From 03560a7d6e57ca2ba3198d5051acfdd1e345f9a4 Mon Sep 17 00:00:00 2001 From: Jeffrey Cody Date: Tue, 5 Dec 2017 16:03:17 +0100 Subject: [PATCH 12/21] blockjob: Make block_job_pause_all() keep a reference to the jobs RH-Author: Jeffrey Cody Message-id: Patchwork-id: 78161 O-Subject: [RHV7.5 qemu-kvm-rhev PATCH 12/11] blockjob: Make block_job_pause_all() keep a reference to the jobs Bugzilla: 1506531 RH-Acked-by: John Snow RH-Acked-by: Paolo Bonzini RH-Acked-by: Stefan Hajnoczi From: Alberto Garcia Starting from commit 40840e419be31e6a32e6ea24511c74b389d5e0e4 we are pausing all block jobs during bdrv_reopen_multiple() to prevent any of them from finishing and removing nodes from the graph while they are being reopened. It turns out that pausing a block job doesn't necessarily prevent it from finishing: a paused block job can still run its exit function from the main loop and call block_job_completed(). The mirror block job in particular always goes to the main loop while it is paused (by virtue of the bdrv_drained_begin() call in mirror_run()). Destroying a paused block job during bdrv_reopen_multiple() has two consequences: 1) The references to the nodes involved in the job are released, possibly destroying some of them. If those nodes were in the reopen queue this would trigger the problem originally described in commit 40840e419be, crashing QEMU. 2) At the end of bdrv_reopen_multiple(), bdrv_drain_all_end() would not be doing all necessary bdrv_parent_drained_end() calls. I can reproduce problem 1) easily with iotest 030 by increasing STREAM_BUFFER_SIZE from 512KB to 8MB in block/stream.c, or by tweaking the iotest like in this example: https://lists.gnu.org/archive/html/qemu-block/2017-11/msg00934.html This patch keeps an additional reference to all block jobs between block_job_pause_all() and block_job_resume_all(), guaranteeing that they are kept alive. Signed-off-by: Alberto Garcia Signed-off-by: Kevin Wolf (cherry picked from commit 3d5d319e1221082974711af1d09d82f0755c1698) Signed-off-by: Jeff Cody Signed-off-by: Miroslav Rezanina --- blockjob.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/blockjob.c b/blockjob.c index 84f526a..63aecce 100644 --- a/blockjob.c +++ b/blockjob.c @@ -730,6 +730,7 @@ void block_job_pause_all(void) AioContext *aio_context = blk_get_aio_context(job->blk); aio_context_acquire(aio_context); + block_job_ref(job); block_job_pause(job); aio_context_release(aio_context); } @@ -808,12 +809,14 @@ void coroutine_fn block_job_pause_point(BlockJob *job) void block_job_resume_all(void) { - BlockJob *job = NULL; - while ((job = block_job_next(job))) { + BlockJob *job, *next; + + QLIST_FOREACH_SAFE(job, &block_jobs, job_list, next) { AioContext *aio_context = blk_get_aio_context(job->blk); aio_context_acquire(aio_context); block_job_resume(job); + block_job_unref(job); aio_context_release(aio_context); } } -- 1.8.3.1