aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorVladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>2020-07-27 21:47:49 +0300
committerEric Blake <eblake@redhat.com>2020-07-28 09:54:43 -0500
commitfbeb3e63b34a1af4a968031de1c82e5edf20bf6c (patch)
tree89dc9e3d352e7b0afe1c1e67647f9ef85eaa7bc8
parentdd1ec1a4afe190e030edfa052d95c9e6e065438c (diff)
block/nbd: on shutdown terminate connection attempt
On shutdown nbd driver may be in a connecting state. We should shutdown it as well, otherwise we may hang in nbd_teardown_connection, waiting for conneciton_co to finish in BDRV_POLL_WHILE(bs, s->connection_co) loop if remote server is down. How to reproduce the dead lock: 1. Create nbd-fault-injector.conf with the following contents: [inject-error "mega1"] event=data io=readwrite when=before 2. In one terminal run nbd-fault-injector in a loop, like this: n=1; while true; do echo $n; ((n++)); ./nbd-fault-injector.py 127.0.0.1:10000 nbd-fault-injector.conf; done 3. In another terminal run qemu-io in a loop, like this: n=1; while true; do echo $n; ((n++)); ./qemu-io -c 'read 0 512' nbd://127.0.0.1:10000; done After some time, qemu-io will hang. Note, that this hang may be triggered by another bug, so the whole case is fixed only together with commit "block/nbd: allow drain during reconnect attempt". Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-Id: <20200727184751.15704-4-vsementsov@virtuozzo.com> Signed-off-by: Eric Blake <eblake@redhat.com>
-rw-r--r--block/nbd.c15
1 files changed, 11 insertions, 4 deletions
diff --git a/block/nbd.c b/block/nbd.c
index ee9ab7512b..620c97be6b 100644
--- a/block/nbd.c
+++ b/block/nbd.c
@@ -209,11 +209,15 @@ static void nbd_teardown_connection(BlockDriverState *bs)
{
BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
- if (s->state == NBD_CLIENT_CONNECTED) {
+ if (s->ioc) {
/* finish any pending coroutines */
- assert(s->ioc);
qio_channel_shutdown(s->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
+ } else if (s->sioc) {
+ /* abort negotiation */
+ qio_channel_shutdown(QIO_CHANNEL(s->sioc), QIO_CHANNEL_SHUTDOWN_BOTH,
+ NULL);
}
+
s->state = NBD_CLIENT_QUIT;
if (s->connection_co) {
if (s->connection_co_sleep_ns_state) {
@@ -1459,6 +1463,9 @@ static int nbd_client_handshake(BlockDriverState *bs, QIOChannelSocket *sioc,
int ret;
trace_nbd_client_handshake(s->export);
+
+ s->sioc = sioc;
+
qio_channel_set_blocking(QIO_CHANNEL(sioc), false, NULL);
qio_channel_attach_aio_context(QIO_CHANNEL(sioc), aio_context);
@@ -1473,6 +1480,7 @@ static int nbd_client_handshake(BlockDriverState *bs, QIOChannelSocket *sioc,
g_free(s->info.name);
if (ret < 0) {
object_unref(OBJECT(sioc));
+ s->sioc = NULL;
return ret;
}
if (s->x_dirty_bitmap && !s->info.base_allocation) {
@@ -1498,8 +1506,6 @@ static int nbd_client_handshake(BlockDriverState *bs, QIOChannelSocket *sioc,
}
}
- s->sioc = sioc;
-
if (!s->ioc) {
s->ioc = QIO_CHANNEL(sioc);
object_ref(OBJECT(s->ioc));
@@ -1520,6 +1526,7 @@ static int nbd_client_handshake(BlockDriverState *bs, QIOChannelSocket *sioc,
nbd_send_request(s->ioc ?: QIO_CHANNEL(sioc), &request);
object_unref(OBJECT(sioc));
+ s->sioc = NULL;
return ret;
}