[RFC v4 09/11] vhost: Support VDUSE QUEUE_READY feature

["Eugenio Pérez" <eperezma@redhat.com>]

Add support for the VDUSE_F_QUEUE_READY feature.

In VDUSE, the dataplane is enabled only after control virtqueue so the
device is fully configured in the destination of a live migration before
the dataplane starts.  This message signals the VDUSE device when the
dataplane queues should be enabled.

Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
---
v4:
* Use new VDUSE_SET_FEATURES ioctl.
* Clarified some error messages and check for more conditions, like
  invalid queue index.

v3:
* Replace incorrect '%lx' DEBUG print format specifier with PRIx64

v2:
* Following latest comments on kernel series about VDUSE features, not
  checking API version but only check if VDUSE_GET_FEATURES success.
---
 lib/vhost/vduse.c | 85 +++++++++++++++++++++++++++++++++++++++++++++--
 lib/vhost/vhost.h |  1 +
 2 files changed, 84 insertions(+), 2 deletions(-)

diff --git a/lib/vhost/vduse.c b/lib/vhost/vduse.c
index a94cbb40a1d8..cb0bbed96012 100644
--- a/lib/vhost/vduse.c
+++ b/lib/vhost/vduse.c
@@ -39,12 +39,15 @@ static const char * const vduse_reqs_str[] = {
 	"VDUSE_SET_STATUS",
 	"VDUSE_UPDATE_IOTLB",
 	"VDUSE_SET_VQ_GROUP_ASID",
+	"VDUSE_SET_VQ_READY",
 };
 
 #define vduse_req_id_to_str(id) \
 	(id < RTE_DIM(vduse_reqs_str) ? \
 	vduse_reqs_str[id] : "Unknown")
 
+static const uint64_t supported_vduse_features = RTE_BIT64(VDUSE_F_QUEUE_READY);
+
 static uint64_t vduse_vq_to_group(struct virtio_net *dev, struct vhost_virtqueue *vq)
 {
 	if (dev->vduse_api_ver < 1)
@@ -500,6 +503,51 @@ vduse_events_handler(int fd, void *arg, int *close __rte_unused)
 		}
 		resp.result = VDUSE_REQ_RESULT_OK;
 		break;
+	case VDUSE_SET_VQ_READY:
+		if (!(dev->status & VIRTIO_DEVICE_STATUS_DRIVER_OK)) {
+			/*
+			 * dev->notify_ops is NULL if !S_DRIVER_OK,
+			 * vduse_device_start will check the queue readiness.
+			 */
+			resp.result = VDUSE_REQ_RESULT_OK;
+			break;
+		}
+		if (!(dev->vduse_features & RTE_BIT64(VDUSE_F_QUEUE_READY))) {
+			VHOST_CONFIG_LOG(dev->ifname, ERR,
+				"Unexpected ready message with no ready feature acked");
+			resp.result = VDUSE_REQ_RESULT_FAILED;
+			break;
+		}
+
+		i = req.vq_ready.num;
+		if (i >= dev->nr_vring) {
+			VHOST_CONFIG_LOG(dev->ifname, ERR,
+					"Invalid virtqueue index: %u", i);
+			resp.result = VDUSE_REQ_RESULT_FAILED;
+			break;
+		}
+
+		vq = dev->virtqueue[i];
+		if (dev->notify_ops == NULL || dev->notify_ops->vring_state_changed == NULL) {
+			VHOST_CONFIG_LOG(dev->ifname, ERR,
+					 "No ops->vring_state_changed");
+			resp.result = VDUSE_REQ_RESULT_FAILED;
+			break;
+		}
+
+		ret = dev->notify_ops->vring_state_changed(dev->vid, i,
+				req.vq_ready.ready);
+		VHOST_CONFIG_LOG(dev->ifname, INFO,
+				"\t\t VQ %d gets ready %d ok %d", i,
+				req.vq_ready.ready, ret);
+		if (ret != 0) {
+			resp.result = VDUSE_REQ_RESULT_FAILED;
+			break;
+		}
+
+		vq->enabled = req.vq_ready.ready;
+		resp.result = VDUSE_REQ_RESULT_OK;
+		break;
 	default:
 		resp.result = VDUSE_REQ_RESULT_FAILED;
 		break;
@@ -517,7 +565,8 @@ vduse_events_handler(int fd, void *arg, int *close __rte_unused)
 	if ((old_status ^ dev->status) & VIRTIO_DEVICE_STATUS_DRIVER_OK) {
 		if (dev->status & VIRTIO_DEVICE_STATUS_DRIVER_OK) {
 			/* Poll virtqueues ready states before starting device */
-			ret = vduse_wait_for_virtqueues_ready(dev);
+			ret = dev->vduse_features & RTE_BIT64(VDUSE_F_QUEUE_READY) ? 0
+				: vduse_wait_for_virtqueues_ready(dev);
 			if (ret < 0) {
 				VHOST_CONFIG_LOG(dev->ifname, ERR,
 					"Failed to wait for virtqueues ready, aborting device start");
@@ -723,6 +772,26 @@ vduse_reconnect_start_device(struct virtio_net *dev)
 	return ret;
 }
 
+/* If some error occurs just continue as if the kernel exposed no features */
+static uint64_t
+vduse_device_get_vduse_features(int control_fd, const char *log_name)
+{
+	uint64_t vduse_kernel_features;
+	int ret;
+
+	ret = ioctl(control_fd, VDUSE_GET_FEATURES, &vduse_kernel_features);
+	if (ret < 0) {
+		VHOST_CONFIG_LOG(log_name, INFO,
+			"Failed to get kernel VDUSE features, assuming not supported: %d(%s)",
+			errno, strerror(errno));
+		return 0;
+	}
+
+	VHOST_CONFIG_LOG(log_name, DEBUG, "Setting vhost kernel features: %"PRIx64,
+			vduse_kernel_features & supported_vduse_features);
+	return vduse_kernel_features & supported_vduse_features;
+}
+
 int
 vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool linearbuf)
 {
@@ -731,7 +800,7 @@ vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool
 	struct virtio_net *dev;
 	struct virtio_net_config vnet_config = {{ 0 }};
 	uint64_t ver;
-	uint64_t features;
+	uint64_t features, vduse_features = 0;
 	const char *name = path + strlen("/dev/vduse/");
 	bool reconnect = false;
 
@@ -815,9 +884,20 @@ vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool
 			dev_config->ngroups = 2;
 			dev_config->nas = 2;
 		}
+
+		vduse_features = vduse_device_get_vduse_features(control_fd, name);
 		dev_config->config_size = sizeof(struct virtio_net_config);
 		memcpy(dev_config->config, &vnet_config, sizeof(vnet_config));
 
+		if (vduse_features) {
+			ret = ioctl(control_fd, VDUSE_SET_FEATURES, &vduse_features);
+			if (ret < 0) {
+				VHOST_CONFIG_LOG(name, ERR, "Failed to set VDUSE features: %s",
+						strerror(errno));
+				goto out_ctrl_close;
+			}
+		}
+
 		ret = ioctl(control_fd, VDUSE_CREATE_DEV, dev_config);
 		free(dev_config);
 		dev_config = NULL;
@@ -865,6 +945,7 @@ vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool
 	dev->vduse_ctrl_fd = control_fd;
 	dev->vduse_dev_fd = dev_fd;
 	dev->vduse_api_ver = ver;
+	dev->vduse_features = vduse_features;
 
 	ret = vduse_reconnect_log_map(dev, !reconnect);
 	if (ret < 0)
diff --git a/lib/vhost/vhost.h b/lib/vhost/vhost.h
index 5cbd64d539b9..c2b645c2d4b0 100644
--- a/lib/vhost/vhost.h
+++ b/lib/vhost/vhost.h
@@ -533,6 +533,7 @@ struct __rte_cache_aligned virtio_net {
 	int			vduse_ctrl_fd;
 	int			vduse_dev_fd;
 	uint64_t		vduse_api_ver;
+	uint64_t		vduse_features;
 
 	struct vhost_virtqueue	*cvq;
 
-- 
2.55.0