmap_gran * iscsilun->block_size <= 16 * 1024 * 1024) {
-        iscsilun->cluster_sectors = (iscsilun->bl.opt_unmap_gran *
-                                     iscsilun->block_size) >> BDRV_SECTOR_BITS;
+        iscsilun->cluster_size = iscsilun->bl.opt_unmap_gran *
+            iscsilun->block_size;
         if (iscsilun->lbprz) {
             ret = iscsi_allocmap_init(iscsilun, bs->open_flags);
         }
@@ -2108,7 +2117,8 @@ static int iscsi_truncate(BlockDriverState *bs, int64_t offset,
     return 0;
 }
 
-static int iscsi_create(const char *filename, QemuOpts *opts, Error **errp)
+static int coroutine_fn iscsi_co_create_opts(const char *filename, QemuOpts *opts,
+                                             Error **errp)
 {
     int ret = 0;
     int64_t total_size = 0;
@@ -2163,7 +2173,7 @@ static int iscsi_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 {
     IscsiLun *iscsilun = bs->opaque;
     bdi->unallocated_blocks_are_zero = iscsilun->lbprz;
-    bdi->cluster_size = iscsilun->cluster_sectors * BDRV_SECTOR_SIZE;
+    bdi->cluster_size = iscsilun->cluster_size;
     return 0;
 }
 
@@ -2195,7 +2205,7 @@ static BlockDriver bdrv_iscsi = {
     .bdrv_parse_filename    = iscsi_parse_filename,
     .bdrv_file_open         = iscsi_open,
     .bdrv_close             = iscsi_close,
-    .bdrv_create            = iscsi_create,
+    .bdrv_co_create_opts    = iscsi_co_create_opts,
     .create_opts            = &iscsi_create_opts,
     .bdrv_reopen_prepare    = iscsi_reopen_prepare,
     .bdrv_reopen_commit     = iscsi_reopen_commit,
@@ -2206,7 +2216,7 @@ static BlockDriver bdrv_iscsi = {
     .bdrv_truncate   = iscsi_truncate,
     .bdrv_refresh_limits = iscsi_refresh_limits,
 
-    .bdrv_co_get_block_status = iscsi_co_get_block_status,
+    .bdrv_co_block_status  = iscsi_co_block_status,
     .bdrv_co_pdiscard      = iscsi_co_pdiscard,
     .bdrv_co_pwrite_zeroes = iscsi_co_pwrite_zeroes,
     .bdrv_co_readv         = iscsi_co_readv,
@@ -2230,7 +2240,7 @@ static BlockDriver bdrv_iser = {
     .bdrv_parse_filename    = iscsi_parse_filename,
     .bdrv_file_open         = iscsi_open,
     .bdrv_close             = iscsi_close,
-    .bdrv_create            = iscsi_create,
+    .bdrv_co_create_opts    = iscsi_co_create_opts,
     .create_opts            = &iscsi_create_opts,
     .bdrv_reopen_prepare    = iscsi_reopen_prepare,
     .bdrv_reopen_commit     = iscsi_reopen_commit,
@@ -2241,7 +2251,7 @@ static BlockDriver bdrv_iser = {
     .bdrv_truncate   = iscsi_truncate,
     .bdrv_refresh_limits = iscsi_refresh_limits,
 
-    .bdrv_co_get_block_status = iscsi_co_get_block_status,
+    .bdrv_co_block_status  = iscsi_co_block_status,
     .bdrv_co_pdiscard      = iscsi_co_pdiscard,
     .bdrv_co_pwrite_zeroes = iscsi_co_pwrite_zeroes,
     .bdrv_co_readv         = iscsi_co_readv,
diff --git a/block/mirror.c b/block/mirror.c
index c9badc1203..f5bf620942 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -1094,7 +1094,7 @@ 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_get_block_status   = bdrv_co_get_block_status_from_backing,
+    .bdrv_co_block_status       = bdrv_co_block_status_from_backing,
     .bdrv_refresh_filename      = bdrv_mirror_top_refresh_filename,
     .bdrv_close                 = bdrv_mirror_top_close,
     .bdrv_child_perm            = bdrv_mirror_top_child_perm,
diff --git a/block/nfs.c b/block/nfs.c
index bbdb4fadad..1d82ff5042 100644
--- a/block/nfs.c
+++ b/block/nfs.c
@@ -684,7 +684,8 @@ static QemuOptsList nfs_create_opts = {
     }
 };
 
-static int nfs_file_create(const char *url, QemuOpts *opts, Error **errp)
+static int coroutine_fn nfs_file_co_create_opts(const char *url, QemuOpts *opts,
+                                                Error **errp)
 {
     int64_t ret, total_size;
     NFSClient *client = g_new0(NFSClient, 1);
@@ -897,7 +898,7 @@ static BlockDriver bdrv_nfs = {
 
     .bdrv_file_open                 = nfs_file_open,
     .bdrv_close                     = nfs_file_close,
-    .bdrv_create                    = nfs_file_create,
+    .bdrv_co_create_opts            = nfs_file_co_create_opts,
     .bdrv_reopen_prepare            = nfs_reopen_prepare,
 
     .bdrv_co_preadv                 = nfs_co_preadv,
diff --git a/block/null.c b/block/null.c
index 214d394fff..806a8631e4 100644
--- a/block/null.c
+++ b/block/null.c
@@ -223,22 +223,23 @@ static int null_reopen_prepare(BDRVReopenState *reopen_state,
     return 0;
 }
 
-static int64_t coroutine_fn null_co_get_block_status(BlockDriverState *bs,
-                                                     int64_t sector_num,
-                                                     int nb_sectors, int *pnum,
-                                                     BlockDriverState **file)
+static int coroutine_fn null_co_block_status(BlockDriverState *bs,
+                                             bool want_zero, int64_t offset,
+                                             int64_t bytes, int64_t *pnum,
+                                             int64_t *map,
+                                             BlockDriverState **file)
 {
     BDRVNullState *s = bs->opaque;
-    off_t start = sector_num * BDRV_SECTOR_SIZE;
+    int ret = BDRV_BLOCK_OFFSET_VALID;
 
-    *pnum = nb_sectors;
+    *pnum = bytes;
+    *map = offset;
     *file = bs;
 
     if (s->read_zeroes) {
-        return BDRV_BLOCK_OFFSET_VALID | start | BDRV_BLOCK_ZERO;
-    } else {
-        return BDRV_BLOCK_OFFSET_VALID | start;
+        ret |= BDRV_BLOCK_ZERO;
     }
+    return ret;
 }
 
 static void null_refresh_filename(BlockDriverState *bs, QDict *opts)
@@ -270,7 +271,7 @@ static BlockDriver bdrv_null_co = {
     .bdrv_co_flush_to_disk  = null_co_flush,
     .bdrv_reopen_prepare    = null_reopen_prepare,
 
-    .bdrv_co_get_block_status   = null_co_get_block_status,
+    .bdrv_co_block_status   = null_co_block_status,
 
     .bdrv_refresh_filename  = null_refresh_filename,
 };
@@ -290,7 +291,7 @@ static BlockDriver bdrv_null_aio = {
     .bdrv_aio_flush         = null_aio_flush,
     .bdrv_reopen_prepare    = null_reopen_prepare,
 
-    .bdrv_co_get_block_status   = null_co_get_block_status,
+    .bdrv_co_block_status   = null_co_block_status,
 
     .bdrv_refresh_filename  = null_refresh_filename,
 };
diff --git a/block/nvme.c b/block/nvme.c
index 75078022f6..8bca57aae6 100644
--- a/block/nvme.c
+++ b/block/nvme.c
@@ -1072,18 +1072,6 @@ static int nvme_reopen_prepare(BDRVReopenState *reopen_state,
     return 0;
 }
 
-static int64_t coroutine_fn nvme_co_get_block_status(BlockDriverState *bs,
-                                                     int64_t sector_num,
-                                                     int nb_sectors, int *pnum,
-                                                     BlockDriverState **file)
-{
-    *pnum = nb_sectors;
-    *file = bs;
-
-    return BDRV_BLOCK_ALLOCATED | BDRV_BLOCK_OFFSET_VALID |
-           (sector_num << BDRV_SECTOR_BITS);
-}
-
 static void nvme_refresh_filename(BlockDriverState *bs, QDict *opts)
 {
     QINCREF(opts);
@@ -1183,8 +1171,6 @@ static BlockDriver bdrv_nvme = {
     .bdrv_co_flush_to_disk    = nvme_co_flush,
     .bdrv_reopen_prepare      = nvme_reopen_prepare,
 
-    .bdrv_co_get_block_status = nvme_co_get_block_status,
-
     .bdrv_refresh_filename    = nvme_refresh_filename,
     .bdrv_refresh_limits      = nvme_refresh_limits,
 
diff --git a/block/parallels.c b/block/parallels.c
index e1e3d80c88..81085795c2 100644
--- a/block/parallels.c
+++ b/block/parallels.c
@@ -261,23 +261,31 @@ static coroutine_fn int parallels_co_flush_to_os(BlockDriverState *bs)
 }
 
 
-static int64_t coroutine_fn parallels_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
+static int coroutine_fn parallels_co_block_status(BlockDriverState *bs,
+                                                  bool want_zero,
+                                                  int64_t offset,
+                                                  int64_t bytes,
+                                                  int64_t *pnum,
+                                                  int64_t *map,
+                                                  BlockDriverState **file)
 {
     BDRVParallelsState *s = bs->opaque;
-    int64_t offset;
+    int count;
 
+    assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE));
     qemu_co_mutex_lock(&s->lock);
-    offset = block_status(s, sector_num, nb_sectors, pnum);
+    offset = block_status(s, offset >> BDRV_SECTOR_BITS,
+                          bytes >> BDRV_SECTOR_BITS, &count);
     qemu_co_mutex_unlock(&s->lock);
 
+    *pnum = count * BDRV_SECTOR_SIZE;
     if (offset < 0) {
         return 0;
     }
 
+    *map = offset * BDRV_SECTOR_SIZE;
     *file = bs->file->bs;
-    return (offset << BDRV_SECTOR_BITS) |
-        BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
+    return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
 }
 
 static coroutine_fn int parallels_co_writev(BlockDriverState *bs,
@@ -467,7 +475,9 @@ static int parallels_check(BlockDriverState *bs, BdrvCheckResult *res,
 }
 
 
-static int parallels_create(const char *filename, QemuOpts *opts, Error **errp)
+static int coroutine_fn parallels_co_create_opts(const char *filename,
+                                                 QemuOpts *opts,
+                                                 Error **errp)
 {
     int64_t total_size, cl_size;
     uint8_t tmp[BDRV_SECTOR_SIZE];
@@ -782,13 +792,13 @@ static BlockDriver bdrv_parallels = {
     .bdrv_open		= parallels_open,
     .bdrv_close		= parallels_close,
     .bdrv_child_perm          = bdrv_format_default_perms,
-    .bdrv_co_get_block_status = parallels_co_get_block_status,
+    .bdrv_co_block_status     = parallels_co_block_status,
     .bdrv_has_zero_init       = bdrv_has_zero_init_1,
     .bdrv_co_flush_to_os      = parallels_co_flush_to_os,
     .bdrv_co_readv  = parallels_co_readv,
     .bdrv_co_writev = parallels_co_writev,
     .supports_backing = true,
-    .bdrv_create    = parallels_create,
+    .bdrv_co_create_opts = parallels_co_create_opts,
     .bdrv_check     = parallels_check,
     .create_opts    = &parallels_create_opts,
 };
diff --git a/block/qcow.c b/block/qcow.c
index 8631155ac8..47a18d9a3a 100644
--- a/block/qcow.c
+++ b/block/qcow.c
@@ -524,23 +524,28 @@ static int get_cluster_offset(BlockDriverState *bs,
     return 1;
 }
 
-static int64_t coroutine_fn qcow_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
+static int coroutine_fn qcow_co_block_status(BlockDriverState *bs,
+                                             bool want_zero,
+                                             int64_t offset, int64_t bytes,
+                                             int64_t *pnum, int64_t *map,
+                                             BlockDriverState **file)
 {
     BDRVQcowState *s = bs->opaque;
-    int index_in_cluster, n, ret;
+    int index_in_cluster, ret;
+    int64_t n;
     uint64_t cluster_offset;
 
     qemu_co_mutex_lock(&s->lock);
-    ret = get_cluster_offset(bs, sector_num << 9, 0, 0, 0, 0, &cluster_offset);
+    ret = get_cluster_offset(bs, offset, 0, 0, 0, 0, &cluster_offset);
     qemu_co_mutex_unlock(&s->lock);
     if (ret < 0) {
         return ret;
     }
-    index_in_cluster = sector_num & (s->cluster_sectors - 1);
-    n = s->cluster_sectors - index_in_cluster;
-    if (n > nb_sectors)
-        n = nb_sectors;
+    index_in_cluster = offset & (s->cluster_size - 1);
+    n = s->cluster_size - index_in_cluster;
+    if (n > bytes) {
+        n = bytes;
+    }
     *pnum = n;
     if (!cluster_offset) {
         return 0;
@@ -548,9 +553,9 @@ static int64_t coroutine_fn qcow_co_get_block_status(BlockDriverState *bs,
     if ((cluster_offset & QCOW_OFLAG_COMPRESSED) || s->crypto) {
         return BDRV_BLOCK_DATA;
     }
-    cluster_offset |= (index_in_cluster << BDRV_SECTOR_BITS);
+    *map = cluster_offset | index_in_cluster;
     *file = bs->file->bs;
-    return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | cluster_offset;
+    return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
 }
 
 static int decompress_buffer(uint8_t *out_buf, int out_buf_size,
@@ -805,7 +810,8 @@ static void qcow_close(BlockDriverState *bs)
     error_free(s->migration_blocker);
 }
 
-static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
+static int coroutine_fn qcow_co_create_opts(const char *filename, QemuOpts *opts,
+                                            Error **errp)
 {
     int header_size, backing_filename_len, l1_size, shift, i;
     QCowHeader header;
@@ -1122,13 +1128,13 @@ static BlockDriver bdrv_qcow = {
     .bdrv_close		= qcow_close,
     .bdrv_child_perm        = bdrv_format_default_perms,
     .bdrv_reopen_prepare    = qcow_reopen_prepare,
-    .bdrv_create            = qcow_create,
+    .bdrv_co_create_opts    = qcow_co_create_opts,
     .bdrv_has_zero_init     = bdrv_has_zero_init_1,
     .supports_backing       = true,
 
     .bdrv_co_readv          = qcow_co_readv,
     .bdrv_co_writev         = qcow_co_writev,
-    .bdrv_co_get_block_status   = qcow_co_get_block_status,
+    .bdrv_co_block_status   = qcow_co_block_status,
 
     .bdrv_make_empty        = qcow_make_empty,
     .bdrv_co_pwritev_compressed = qcow_co_pwritev_compressed,
diff --git a/block/qcow2-bitmap.c b/block/qcow2-bitmap.c
index 4f6fd863ea..5127276f90 100644
--- a/block/qcow2-bitmap.c
+++ b/block/qcow2-bitmap.c
@@ -413,8 +413,8 @@ static inline void bitmap_dir_entry_to_be(Qcow2BitmapDirEntry *entry)
 
 static inline int calc_dir_entry_size(size_t name_size, size_t extra_data_size)
 {
-    return align_offset(sizeof(Qcow2BitmapDirEntry) +
-                        name_size + extra_data_size, 8);
+    int size = sizeof(Qcow2BitmapDirEntry) + name_size + extra_data_size;
+    return ROUND_UP(size, 8);
 }
 
 static inline int dir_entry_size(Qcow2BitmapDirEntry *entry)
diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c
index e406b0f3b9..98908c4264 100644
--- a/block/qcow2-cluster.c
+++ b/block/qcow2-cluster.c
@@ -126,11 +126,11 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
 
     new_l1_size2 = sizeof(uint64_t) * new_l1_size;
     new_l1_table = qemu_try_blockalign(bs->file->bs,
-                                       align_offset(new_l1_size2, 512));
+                                       ROUND_UP(new_l1_size2, 512));
     if (new_l1_table == NULL) {
         return -ENOMEM;
     }
-    memset(new_l1_table, 0, align_offset(new_l1_size2, 512));
+    memset(new_l1_table, 0, ROUND_UP(new_l1_size2, 512));
 
     if (s->l1_size) {
         memcpy(new_l1_table, s->l1_table, s->l1_size * sizeof(uint64_t));
diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c
index d46b69d7f3..126cca3276 100644
--- a/block/qcow2-refcount.c
+++ b/block/qcow2-refcount.c
@@ -1204,7 +1204,7 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
      * l1_table_offset when it is the current s->l1_table_offset! Be careful
      * when changing this! */
     if (l1_table_offset != s->l1_table_offset) {
-        l1_table = g_try_malloc0(align_offset(l1_size2, 512));
+        l1_table = g_try_malloc0(ROUND_UP(l1_size2, 512));
         if (l1_size2 && l1_table == NULL) {
             ret = -ENOMEM;
             goto fail;
@@ -2553,7 +2553,7 @@ int qcow2_check_metadata_overlap(BlockDriverState *bs, int ign, int64_t offset,
     }
 
     /* align range to test to cluster boundaries */
-    size = align_offset(offset_into_cluster(s, offset) + size, s->cluster_size);
+    size = ROUND_UP(offset_into_cluster(s, offset) + size, s->cluster_size);
     offset = start_of_cluster(s, offset);
 
     if ((chk & QCOW2_OL_ACTIVE_L1) && s->l1_size) {
diff --git a/block/qcow2-snapshot.c b/block/qcow2-snapshot.c
index 44243e0e95..cee25f582b 100644
--- a/block/qcow2-snapshot.c
+++ b/block/qcow2-snapshot.c
@@ -66,7 +66,7 @@ int qcow2_read_snapshots(BlockDriverState *bs)
 
     for(i = 0; i < s->nb_snapshots; i++) {
         /* Read statically sized part of the snapshot header */
-        offset = align_offset(offset, 8);
+        offset = ROUND_UP(offset, 8);
         ret = bdrv_pread(bs->file, offset, &h, sizeof(h));
         if (ret < 0) {
             goto fail;
@@ -155,7 +155,7 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
     offset = 0;
     for(i = 0; i < s->nb_snapshots; i++) {
         sn = s->snapshots + i;
-        offset = align_offset(offset, 8);
+        offset = ROUND_UP(offset, 8);
         offset += sizeof(h);
         offset += sizeof(extra);
         offset += strlen(sn->id_str);
@@ -215,7 +215,7 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
         assert(id_str_size <= UINT16_MAX && name_size <= UINT16_MAX);
         h.id_str_size = cpu_to_be16(id_str_size);
         h.name_size = cpu_to_be16(name_size);
-        offset = align_offset(offset, 8);
+        offset = ROUND_UP(offset, 8);
 
         ret = bdrv_pwrite(bs->file, offset, &h, sizeof(h));
         if (ret < 0) {
@@ -441,7 +441,7 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     /* The VM state isn't needed any more in the active L1 table; in fact, it
      * hurts by causing expensive COW for the next snapshot. */
     qcow2_cluster_discard(bs, qcow2_vm_state_offset(s),
-                          align_offset(sn->vm_state_size, s->cluster_size),
+                          ROUND_UP(sn->vm_state_size, s->cluster_size),
                           QCOW2_DISCARD_NEVER, false);
 
 #ifdef DEBUG_ALLOC
@@ -710,7 +710,7 @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs,
     }
     new_l1_bytes = sn->l1_size * sizeof(uint64_t);
     new_l1_table = qemu_try_blockalign(bs->file->bs,
-                                       align_offset(new_l1_bytes, 512));
+                                       ROUND_UP(new_l1_bytes, 512));
     if (new_l1_table == NULL) {
         return -ENOMEM;
     }
diff --git a/block/qcow2.c b/block/qcow2.c
index 3dd098b74f..071dc4d608 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -1377,7 +1377,7 @@ static int qcow2_do_open(BlockDriverState *bs, QDict *options, int flags,
 
     if (s->l1_size > 0) {
         s->l1_table = qemu_try_blockalign(bs->file->bs,
-            align_offset(s->l1_size * sizeof(uint64_t), 512));
+            ROUND_UP(s->l1_size * sizeof(uint64_t), 512));
         if (s->l1_table == NULL) {
             error_setg(errp, "Could not allocate L1 table");
             ret = -ENOMEM;
@@ -1668,32 +1668,34 @@ static void qcow2_join_options(QDict *options, QDict *old_options)
     }
 }
 
-static int64_t coroutine_fn qcow2_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
+static int coroutine_fn qcow2_co_block_status(BlockDriverState *bs,
+                                              bool want_zero,
+                                              int64_t offset, int64_t count,
+                                              int64_t *pnum, int64_t *map,
+                                              BlockDriverState **file)
 {
     BDRVQcow2State *s = bs->opaque;
     uint64_t cluster_offset;
     int index_in_cluster, ret;
     unsigned int bytes;
-    int64_t status = 0;
+    int status = 0;
 
-    bytes = MIN(INT_MAX, nb_sectors * BDRV_SECTOR_SIZE);
+    bytes = MIN(INT_MAX, count);
     qemu_co_mutex_lock(&s->lock);
-    ret = qcow2_get_cluster_offset(bs, sector_num << BDRV_SECTOR_BITS, &bytes,
-                                   &cluster_offset);
+    ret = qcow2_get_cluster_offset(bs, offset, &bytes, &cluster_offset);
     qemu_co_mutex_unlock(&s->lock);
     if (ret < 0) {
         return ret;
     }
 
-    *pnum = bytes >> BDRV_SECTOR_BITS;
+    *pnum = bytes;
 
     if (cluster_offset != 0 && ret != QCOW2_CLUSTER_COMPRESSED &&
         !s->crypto) {
-        index_in_cluster = sector_num & (s->cluster_sectors - 1);
-        cluster_offset |= (index_in_cluster << BDRV_SECTOR_BITS);
+        index_in_cluster = offset & (s->cluster_size - 1);
+        *map = cluster_offset | index_in_cluster;
         *file = bs->file->bs;
-        status |= BDRV_BLOCK_OFFSET_VALID | cluster_offset;
+        status |= BDRV_BLOCK_OFFSET_VALID;
     }
     if (ret == QCOW2_CLUSTER_ZERO_PLAIN || ret == QCOW2_CLUSTER_ZERO_ALLOC) {
         status |= BDRV_BLOCK_ZERO;
@@ -2638,19 +2640,19 @@ static int64_t qcow2_calc_prealloc_size(int64_t total_size,
 {
     int64_t meta_size = 0;
     uint64_t nl1e, nl2e;
-    int64_t aligned_total_size = align_offset(total_size, cluster_size);
+    int64_t aligned_total_size = ROUND_UP(total_size, cluster_size);
 
     /* header: 1 cluster */
     meta_size += cluster_size;
 
     /* total size of L2 tables */
     nl2e = aligned_total_size / cluster_size;
-    nl2e = align_offset(nl2e, cluster_size / sizeof(uint64_t));
+    nl2e = ROUND_UP(nl2e, cluster_size / sizeof(uint64_t));
     meta_size += nl2e * sizeof(uint64_t);
 
     /* total size of L1 tables */
     nl1e = nl2e * sizeof(uint64_t) / cluster_size;
-    nl1e = align_offset(nl1e, cluster_size / sizeof(uint64_t));
+    nl1e = ROUND_UP(nl1e, cluster_size / sizeof(uint64_t));
     meta_size += nl1e * sizeof(uint64_t);
 
     /* total size of refcount table and blocks */
@@ -2721,11 +2723,12 @@ static uint64_t qcow2_opt_get_refcount_bits_del(QemuOpts *opts, int version,
     return refcount_bits;
 }
 
-static int qcow2_create2(const char *filename, int64_t total_size,
-                         const char *backing_file, const char *backing_format,
-                         int flags, size_t cluster_size, PreallocMode prealloc,
-                         QemuOpts *opts, int version, int refcount_order,
-                         const char *encryptfmt, Error **errp)
+static int coroutine_fn
+qcow2_co_create2(const char *filename, int64_t total_size,
+                 const char *backing_file, const char *backing_format,
+                 int flags, size_t cluster_size, PreallocMode prealloc,
+                 QemuOpts *opts, int version, int refcount_order,
+                 const char *encryptfmt, Error **errp)
 {
     QDict *options;
 
@@ -2912,7 +2915,8 @@ out:
     return ret;
 }
 
-static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
+static int coroutine_fn qcow2_co_create_opts(const char *filename, QemuOpts *opts,
+                                             Error **errp)
 {
     char *backing_file = NULL;
     char *backing_fmt = NULL;
@@ -2993,9 +2997,9 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
 
     refcount_order = ctz32(refcount_bits);
 
-    ret = qcow2_create2(filename, size, backing_file, backing_fmt, flags,
-                        cluster_size, prealloc, opts, version, refcount_order,
-                        encryptfmt, &local_err);
+    ret = qcow2_co_create2(filename, size, backing_file, backing_fmt, flags,
+                           cluster_size, prealloc, opts, version, refcount_order,
+                           encryptfmt, &local_err);
     error_propagate(errp, local_err);
 
 finish:
@@ -3704,8 +3708,8 @@ static BlockMeasureInfo *qcow2_measure(QemuOpts *opts, BlockDriverState *in_bs,
     has_backing_file = !!optstr;
     g_free(optstr);
 
-    virtual_size = align_offset(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
-                                cluster_size);
+    virtual_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    virtual_size = ROUND_UP(virtual_size, cluster_size);
 
     /* Check that virtual disk size is valid */
     l2_tables = DIV_ROUND_UP(virtual_size / cluster_size,
@@ -3725,7 +3729,7 @@ static BlockMeasureInfo *qcow2_measure(QemuOpts *opts, BlockDriverState *in_bs,
             goto err;
         }
 
-        virtual_size = align_offset(ssize, cluster_size);
+        virtual_size = ROUND_UP(ssize, cluster_size);
 
         if (has_backing_file) {
             /* We don't how much of the backing chain is shared by the input
@@ -4348,9 +4352,9 @@ BlockDriver bdrv_qcow2 = {
     .bdrv_reopen_abort    = qcow2_reopen_abort,
     .bdrv_join_options    = qcow2_join_options,
     .bdrv_child_perm      = bdrv_format_default_perms,
-    .bdrv_create        = qcow2_create,
+    .bdrv_co_create_opts  = qcow2_co_create_opts,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
-    .bdrv_co_get_block_status = qcow2_co_get_block_status,
+    .bdrv_co_block_status = qcow2_co_block_status,
 
     .bdrv_co_preadv         = qcow2_co_preadv,
     .bdrv_co_pwritev        = qcow2_co_pwritev,
diff --git a/block/qcow2.h b/block/qcow2.h
index 883802241f..1a84cc77b0 100644
--- a/block/qcow2.h
+++ b/block/qcow2.h
@@ -480,12 +480,6 @@ static inline int offset_to_l2_slice_index(BDRVQcow2State *s, int64_t offset)
     return (offset >> s->cluster_bits) & (s->l2_slice_size - 1);
 }
 
-static inline int64_t align_offset(int64_t offset, int n)
-{
-    offset = (offset + n - 1) & ~(n - 1);
-    return offset;
-}
-
 static inline int64_t qcow2_vm_state_offset(BDRVQcow2State *s)
 {
     return (int64_t)s->l1_vm_state_index << (s->cluster_bits + s->l2_bits);
diff --git a/block/qed.c b/block/qed.c
index c6ff3ab015..72cf2f58ab 100644
--- a/block/qed.c
+++ b/block/qed.c
@@ -638,7 +638,9 @@ out:
     return ret;
 }
 
-static int bdrv_qed_create(const char *filename, QemuOpts *opts, Error **errp)
+static int coroutine_fn bdrv_qed_co_create_opts(const char *filename,
+                                                QemuOpts *opts,
+                                                Error **errp)
 {
     uint64_t image_size = 0;
     uint32_t cluster_size = QED_DEFAULT_CLUSTER_SIZE;
@@ -688,74 +690,46 @@ finish:
     return ret;
 }
 
-typedef struct {
-    BlockDriverState *bs;
-    Coroutine *co;
-    uint64_t pos;
-    int64_t status;
-    int *pnum;
-    BlockDriverState **file;
-} QEDIsAllocatedCB;
-
-/* Called with table_lock held.  */
-static void qed_is_allocated_cb(void *opaque, int ret, uint64_t offset, size_t len)
+static int coroutine_fn bdrv_qed_co_block_status(BlockDriverState *bs,
+                                                 bool want_zero,
+                                                 int64_t pos, int64_t bytes,
+                                                 int64_t *pnum, int64_t *map,
+                                                 BlockDriverState **file)
 {
-    QEDIsAllocatedCB *cb = opaque;
-    BDRVQEDState *s = cb->bs->opaque;
-    *cb->pnum = len / BDRV_SECTOR_SIZE;
+    BDRVQEDState *s = bs->opaque;
+    size_t len = MIN(bytes, SIZE_MAX);
+    int status;
+    QEDRequest request = { .l2_table = NULL };
+    uint64_t offset;
+    int ret;
+
+    qemu_co_mutex_lock(&s->table_lock);
+    ret = qed_find_cluster(s, &request, pos, &len, &offset);
+
+    *pnum = len;
     switch (ret) {
     case QED_CLUSTER_FOUND:
-        offset |= qed_offset_into_cluster(s, cb->pos);
-        cb->status = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | offset;
-        *cb->file = cb->bs->file->bs;
+        *map = offset | qed_offset_into_cluster(s, pos);
+        status = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
+        *file = bs->file->bs;
         break;
     case QED_CLUSTER_ZERO:
-        cb->status = BDRV_BLOCK_ZERO;
+        status = BDRV_BLOCK_ZERO;
         break;
     case QED_CLUSTER_L2:
     case QED_CLUSTER_L1:
-        cb->status = 0;
+        status = 0;
         break;
     default:
         assert(ret < 0);
-        cb->status = ret;
+        status = ret;
         break;
     }
 
-    if (cb->co) {
-        aio_co_wake(cb->co);
-    }
-}
-
-static int64_t coroutine_fn bdrv_qed_co_get_block_status(BlockDriverState *bs,
-                                                 int64_t sector_num,
-                                                 int nb_sectors, int *pnum,
-                                                 BlockDriverState **file)
-{
-    BDRVQEDState *s = bs->opaque;
-    size_t len = (size_t)nb_sectors * BDRV_SECTOR_SIZE;
-    QEDIsAllocatedCB cb = {
-        .bs = bs,
-        .pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE,
-        .status = BDRV_BLOCK_OFFSET_MASK,
-        .pnum = pnum,
-        .file = file,
-    };
-    QEDRequest request = { .l2_table = NULL };
-    uint64_t offset;
-    int ret;
-
-    qemu_co_mutex_lock(&s->table_lock);
-    ret = qed_find_cluster(s, &request, cb.pos, &len, &offset);
-    qed_is_allocated_cb(&cb, ret, offset, len);
-
-    /* The callback was invoked immediately */
-    assert(cb.status != BDRV_BLOCK_OFFSET_MASK);
-
     qed_unref_l2_cache_entry(request.l2_table);
     qemu_co_mutex_unlock(&s->table_lock);
 
-    return cb.status;
+    return status;
 }
 
 static BDRVQEDState *acb_to_s(QEDAIOCB *acb)
@@ -1592,9 +1566,9 @@ static BlockDriver bdrv_qed = {
     .bdrv_close               = bdrv_qed_close,
     .bdrv_reopen_prepare      = bdrv_qed_reopen_prepare,
     .bdrv_child_perm          = bdrv_format_default_perms,
-    .bdrv_create              = bdrv_qed_create,
+    .bdrv_co_create_opts      = bdrv_qed_co_create_opts,
     .bdrv_has_zero_init       = bdrv_has_zero_init_1,
-    .bdrv_co_get_block_status = bdrv_qed_co_get_block_status,
+    .bdrv_co_block_status     = bdrv_qed_co_block_status,
     .bdrv_co_readv            = bdrv_qed_co_readv,
     .bdrv_co_writev           = bdrv_qed_co_writev,
     .bdrv_co_pwrite_zeroes    = bdrv_qed_co_pwrite_zeroes,
diff --git a/block/raw-format.c b/block/raw-format.c
index ab552c0954..a378547c99 100644
--- a/block/raw-format.c
+++ b/block/raw-format.c
@@ -250,17 +250,17 @@ fail:
     return ret;
 }
 
-static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
-                                            int64_t sector_num,
-                                            int nb_sectors, int *pnum,
+static int coroutine_fn raw_co_block_status(BlockDriverState *bs,
+                                            bool want_zero, int64_t offset,
+                                            int64_t bytes, int64_t *pnum,
+                                            int64_t *map,
                                             BlockDriverState **file)
 {
     BDRVRawState *s = bs->opaque;
-    *pnum = nb_sectors;
+    *pnum = bytes;
     *file = bs->file->bs;
-    sector_num += s->offset / BDRV_SECTOR_SIZE;
-    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID |
-           (sector_num << BDRV_SECTOR_BITS);
+    *map = offset + s->offset;
+    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID;
 }
 
 static int coroutine_fn raw_co_pwrite_zeroes(BlockDriverState *bs,
@@ -396,7 +396,8 @@ static int raw_has_zero_init(BlockDriverState *bs)
     return bdrv_has_zero_init(bs->file->bs);
 }
 
-static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
+static int coroutine_fn raw_co_create_opts(const char *filename, QemuOpts *opts,
+                                           Error **errp)
 {
     return bdrv_create_file(filename, opts, errp);
 }
@@ -491,12 +492,12 @@ BlockDriver bdrv_raw = {
     .bdrv_open            = &raw_open,
     .bdrv_close           = &raw_close,
     .bdrv_child_perm      = bdrv_filter_default_perms,
-    .bdrv_create          = &raw_create,
+    .bdrv_co_create_opts  = &raw_co_create_opts,
     .bdrv_co_preadv       = &raw_co_preadv,
     .bdrv_co_pwritev      = &raw_co_pwritev,
     .bdrv_co_pwrite_zeroes = &raw_co_pwrite_zeroes,
     .bdrv_co_pdiscard     = &raw_co_pdiscard,
-    .bdrv_co_get_block_status = &raw_co_get_block_status,
+    .bdrv_co_block_status = &raw_co_block_status,
     .bdrv_truncate        = &raw_truncate,
     .bdrv_getlength       = &raw_getlength,
     .has_variable_length  = true,
diff --git a/block/rbd.c b/block/rbd.c
index 8474b0ba11..c7dd32e213 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -351,7 +351,9 @@ static QemuOptsList runtime_opts = {
     },
 };
 
-static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
+static int coroutine_fn qemu_rbd_co_create_opts(const char *filename,
+                                                QemuOpts *opts,
+                                                Error **errp)
 {
     Error *local_err = NULL;
     int64_t bytes = 0;
@@ -1132,7 +1134,7 @@ static BlockDriver bdrv_rbd = {
     .bdrv_file_open         = qemu_rbd_open,
     .bdrv_close             = qemu_rbd_close,
     .bdrv_reopen_prepare    = qemu_rbd_reopen_prepare,
-    .bdrv_create            = qemu_rbd_create,
+    .bdrv_co_create_opts    = qemu_rbd_co_create_opts,
     .bdrv_has_zero_init     = bdrv_has_zero_init_1,
     .bdrv_get_info          = qemu_rbd_getinfo,
     .create_opts            = &qemu_rbd_create_opts,
diff --git a/block/sheepdog.c b/block/sheepdog.c
index 215223053b..d8c10b7cac 100644
--- a/block/sheepdog.c
+++ b/block/sheepdog.c
@@ -1959,8 +1959,8 @@ static int parse_block_size_shift(BDRVSheepdogState *s, QemuOpts *opt)
     return 0;
 }
 
-static int sd_create(const char *filename, QemuOpts *opts,
-                     Error **errp)
+static int coroutine_fn sd_co_create_opts(const char *filename, QemuOpts *opts,
+                                          Error **errp)
 {
     Error *err = NULL;
     int ret = 0;
@@ -3004,19 +3004,19 @@ static coroutine_fn int sd_co_pdiscard(BlockDriverState *bs, int64_t offset,
     return acb.ret;
 }
 
-static coroutine_fn int64_t
-sd_co_get_block_status(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
-                       int *pnum, BlockDriverState **file)
+static coroutine_fn int
+sd_co_block_status(BlockDriverState *bs, bool want_zero, int64_t offset,
+                   int64_t bytes, int64_t *pnum, int64_t *map,
+                   BlockDriverState **file)
 {
     BDRVSheepdogState *s = bs->opaque;
     SheepdogInode *inode = &s->inode;
     uint32_t object_size = (UINT32_C(1) << inode->block_size_shift);
-    uint64_t offset = sector_num * BDRV_SECTOR_SIZE;
     unsigned long start = offset / object_size,
-                  end = DIV_ROUND_UP((sector_num + nb_sectors) *
-                                     BDRV_SECTOR_SIZE, object_size);
+                  end = DIV_ROUND_UP(offset + bytes, object_size);
     unsigned long idx;
-    int64_t ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | offset;
+    *map = offset;
+    int ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
 
     for (idx = start; idx < end; idx++) {
         if (inode->data_vdi_id[idx] == 0) {
@@ -3033,9 +3033,9 @@ sd_co_get_block_status(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
         }
     }
 
-    *pnum = (idx - start) * object_size / BDRV_SECTOR_SIZE;
-    if (*pnum > nb_sectors) {
-        *pnum = nb_sectors;
+    *pnum = (idx - start) * object_size;
+    if (*pnum > bytes) {
+        *pnum = bytes;
     }
     if (ret > 0 && ret & BDRV_BLOCK_OFFSET_VALID) {
         *file = bs;
@@ -3103,7 +3103,7 @@ static BlockDriver bdrv_sheepdog = {
     .bdrv_reopen_commit           = sd_reopen_commit,
     .bdrv_reopen_abort            = sd_reopen_abort,
     .bdrv_close                   = sd_close,
-    .bdrv_create                  = sd_create,
+    .bdrv_co_create_opts          = sd_co_create_opts,
     .bdrv_has_zero_init           = bdrv_has_zero_init_1,
     .bdrv_getlength               = sd_getlength,
     .bdrv_get_allocated_file_size = sd_get_allocated_file_size,
@@ -3113,7 +3113,7 @@ static BlockDriver bdrv_sheepdog = {
     .bdrv_co_writev               = sd_co_writev,
     .bdrv_co_flush_to_disk        = sd_co_flush_to_disk,
     .bdrv_co_pdiscard             = sd_co_pdiscard,
-    .bdrv_co_get_block_status     = sd_co_get_block_status,
+    .bdrv_co_block_status         = sd_co_block_status,
 
     .bdrv_snapshot_create         = sd_snapshot_create,
     .bdrv_snapshot_goto           = sd_snapshot_goto,
@@ -3139,7 +3139,7 @@ static BlockDriver bdrv_sheepdog_tcp = {
     .bdrv_reopen_commit           = sd_reopen_commit,
     .bdrv_reopen_abort            = sd_reopen_abort,
     .bdrv_close                   = sd_close,
-    .bdrv_create                  = sd_create,
+    .bdrv_co_create_opts          = sd_co_create_opts,
     .bdrv_has_zero_init           = bdrv_has_zero_init_1,
     .bdrv_getlength               = sd_getlength,
     .bdrv_get_allocated_file_size = sd_get_allocated_file_size,
@@ -3149,7 +3149,7 @@ static BlockDriver bdrv_sheepdog_tcp = {
     .bdrv_co_writev               = sd_co_writev,
     .bdrv_co_flush_to_disk        = sd_co_flush_to_disk,
     .bdrv_co_pdiscard             = sd_co_pdiscard,
-    .bdrv_co_get_block_status     = sd_co_get_block_status,
+    .bdrv_co_block_status         = sd_co_block_status,
 
     .bdrv_snapshot_create         = sd_snapshot_create,
     .bdrv_snapshot_goto           = sd_snapshot_goto,
@@ -3175,7 +3175,7 @@ static BlockDriver bdrv_sheepdog_unix = {
     .bdrv_reopen_commit           = sd_reopen_commit,
     .bdrv_reopen_abort            = sd_reopen_abort,
     .bdrv_close                   = sd_close,
-    .bdrv_create                  = sd_create,
+    .bdrv_co_create_opts          = sd_co_create_opts,
     .bdrv_has_zero_init           = bdrv_has_zero_init_1,
     .bdrv_getlength               = sd_getlength,
     .bdrv_get_allocated_file_size = sd_get_allocated_file_size,
@@ -3185,7 +3185,7 @@ static BlockDriver bdrv_sheepdog_unix = {
     .bdrv_co_writev               = sd_co_writev,
     .bdrv_co_flush_to_disk        = sd_co_flush_to_disk,
     .bdrv_co_pdiscard             = sd_co_pdiscard,
-    .bdrv_co_get_block_status     = sd_co_get_block_status,
+    .bdrv_co_block_status         = sd_co_block_status,
 
     .bdrv_snapshot_create         = sd_snapshot_create,
     .bdrv_snapshot_goto           = sd_snapshot_goto,
diff --git a/block/ssh.c b/block/ssh.c
index b11d4c5e86..ff9929497d 100644
--- a/block/ssh.c
+++ b/block/ssh.c
@@ -803,6 +803,33 @@ static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags,
     return ret;
 }
 
+/* Note: This is a blocking operation */
+static int ssh_grow_file(BDRVSSHState *s, int64_t offset, Error **errp)
+{
+    ssize_t ret;
+    char c[1] = { '\0' };
+    int was_blocking = libssh2_session_get_blocking(s->session);
+
+    /* offset must be strictly greater than the current size so we do
+     * not overwrite anything */
+    assert(offset > 0 && offset > s->attrs.filesize);
+
+    libssh2_session_set_blocking(s->session, 1);
+
+    libssh2_sftp_seek64(s->sftp_handle, offset - 1);
+    ret = libssh2_sftp_write(s->sftp_handle, c, 1);
+
+    libssh2_session_set_blocking(s->session, was_blocking);
+
+    if (ret < 0) {
+        sftp_error_setg(errp, s, "Failed to grow file");
+        return -EIO;
+    }
+
+    s->attrs.filesize = offset;
+    return 0;
+}
+
 static QemuOptsList ssh_create_opts = {
     .name = "ssh-create-opts",
     .head = QTAILQ_HEAD_INITIALIZER(ssh_create_opts.head),
@@ -816,14 +843,13 @@ static QemuOptsList ssh_create_opts = {
     }
 };
 
-static int ssh_create(const char *filename, QemuOpts *opts, Error **errp)
+static int coroutine_fn ssh_co_create_opts(const char *filename, QemuOpts *opts,
+                                           Error **errp)
 {
     int r, ret;
     int64_t total_size = 0;
     QDict *uri_options = NULL;
     BDRVSSHState s;
-    ssize_t r2;
-    char c[1] = { '\0' };
 
     ssh_state_init(&s);
 
@@ -849,14 +875,10 @@ static int ssh_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     if (total_size > 0) {
-        libssh2_sftp_seek64(s.sftp_handle, total_size-1);
-        r2 = libssh2_sftp_write(s.sftp_handle, c, 1);
-        if (r2 < 0) {
-            sftp_error_setg(errp, &s, "truncate failed");
-            ret = -EINVAL;
+        ret = ssh_grow_file(&s, total_size, errp);
+        if (ret < 0) {
             goto out;
         }
-        s.attrs.filesize = total_size;
     }
 
     ret = 0;
@@ -1198,18 +1220,42 @@ static int64_t ssh_getlength(BlockDriverState *bs)
     return length;
 }
 
+static int ssh_truncate(BlockDriverState *bs, int64_t offset,
+                        PreallocMode prealloc, Error **errp)
+{
+    BDRVSSHState *s = bs->opaque;
+
+    if (prealloc != PREALLOC_MODE_OFF) {
+        error_setg(errp, "Unsupported preallocation mode '%s'",
+                   PreallocMode_str(prealloc));
+        return -ENOTSUP;
+    }
+
+    if (offset < s->attrs.filesize) {
+        error_setg(errp, "ssh driver does not support shrinking files");
+        return -ENOTSUP;
+    }
+
+    if (offset == s->attrs.filesize) {
+        return 0;
+    }
+
+    return ssh_grow_file(s, offset, errp);
+}
+
 static BlockDriver bdrv_ssh = {
     .format_name                  = "ssh",
     .protocol_name                = "ssh",
     .instance_size                = sizeof(BDRVSSHState),
     .bdrv_parse_filename          = ssh_parse_filename,
     .bdrv_file_open               = ssh_file_open,
-    .bdrv_create                  = ssh_create,
+    .bdrv_co_create_opts          = ssh_co_create_opts,
     .bdrv_close                   = ssh_close,
     .bdrv_has_zero_init           = ssh_has_zero_init,
     .bdrv_co_readv                = ssh_co_readv,
     .bdrv_co_writev               = ssh_co_writev,
     .bdrv_getlength               = ssh_getlength,
+    .bdrv_truncate                = ssh_truncate,
     .bdrv_co_flush_to_disk        = ssh_co_flush,
     .create_opts                  = &ssh_create_opts,
 };
diff --git a/block/throttle.c b/block/throttle.c
index 495f88c752..5f4d43d0fc 100644
--- a/block/throttle.c
+++ b/block/throttle.c
@@ -240,7 +240,7 @@ static BlockDriver bdrv_throttle = {
     .bdrv_reopen_prepare                =   throttle_reopen_prepare,
     .bdrv_reopen_commit                 =   throttle_reopen_commit,
     .bdrv_reopen_abort                  =   throttle_reopen_abort,
-    .bdrv_co_get_block_status           =   bdrv_co_get_block_status_from_file,
+    .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,
diff --git a/block/vdi.c b/block/vdi.c
index fc1c614cb1..68592cc58d 100644
--- a/block/vdi.c
+++ b/block/vdi.c
@@ -87,12 +87,18 @@
 #define DEFAULT_CLUSTER_SIZE (1 * MiB)
 
 #if defined(CONFIG_VDI_DEBUG)
-#define logout(fmt, ...) \
-                fprintf(stderr, "vdi\t%-24s" fmt, __func__, ##__VA_ARGS__)
+#define VDI_DEBUG 1
 #else
-#define logout(fmt, ...) ((void)0)
+#define VDI_DEBUG 0
 #endif
 
+#define logout(fmt, ...) \
+    do {                                                                \
+        if (VDI_DEBUG) {                                                \
+            fprintf(stderr, "vdi\t%-24s" fmt, __func__, ##__VA_ARGS__); \
+        }                                                               \
+    } while (0)
+
 /* Image signature. */
 #define VDI_SIGNATURE 0xbeda107f
 
@@ -166,8 +172,6 @@ typedef struct {
     uint32_t *bmap;
     /* Size of block (bytes). */
     uint32_t block_size;
-    /* Size of block (sectors). */
-    uint32_t block_sectors;
     /* First sector of block map. */
     uint32_t bmap_sector;
     /* VDI header (converted to host endianness). */
@@ -457,7 +461,6 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
     bs->total_sectors = header.disk_size / SECTOR_SIZE;
 
     s->block_size = header.block_size;
-    s->block_sectors = header.block_size / SECTOR_SIZE;
     s->bmap_sector = header.offset_bmap / SECTOR_SIZE;
     s->header = header;
 
@@ -503,33 +506,29 @@ static int vdi_reopen_prepare(BDRVReopenState *state,
     return 0;
 }
 
-static int64_t coroutine_fn vdi_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
+static int coroutine_fn vdi_co_block_status(BlockDriverState *bs,
+                                            bool want_zero,
+                                            int64_t offset, int64_t bytes,
+                                            int64_t *pnum, int64_t *map,
+                                            BlockDriverState **file)
 {
-    /* TODO: Check for too large sector_num (in bdrv_is_allocated or here). */
     BDRVVdiState *s = (BDRVVdiState *)bs->opaque;
-    size_t bmap_index = sector_num / s->block_sectors;
-    size_t sector_in_block = sector_num % s->block_sectors;
-    int n_sectors = s->block_sectors - sector_in_block;
+    size_t bmap_index = offset / s->block_size;
+    size_t index_in_block = offset % s->block_size;
     uint32_t bmap_entry = le32_to_cpu(s->bmap[bmap_index]);
-    uint64_t offset;
     int result;
 
-    logout("%p, %" PRId64 ", %d, %p\n", bs, sector_num, nb_sectors, pnum);
-    if (n_sectors > nb_sectors) {
-        n_sectors = nb_sectors;
-    }
-    *pnum = n_sectors;
+    logout("%p, %" PRId64 ", %" PRId64 ", %p\n", bs, offset, bytes, pnum);
+    *pnum = MIN(s->block_size - index_in_block, bytes);
     result = VDI_IS_ALLOCATED(bmap_entry);
     if (!result) {
         return 0;
     }
 
-    offset = s->header.offset_data +
-                              (uint64_t)bmap_entry * s->block_size +
-                              sector_in_block * SECTOR_SIZE;
+    *map = s->header.offset_data + (uint64_t)bmap_entry * s->block_size +
+        index_in_block;
     *file = bs->file->bs;
-    return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | offset;
+    return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
 }
 
 static int coroutine_fn
@@ -717,7 +716,8 @@ nonallocating_write:
     return ret;
 }
 
-static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
+static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts,
+                                           Error **errp)
 {
     int ret = 0;
     uint64_t bytes = 0;
@@ -895,9 +895,9 @@ static BlockDriver bdrv_vdi = {
     .bdrv_close = vdi_close,
     .bdrv_reopen_prepare = vdi_reopen_prepare,
     .bdrv_child_perm          = bdrv_format_default_perms,
-    .bdrv_create = vdi_create,
+    .bdrv_co_create_opts = vdi_co_create_opts,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
-    .bdrv_co_get_block_status = vdi_co_get_block_status,
+    .bdrv_co_block_status = vdi_co_block_status,
     .bdrv_make_empty = vdi_make_empty,
 
     .bdrv_co_preadv     = vdi_co_preadv,
diff --git a/block/vhdx.c b/block/vhdx.c
index c449c5dcfd..3fbff5048b 100644
--- a/block/vhdx.c
+++ b/block/vhdx.c
@@ -1792,7 +1792,8 @@ exit:
  *    .---- ~ ----------- ~ ------------ ~ ---------------- ~ -----------.
  *   1MB
  */
-static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
+static int coroutine_fn vhdx_co_create_opts(const char *filename, QemuOpts *opts,
+                                            Error **errp)
 {
     int ret = 0;
     uint64_t image_size = (uint64_t) 2 * GiB;
@@ -2003,7 +2004,7 @@ static BlockDriver bdrv_vhdx = {
     .bdrv_child_perm        = bdrv_format_default_perms,
     .bdrv_co_readv          = vhdx_co_readv,
     .bdrv_co_writev         = vhdx_co_writev,
-    .bdrv_create            = vhdx_create,
+    .bdrv_co_create_opts    = vhdx_co_create_opts,
     .bdrv_get_info          = vhdx_get_info,
     .bdrv_check             = vhdx_check,
     .bdrv_has_zero_init     = bdrv_has_zero_init_1,
diff --git a/block/vmdk.c b/block/vmdk.c
index ef15ddbfd3..67342ed69b 100644
--- a/block/vmdk.c
+++ b/block/vmdk.c
@@ -1304,33 +1304,27 @@ static inline uint64_t vmdk_find_offset_in_cluster(VmdkExtent *extent,
     return extent_relative_offset % cluster_size;
 }
 
-static inline uint64_t vmdk_find_index_in_cluster(VmdkExtent *extent,
-                                                  int64_t sector_num)
-{
-    uint64_t offset;
-    offset = vmdk_find_offset_in_cluster(extent, sector_num * BDRV_SECTOR_SIZE);
-    return offset / BDRV_SECTOR_SIZE;
-}
-
-static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
+static int coroutine_fn vmdk_co_block_status(BlockDriverState *bs,
+                                             bool want_zero,
+                                             int64_t offset, int64_t bytes,
+                                             int64_t *pnum, int64_t *map,
+                                             BlockDriverState **file)
 {
     BDRVVmdkState *s = bs->opaque;
     int64_t index_in_cluster, n, ret;
-    uint64_t offset;
+    uint64_t cluster_offset;
     VmdkExtent *extent;
 
-    extent = find_extent(s, sector_num, NULL);
+    extent = find_extent(s, offset >> BDRV_SECTOR_BITS, NULL);
     if (!extent) {
-        return 0;
+        return -EIO;
     }
     qemu_co_mutex_lock(&s->lock);
-    ret = get_cluster_offset(bs, extent, NULL,
-                             sector_num * 512, false, &offset,
+    ret = get_cluster_offset(bs, extent, NULL, offset, false, &cluster_offset,
                              0, 0);
     qemu_co_mutex_unlock(&s->lock);
 
-    index_in_cluster = vmdk_find_index_in_cluster(extent, sector_num);
+    index_in_cluster = vmdk_find_offset_in_cluster(extent, offset);
     switch (ret) {
     case VMDK_ERROR:
         ret = -EIO;
@@ -1345,18 +1339,14 @@ static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
         ret = BDRV_BLOCK_DATA;
         if (!extent->compressed) {
             ret |= BDRV_BLOCK_OFFSET_VALID;
-            ret |= (offset + (index_in_cluster << BDRV_SECTOR_BITS))
-                    & BDRV_BLOCK_OFFSET_MASK;
+            *map = cluster_offset + index_in_cluster;
         }
         *file = extent->file->bs;
         break;
     }
 
-    n = extent->cluster_sectors - index_in_cluster;
-    if (n > nb_sectors) {
-        n = nb_sectors;
-    }
-    *pnum = n;
+    n = extent->cluster_sectors * BDRV_SECTOR_SIZE - index_in_cluster;
+    *pnum = MIN(n, bytes);
     return ret;
 }
 
@@ -1892,7 +1882,8 @@ static int filename_decompose(const char *filename, char *path, char *prefix,
     return VMDK_OK;
 }
 
-static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
+static int coroutine_fn vmdk_co_create_opts(const char *filename, QemuOpts *opts,
+                                            Error **errp)
 {
     int idx = 0;
     BlockBackend *new_blk = NULL;
@@ -2408,9 +2399,9 @@ static BlockDriver bdrv_vmdk = {
     .bdrv_co_pwritev_compressed   = vmdk_co_pwritev_compressed,
     .bdrv_co_pwrite_zeroes        = vmdk_co_pwrite_zeroes,
     .bdrv_close                   = vmdk_close,
-    .bdrv_create                  = vmdk_create,
+    .bdrv_co_create_opts          = vmdk_co_create_opts,
     .bdrv_co_flush_to_disk        = vmdk_co_flush,
-    .bdrv_co_get_block_status     = vmdk_co_get_block_status,
+    .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,
     .bdrv_get_specific_info       = vmdk_get_specific_info,
diff --git a/block/vpc.c b/block/vpc.c
index cfa5144e86..b2e2b9ebd4 100644
--- a/block/vpc.c
+++ b/block/vpc.c
@@ -706,53 +706,54 @@ fail:
     return ret;
 }
 
-static int64_t coroutine_fn vpc_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
+static int coroutine_fn vpc_co_block_status(BlockDriverState *bs,
+                                            bool want_zero,
+                                            int64_t offset, int64_t bytes,
+                                            int64_t *pnum, int64_t *map,
+                                            BlockDriverState **file)
 {
     BDRVVPCState *s = bs->opaque;
     VHDFooter *footer = (VHDFooter*) s->footer_buf;
-    int64_t start, offset;
+    int64_t image_offset;
     bool allocated;
-    int64_t ret;
-    int n;
+    int ret;
+    int64_t n;
 
     if (be32_to_cpu(footer->type) == VHD_FIXED) {
-        *pnum = nb_sectors;
+        *pnum = bytes;
+        *map = offset;
         *file = bs->file->bs;
-        return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID |
-               (sector_num << BDRV_SECTOR_BITS);
+        return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID;
     }
 
     qemu_co_mutex_lock(&s->lock);
 
-    offset = get_image_offset(bs, sector_num << BDRV_SECTOR_BITS, false, NULL);
-    start = offset;
-    allocated = (offset != -1);
+    image_offset = get_image_offset(bs, offset, false, NULL);
+    allocated = (image_offset != -1);
     *pnum = 0;
     ret = 0;
 
     do {
         /* All sectors in a block are contiguous (without using the bitmap) */
-        n = ROUND_UP(sector_num + 1, s->block_size / BDRV_SECTOR_SIZE)
-          - sector_num;
-        n = MIN(n, nb_sectors);
+        n = ROUND_UP(offset + 1, s->block_size) - offset;
+        n = MIN(n, bytes);
 
         *pnum += n;
-        sector_num += n;
-        nb_sectors -= n;
+        offset += n;
+        bytes -= n;
         /* *pnum can't be greater than one block for allocated
          * sectors since there is always a bitmap in between. */
         if (allocated) {
             *file = bs->file->bs;
-            ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | start;
+            *map = image_offset;
+            ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
             break;
         }
-        if (nb_sectors == 0) {
+        if (bytes == 0) {
             break;
         }
-        offset = get_image_offset(bs, sector_num << BDRV_SECTOR_BITS, false,
-                                  NULL);
-    } while (offset == -1);
+        image_offset = get_image_offset(bs, offset, false, NULL);
+    } while (image_offset == -1);
 
     qemu_co_mutex_unlock(&s->lock);
     return ret;
@@ -896,7 +897,8 @@ static int create_fixed_disk(BlockBackend *blk, uint8_t *buf,
     return ret;
 }
 
-static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
+static int coroutine_fn vpc_co_create_opts(const char *filename, QemuOpts *opts,
+                                           Error **errp)
 {
     uint8_t buf[1024];
     VHDFooter *footer = (VHDFooter *) buf;
@@ -1094,11 +1096,11 @@ static BlockDriver bdrv_vpc = {
     .bdrv_close             = vpc_close,
     .bdrv_reopen_prepare    = vpc_reopen_prepare,
     .bdrv_child_perm        = bdrv_format_default_perms,
-    .bdrv_create            = vpc_create,
+    .bdrv_co_create_opts    = vpc_co_create_opts,
 
     .bdrv_co_preadv             = vpc_co_preadv,
     .bdrv_co_pwritev            = vpc_co_pwritev,
-    .bdrv_co_get_block_status   = vpc_co_get_block_status,
+    .bdrv_co_block_status       = vpc_co_block_status,
 
     .bdrv_get_info          = vpc_get_info,
 
diff --git a/block/vvfat.c b/block/vvfat.c
index 7e06ebacf6..4a17a49e12 100644
--- a/block/vvfat.c
+++ b/block/vvfat.c
@@ -3088,15 +3088,13 @@ vvfat_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
     return ret;
 }
 
-static int64_t coroutine_fn vvfat_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *n, BlockDriverState **file)
+static int coroutine_fn vvfat_co_block_status(BlockDriverState *bs,
+                                              bool want_zero, int64_t offset,
+                                              int64_t bytes, int64_t *n,
+                                              int64_t *map,
+                                              BlockDriverState **file)
 {
-    *n = bs->total_sectors - sector_num;
-    if (*n > nb_sectors) {
-        *n = nb_sectors;
-    } else if (*n < 0) {
-        return 0;
-    }
+    *n = bytes;
     return BDRV_BLOCK_DATA;
 }
 
@@ -3257,7 +3255,7 @@ static BlockDriver bdrv_vvfat = {
 
     .bdrv_co_preadv         = vvfat_co_preadv,
     .bdrv_co_pwritev        = vvfat_co_pwritev,
-    .bdrv_co_get_block_status = vvfat_co_get_block_status,
+    .bdrv_co_block_status   = vvfat_co_block_status,
 };
 
 static void bdrv_vvfat_init(void)