@@ -55,6 +55,7 @@
 #include <rte_memory.h>
 #include <rte_eal.h>
 #include <rte_dev.h>
+#include <rte_cycles.h>
 
 #include "virtio_ethdev.h"
 #include "virtio_pci.h"

@@ -1249,6 +1250,57 @@ virtio_negotiate_features(struct virtio_hw *hw, uint64_t req_features)
 	return 0;
 }
 
+int
+virtio_dev_pause(struct rte_eth_dev *dev)
+{
+	struct virtio_hw *hw = dev->data->dev_private;
+
+	rte_spinlock_lock(&hw->state_lock);
+
+	if (hw->started == 0) {
+		/* Device is just stopped. */
+		rte_spinlock_unlock(&hw->state_lock);
+		return -1;
+	}
+	hw->started = 0;
+	/*
+	 * Prevent the worker threads from touching queues to avoid contention,
+	 * 1 ms should be enough for the ongoing Tx function to finish.
+	 */
+	rte_delay_ms(1);
+	return 0;
+}
+
+/*
+ * Recover hw state to let the worker threads continue.
+ */
+void
+virtio_dev_resume(struct rte_eth_dev *dev)
+{
+	struct virtio_hw *hw = dev->data->dev_private;
+
+	hw->started = 1;
+	rte_spinlock_unlock(&hw->state_lock);
+}
+
+/*
+ * Should be called only after device is paused.
+ */
+int
+virtio_inject_pkts(struct rte_eth_dev *dev, struct rte_mbuf **tx_pkts,
+		int nb_pkts)
+{
+	struct virtio_hw *hw = dev->data->dev_private;
+	struct virtnet_tx *txvq = dev->data->tx_queues[0];
+	int ret;
+
+	hw->inject_pkts = tx_pkts;
+	ret = dev->tx_pkt_burst(txvq, tx_pkts, nb_pkts);
+	hw->inject_pkts = NULL;
+
+	return ret;
+}
+
 /*
  * Process Virtio Config changed interrupt and call the callback
  * if link state changed.

@@ -1786,6 +1838,8 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 			return -EBUSY;
 		}
 
+	rte_spinlock_init(&hw->state_lock);
+
 	hw->use_simple_rx = 1;
 	hw->use_simple_tx = 1;
 

@@ -1952,12 +2006,14 @@ virtio_dev_stop(struct rte_eth_dev *dev)
 
 	PMD_INIT_LOG(DEBUG, "stop");
 
+	rte_spinlock_lock(&hw->state_lock);
 	if (intr_conf->lsc || intr_conf->rxq)
 		virtio_intr_disable(dev);
 
 	hw->started = 0;
 	memset(&link, 0, sizeof(link));
 	virtio_dev_atomic_write_link_status(dev, &link);
+	rte_spinlock_unlock(&hw->state_lock);
 }
 
 static int

@@ -121,4 +121,9 @@ int eth_virtio_dev_init(struct rte_eth_dev *eth_dev);
 
 void virtio_interrupt_handler(void *param);
 
+int virtio_dev_pause(struct rte_eth_dev *dev);
+void virtio_dev_resume(struct rte_eth_dev *dev);
+int virtio_inject_pkts(struct rte_eth_dev *dev, struct rte_mbuf **tx_pkts,
+		int nb_pkts);
+
 #endif /* _VIRTIO_ETHDEV_H_ */

@@ -270,6 +270,13 @@ struct virtio_hw {
 	struct virtio_pci_common_cfg *common_cfg;
 	struct virtio_net_config *dev_cfg;
 	void	    *virtio_user_dev;
+	/*
+	 * App management thread and virtio interrupt handler thread
+	 * both can change the 'started' flag, this lock is meant to
+	 * avoid such a contention.
+	 */
+	rte_spinlock_t state_lock;
+	struct rte_mbuf **inject_pkts;
 
 	struct virtqueue **vqs;
 };

@@ -1017,7 +1017,7 @@ virtio_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 	uint16_t nb_used, nb_tx = 0;
 	int error;
 
-	if (unlikely(hw->started == 0))
+	if (unlikely(hw->started == 0 && tx_pkts != hw->inject_pkts))
 		return nb_tx;
 
 	if (unlikely(nb_pkts < 1))

@@ -99,7 +99,7 @@ virtio_xmit_pkts_simple(void *tx_queue, struct rte_mbuf **tx_pkts,
 	uint16_t desc_idx_max = (vq->vq_nentries >> 1) - 1;
 	uint16_t nb_tx = 0;
 
-	if (unlikely(hw->started == 0))
+	if (unlikely(hw->started == 0 && tx_pkts != hw->inject_pkts))
 		return nb_tx;
 
 	nb_used = VIRTQUEUE_NUSED(vq);