Merge remote-tracking branch 'remotes/xanclic/tags/pull-block-2018-09-25' into staging

Block layer patches:
- Drain fixes
- node-name parameters for block-commit
- Refactor block jobs to use transactional callbacks for exiting

# gpg: Signature made Tue 25 Sep 2018 16:12:44 BST
# gpg:                using RSA key F407DB0061D5CF40
# gpg: Good signature from "Max Reitz <mreitz@redhat.com>"
# Primary key fingerprint: 91BE B60A 30DB 3E88 57D1  1829 F407 DB00 61D5 CF40

* remotes/xanclic/tags/pull-block-2018-09-25: (42 commits)
  test-bdrv-drain: Test draining job source child and parent
  block: Use a single global AioWait
  test-bdrv-drain: Fix outdated comments
  test-bdrv-drain: AIO_WAIT_WHILE() in job .commit/.abort
  job: Avoid deadlocks in job_completed_txn_abort()
  test-bdrv-drain: Test nested poll in bdrv_drain_poll_top_level()
  block: Remove aio_poll() in bdrv_drain_poll variants
  blockjob: Lie better in child_job_drained_poll()
  block-backend: Decrease in_flight only after callback
  block-backend: Fix potential double blk_delete()
  block-backend: Add .drained_poll callback
  block: Add missing locking in bdrv_co_drain_bh_cb()
  test-bdrv-drain: Test AIO_WAIT_WHILE() in completion callback
  job: Use AIO_WAIT_WHILE() in job_finish_sync()
  test-blockjob: Acquire AioContext around job_cancel_sync()
  test-bdrv-drain: Drain with block jobs in an I/O thread
  aio-wait: Increase num_waiters even in home thread
  blockjob: Wake up BDS when job becomes idle
  job: Fix missing locking due to mismerge
  job: Fix nested aio_poll() hanging in job_txn_apply
  ...

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

1 files changed, 54 insertions, 43 deletions

diff --git a/block/commit.c b/block/commit.c
index da69165de3..a2da5740b0 100644
--- a/block/commit.c
+++ b/block/commit.c
@@ -36,6 +36,7 @@ typedef struct CommitBlockJob {
     BlockDriverState *commit_top_bs;
     BlockBackend *top;
     BlockBackend *base;
+    BlockDriverState *base_bs;
     BlockdevOnError on_error;
     int base_flags;
     char *backing_file_str;
@@ -68,61 +69,67 @@ static int coroutine_fn commit_populate(BlockBackend *bs, BlockBackend *base,
     return 0;
 }
 
-static void commit_exit(Job *job)
+static int commit_prepare(Job *job)
 {
     CommitBlockJob *s = container_of(job, CommitBlockJob, common.job);
-    BlockJob *bjob = &s->common;
-    BlockDriverState *top = blk_bs(s->top);
-    BlockDriverState *base = blk_bs(s->base);
-    BlockDriverState *commit_top_bs = s->commit_top_bs;
-    bool remove_commit_top_bs = false;
-
-    /* Make sure commit_top_bs and top stay around until bdrv_replace_node() */
-    bdrv_ref(top);
-    bdrv_ref(commit_top_bs);
 
     /* Remove base node parent that still uses BLK_PERM_WRITE/RESIZE before
      * the normal backing chain can be restored. */
     blk_unref(s->base);
+    s->base = NULL;
+
+    /* FIXME: bdrv_drop_intermediate treats total failures and partial failures
+     * identically. Further work is needed to disambiguate these cases. */
+    return bdrv_drop_intermediate(s->commit_top_bs, s->base_bs,
+                                  s->backing_file_str);
+}
 
-    if (!job_is_cancelled(job) && job->ret == 0) {
-        /* success */
-        job->ret = bdrv_drop_intermediate(s->commit_top_bs, base,
-                                          s->backing_file_str);
-    } else {
-        /* XXX Can (or should) we somehow keep 'consistent read' blocked even
-         * after the failed/cancelled commit job is gone? If we already wrote
-         * something to base, the intermediate images aren't valid any more. */
-        remove_commit_top_bs = true;
+static void commit_abort(Job *job)
+{
+    CommitBlockJob *s = container_of(job, CommitBlockJob, common.job);
+    BlockDriverState *top_bs = blk_bs(s->top);
+
+    /* Make sure commit_top_bs and top stay around until bdrv_replace_node() */
+    bdrv_ref(top_bs);
+    bdrv_ref(s->commit_top_bs);
+
+    if (s->base) {
+        blk_unref(s->base);
     }
 
+    /* free the blockers on the intermediate nodes so that bdrv_replace_nodes
+     * can succeed */
+    block_job_remove_all_bdrv(&s->common);
+
+    /* If bdrv_drop_intermediate() failed (or was not invoked), remove the
+     * commit filter driver from the backing chain now. Do this as the final
+     * step so that the 'consistent read' permission can be granted.
+     *
+     * XXX Can (or should) we somehow keep 'consistent read' blocked even
+     * after the failed/cancelled commit job is gone? If we already wrote
+     * something to base, the intermediate images aren't valid any more. */
+    bdrv_child_try_set_perm(s->commit_top_bs->backing, 0, BLK_PERM_ALL,
+                            &error_abort);
+    bdrv_replace_node(s->commit_top_bs, backing_bs(s->commit_top_bs),
+                      &error_abort);
+
+    bdrv_unref(s->commit_top_bs);
+    bdrv_unref(top_bs);
+}
+
+static void commit_clean(Job *job)
+{
+    CommitBlockJob *s = container_of(job, CommitBlockJob, common.job);
+
     /* restore base open flags here if appropriate (e.g., change the base back
      * to r/o). These reopens do not need to be atomic, since we won't abort
      * even on failure here */
-    if (s->base_flags != bdrv_get_flags(base)) {
-        bdrv_reopen(base, s->base_flags, NULL);
+    if (s->base_flags != bdrv_get_flags(s->base_bs)) {
+        bdrv_reopen(s->base_bs, s->base_flags, NULL);
     }
+
     g_free(s->backing_file_str);
     blk_unref(s->top);
-
-    /* If there is more than one reference to the job (e.g. if called from
-     * job_finish_sync()), job_completed() won't free it and therefore the
-     * blockers on the intermediate nodes remain. This would cause
-     * bdrv_set_backing_hd() to fail. */
-    block_job_remove_all_bdrv(bjob);
-
-    /* If bdrv_drop_intermediate() didn't already do that, remove the commit
-     * filter driver from the backing chain. Do this as the final step so that
-     * the 'consistent read' permission can be granted.  */
-    if (remove_commit_top_bs) {
-        bdrv_child_try_set_perm(commit_top_bs->backing, 0, BLK_PERM_ALL,
-                                &error_abort);
-        bdrv_replace_node(commit_top_bs, backing_bs(commit_top_bs),
-                          &error_abort);
-    }
-
-    bdrv_unref(commit_top_bs);
-    bdrv_unref(top);
 }
 
 static int coroutine_fn commit_run(Job *job, Error **errp)
@@ -211,7 +218,9 @@ static const BlockJobDriver commit_job_driver = {
         .user_resume   = block_job_user_resume,
         .drain         = block_job_drain,
         .run           = commit_run,
-        .exit          = commit_exit,
+        .prepare       = commit_prepare,
+        .abort         = commit_abort,
+        .clean         = commit_clean
     },
 };
 
@@ -249,7 +258,8 @@ static BlockDriver bdrv_commit_top = {
 };
 
 void commit_start(const char *job_id, BlockDriverState *bs,
-                  BlockDriverState *base, BlockDriverState *top, int64_t speed,
+                  BlockDriverState *base, BlockDriverState *top,
+                  int creation_flags, int64_t speed,
                   BlockdevOnError on_error, const char *backing_file_str,
                   const char *filter_node_name, Error **errp)
 {
@@ -267,7 +277,7 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     }
 
     s = block_job_create(job_id, &commit_job_driver, NULL, bs, 0, BLK_PERM_ALL,
-                         speed, JOB_DEFAULT, NULL, NULL, errp);
+                         speed, creation_flags, NULL, NULL, errp);
     if (!s) {
         return;
     }
@@ -344,6 +354,7 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     if (ret < 0) {
         goto fail;
     }
+    s->base_bs = base;
 
     /* Required permissions are already taken with block_job_add_bdrv() */
     s->top = blk_new(0, BLK_PERM_ALL);