[dpdk-dev] [PATCH v3 13/19] vhost: enable rings at the right time

[Maxime Coquelin <maxime.coquelin@redhat.com>]

When VHOST_USER_F_PROTOCOL_FEATURES is negotiated, the ring is not
enabled when started, but enabled through dedicated
VHOST_USER_SET_VRING_ENABLE request.

When not negotiated, the ring is started in enabled state, at
VHOST_USER_SET_VRING_KICK request time.

Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
 lib/librte_vhost/vhost.c      | 6 ------
 lib/librte_vhost/vhost_user.c | 9 +++++++++
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/lib/librte_vhost/vhost.c b/lib/librte_vhost/vhost.c
index 6f243534e..0e2ad3322 100644
--- a/lib/librte_vhost/vhost.c
+++ b/lib/librte_vhost/vhost.c
@@ -158,12 +158,6 @@ init_vring_queue(struct virtio_net *dev, uint32_t vring_idx)
 	/* Backends are set to -1 indicating an inactive device. */
 	vq->backend = -1;
 
-	/*
-	 * always set the vq to enabled; this is to keep compatibility
-	 * with the old QEMU, whereas there is no SET_VRING_ENABLE message.
-	 */
-	vq->enabled = 1;
-
 	TAILQ_INIT(&vq->zmbuf_list);
 }
 
diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index 0f23ea388..8aca7ef7e 100644
--- a/lib/librte_vhost/vhost_user.c
+++ b/lib/librte_vhost/vhost_user.c
@@ -699,6 +699,15 @@ vhost_user_set_vring_kick(struct virtio_net *dev, struct VhostUserMsg *pmsg)
 		"vring kick idx:%d file:%d\n", file.index, file.fd);
 
 	vq = dev->virtqueue[file.index];
+
+	/*
+	 * When VHOST_USER_F_PROTOCOL_FEATURES is not negotiated,
+	 * the ring starts already enabled. Otherwise, it is enabled via
+	 * the SET_VRING_ENABLE message.
+	 */
+	if (!(dev->features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES)))
+		vq->enabled = 1;
+
 	if (vq->kickfd >= 0)
 		close(vq->kickfd);
 	vq->kickfd = file.fd;
-- 
2.13.6