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

Block layer patches

# gpg: Signature made Mon 09 Jan 2017 13:43:44 GMT
# gpg:                using RSA key 0x7F09B272C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* remotes/kevin/tags/for-upstream:
  block: Rename raw-{posix,win32} to file-*.c
  block: Rename raw_bsd to raw-format.c
  blkverify: Implement bdrv_co_preadv/pwritev/flush
  blkdebug: Implement bdrv_co_preadv/pwritev/flush
  quorum: Clean up quorum_aio_get()
  quorum: Inline quorum_fifo_aio_cb()
  quorum: Implement .bdrv_co_preadv/pwritev()
  quorum: Avoid bdrv_aio_writev() for rewrites
  quorum: Inline quorum_aio_cb()
  quorum: Do cleanup in caller coroutine
  quorum: Implement .bdrv_co_readv/writev
  quorum: Remove s from quorum_aio_get() arguments
  coroutine: Introduce qemu_coroutine_enter_if_inactive()
  qemu-img: fix in-flight count for qemu-img bench

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

16 files changed, 392 insertions, 369 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index ed884b2f19..1444b26dc0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1718,9 +1718,9 @@ L: qemu-block@nongnu.org
 S: Supported
 F: block/linux-aio.c
 F: include/block/raw-aio.h
-F: block/raw-posix.c
-F: block/raw-win32.c
-F: block/raw_bsd.c
+F: block/raw-format.c
+F: block/file-posix.c
+F: block/file-win32.c
 F: block/win32-aio.c
 
 qcow2
diff --git a/block/Makefile.objs b/block/Makefile.objs
index 67a036a1df..0b8fd06f27 100644
--- a/block/Makefile.objs
+++ b/block/Makefile.objs
@@ -1,4 +1,4 @@
-block-obj-y += raw_bsd.o qcow.o vdi.o vmdk.o cloop.o bochs.o vpc.o vvfat.o dmg.o
+block-obj-y += raw-format.o qcow.o vdi.o vmdk.o cloop.o bochs.o vpc.o vvfat.o dmg.o
 block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
 block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
 block-obj-y += qed-check.o
@@ -6,8 +6,8 @@ block-obj-y += vhdx.o vhdx-endian.o vhdx-log.o
 block-obj-y += quorum.o
 block-obj-y += parallels.o blkdebug.o blkverify.o blkreplay.o
 block-obj-y += block-backend.o snapshot.o qapi.o
-block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
-block-obj-$(CONFIG_POSIX) += raw-posix.o
+block-obj-$(CONFIG_WIN32) += file-win32.o win32-aio.o
+block-obj-$(CONFIG_POSIX) += file-posix.o
 block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
 block-obj-y += null.o mirror.o commit.o io.o
 block-obj-y += throttle-groups.o
diff --git a/block/blkdebug.c b/block/blkdebug.c
index 4127571454..acccf85666 100644
--- a/block/blkdebug.c
+++ b/block/blkdebug.c
@@ -58,10 +58,6 @@ typedef struct BlkdebugSuspendedReq {
     QLIST_ENTRY(BlkdebugSuspendedReq) next;
 } BlkdebugSuspendedReq;
 
-static const AIOCBInfo blkdebug_aiocb_info = {
-    .aiocb_size    = sizeof(BlkdebugAIOCB),
-};
-
 enum {
     ACTION_INJECT_ERROR,
     ACTION_SET_STATE,
@@ -77,7 +73,7 @@ typedef struct BlkdebugRule {
             int error;
             int immediately;
             int once;
-            int64_t sector;
+            int64_t offset;
         } inject;
         struct {
             int new_state;
@@ -174,6 +170,7 @@ static int add_rule(void *opaque, QemuOpts *opts, Error **errp)
     const char* event_name;
     BlkdebugEvent event;
     struct BlkdebugRule *rule;
+    int64_t sector;
 
     /* Find the right event for the rule */
     event_name = qemu_opt_get(opts, "event");
@@ -200,7 +197,9 @@ static int add_rule(void *opaque, QemuOpts *opts, Error **errp)
         rule->options.inject.once  = qemu_opt_get_bool(opts, "once", 0);
         rule->options.inject.immediately =
             qemu_opt_get_bool(opts, "immediately", 0);
-        rule->options.inject.sector = qemu_opt_get_number(opts, "sector", -1);
+        sector = qemu_opt_get_number(opts, "sector", -1);
+        rule->options.inject.offset =
+            sector == -1 ? -1 : sector * BDRV_SECTOR_SIZE;
         break;
 
     case ACTION_SET_STATE:
@@ -408,17 +407,14 @@ out:
 
 static void error_callback_bh(void *opaque)
 {
-    struct BlkdebugAIOCB *acb = opaque;
-    acb->common.cb(acb->common.opaque, acb->ret);
-    qemu_aio_unref(acb);
+    Coroutine *co = opaque;
+    qemu_coroutine_enter(co);
 }
 
-static BlockAIOCB *inject_error(BlockDriverState *bs,
-    BlockCompletionFunc *cb, void *opaque, BlkdebugRule *rule)
+static int inject_error(BlockDriverState *bs, BlkdebugRule *rule)
 {
     BDRVBlkdebugState *s = bs->opaque;
     int error = rule->options.inject.error;
-    struct BlkdebugAIOCB *acb;
     bool immediately = rule->options.inject.immediately;
 
     if (rule->options.inject.once) {
@@ -426,81 +422,79 @@ static BlockAIOCB *inject_error(BlockDriverState *bs,
         remove_rule(rule);
     }
 
-    if (immediately) {
-        return NULL;
+    if (!immediately) {
+        aio_bh_schedule_oneshot(bdrv_get_aio_context(bs), error_callback_bh,
+                                qemu_coroutine_self());
+        qemu_coroutine_yield();
     }
 
-    acb = qemu_aio_get(&blkdebug_aiocb_info, bs, cb, opaque);
-    acb->ret = -error;
-
-    aio_bh_schedule_oneshot(bdrv_get_aio_context(bs), error_callback_bh, acb);
-
-    return &acb->common;
+    return -error;
 }
 
-static BlockAIOCB *blkdebug_aio_readv(BlockDriverState *bs,
-    int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-    BlockCompletionFunc *cb, void *opaque)
+static int coroutine_fn
+blkdebug_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
+                   QEMUIOVector *qiov, int flags)
 {
     BDRVBlkdebugState *s = bs->opaque;
     BlkdebugRule *rule = NULL;
 
     QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
-        if (rule->options.inject.sector == -1 ||
-            (rule->options.inject.sector >= sector_num &&
-             rule->options.inject.sector < sector_num + nb_sectors)) {
+        uint64_t inject_offset = rule->options.inject.offset;
+
+        if (inject_offset == -1 ||
+            (inject_offset >= offset && inject_offset < offset + bytes))
+        {
             break;
         }
     }
 
     if (rule && rule->options.inject.error) {
-        return inject_error(bs, cb, opaque, rule);
+        return inject_error(bs, rule);
     }
 
-    return bdrv_aio_readv(bs->file, sector_num, qiov, nb_sectors,
-                          cb, opaque);
+    return bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
 }
 
-static BlockAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
-    int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-    BlockCompletionFunc *cb, void *opaque)
+static int coroutine_fn
+blkdebug_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
+                    QEMUIOVector *qiov, int flags)
 {
     BDRVBlkdebugState *s = bs->opaque;
     BlkdebugRule *rule = NULL;
 
     QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
-        if (rule->options.inject.sector == -1 ||
-            (rule->options.inject.sector >= sector_num &&
-             rule->options.inject.sector < sector_num + nb_sectors)) {
+        uint64_t inject_offset = rule->options.inject.offset;
+
+        if (inject_offset == -1 ||
+            (inject_offset >= offset && inject_offset < offset + bytes))
+        {
             break;
         }
     }
 
     if (rule && rule->options.inject.error) {
-        return inject_error(bs, cb, opaque, rule);
+        return inject_error(bs, rule);
     }
 
-    return bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors,
-                           cb, opaque);
+    return bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
 }
 
-static BlockAIOCB *blkdebug_aio_flush(BlockDriverState *bs,
-    BlockCompletionFunc *cb, void *opaque)
+static int blkdebug_co_flush(BlockDriverState *bs)
 {
     BDRVBlkdebugState *s = bs->opaque;
     BlkdebugRule *rule = NULL;
 
     QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
-        if (rule->options.inject.sector == -1) {
+        if (rule->options.inject.offset == -1) {
             break;
         }
     }
 
     if (rule && rule->options.inject.error) {
-        return inject_error(bs, cb, opaque, rule);
+        return inject_error(bs, rule);
     }
 
-    return bdrv_aio_flush(bs->file->bs, cb, opaque);
+    return bdrv_co_flush(bs->file->bs);
 }
 
 
@@ -752,9 +746,9 @@ static BlockDriver bdrv_blkdebug = {
     .bdrv_refresh_filename  = blkdebug_refresh_filename,
     .bdrv_refresh_limits    = blkdebug_refresh_limits,
 
-    .bdrv_aio_readv         = blkdebug_aio_readv,
-    .bdrv_aio_writev        = blkdebug_aio_writev,
-    .bdrv_aio_flush         = blkdebug_aio_flush,
+    .bdrv_co_preadv         = blkdebug_co_preadv,
+    .bdrv_co_pwritev        = blkdebug_co_pwritev,
+    .bdrv_co_flush_to_disk  = blkdebug_co_flush,
 
     .bdrv_debug_event           = blkdebug_debug_event,
     .bdrv_debug_breakpoint      = blkdebug_debug_breakpoint,
diff --git a/block/blkverify.c b/block/blkverify.c
index 28f9af6dba..43a940c2f5 100644
--- a/block/blkverify.c
+++ b/block/blkverify.c
@@ -19,38 +19,36 @@ typedef struct {
     BdrvChild *test_file;
 } BDRVBlkverifyState;
 
-typedef struct BlkverifyAIOCB BlkverifyAIOCB;
-struct BlkverifyAIOCB {
-    BlockAIOCB common;
+typedef struct BlkverifyRequest {
+    Coroutine *co;
+    BlockDriverState *bs;
 
     /* Request metadata */
     bool is_write;
-    int64_t sector_num;
-    int nb_sectors;
+    uint64_t offset;
+    uint64_t bytes;
+    int flags;
 
-    int ret;                    /* first completed request's result */
-    unsigned int done;          /* completion counter */
+    int (*request_fn)(BdrvChild *, int64_t, unsigned int, QEMUIOVector *,
+                      BdrvRequestFlags);
 
-    QEMUIOVector *qiov;         /* user I/O vector */
-    QEMUIOVector raw_qiov;      /* cloned I/O vector for raw file */
-    void *buf;                  /* buffer for raw file I/O */
+    int ret;                    /* test image result */
+    int raw_ret;                /* raw image result */
 
-    void (*verify)(BlkverifyAIOCB *acb);
-};
+    unsigned int done;          /* completion counter */
 
-static const AIOCBInfo blkverify_aiocb_info = {
-    .aiocb_size         = sizeof(BlkverifyAIOCB),
-};
+    QEMUIOVector *qiov;         /* user I/O vector */
+    QEMUIOVector *raw_qiov;     /* cloned I/O vector for raw file */
+} BlkverifyRequest;
 
-static void GCC_FMT_ATTR(2, 3) blkverify_err(BlkverifyAIOCB *acb,
+static void GCC_FMT_ATTR(2, 3) blkverify_err(BlkverifyRequest *r,
                                              const char *fmt, ...)
 {
     va_list ap;
 
     va_start(ap, fmt);
-    fprintf(stderr, "blkverify: %s sector_num=%" PRId64 " nb_sectors=%d ",
-            acb->is_write ? "write" : "read", acb->sector_num,
-            acb->nb_sectors);
+    fprintf(stderr, "blkverify: %s offset=%" PRId64 " bytes=%" PRId64 " ",
+            r->is_write ? "write" : "read", r->offset, r->bytes);
     vfprintf(stderr, fmt, ap);
     fprintf(stderr, "\n");
     va_end(ap);
@@ -166,113 +164,106 @@ static int64_t blkverify_getlength(BlockDriverState *bs)
     return bdrv_getlength(s->test_file->bs);
 }
 
-static BlkverifyAIOCB *blkverify_aio_get(BlockDriverState *bs, bool is_write,
-                                         int64_t sector_num, QEMUIOVector *qiov,
-                                         int nb_sectors,
-                                         BlockCompletionFunc *cb,
-                                         void *opaque)
+static void coroutine_fn blkverify_do_test_req(void *opaque)
 {
-    BlkverifyAIOCB *acb = qemu_aio_get(&blkverify_aiocb_info, bs, cb, opaque);
-
-    acb->is_write = is_write;
-    acb->sector_num = sector_num;
-    acb->nb_sectors = nb_sectors;
-    acb->ret = -EINPROGRESS;
-    acb->done = 0;
-    acb->qiov = qiov;
-    acb->buf = NULL;
-    acb->verify = NULL;
-    return acb;
+    BlkverifyRequest *r = opaque;
+    BDRVBlkverifyState *s = r->bs->opaque;
+
+    r->ret = r->request_fn(s->test_file, r->offset, r->bytes, r->qiov,
+                           r->flags);
+    r->done++;
+    qemu_coroutine_enter_if_inactive(r->co);
 }
 
-static void blkverify_aio_bh(void *opaque)
+static void coroutine_fn blkverify_do_raw_req(void *opaque)
 {
-    BlkverifyAIOCB *acb = opaque;
+    BlkverifyRequest *r = opaque;
 
-    if (acb->buf) {
-        qemu_iovec_destroy(&acb->raw_qiov);
-        qemu_vfree(acb->buf);
-    }
-    acb->common.cb(acb->common.opaque, acb->ret);
-    qemu_aio_unref(acb);
+    r->raw_ret = r->request_fn(r->bs->file, r->offset, r->bytes, r->raw_qiov,
+                               r->flags);
+    r->done++;
+    qemu_coroutine_enter_if_inactive(r->co);
 }
 
-static void blkverify_aio_cb(void *opaque, int ret)
+static int coroutine_fn
+blkverify_co_prwv(BlockDriverState *bs, BlkverifyRequest *r, uint64_t offset,
+                  uint64_t bytes, QEMUIOVector *qiov, QEMUIOVector *raw_qiov,
+                  int flags, bool is_write)
 {
-    BlkverifyAIOCB *acb = opaque;
-
-    switch (++acb->done) {
-    case 1:
-        acb->ret = ret;
-        break;
-
-    case 2:
-        if (acb->ret != ret) {
-            blkverify_err(acb, "return value mismatch %d != %d", acb->ret, ret);
-        }
-
-        if (acb->verify) {
-            acb->verify(acb);
-        }
+    Coroutine *co_a, *co_b;
+
+    *r = (BlkverifyRequest) {
+        .co         = qemu_coroutine_self(),
+        .bs         = bs,
+        .offset     = offset,
+        .bytes      = bytes,
+        .qiov       = qiov,
+        .raw_qiov   = raw_qiov,
+        .flags      = flags,
+        .is_write   = is_write,
+        .request_fn = is_write ? bdrv_co_pwritev : bdrv_co_preadv,
+    };
+
+    co_a = qemu_coroutine_create(blkverify_do_test_req, r);
+    co_b = qemu_coroutine_create(blkverify_do_raw_req, r);
+
+    qemu_coroutine_enter(co_a);
+    qemu_coroutine_enter(co_b);
+
+    while (r->done < 2) {
+        qemu_coroutine_yield();
+    }
 
-        aio_bh_schedule_oneshot(bdrv_get_aio_context(acb->common.bs),
-                                blkverify_aio_bh, acb);
-        break;
+    if (r->ret != r->raw_ret) {
+        blkverify_err(r, "return value mismatch %d != %d", r->ret, r->raw_ret);
     }
+
+    return r->ret;
 }
 
-static void blkverify_verify_readv(BlkverifyAIOCB *acb)
+static int coroutine_fn
+blkverify_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
+                    QEMUIOVector *qiov, int flags)
 {
-    ssize_t offset = qemu_iovec_compare(acb->qiov, &acb->raw_qiov);
-    if (offset != -1) {
-        blkverify_err(acb, "contents mismatch in sector %" PRId64,
-                      acb->sector_num + (int64_t)(offset / BDRV_SECTOR_SIZE));
+    BlkverifyRequest r;
+    QEMUIOVector raw_qiov;
+    void *buf;
+    ssize_t cmp_offset;
+    int ret;
+
+    buf = qemu_blockalign(bs->file->bs, qiov->size);
+    qemu_iovec_init(&raw_qiov, qiov->niov);
+    qemu_iovec_clone(&raw_qiov, qiov, buf);
+
+    ret = blkverify_co_prwv(bs, &r, offset, bytes, qiov, &raw_qiov, flags,
+                            false);
+
+    cmp_offset = qemu_iovec_compare(qiov, &raw_qiov);
+    if (cmp_offset != -1) {
+        blkverify_err(&r, "contents mismatch at offset %" PRId64,
+                      offset + cmp_offset);
     }
-}
 
-static BlockAIOCB *blkverify_aio_readv(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockCompletionFunc *cb, void *opaque)
-{
-    BDRVBlkverifyState *s = bs->opaque;
-    BlkverifyAIOCB *acb = blkverify_aio_get(bs, false, sector_num, qiov,
-                                            nb_sectors, cb, opaque);
-
-    acb->verify = blkverify_verify_readv;
-    acb->buf = qemu_blockalign(bs->file->bs, qiov->size);
-    qemu_iovec_init(&acb->raw_qiov, acb->qiov->niov);
-    qemu_iovec_clone(&acb->raw_qiov, qiov, acb->buf);
-
-    bdrv_aio_readv(s->test_file, sector_num, qiov, nb_sectors,
-                   blkverify_aio_cb, acb);
-    bdrv_aio_readv(bs->file, sector_num, &acb->raw_qiov, nb_sectors,
-                   blkverify_aio_cb, acb);
-    return &acb->common;
+    qemu_iovec_destroy(&raw_qiov);
+    qemu_vfree(buf);
+
+    return ret;
 }
 
-static BlockAIOCB *blkverify_aio_writev(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockCompletionFunc *cb, void *opaque)
+static int coroutine_fn
+blkverify_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
+                     QEMUIOVector *qiov, int flags)
 {
-    BDRVBlkverifyState *s = bs->opaque;
-    BlkverifyAIOCB *acb = blkverify_aio_get(bs, true, sector_num, qiov,
-                                            nb_sectors, cb, opaque);
-
-    bdrv_aio_writev(s->test_file, sector_num, qiov, nb_sectors,
-                    blkverify_aio_cb, acb);
-    bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors,
-                    blkverify_aio_cb, acb);
-    return &acb->common;
+    BlkverifyRequest r;
+    return blkverify_co_prwv(bs, &r, offset, bytes, qiov, qiov, flags, true);
 }
 
-static BlockAIOCB *blkverify_aio_flush(BlockDriverState *bs,
-                                       BlockCompletionFunc *cb,
-                                       void *opaque)
+static int blkverify_co_flush(BlockDriverState *bs)
 {
     BDRVBlkverifyState *s = bs->opaque;
 
     /* Only flush test file, the raw file is not important */
-    return bdrv_aio_flush(s->test_file->bs, cb, opaque);
+    return bdrv_co_flush(s->test_file->bs);
 }
 
 static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs,
@@ -332,9 +323,9 @@ static BlockDriver bdrv_blkverify = {
     .bdrv_getlength                   = blkverify_getlength,
     .bdrv_refresh_filename            = blkverify_refresh_filename,
 
-    .bdrv_aio_readv                   = blkverify_aio_readv,
-    .bdrv_aio_writev                  = blkverify_aio_writev,
-    .bdrv_aio_flush                   = blkverify_aio_flush,
+    .bdrv_co_preadv                   = blkverify_co_preadv,
+    .bdrv_co_pwritev                  = blkverify_co_pwritev,
+    .bdrv_co_flush                    = blkverify_co_flush,
 
     .is_filter                        = true,
     .bdrv_recurse_is_first_non_filter = blkverify_recurse_is_first_non_filter,
diff --git a/block/raw-posix.c b/block/file-posix.c
index 28b47d977b..28b47d977b 100644
--- a/block/raw-posix.c
+++ b/block/file-posix.c
diff --git a/block/raw-win32.c b/block/file-win32.c
index 800fabdd72..800fabdd72 100644
--- a/block/raw-win32.c
+++ b/block/file-win32.c
diff --git a/block/gluster.c b/block/gluster.c
index a0a74e49fd..1a22f2982d 100644
--- a/block/gluster.c
+++ b/block/gluster.c
@@ -1253,7 +1253,7 @@ static int qemu_gluster_has_zero_init(BlockDriverState *bs)
  * If @start is in a trailing hole or beyond EOF, return -ENXIO.
  * If we can't find out, return a negative errno other than -ENXIO.
  *
- * (Shamefully copied from raw-posix.c, only miniscule adaptions.)
+ * (Shamefully copied from file-posix.c, only miniscule adaptions.)
  */
 static int find_allocation(BlockDriverState *bs, off_t start,
                            off_t *data, off_t *hole)
@@ -1349,7 +1349,7 @@ exit:
  * '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.
  *
- * (Based on raw_co_get_block_status() from raw-posix.c.)
+ * (Based on raw_co_get_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,
diff --git a/block/quorum.c b/block/quorum.c
index d122299352..86e2072dce 100644
--- a/block/quorum.c
+++ b/block/quorum.c
@@ -97,7 +97,7 @@ typedef struct QuorumAIOCB QuorumAIOCB;
  * $children_count QuorumChildRequest.
  */
 typedef struct QuorumChildRequest {
-    BlockAIOCB *aiocb;
+    BlockDriverState *bs;
     QEMUIOVector qiov;
     uint8_t *buf;
     int ret;
@@ -110,11 +110,12 @@ typedef struct QuorumChildRequest {
  * used to do operations on each children and track overall progress.
  */
 struct QuorumAIOCB {
-    BlockAIOCB common;
+    BlockDriverState *bs;
+    Coroutine *co;
 
     /* Request metadata */
-    uint64_t sector_num;
-    int nb_sectors;
+    uint64_t offset;
+    uint64_t bytes;
 
     QEMUIOVector *qiov;         /* calling IOV */
 
@@ -133,32 +134,15 @@ struct QuorumAIOCB {
     int children_read;          /* how many children have been read from */
 };
 
-static bool quorum_vote(QuorumAIOCB *acb);
-
-static void quorum_aio_cancel(BlockAIOCB *blockacb)
-{
-    QuorumAIOCB *acb = container_of(blockacb, QuorumAIOCB, common);
-    BDRVQuorumState *s = acb->common.bs->opaque;
-    int i;
-
-    /* cancel all callbacks */
-    for (i = 0; i < s->num_children; i++) {
-        if (acb->qcrs[i].aiocb) {
-            bdrv_aio_cancel_async(acb->qcrs[i].aiocb);
-        }
-    }
-}
-
-static AIOCBInfo quorum_aiocb_info = {
-    .aiocb_size         = sizeof(QuorumAIOCB),
-    .cancel_async       = quorum_aio_cancel,
-};
+typedef struct QuorumCo {
+    QuorumAIOCB *acb;
+    int idx;
+} QuorumCo;
 
 static void quorum_aio_finalize(QuorumAIOCB *acb)
 {
-    acb->common.cb(acb->common.opaque, acb->vote_ret);
     g_free(acb->qcrs);
-    qemu_aio_unref(acb);
+    g_free(acb);
 }
 
 static bool quorum_sha256_compare(QuorumVoteValue *a, QuorumVoteValue *b)
@@ -171,30 +155,26 @@ static bool quorum_64bits_compare(QuorumVoteValue *a, QuorumVoteValue *b)
     return a->l == b->l;
 }
 
-static QuorumAIOCB *quorum_aio_get(BDRVQuorumState *s,
-                                   BlockDriverState *bs,
+static QuorumAIOCB *quorum_aio_get(BlockDriverState *bs,
                                    QEMUIOVector *qiov,
-                                   uint64_t sector_num,
-                                   int nb_sectors,
-                                   BlockCompletionFunc *cb,
-                                   void *opaque)
+                                   uint64_t offset,
+                                   uint64_t bytes)
 {
-    QuorumAIOCB *acb = qemu_aio_get(&quorum_aiocb_info, bs, cb, opaque);
+    BDRVQuorumState *s = bs->opaque;
+    QuorumAIOCB *acb = g_new(QuorumAIOCB, 1);
     int i;
 
-    acb->common.bs->opaque = s;
-    acb->sector_num = sector_num;
-    acb->nb_sectors = nb_sectors;
-    acb->qiov = qiov;
-    acb->qcrs = g_new0(QuorumChildRequest, s->num_children);
-    acb->count = 0;
-    acb->success_count = 0;
-    acb->rewrite_count = 0;
-    acb->votes.compare = quorum_sha256_compare;
-    QLIST_INIT(&acb->votes.vote_list);
-    acb->is_read = false;
-    acb->vote_ret = 0;
+    *acb = (QuorumAIOCB) {
+        .co                 = qemu_coroutine_self(),
+        .bs                 = bs,
+        .offset             = offset,
+        .bytes              = bytes,
+        .qiov               = qiov,
+        .votes.compare      = quorum_sha256_compare,
+        .votes.vote_list    = QLIST_HEAD_INITIALIZER(acb.votes.vote_list),
+    };
 
+    acb->qcrs = g_new0(QuorumChildRequest, s->num_children);
     for (i = 0; i < s->num_children; i++) {
         acb->qcrs[i].buf = NULL;
         acb->qcrs[i].ret = 0;
@@ -204,30 +184,37 @@ static QuorumAIOCB *quorum_aio_get(BDRVQuorumState *s,
     return acb;
 }
 
-static void quorum_report_bad(QuorumOpType type, uint64_t sector_num,
-                              int nb_sectors, char *node_name, int ret)
+static void quorum_report_bad(QuorumOpType type, uint64_t offset,
+                              uint64_t bytes, char *node_name, int ret)
 {
     const char *msg = NULL;
+    int64_t start_sector = offset / BDRV_SECTOR_SIZE;
+    int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE);
+
     if (ret < 0) {
         msg = strerror(-ret);
     }
 
-    qapi_event_send_quorum_report_bad(type, !!msg, msg, node_name,
-                                      sector_num, nb_sectors, &error_abort);
+    qapi_event_send_quorum_report_bad(type, !!msg, msg, node_name, start_sector,
+                                      end_sector - start_sector, &error_abort);
 }
 
 static void quorum_report_failure(QuorumAIOCB *acb)
 {
-    const char *reference = bdrv_get_device_or_node_name(acb->common.bs);
-    qapi_event_send_quorum_failure(reference, acb->sector_num,
-                                   acb->nb_sectors, &error_abort);
+    const char *reference = bdrv_get_device_or_node_name(acb->bs);
+    int64_t start_sector = acb->offset / BDRV_SECTOR_SIZE;
+    int64_t end_sector = DIV_ROUND_UP(acb->offset + acb->bytes,
+                                      BDRV_SECTOR_SIZE);
+
+    qapi_event_send_quorum_failure(reference, start_sector,
+                                   end_sector - start_sector, &error_abort);
 }
 
 static int quorum_vote_error(QuorumAIOCB *acb);
 
 static bool quorum_has_too_much_io_failed(QuorumAIOCB *acb)
 {
-    BDRVQuorumState *s = acb->common.bs->opaque;
+    BDRVQuorumState *s = acb->bs->opaque;
 
     if (acb->success_count < s->threshold) {
         acb->vote_ret = quorum_vote_error(acb);
@@ -238,22 +225,7 @@ static bool quorum_has_too_much_io_failed(QuorumAIOCB *acb)
     return false;
 }
 
-static void quorum_rewrite_aio_cb(void *opaque, int ret)
-{
-    QuorumAIOCB *acb = opaque;
-
-    /* one less rewrite to do */
-    acb->rewrite_count--;
-
-    /* wait until all rewrite callbacks have completed */
-    if (acb->rewrite_count) {
-        return;
-    }
-
-    quorum_aio_finalize(acb);
-}
-
-static BlockAIOCB *read_fifo_child(QuorumAIOCB *acb);
+static int read_fifo_child(QuorumAIOCB *acb);
 
 static void quorum_copy_qiov(QEMUIOVector *dest, QEMUIOVector *source)
 {
@@ -272,70 +244,7 @@ static void quorum_report_bad_acb(QuorumChildRequest *sacb, int ret)
 {
     QuorumAIOCB *acb = sacb->parent;
     QuorumOpType type = acb->is_read ? QUORUM_OP_TYPE_READ : QUORUM_OP_TYPE_WRITE;
-    quorum_report_bad(type, acb->sector_num, acb->nb_sectors,
-                      sacb->aiocb->bs->node_name, ret);
-}
-
-static void quorum_fifo_aio_cb(void *opaque, int ret)
-{
-    QuorumChildRequest *sacb = opaque;
-    QuorumAIOCB *acb = sacb->parent;
-    BDRVQuorumState *s = acb->common.bs->opaque;
-
-    assert(acb->is_read && s->read_pattern == QUORUM_READ_PATTERN_FIFO);
-
-    if (ret < 0) {
-        quorum_report_bad_acb(sacb, ret);
-
-        /* We try to read next child in FIFO order if we fail to read */
-        if (acb->children_read < s->num_children) {
-            read_fifo_child(acb);
-            return;
-        }
-    }
-
-    acb->vote_ret = ret;
-
-    /* FIXME: rewrite failed children if acb->children_read > 1? */
-    quorum_aio_finalize(acb);
-}
-
-static void quorum_aio_cb(void *opaque, int ret)
-{
-    QuorumChildRequest *sacb = opaque;
-    QuorumAIOCB *acb = sacb->parent;
-    BDRVQuorumState *s = acb->common.bs->opaque;
-    bool rewrite = false;
-    int i;
-
-    sacb->ret = ret;
-    if (ret == 0) {
-        acb->success_count++;
-    } else {
-        quorum_report_bad_acb(sacb, ret);
-    }
-    acb->count++;
-    assert(acb->count <= s->num_children);
-    assert(acb->success_count <= s->num_children);
-    if (acb->count < s->num_children) {
-        return;
-    }
-
-    /* Do the vote on read */
-    if (acb->is_read) {
-        rewrite = quorum_vote(acb);
-        for (i = 0; i < s->num_children; i++) {
-            qemu_vfree(acb->qcrs[i].buf);
-            qemu_iovec_destroy(&acb->qcrs[i].qiov);
-        }
-    } else {
-        quorum_has_too_much_io_failed(acb);
-    }
-
-    /* if no rewrite is done the code will finish right away */
-    if (!rewrite) {
-        quorum_aio_finalize(acb);
-    }
+    quorum_report_bad(type, acb->offset, acb->bytes, sacb->bs->node_name, ret);
 }
 
 static void quorum_report_bad_versions(BDRVQuorumState *s,
@@ -350,14 +259,31 @@ static void quorum_report_bad_versions(BDRVQuorumState *s,
             continue;
         }
         QLIST_FOREACH(item, &version->items, next) {
-            quorum_report_bad(QUORUM_OP_TYPE_READ, acb->sector_num,
-                              acb->nb_sectors,
+            quorum_report_bad(QUORUM_OP_TYPE_READ, acb->offset, acb->bytes,
                               s->children[item->index]->bs->node_name, 0);
         }
     }
 }
 
-static bool quorum_rewrite_bad_versions(BDRVQuorumState *s, QuorumAIOCB *acb,
+static void quorum_rewrite_entry(void *opaque)
+{
+    QuorumCo *co = opaque;
+    QuorumAIOCB *acb = co->acb;
+    BDRVQuorumState *s = acb->bs->opaque;
+
+    /* Ignore any errors, it's just a correction attempt for already
+     * corrupted data. */
+    bdrv_co_pwritev(s->children[co->idx], acb->offset, acb->bytes,
+                    acb->qiov, 0);
+
+    /* Wake up the caller after the last rewrite */
+    acb->rewrite_count--;
+    if (!acb->rewrite_count) {
+        qemu_coroutine_enter_if_inactive(acb->co);
+    }
+}
+
+static bool quorum_rewrite_bad_versions(QuorumAIOCB *acb,
                                         QuorumVoteValue *value)
 {
     QuorumVoteVersion *version;
@@ -376,7 +302,7 @@ static bool quorum_rewrite_bad_versions(BDRVQuorumState *s, QuorumAIOCB *acb,
         }
     }
 
-    /* quorum_rewrite_aio_cb will count down this to zero */
+    /* quorum_rewrite_entry will count down this to zero */
     acb->rewrite_count = count;
 
     /* now fire the correcting rewrites */
@@ -385,9 +311,14 @@ static bool quorum_rewrite_bad_versions(BDRVQuorumState *s, QuorumAIOCB *acb,
             continue;
         }
         QLIST_FOREACH(item, &version->items, next) {
-            bdrv_aio_writev(s->children[item->index], acb->sector_num,
-                            acb->qiov, acb->nb_sectors, quorum_rewrite_aio_cb,
-                            acb);
+            Coroutine *co;
+            QuorumCo data = {
+                .acb = acb,
+                .idx = item->index,
+            };
+
+            co = qemu_coroutine_create(quorum_rewrite_entry, &data);
+            qemu_coroutine_enter(co);
         }
     }
 
@@ -507,8 +438,8 @@ static void GCC_FMT_ATTR(2, 3) quorum_err(QuorumAIOCB *acb,
     va_list ap;
 
     va_start(ap, fmt);
-    fprintf(stderr, "quorum: sector_num=%" PRId64 " nb_sectors=%d ",
-            acb->sector_num, acb->nb_sectors);
+    fprintf(stderr, "quorum: offset=%" PRIu64 " bytes=%" PRIu64 " ",
+            acb->offset, acb->bytes);
     vfprintf(stderr, fmt, ap);
     fprintf(stderr, "\n");
     va_end(ap);
@@ -519,16 +450,15 @@ static bool quorum_compare(QuorumAIOCB *acb,
                            QEMUIOVector *a,
                            QEMUIOVector *b)
 {
-    BDRVQuorumState *s = acb->common.bs->opaque;
+    BDRVQuorumState *s = acb->bs->opaque;
     ssize_t offset;
 
     /* This driver will replace blkverify in this particular case */
     if (s->is_blkverify) {
         offset = qemu_iovec_compare(a, b);
         if (offset != -1) {
-            quorum_err(acb, "contents mismatch in sector %" PRId64,
-                       acb->sector_num +
-                       (uint64_t)(offset / BDRV_SECTOR_SIZE));
+            quorum_err(acb, "contents mismatch at offset %" PRIu64,
+                       acb->offset + offset);
         }
         return true;
     }
@@ -539,7 +469,7 @@ static bool quorum_compare(QuorumAIOCB *acb,
 /* Do a vote to get the error code */
 static int quorum_vote_error(QuorumAIOCB *acb)
 {
-    BDRVQuorumState *s = acb->common.bs->opaque;
+    BDRVQuorumState *s = acb->bs->opaque;
     QuorumVoteVersion *winner = NULL;
     QuorumVotes error_votes;
     QuorumVoteValue result_value;
@@ -568,17 +498,16 @@ static int quorum_vote_error(QuorumAIOCB *acb)
     return ret;
 }
 
-static bool quorum_vote(QuorumAIOCB *acb)
+static void quorum_vote(QuorumAIOCB *acb)
 {
     bool quorum = true;
-    bool rewrite = false;
     int i, j, ret;
     QuorumVoteValue hash;
-    BDRVQuorumState *s = acb->common.bs->opaque;
+    BDRVQuorumState *s = acb->bs->opaque;
     QuorumVoteVersion *winner;
 
     if (quorum_has_too_much_io_failed(acb)) {
-        return false;
+        return;
     }
 
     /* get the index of the first successful read */
@@ -606,7 +535,7 @@ static bool quorum_vote(QuorumAIOCB *acb)
     /* Every successful read agrees */
     if (quorum) {
         quorum_copy_qiov(acb->qiov, &acb->qcrs[i].qiov);
-        return false;
+        return;
     }
 
     /* compute hashes for each successful read, also store indexes */
@@ -641,19 +570,46 @@ static bool quorum_vote(QuorumAIOCB *acb)
 
     /* corruption correction is enabled */
     if (s->rewrite_corrupted) {
-        rewrite = quorum_rewrite_bad_versions(s, acb, &winner->value);
+        quorum_rewrite_bad_versions(acb, &winner->value);
     }
 
 free_exit:
     /* free lists */
     quorum_free_vote_list(&acb->votes);
-    return rewrite;
 }
 
-static BlockAIOCB *read_quorum_children(QuorumAIOCB *acb)
+static void read_quorum_children_entry(void *opaque)
 {
-    BDRVQuorumState *s = acb->common.bs->opaque;
-    int i;
+    QuorumCo *co = opaque;
+    QuorumAIOCB *acb = co->acb;
+    BDRVQuorumState *s = acb->bs->opaque;
+    int i = co->idx;
+    QuorumChildRequest *sacb = &acb->qcrs[i];
+
+    sacb->bs = s->children[i]->bs;
+    sacb->ret = bdrv_co_preadv(s->children[i], acb->offset, acb->bytes,
+                               &acb->qcrs[i].qiov, 0);
+
+    if (sacb->ret == 0) {
+        acb->success_count++;
+    } else {
+        quorum_report_bad_acb(sacb, sacb->ret);
+    }
+
+    acb->count++;
+    assert(acb->count <= s->num_children);
+    assert(acb->success_count <= s->num_children);
+
+    /* Wake up the caller after the last read */
+    if (acb->count == s->num_children) {
+        qemu_coroutine_enter_if_inactive(acb->co);
+    }
+}
+
+static int read_quorum_children(QuorumAIOCB *acb)
+{
+    BDRVQuorumState *s = acb->bs->opaque;
+    int i, ret;
 
     acb->children_read = s->num_children;
     for (i = 0; i < s->num_children; i++) {
@@ -663,65 +619,131 @@ static BlockAIOCB *read_quorum_children(QuorumAIOCB *acb)
     }
 
     for (i = 0; i < s->num_children; i++) {
-        acb->qcrs[i].aiocb = bdrv_aio_readv(s->children[i], acb->sector_num,
-                                            &acb->qcrs[i].qiov, acb->nb_sectors,
-                                            quorum_aio_cb, &acb->qcrs[i]);
+        Coroutine *co;
+        QuorumCo data = {
+            .acb = acb,
+            .idx = i,
+        };
+
+        co = qemu_coroutine_create(read_quorum_children_entry, &data);
+        qemu_coroutine_enter(co);
     }
 
-    return &acb->common;
+    while (acb->count < s->num_children) {
+        qemu_coroutine_yield();
+    }
+
+    /* Do the vote on read */
+    quorum_vote(acb);
+    for (i = 0; i < s->num_children; i++) {
+        qemu_vfree(acb->qcrs[i].buf);
+        qemu_iovec_destroy(&acb->qcrs[i].qiov);
+    }
+
+    while (acb->rewrite_count) {
+        qemu_coroutine_yield();
+    }
+
+    ret = acb->vote_ret;
+
+    return ret;
 }
 
-static BlockAIOCB *read_fifo_child(QuorumAIOCB *acb)
+static int read_fifo_child(QuorumAIOCB *acb)
 {
-    BDRVQuorumState *s = acb->common.bs->opaque;
-    int n = acb->children_read++;
+    BDRVQuorumState *s = acb->bs->opaque;
+    int n, ret;
+
+    /* We try to read the next child in FIFO order if we failed to read */
+    do {
+        n = acb->children_read++;
+        acb->qcrs[n].bs = s->children[n]->bs;
+        ret = bdrv_co_preadv(s->children[n], acb->offset, acb->bytes,
+                             acb->qiov, 0);
+        if (ret < 0) {
+            quorum_report_bad_acb(&acb->qcrs[n], ret);
+        }
+    } while (ret < 0 && acb->children_read < s->num_children);
 
-    acb->qcrs[n].aiocb = bdrv_aio_readv(s->children[n], acb->sector_num,
-                                        acb->qiov, acb->nb_sectors,
-                                        quorum_fifo_aio_cb, &acb->qcrs[n]);
+    /* FIXME: rewrite failed children if acb->children_read > 1? */
 
-    return &acb->common;
+    return ret;
 }
 
-static BlockAIOCB *quorum_aio_readv(BlockDriverState *bs,
-                                    int64_t sector_num,
-                                    QEMUIOVector *qiov,
-                                    int nb_sectors,
-                                    BlockCompletionFunc *cb,
-                                    void *opaque)
+static int quorum_co_preadv(BlockDriverState *bs, uint64_t offset,
+                            uint64_t bytes, QEMUIOVector *qiov, int flags)
 {
     BDRVQuorumState *s = bs->opaque;
-    QuorumAIOCB *acb = quorum_aio_get(s, bs, qiov, sector_num,
-                                      nb_sectors, cb, opaque);
+    QuorumAIOCB *acb = quorum_aio_get(bs, qiov, offset, bytes);
+    int ret;
+
     acb->is_read = true;
     acb->children_read = 0;
 
     if (s->read_pattern == QUORUM_READ_PATTERN_QUORUM) {
-        return read_quorum_children(acb);
+        ret = read_quorum_children(acb);
+    } else {
+        ret = read_fifo_child(acb);
+    }
+    quorum_aio_finalize(acb);
+
+    return ret;
+}
+
+static void write_quorum_entry(void *opaque)
+{
+    QuorumCo *co = opaque;
+    QuorumAIOCB *acb = co->acb;
+    BDRVQuorumState *s = acb->bs->opaque;
+    int i = co->idx;
+    QuorumChildRequest *sacb = &acb->qcrs[i];
+
+    sacb->bs = s->children[i]->bs;
+    sacb->ret = bdrv_co_pwritev(s->children[i], acb->offset, acb->bytes,
+                                acb->qiov, 0);
+    if (sacb->ret == 0) {
+        acb->success_count++;
+    } else {
+        quorum_report_bad_acb(sacb, sacb->ret);
     }
+    acb->count++;
+    assert(acb->count <= s->num_children);
+    assert(acb->success_count <= s->num_children);
 
-    return read_fifo_child(acb);
+    /* Wake up the caller after the last write */
+    if (acb->count == s->num_children) {
+        qemu_coroutine_enter_if_inactive(acb->co);
+    }
 }
 
-static BlockAIOCB *quorum_aio_writev(BlockDriverState *bs,
-                                     int64_t sector_num,
-                                     QEMUIOVector *qiov,
-                                     int nb_sectors,
-                                     BlockCompletionFunc *cb,
-                                     void *opaque)
+static int quorum_co_pwritev(BlockDriverState *bs, uint64_t offset,
+                             uint64_t bytes, QEMUIOVector *qiov, int flags)
 {
     BDRVQuorumState *s = bs->opaque;
-    QuorumAIOCB *acb = quorum_aio_get(s, bs, qiov, sector_num, nb_sectors,
-                                      cb, opaque);
-    int i;
+    QuorumAIOCB *acb = quorum_aio_get(bs, qiov, offset, bytes);
+    int i, ret;
 
     for (i = 0; i < s->num_children; i++) {
-        acb->qcrs[i].aiocb = bdrv_aio_writev(s->children[i], sector_num,
-                                             qiov, nb_sectors, &quorum_aio_cb,
-                                             &acb->qcrs[i]);
+        Coroutine *co;
+        QuorumCo data = {
+            .acb = acb,
+            .idx = i,
+        };
+
+        co = qemu_coroutine_create(write_quorum_entry, &data);
+        qemu_coroutine_enter(co);
+    }
+
+    while (acb->count < s->num_children) {
+        qemu_coroutine_yield();
     }
 
-    return &acb->common;
+    quorum_has_too_much_io_failed(acb);
+
+    ret = acb->vote_ret;
+    quorum_aio_finalize(acb);
+
+    return ret;
 }
 
 static int64_t quorum_getlength(BlockDriverState *bs)
@@ -765,7 +787,7 @@ static coroutine_fn int quorum_co_flush(BlockDriverState *bs)
         result = bdrv_co_flush(s->children[i]->bs);
         if (result) {
             quorum_report_bad(QUORUM_OP_TYPE_FLUSH, 0,
-                              bdrv_nb_sectors(s->children[i]->bs),
+                              bdrv_getlength(s->children[i]->bs),
                               s->children[i]->bs->node_name, result);
             result_value.l = result;
             quorum_count_vote(&error_votes, &result_value, i);
@@ -1098,8 +1120,8 @@ static BlockDriver bdrv_quorum = {
 
     .bdrv_getlength                     = quorum_getlength,
 
-    .bdrv_aio_readv                     = quorum_aio_readv,
-    .bdrv_aio_writev                    = quorum_aio_writev,
+    .bdrv_co_preadv                     = quorum_co_preadv,
+    .bdrv_co_pwritev                    = quorum_co_pwritev,
 
     .bdrv_add_child                     = quorum_add_child,
     .bdrv_del_child                     = quorum_del_child,
diff --git a/block/raw_bsd.c b/block/raw-format.c
index 8a5b9b0424..8404a82e0c 100644
--- a/block/raw_bsd.c
+++ b/block/raw-format.c
@@ -1,4 +1,4 @@
-/* BlockDriver implementation for "raw"
+/* BlockDriver implementation for "raw" format driver
  *
  * Copyright (C) 2010-2016 Red Hat, Inc.
  * Copyright (C) 2010, Blue Swirl <blauwirbel@gmail.com>
diff --git a/block/trace-events b/block/trace-events
index cfc05f2478..671a6a851c 100644
--- a/block/trace-events
+++ b/block/trace-events
@@ -53,8 +53,8 @@ qmp_block_job_resume(void *job) "job %p"
 qmp_block_job_complete(void *job) "job %p"
 qmp_block_stream(void *bs, void *job) "bs %p job %p"
 
-# block/raw-win32.c
-# block/raw-posix.c
+# block/file-win32.c
+# block/file-posix.c
 paio_submit_co(int64_t offset, int count, int type) "offset %"PRId64" count %d type %d"
 paio_submit(void *acb, void *opaque, int64_t offset, int count, int type) "acb %p opaque %p offset %"PRId64" count %d type %d"
 
diff --git a/configure b/configure
index 218df87d21..86f5214dd0 100755
--- a/configure
+++ b/configure
@@ -2750,7 +2750,7 @@ if compile_prog "" "" ; then
 fi
 
 ##########################################
-# xfsctl() probe, used for raw-posix
+# xfsctl() probe, used for file-posix.c
 if test "$xfs" != "no" ; then
   cat > $TMPC << EOF
 #include <stddef.h>  /* NULL */
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 83a423c580..4e4562d444 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -184,7 +184,7 @@ struct BlockDriver {
 
     /*
      * Flushes all data that was already written to the OS all the way down to
-     * the disk (for example raw-posix calls fsync()).
+     * the disk (for example file-posix.c calls fsync()).
      */
     int coroutine_fn (*bdrv_co_flush_to_disk)(BlockDriverState *bs);
 
diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h
index e6a60d55fd..12584ed1b7 100644
--- a/include/qemu/coroutine.h
+++ b/include/qemu/coroutine.h
@@ -71,6 +71,12 @@ Coroutine *qemu_coroutine_create(CoroutineEntry *entry, void *opaque);
 void qemu_coroutine_enter(Coroutine *coroutine);
 
 /**
+ * Transfer control to a coroutine if it's not active (i.e. part of the call
+ * stack of the running coroutine). Otherwise, do nothing.
+ */
+void qemu_coroutine_enter_if_inactive(Coroutine *co);
+
+/**
  * Transfer control back to a coroutine's caller
  *
  * This function does not return until the coroutine is re-entered using
diff --git a/qemu-img.c b/qemu-img.c
index 6949b73ca5..5df66fe661 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -3559,20 +3559,23 @@ static void bench_cb(void *opaque, int ret)
     }
 
     while (b->n > b->in_flight && b->in_flight < b->nrreq) {
+        int64_t offset = b->offset;
+        /* blk_aio_* might look for completed I/Os and kick bench_cb
+         * again, so make sure this operation is counted by in_flight
+         * and b->offset is ready for the next submission.
+         */
+        b->in_flight++;
+        b->offset += b->step;
+        b->offset %= b->image_size;
         if (b->write) {
-            acb = blk_aio_pwritev(b->blk, b->offset, b->qiov, 0,
-                                  bench_cb, b);
+            acb = blk_aio_pwritev(b->blk, offset, b->qiov, 0, bench_cb, b);
         } else {
-            acb = blk_aio_preadv(b->blk, b->offset, b->qiov, 0,
-                                 bench_cb, b);
+            acb = blk_aio_preadv(b->blk, offset, b->qiov, 0, bench_cb, b);
         }
         if (!acb) {
             error_report("Failed to issue request");
             exit(EXIT_FAILURE);
         }
-        b->in_flight++;
-        b->offset += b->step;
-        b->offset %= b->image_size;
     }
 }
 
diff --git a/tests/qemu-iotests/071.out b/tests/qemu-iotests/071.out
index 8ff423f56b..dd879f1212 100644
--- a/tests/qemu-iotests/071.out
+++ b/tests/qemu-iotests/071.out
@@ -12,7 +12,7 @@ read 512/512 bytes at offset 229376
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-blkverify: read sector_num=0 nb_sectors=1 contents mismatch in sector 0
+blkverify: read offset=0 bytes=512 contents mismatch at offset 0
 
 === Testing blkverify through file blockref ===
 
@@ -26,7 +26,7 @@ read 512/512 bytes at offset 229376
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-blkverify: read sector_num=0 nb_sectors=1 contents mismatch in sector 0
+blkverify: read offset=0 bytes=512 contents mismatch at offset 0
 
 === Testing blkdebug through filename ===
 
@@ -56,7 +56,7 @@ QMP_VERSION
 {"return": {}}
 {"return": {}}
 {"return": {}}
-blkverify: read sector_num=0 nb_sectors=1 contents mismatch in sector 0
+blkverify: read offset=0 bytes=512 contents mismatch at offset 0
 
 
 === Testing blkverify on existing raw block device ===
@@ -66,7 +66,7 @@ QMP_VERSION
 {"return": {}}
 {"return": {}}
 {"return": {}}
-blkverify: read sector_num=0 nb_sectors=1 contents mismatch in sector 0
+blkverify: read offset=0 bytes=512 contents mismatch at offset 0
 
 
 === Testing blkdebug's set-state through QMP ===
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index 737bffa984..a5d2f6c0c3 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -131,6 +131,13 @@ void qemu_coroutine_enter(Coroutine *co)
     }
 }
 
+void qemu_coroutine_enter_if_inactive(Coroutine *co)
+{
+    if (!qemu_coroutine_entered(co)) {
+        qemu_coroutine_enter(co);
+    }
+}
+
 void coroutine_fn qemu_coroutine_yield(void)
 {
     Coroutine *self = qemu_coroutine_self();