Commit ccb9dc10129954d0bcd7814298ed445e684d5a2a ("linux-aio: Cancel BH
if not needed") exposed a side-effect of scheduling the BH for nested
event loops. When io_getevents(2) fetches MAX_EVENTS events then it's
necessary to call it again. Failure to do so can lead to hung I/O
because the eventfd has already been cleared and the completion BH will
not run again.
This patch fixes the hang by calling io_getevents(2) again if the events
array was totally full.
Reported-by: Roman Penyaev <roman.peny...@profitbricks.com>
Signed-off-by: Stefan Hajnoczi <stefa...@redhat.com>
---
block/linux-aio.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/block/linux-aio.c b/block/linux-aio.c
index e468960..af15f85 100644
--- a/block/linux-aio.c
+++ b/block/linux-aio.c
@@ -117,6 +117,7 @@ static void qemu_laio_completion_bh(void *opaque)
LinuxAioState *s = opaque;
/* Fetch more completion events when empty */
+more_events:
if (s->event_idx == s->event_max) {
do {
struct timespec ts = { 0 };
@@ -146,6 +147,10 @@ static void qemu_laio_completion_bh(void *opaque)
qemu_laio_process_completion(laiocb);
}
+ if (s->event_idx == MAX_EVENTS) {
+ goto more_events; /* there might still be events waiting for us */
+ }
+
if (!s->io_q.plugged && !QSIMPLEQ_EMPTY(&s->io_q.pending)) {
ioq_submit(s);
}
--
2.7.4
