From 4afeffc8572f40d8844b946a30c00b10da4442b1 Mon Sep 17 00:00:00 2001 From: Jeff Cody Date: Fri, 17 Nov 2017 22:26:16 -0500 Subject: [PATCH] blockjob: do not allow coroutine double entry or entry-after-completion When block_job_sleep_ns() is called, the co-routine is scheduled for future execution. If we allow the job to be re-entered prior to the scheduled time, we present a race condition in which a coroutine can be entered recursively, or even entered after the coroutine is deleted. The job->busy flag is used by blockjobs when a coroutine is busy executing. The function 'block_job_enter()' obeys the busy flag, and will not enter a coroutine if set. If we sleep a job, we need to leave the busy flag set, so that subsequent calls to block_job_enter() are prevented. This changes the prior behavior of block_job_cancel() being able to immediately wake up and cancel a job; in practice, this should not be an issue, as the coroutine sleep times are generally very small, and the cancel will occur the next time the coroutine wakes up. This fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1508708 Signed-off-by: Jeff Cody Reviewed-by: Stefan Hajnoczi --- blockjob.c | 7 +++++-- include/block/blockjob_int.h | 3 ++- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/blockjob.c b/blockjob.c index 3a0c49137e..ff9a614531 100644 --- a/blockjob.c +++ b/blockjob.c @@ -797,11 +797,14 @@ void block_job_sleep_ns(BlockJob *job, QEMUClockType type, int64_t ns) return; } - job->busy = false; + /* We need to leave job->busy set here, because when we have + * put a coroutine to 'sleep', we have scheduled it to run in + * the future. We cannot enter that same coroutine again before + * it wakes and runs, otherwise we risk double-entry or entry after + * completion. */ if (!block_job_should_pause(job)) { co_aio_sleep_ns(blk_get_aio_context(job->blk), type, ns); } - job->busy = true; block_job_pause_point(job); } diff --git a/include/block/blockjob_int.h b/include/block/blockjob_int.h index f13ad05c0d..43f3be2965 100644 --- a/include/block/blockjob_int.h +++ b/include/block/blockjob_int.h @@ -143,7 +143,8 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, * @ns: How many nanoseconds to stop for. * * Put the job to sleep (assuming that it wasn't canceled) for @ns - * nanoseconds. Canceling the job will interrupt the wait immediately. + * nanoseconds. Canceling the job will not interrupt the wait, so the + * cancel will not process until the coroutine wakes up. */ void block_job_sleep_ns(BlockJob *job, QEMUClockType type, int64_t ns); -- 2.11.4.GIT