This occurs on v2.9.0-rc4, but not on v2.8.0.
When running QEMU with an iothread, and then performing a block-mirror, if
we do a system-reset after the BLOCK_JOB_READY event has emitted, qemu
becomes deadlocked.
The block job is not paused, nor cancelled, so we are stuck in the while
loop in block_job_detach_aio_context:
static void block_job_detach_aio_context(void *opaque)
{
BlockJob *job = opaque;
/* In case the job terminates during aio_poll()... */
block_job_ref(job);
block_job_pause(job);
while (!job->paused && !job->completed) {
block_job_drain(job);
}
block_job_unref(job);
}
Reproducer script and QAPI commands:
# QEMU script:
gdb --args /home/user/deploy-${1}/bin/qemu-system-x86_64 -enable-kvm -smp 4
-object iothread,id=iothread0 -drive
file=${2},if=none,id=drive-virtio-disk0,aio=native,cache=none,discard=unmap
-device
virtio-blk-pci,scsi=off,bus=pci.0,drive=drive-virtio-disk0,id=virtio-disk0,iothread=iothread0
-m 1024 -boot menu=on -qmp stdio -drive
file=${3},if=none,id=drive-data-disk0,format=qcow2,cache=none,aio=native,werror=stop,rerror=stop
-device
virtio-blk-pci,drive=drive-data-disk0,id=data-disk0,iothread=iothread0,bus=pci.0,addr=0x7
# QAPI commands:
{ "execute": "drive-mirror", "arguments": { "device": "drive-data-disk0",
"target": "/home/user/sn1", "format": "qcow2", "mode": "absolute-paths",
"sync": "full", "speed": 1000000000, "on-source-error": "stop",
"on-target-error": "stop" } }
# after BLOCK_JOB_READY, do system reset
{ "execute": "system_reset" }
gbd bt:
(gdb) bt
#0 0x0000555555aa79f3 in bdrv_drain_recurse (bs=bs@entry=0x55555783e900) at
block/io.c:164
#1 0x0000555555aa825d in bdrv_drained_begin (bs=bs@entry=0x55555783e900) at
block/io.c:231
#2 0x0000555555aa8449 in bdrv_drain (bs=0x55555783e900) at block/io.c:265
#3 0x0000555555a9c356 in blk_drain (blk=<optimized out>) at
block/block-backend.c:1383
#4 0x0000555555aa3cfd in mirror_drain (job=<optimized out>) at
block/mirror.c:1000
#5 0x0000555555a66e11 in block_job_detach_aio_context (opaque=0x555557a19a40)
at blockjob.c:142
#6 0x0000555555a62f4d in bdrv_detach_aio_context (bs=bs@entry=0x555557839410)
at block.c:4357
#7 0x0000555555a63116 in bdrv_set_aio_context (bs=bs@entry=0x555557839410,
new_context=new_context@entry=0x55555668bc20) at block.c:4418
#8 0x0000555555a9d326 in blk_set_aio_context (blk=0x5555566db520,
new_context=0x55555668bc20) at block/block-backend.c:1662
#9 0x00005555557e38da in virtio_blk_data_plane_stop (vdev=<optimized out>) at
/home/jcody/work/upstream/qemu-kvm/hw/block/dataplane/virtio-blk.c:262
#10 0x00005555559f9d5f in virtio_bus_stop_ioeventfd
(bus=bus@entry=0x5555583089a8) at hw/virtio/virtio-bus.c:246
#11 0x00005555559fa49b in virtio_bus_stop_ioeventfd
(bus=bus@entry=0x5555583089a8) at hw/virtio/virtio-bus.c:238
#12 0x00005555559f6a18 in virtio_pci_stop_ioeventfd (proxy=0x555558300510) at
hw/virtio/virtio-pci.c:348
#13 0x00005555559f6a18 in virtio_pci_reset (qdev=<optimized out>) at
hw/virtio/virtio-pci.c:1872
#14 0x00005555559139a9 in qdev_reset_one (dev=<optimized out>,
opaque=<optimized out>) at hw/core/qdev.c:310
#15 0x0000555555916738 in qbus_walk_children (bus=0x55555693aa30,
pre_devfn=0x0, pre_busfn=0x0, post_devfn=0x5555559139a0 <qdev_reset_one>,
post_busfn=0x5555559120f0 <qbus_reset_one>, opaque=0x0) at hw/core/bus.c:59
#16 0x0000555555913318 in qdev_walk_children (dev=0x5555569387d0,
pre_devfn=0x0, pre_busfn=0x0, post_devfn=0x5555559139a0 <qdev_reset_one>,
post_busfn=0x5555559120f0 <qbus_reset_one>, opaque=0x0) at hw/core/qdev.c:617
#17 0x0000555555916738 in qbus_walk_children (bus=0x555556756f70,
pre_devfn=0x0, pre_busfn=0x0, post_devfn=0x5555559139a0 <qdev_reset_one>,
post_busfn=0x5555559120f0 <qbus_reset_one>, opaque=0x0) at hw/core/bus.c:59
#18 0x00005555559168ca in qemu_devices_reset () at hw/core/reset.c:69
#19 0x000055555581fcbb in pc_machine_reset () at
/home/jcody/work/upstream/qemu-kvm/hw/i386/pc.c:2234
#20 0x00005555558a4d96 in qemu_system_reset (report=<optimized out>) at
vl.c:1697
#21 0x000055555577157a in main_loop_should_exit () at vl.c:1865
#22 0x000055555577157a in main_loop () at vl.c:1902
#23 0x000055555577157a in main (argc=<optimized out>, argv=<optimized out>,
envp=<optimized out>) at vl.c:4709
-Jeff
