mirror of
https://github.com/xemu-project/xemu.git
synced 2024-11-25 04:30:02 +00:00
eabc977973
This patch rewrites the ctx->dispatching optimization, which was the cause
of some mysterious hangs that could be reproduced on aarch64 KVM only.
The hangs were indirectly caused by aio_poll() and in particular by
flash memory updates's call to blk_write(), which invokes aio_poll().
Fun stuff: they had an extremely short race window, so much that
adding all kind of tracing to either the kernel or QEMU made it
go away (a single printf made it half as reproducible).
On the plus side, the failure mode (a hang until the next keypress)
made it very easy to examine the state of the process with a debugger.
And there was a very nice reproducer from Laszlo, which failed pretty
often (more than half of the time) on any version of QEMU with a non-debug
kernel; it also failed fast, while still in the firmware. So, it could
have been worse.
For some unknown reason they happened only with virtio-scsi, but
that's not important. It's more interesting that they disappeared with
io=native, making thread-pool.c a likely suspect for where the bug arose.
thread-pool.c is also one of the few places which use bottom halves
across threads, by the way.
I hope that no other similar bugs exist, but just in case :) I am
going to describe how the successful debugging went... Since the
likely culprit was the ctx->dispatching optimization, which mostly
affects bottom halves, the first observation was that there are two
qemu_bh_schedule() invocations in the thread pool: the one in the aio
worker and the one in thread_pool_completion_bh. The latter always
causes the optimization to trigger, the former may or may not. In
order to restrict the possibilities, I introduced new functions
qemu_bh_schedule_slow() and qemu_bh_schedule_fast():
/* qemu_bh_schedule_slow: */
ctx = bh->ctx;
bh->idle = 0;
if (atomic_xchg(&bh->scheduled, 1) == 0) {
event_notifier_set(&ctx->notifier);
}
/* qemu_bh_schedule_fast: */
ctx = bh->ctx;
bh->idle = 0;
assert(ctx->dispatching);
atomic_xchg(&bh->scheduled, 1);
Notice how the atomic_xchg is still in qemu_bh_schedule_slow(). This
was already debated a few months ago, so I assumed it to be correct.
In retrospect this was a very good idea, as you'll see later.
Changing thread_pool_completion_bh() to qemu_bh_schedule_fast() didn't
trigger the assertion (as expected). Changing the worker's invocation
to qemu_bh_schedule_slow() didn't hide the bug (another assumption
which luckily held). This already limited heavily the amount of
interaction between the threads, hinting that the problematic events
must have triggered around thread_pool_completion_bh().
As mentioned early, invoking a debugger to examine the state of a
hung process was pretty easy; the iothread was always waiting on a
poll(..., -1) system call. Infinite timeouts are much rarer on x86,
and this could be the reason why the bug was never observed there.
With the buggy sequence more or less resolved to an interaction between
thread_pool_completion_bh() and poll(..., -1), my "tracing" strategy was
to just add a few qemu_clock_get_ns(QEMU_CLOCK_REALTIME) calls, hoping
that the ordering of aio_ctx_prepare(), aio_ctx_dispatch, poll() and
qemu_bh_schedule_fast() would provide some hint. The output was:
(gdb) p last_prepare
$3 = 103885451
(gdb) p last_dispatch
$4 = 103876492
(gdb) p last_poll
$5 = 115909333
(gdb) p last_schedule
$6 = 115925212
Notice how the last call to qemu_poll_ns() came after aio_ctx_dispatch().
This makes little sense unless there is an aio_poll() call involved,
and indeed with a slightly different instrumentation you can see that
there is one:
(gdb) p last_prepare
$3 = 107569679
(gdb) p last_dispatch
$4 = 107561600
(gdb) p last_aio_poll
$5 = 110671400
(gdb) p last_schedule
$6 = 110698917
So the scenario becomes clearer:
iothread VCPU thread
--------------------------------------------------------------------------
aio_ctx_prepare
aio_ctx_check
qemu_poll_ns(timeout=-1)
aio_poll
aio_dispatch
thread_pool_completion_bh
qemu_bh_schedule()
At this point bh->scheduled = 1 and the iothread has not been woken up.
The solution must be close, but this alone should not be a problem,
because the bottom half is only rescheduled to account for rare situations
(see commit
|
||
|---|---|---|
| .. | ||
| acpi-test-data | ||
| image-fuzzer | ||
| libqos | ||
| multiboot | ||
| qapi-schema | ||
| qemu-iotests | ||
| rocker | ||
| tcg | ||
| vmstate-static-checker-data | ||
| .gitignore | ||
| ac97-test.c | ||
| ahci-test.c | ||
| bios-tables-test.c | ||
| boot-order-test.c | ||
| check-block.sh | ||
| check-qdict.c | ||
| check-qfloat.c | ||
| check-qint.c | ||
| check-qjson.c | ||
| check-qlist.c | ||
| check-qom-interface.c | ||
| check-qom-proplist.c | ||
| check-qstring.c | ||
| display-vga-test.c | ||
| drive_del-test.c | ||
| e1000-test.c | ||
| eepro100-test.c | ||
| endianness-test.c | ||
| es1370-test.c | ||
| fdc-test.c | ||
| fw_cfg-test.c | ||
| hd-geo-test.c | ||
| i440fx-test.c | ||
| i82801b11-test.c | ||
| ide-test.c | ||
| intel-hda-test.c | ||
| ioh3420-test.c | ||
| ipoctal232-test.c | ||
| libqtest.c | ||
| libqtest.h | ||
| m48t59-test.c | ||
| Makefile | ||
| ne2000-test.c | ||
| nvme-test.c | ||
| pc-cpu-test.c | ||
| pcnet-test.c | ||
| pvpanic-test.c | ||
| q35-test.c | ||
| qemu-iotests-quick.sh | ||
| qom-test.c | ||
| rcutorture.c | ||
| rtc-test.c | ||
| rtl8139-test.c | ||
| spapr-phb-test.c | ||
| tco-test.c | ||
| test-aio.c | ||
| test-bitops.c | ||
| test-coroutine.c | ||
| test-crypto-cipher.c | ||
| test-crypto-hash.c | ||
| test-cutils.c | ||
| test-hbitmap.c | ||
| test-int128.c | ||
| test-iov.c | ||
| test-mul64.c | ||
| test-opts-visitor.c | ||
| test-qdev-global-props.c | ||
| test-qemu-opts.c | ||
| test-qmp-commands.c | ||
| test-qmp-event.c | ||
| test-qmp-input-strict.c | ||
| test-qmp-input-visitor.c | ||
| test-qmp-output-visitor.c | ||
| test-rcu-list.c | ||
| test-rfifolock.c | ||
| test-string-input-visitor.c | ||
| test-string-output-visitor.c | ||
| test-thread-pool.c | ||
| test-throttle.c | ||
| test-visitor-serialization.c | ||
| test-vmstate.c | ||
| test-write-threshold.c | ||
| test-x86-cpuid.c | ||
| test-xbzrle.c | ||
| tmp105-test.c | ||
| tpci200-test.c | ||
| usb-hcd-ehci-test.c | ||
| usb-hcd-ohci-test.c | ||
| usb-hcd-uhci-test.c | ||
| usb-hcd-xhci-test.c | ||
| vhost-user-test.c | ||
| virtio-9p-test.c | ||
| virtio-balloon-test.c | ||
| virtio-blk-test.c | ||
| virtio-console-test.c | ||
| virtio-net-test.c | ||
| virtio-rng-test.c | ||
| virtio-scsi-test.c | ||
| virtio-serial-test.c | ||
| vmxnet3-test.c | ||
| wdt_ib700-test.c | ||