From 8ca94edad4b07d6191bc4761a44d8289b0f8ad5d Mon Sep 17 00:00:00 2001

From: John Snow <jsnow@redhat.com>

Date: Mon, 10 Sep 2018 18:17:41 +0200

Subject: [PATCH 03/25] jobs: add exit shim

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

Message-id: <20180910181803.11781-4-jsnow@redhat.com>

Patchwork-id: 82104

O-Subject: [RHEL-7.6 qemu-kvm-rhev PATCH 03/25] jobs: add exit shim

Bugzilla: 1626061

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

RH-Acked-by: Jeffrey Cody <jcody@redhat.com>

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

All jobs do the same thing when they leave their running loop:

- Store the return code in a structure

- wait to receive this structure in the main thread

- signal job completion via job_completed

Few jobs do anything beyond exactly this. Consolidate this exit

logic for a net reduction in SLOC.

More seriously, when we utilize job_defer_to_main_loop_bh to call

a function that calls job_completed, job_finalize_single will run

in a context where it has recursively taken the aio_context lock,

which can cause hangs if it puts down a reference that causes a flush.

You can observe this in practice by looking at mirror_exit's careful

placement of job_completed and bdrv_unref calls.

If we centralize job exiting, we can signal job completion from outside

of the aio_context, which should allow for job cleanup code to run with

only one lock, which makes cleanup callbacks less tricky to write.

Signed-off-by: John Snow <jsnow@redhat.com>

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

Message-id: 20180830015734.19765-4-jsnow@redhat.com

Reviewed-by: Jeff Cody <jcody@redhat.com>

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

(cherry picked from commit 00359a71d45a414ee47d8e423104dc0afd24ec65)

Signed-off-by: John Snow <jsnow@redhat.com>

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

---

 include/qemu/job.h | 11 +++++++++++

 job.c              | 18 ++++++++++++++++++

 2 files changed, 29 insertions(+)

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

index 905dfdd..24b5f3f 100644

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

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

@@ -209,6 +209,17 @@ struct JobDriver {

     void (*drain)(Job *job);

     /**

+     * If the callback is not NULL, exit will be invoked from the main thread

+     * when the job's coroutine has finished, but before transactional

+     * convergence; before @prepare or @abort.

+     *

+     * FIXME TODO: This callback is only temporary to transition remaining jobs

+     * to prepare/commit/abort/clean callbacks and will be removed before 3.1.

+     * is released.

+     */

+    void (*exit)(Job *job);

+

+    /**

      * If the callback is not NULL, prepare will be invoked when all the jobs

      * belonging to the same transaction complete; or upon this job's completion

      * if it is not in a transaction.

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

index 020ee0d..a814857 100644

--- a/job.c

+++ b/job.c

@@ -530,6 +530,18 @@ void job_drain(Job *job)

     }

 }

+static void job_exit(void *opaque)

+{

+    Job *job = (Job *)opaque;

+    AioContext *aio_context = job->aio_context;

+

+    if (job->driver->exit) {

+        aio_context_acquire(aio_context);

+        job->driver->exit(job);

+        aio_context_release(aio_context);

+    }

+    job_completed(job, job->ret);

+}

 /**

  * All jobs must allow a pause point before entering their job proper. This

@@ -542,6 +554,12 @@ 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);

+    if (!job->deferred_to_main_loop) {

+        job->deferred_to_main_loop = true;

+        aio_bh_schedule_oneshot(qemu_get_aio_context(),

+                                job_exit,

+                                job);

+    }

 }

-- 

1.8.3.1