aboutsummaryrefslogtreecommitdiff
path: root/block
diff options
context:
space:
mode:
authorSergio Lopez <slp@redhat.com>2019-03-08 16:48:53 +0100
committerKevin Wolf <kwolf@redhat.com>2019-03-19 15:49:29 +0100
commit5e771752a1ffba3a99d7d75b6d492b4a86b59e1b (patch)
tree53cce2c5d3125724611c97870dc5f2b8c4f9e4ae /block
parentb98a66201dbc7cf3b962f4bb260f66100cc75578 (diff)
downloadqemu-5e771752a1ffba3a99d7d75b6d492b4a86b59e1b.zip
qemu-5e771752a1ffba3a99d7d75b6d492b4a86b59e1b.tar.gz
qemu-5e771752a1ffba3a99d7d75b6d492b4a86b59e1b.tar.bz2
mirror: Confirm we're quiesced only if the job is paused or cancelled
While child_job_drained_begin() calls to job_pause(), the job doesn't actually transition between states until it runs again and reaches a pause point. This means bdrv_drained_begin() may return with some jobs using the node still having 'busy == true'. As a consequence, block_job_detach_aio_context() may get into a deadlock, waiting for the job to be actually paused, while the coroutine servicing the job is yielding and doesn't get the opportunity to get scheduled again. This situation can be reproduced by issuing a 'block-commit' immediately followed by a 'device_del'. To ensure bdrv_drained_begin() only returns when the jobs have been paused, we change mirror_drained_poll() to only confirm it's quiesced when job->paused == true and there aren't any in-flight requests, except if we reached that point by a drained section initiated by the mirror/commit job itself. The other block jobs shouldn't need any changes, as the default drained_poll() behavior is to only confirm it's quiesced if the job is not busy or completed. Signed-off-by: Sergio Lopez <slp@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Diffstat (limited to 'block')
-rw-r--r--block/mirror.c16
1 files changed, 16 insertions, 0 deletions
diff --git a/block/mirror.c b/block/mirror.c
index 010fdaf..eb9a4cd 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -80,6 +80,7 @@ typedef struct MirrorBlockJob {
bool initial_zeroing_ongoing;
int in_active_write_counter;
bool prepared;
+ bool in_drain;
} MirrorBlockJob;
typedef struct MirrorBDSOpaque {
@@ -683,6 +684,7 @@ static int mirror_exit_common(Job *job)
/* The mirror job has no requests in flight any more, but we need to
* drain potential other users of the BDS before changing the graph. */
+ assert(s->in_drain);
bdrv_drained_begin(target_bs);
bdrv_replace_node(to_replace, target_bs, &local_err);
bdrv_drained_end(target_bs);
@@ -721,6 +723,7 @@ static int mirror_exit_common(Job *job)
bs_opaque->job = NULL;
bdrv_drained_end(src);
+ s->in_drain = false;
bdrv_unref(mirror_top_bs);
bdrv_unref(src);
@@ -1004,10 +1007,12 @@ static int coroutine_fn mirror_run(Job *job, Error **errp)
*/
trace_mirror_before_drain(s, cnt);
+ s->in_drain = true;
bdrv_drained_begin(bs);
cnt = bdrv_get_dirty_count(s->dirty_bitmap);
if (cnt > 0 || mirror_flush(s) < 0) {
bdrv_drained_end(bs);
+ s->in_drain = false;
continue;
}
@@ -1055,6 +1060,7 @@ immediate_exit:
bdrv_dirty_iter_free(s->dbi);
if (need_drain) {
+ s->in_drain = true;
bdrv_drained_begin(bs);
}
@@ -1123,6 +1129,16 @@ static void coroutine_fn mirror_pause(Job *job)
static bool mirror_drained_poll(BlockJob *job)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
+
+ /* If the job isn't paused nor cancelled, we can't be sure that it won't
+ * issue more requests. We make an exception if we've reached this point
+ * from one of our own drain sections, to avoid a deadlock waiting for
+ * ourselves.
+ */
+ if (!s->common.job.paused && !s->common.job.cancelled && !s->in_drain) {
+ return true;
+ }
+
return !!s->in_flight;
}