@@ -2183,8 +2183,29 @@ int bdrv_aio_multiwrite(BlockDriverState *bs, BlockRequest *reqs, int num_reqs)
// Check for mergable requests
num_reqs = multiwrite_merge(bs, reqs, num_reqs, mcb);
- // Run the aio requests
+ /*
+ * Run the aio requests. As soon as one request can't be submitted
+ * successfully, fail all requests that are not yet submitted (we must
+ * return failure for all requests anyway)
+ *
+ * num_requests cannot be set to the right value immediately: If
+ * bdrv_aio_writev fails for some request, num_requests would be too high
+ * and therefore multiwrite_cb() would never recognize the multiwrite
+ * request as completed. We also cannot use the loop variable i to set it
+ * when the first request fails because the callback may already have been
+ * called for previously submitted requests. Thus, num_requests must be
+ * incremented for each request that is submitted.
+ *
+ * The problem that callbacks may be called early also means that we need
+ * to take care that num_requests doesn't become 0 before all requests are
+ * submitted - multiwrite_cb() would consider the multiwrite request
+ * completed. A dummy request that is "completed" by a manual call to
+ * multiwrite_cb() takes care of this.
+ */
+ mcb->num_requests = 1;
+
for (i = 0; i < num_reqs; i++) {
+ mcb->num_requests++;
acb = bdrv_aio_writev(bs, reqs[i].sector, reqs[i].qiov,
reqs[i].nb_sectors, multiwrite_cb, mcb);
@@ -2192,22 +2213,24 @@ int bdrv_aio_multiwrite(BlockDriverState *bs, BlockRequest *reqs, int num_reqs)
// We can only fail the whole thing if no request has been
// submitted yet. Otherwise we'll wait for the submitted AIOs to
// complete and report the error in the callback.
- if (mcb->num_requests == 0) {
- reqs[i].error = -EIO;
+ if (i == 0) {
goto fail;
} else {
- mcb->num_requests++;
multiwrite_cb(mcb, -EIO);
break;
}
- } else {
- mcb->num_requests++;
}
}
+ /* Complete the dummy request */
+ multiwrite_cb(mcb, 0);
+
return 0;
fail:
+ for (i = 0; i < mcb->num_callbacks; i++) {
+ reqs[i].error = -EIO;
+ }
qemu_free(mcb);
return -1;
}
bdrv_aio_writev may call the callback immediately (and it will commonly do so in error cases). Current code doesn't consider this. For details see the comment added by this patch. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 35 +++++++++++++++++++++++++++++------ 1 files changed, 29 insertions(+), 6 deletions(-)