[dpdk-dev] [PATCH v1] net/virtio-user: fix packed ring server mode

[Xuan Ding]

This patch fixes the situation where datapath does not work properly when
vhost reconnects to virtio in server mode with packed ring.

Currently, virtio and vhost share memory of vring. For split ring, vhost
can read the status of discriptors directly from the available ring and
the used ring during reconnection. Therefore, the datapath can continue.

But for packed ring, when reconnecting to virtio, vhost cannot get the
status of discriptors only through the descriptor ring. By resetting Tx
and Rx queues, the datapath can restart from the beginning.

Fixes: 4c3f5822eb214 ("net/virtio: add packed virtqueue defines")
Cc: stable at dpdk.org

Signed-off-by: Xuan Ding <xuan.ding at intel.com>
---
 drivers/net/virtio/virtio_ethdev.c      | 112 +++++++++++++++++++++++-
 drivers/net/virtio/virtio_ethdev.h      |   3 +
 drivers/net/virtio/virtio_user_ethdev.c |   8 ++
 3 files changed, 121 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c
index 044eb10a7..c0cb0f23c 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++ b/drivers/net/virtio/virtio_ethdev.c
@@ -433,6 +433,94 @@ virtio_init_vring(struct virtqueue *vq)
 	virtqueue_disable_intr(vq);
 }
 
+static int
+virtio_user_reset_rx_queues(struct rte_eth_dev *dev, uint16_t queue_idx)
+{
+	uint16_t vtpci_queue_idx = 2 * queue_idx + VTNET_SQ_RQ_QUEUE_IDX;
+	struct virtio_hw *hw = dev->data->dev_private;
+	struct virtqueue *vq = hw->vqs[vtpci_queue_idx];
+	struct virtnet_rx *rxvq;
+	struct vq_desc_extra *dxp;
+	unsigned int vq_size;
+	uint16_t desc_idx, i;
+
+	vq_size = VTPCI_OPS(hw)->get_queue_num(hw, vtpci_queue_idx);
+
+	vq->vq_packed.used_wrap_counter = 1;
+	vq->vq_packed.cached_flags = VRING_PACKED_DESC_F_AVAIL;
+	vq->vq_packed.event_flags_shadow = 0;
+	vq->vq_packed.cached_flags |= VRING_DESC_F_WRITE;
+
+	rxvq = &vq->rxq;
+	memset(rxvq->mz->addr, 0, rxvq->mz->len);
+
+	for (desc_idx = 0; desc_idx < vq_size; desc_idx++) {
+		dxp = &vq->vq_descx[desc_idx];
+		if (dxp->cookie != NULL) {
+			rte_pktmbuf_free(dxp->cookie);
+			dxp->cookie = NULL;
+		}
+	}
+
+	virtio_init_vring(vq);
+
+	for (i = 0; i < hw->max_queue_pairs; i++)
+		if (rxvq->mpool != NULL)
+			virtio_dev_rx_queue_setup_finish(dev, i);
+
+	return 0;
+}
+
+static int
+virtio_user_reset_tx_queues(struct rte_eth_dev *dev, uint16_t queue_idx)
+{
+	uint8_t vtpci_queue_idx = 2 * queue_idx + VTNET_SQ_TQ_QUEUE_IDX;
+	struct virtio_hw *hw = dev->data->dev_private;
+	struct virtqueue *vq = hw->vqs[vtpci_queue_idx];
+	struct virtnet_tx *txvq;
+	struct vq_desc_extra *dxp;
+	unsigned int vq_size;
+	uint16_t desc_idx;
+
+	vq_size = VTPCI_OPS(hw)->get_queue_num(hw, vtpci_queue_idx);
+
+	vq->vq_packed.used_wrap_counter = 1;
+	vq->vq_packed.cached_flags = VRING_PACKED_DESC_F_AVAIL;
+	vq->vq_packed.event_flags_shadow = 0;
+
+	txvq = &vq->txq;
+	memset(txvq->mz->addr, 0, txvq->mz->len);
+	memset(txvq->virtio_net_hdr_mz->addr, 0,
+		txvq->virtio_net_hdr_mz->len);
+
+	for (desc_idx = 0; desc_idx < vq_size; desc_idx++) {
+		dxp = &vq->vq_descx[desc_idx];
+		if (dxp->cookie != NULL) {
+			rte_pktmbuf_free(dxp->cookie);
+			dxp->cookie = NULL;
+		}
+	}
+
+	virtio_init_vring(vq);
+
+	return 0;
+}
+
+static int
+virtio_user_reset_queues(struct rte_eth_dev *eth_dev)
+{
+	uint16_t i;
+
+	/* Vring reset for each Tx queue and Rx queue. */
+	for (i = 0; i < eth_dev->data->nb_rx_queues; i++)
+		virtio_user_reset_rx_queues(eth_dev, i);
+
+	for (i = 0; i < eth_dev->data->nb_rx_queues; i++)
+		virtio_user_reset_tx_queues(eth_dev, i);
+
+	return 0;
+}
+
 static int
 virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
 {
@@ -1913,6 +2001,8 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 			goto err_vtpci_init;
 	}
 
+	rte_spinlock_init(&hw->state_lock);
+
 	/* reset device and negotiate default features */
 	ret = virtio_init_device(eth_dev, VIRTIO_PMD_DEFAULT_GUEST_FEATURES);
 	if (ret < 0)
@@ -2155,8 +2245,6 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 			return -EBUSY;
 		}
 
-	rte_spinlock_init(&hw->state_lock);
-
 	hw->use_simple_rx = 1;
 
 	if (vtpci_with_feature(hw, VIRTIO_F_IN_ORDER)) {
@@ -2421,6 +2509,26 @@ virtio_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask)
 	return 0;
 }
 
+int
+virtio_user_reset_device(struct rte_eth_dev *eth_dev, struct virtio_hw *hw)
+{
+	/* Add lock to avoid queue contention. */
+	rte_spinlock_lock(&hw->state_lock);
+	hw->started = 0;
+	/*
+	 * Waitting for datapath to complete before resetting queues.
+	 * 1 ms should be enough for the ongoing Tx/Rx function to finish.
+	 */
+	rte_delay_ms(1);
+
+	virtio_user_reset_queues(eth_dev);
+
+	hw->started = 1;
+	rte_spinlock_unlock(&hw->state_lock);
+
+	return 0;
+}
+
 static int
 virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 {
diff --git a/drivers/net/virtio/virtio_ethdev.h b/drivers/net/virtio/virtio_ethdev.h
index a10111758..72e9e3ff8 100644
--- a/drivers/net/virtio/virtio_ethdev.h
+++ b/drivers/net/virtio/virtio_ethdev.h
@@ -49,6 +49,9 @@
 
 extern const struct eth_dev_ops virtio_user_secondary_eth_dev_ops;
 
+int virtio_user_reset_device(struct rte_eth_dev *eth_dev,
+		struct virtio_hw *hw);
+
 /*
  * CQ function prototype
  */
diff --git a/drivers/net/virtio/virtio_user_ethdev.c b/drivers/net/virtio/virtio_user_ethdev.c
index 3fc172573..49068a578 100644
--- a/drivers/net/virtio/virtio_user_ethdev.c
+++ b/drivers/net/virtio/virtio_user_ethdev.c
@@ -31,6 +31,7 @@ virtio_user_server_reconnect(struct virtio_user_dev *dev)
 	int ret;
 	int connectfd;
 	struct rte_eth_dev *eth_dev = &rte_eth_devices[dev->port_id];
+	struct virtio_hw *hw = eth_dev->data->dev_private;
 
 	connectfd = accept(dev->listenfd, NULL, NULL);
 	if (connectfd < 0)
@@ -51,6 +52,13 @@ virtio_user_server_reconnect(struct virtio_user_dev *dev)
 
 	dev->features &= dev->device_features;
 
+	/*
+	 * * For packed ring, resetting queues
+	 * is required in reconnection.
+	 */
+	if (vtpci_packed_queue(hw))
+		virtio_user_reset_device(eth_dev, hw);
+
 	ret = virtio_user_start_device(dev);
 	if (ret < 0)
 		return -1;
-- 
2.17.1