From a174500971a42552a30d238bf9ec065d27fd4b32 Mon Sep 17 00:00:00 2001

From: Kevin Wolf <kwolf@redhat.com>

Date: Fri, 14 Sep 2018 10:55:36 +0200

Subject: [PATCH 45/49] blockjob: Lie better in child_job_drained_poll()

RH-Author: Kevin Wolf <kwolf@redhat.com>

Message-id: <20180914105540.18077-39-kwolf@redhat.com>

Patchwork-id: 82192

O-Subject: [RHV-7.6 qemu-kvm-rhev PATCH 38/42] blockjob: Lie better in child_job_drained_poll()

Bugzilla: 1601212

RH-Acked-by: John Snow <jsnow@redhat.com>

RH-Acked-by: Max Reitz <mreitz@redhat.com>

RH-Acked-by: Fam Zheng <famz@redhat.com>

Block jobs claim in .drained_poll() that they are in a quiescent state

as soon as job->deferred_to_main_loop is true. This is obviously wrong,

they still have a completion BH to run. We only get away with this

because commit 91af091f923 added an unconditional aio_poll(false) to the

drain functions, but this is bypassing the regular drain mechanisms.

However, just removing this and telling that the job is still active

doesn't work either: The completion callbacks themselves call drain

functions (directly, or indirectly with bdrv_reopen), so they would

deadlock then.

As a better lie, tell that the job is active as long as the BH is

pending, but falsely call it quiescent from the point in the BH when the

completion callback is called. At this point, nested drain calls won't

deadlock because they ignore the job, and outer drains will wait for the

job to really reach a quiescent state because the callback is already

running.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>

Reviewed-by: Max Reitz <mreitz@redhat.com>

Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>

---

 blockjob.c         |  2 +-

 include/qemu/job.h |  3 +++

 job.c              | 11 ++++++++++-

 3 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/blockjob.c b/blockjob.c

index 8d27e8e..617d86f 100644

--- a/blockjob.c

+++ b/blockjob.c

@@ -164,7 +164,7 @@ static bool child_job_drained_poll(BdrvChild *c)

     /* An inactive or completed job doesn't have any pending requests. Jobs

      * with !job->busy are either already paused or have a pause point after

      * being reentered, so no job driver code will run before they pause. */

-    if (!job->busy || job_is_completed(job) || job->deferred_to_main_loop) {

+    if (!job->busy || job_is_completed(job)) {

         return false;

     }

diff --git a/include/qemu/job.h b/include/qemu/job.h

index 35ac7a9..d1710f3 100644

--- a/include/qemu/job.h

+++ b/include/qemu/job.h

@@ -76,6 +76,9 @@ typedef struct Job {

      * Set to false by the job while the coroutine has yielded and may be

      * re-entered by job_enter(). There may still be I/O or event loop activity

      * pending. Accessed under block_job_mutex (in blockjob.c).

+     *

+     * When the job is deferred to the main loop, busy is true as long as the

+     * bottom half is still pending.

      */

     bool busy;

diff --git a/job.c b/job.c

index 47b5a11..42af9e2 100644

--- a/job.c

+++ b/job.c

@@ -852,7 +852,16 @@ static void job_exit(void *opaque)

     AioContext *ctx = job->aio_context;

     aio_context_acquire(ctx);

+

+    /* This is a lie, we're not quiescent, but still doing the completion

+     * callbacks. However, completion callbacks tend to involve operations that

+     * drain block nodes, and if .drained_poll still returned true, we would

+     * deadlock. */

+    job->busy = false;

+    job_event_idle(job);

+

     job_completed(job);

+

     aio_context_release(ctx);

 }

@@ -867,8 +876,8 @@ static void coroutine_fn job_co_entry(void *opaque)

     assert(job && job->driver && job->driver->run);

     job_pause_point(job);

     job->ret = job->driver->run(job, &job->err);

-    job_event_idle(job);

     job->deferred_to_main_loop = true;

+    job->busy = true;

     aio_bh_schedule_oneshot(qemu_get_aio_context(), job_exit, job);

 }

-- 

1.8.3.1