The vhost_user_read_cb() and rte_vhost_driver_unregister()
can be called at the same time by 2 threads, and may lead to deadlock.
Eg thread1 calls
vhost_user_read_cb()->vhost_user_get_vring_base()->destroy_device(),
then thread2 calls rte_vhost_driver_unregister(), and will retry the
fdset_try_del() in loop.
Some application implements destroy_device() as a blocking function, eg
OVS calls ovsrcu_synchronize() insides destroy_device(). As a result,
thread1(eg vhost_events) is blocked to wait quiesce of thread2(eg ovs-vswitchd),
and thread2 is in a loop to wait thread1 to give up the use of the vhost fd,
then leads to deadlock.
It is better to return -EAGAIN to application, who will decide how to handle
(eg OVS can call ovsrcu_quiesce() and then retry).
Signed-off-by: Zhike Wang <wangzh...@jd.com>
---
lib/librte_vhost/rte_vhost.h | 4 +++-
lib/librte_vhost/socket.c | 8 ++++----
2 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/lib/librte_vhost/rte_vhost.h b/lib/librte_vhost/rte_vhost.h
index c7b619a..276db11 100644
--- a/lib/librte_vhost/rte_vhost.h
+++ b/lib/librte_vhost/rte_vhost.h
@@ -389,7 +389,9 @@ void rte_vhost_log_used_vring(int vid, uint16_t vring_idx,
*/
int rte_vhost_driver_register(const char *path, uint64_t flags);
-/* Unregister vhost driver. This is only meaningful to vhost user. */
+/* Unregister vhost driver. This is only meaningful to vhost user.
+ * Return -EAGAIN if device is busy, and leave it to be handled by application.
+ */
int rte_vhost_driver_unregister(const char *path);
/**
diff --git a/lib/librte_vhost/socket.c b/lib/librte_vhost/socket.c
index 7c80121..a75a3f6 100644
--- a/lib/librte_vhost/socket.c
+++ b/lib/librte_vhost/socket.c
@@ -1027,7 +1027,8 @@ struct vhost_user_reconnect_list {
}
/**
- * Unregister the specified vhost socket
+ * Unregister the specified vhost socket.
+ * Return -EAGAIN if device is busy, and leave it to be handled by application.
*/
int
rte_vhost_driver_unregister(const char *path)
@@ -1039,7 +1040,6 @@ struct vhost_user_reconnect_list {
if (path == NULL)
return -1;
-again:
pthread_mutex_lock(&vhost_user.mutex);
for (i = 0; i < vhost_user.vsocket_cnt; i++) {
@@ -1063,7 +1063,7 @@ struct vhost_user_reconnect_list {
pthread_mutex_unlock(
&vsocket->conn_mutex);
pthread_mutex_unlock(&vhost_user.mutex);
- goto again;
+ return -EAGAIN;
}
VHOST_LOG_CONFIG(INFO,
@@ -1085,7 +1085,7 @@ struct vhost_user_reconnect_list {
if (fdset_try_del(&vhost_user.fdset,
vsocket->socket_fd) == -1) {
pthread_mutex_unlock(&vhost_user.mutex);
- goto again;
+ return -EAGAIN;
}
close(vsocket->socket_fd);
--
1.8.3.1
