[PATCH v8 7/8] net/gve: add support for queue operations

[Junfeng Guo <junfeng.guo@intel.com>]

Add support for queue operations:
- setup rx/tx queue
- release rx/tx queue
- start rx/tx queues
- stop rx/tx queues

Signed-off-by: Xiaoyun Li <xiaoyun.li@intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
---
 drivers/net/gve/gve_ethdev.c | 204 +++++++++++++++++++++++++++++++++
 drivers/net/gve/gve_ethdev.h |  52 +++++++++
 drivers/net/gve/gve_rx.c     | 212 ++++++++++++++++++++++++++++++++++
 drivers/net/gve/gve_tx.c     | 214 +++++++++++++++++++++++++++++++++++
 drivers/net/gve/meson.build  |   2 +
 5 files changed, 684 insertions(+)
 create mode 100644 drivers/net/gve/gve_rx.c
 create mode 100644 drivers/net/gve/gve_tx.c

diff --git a/drivers/net/gve/gve_ethdev.c b/drivers/net/gve/gve_ethdev.c
index 7fbe0c78c9..892e7e2e1c 100644
--- a/drivers/net/gve/gve_ethdev.c
+++ b/drivers/net/gve/gve_ethdev.c
@@ -28,6 +28,68 @@ gve_write_version(uint8_t *driver_version_register)
 	writeb('\n', driver_version_register);
 }
 
+static int
+gve_alloc_queue_page_list(struct gve_priv *priv, uint32_t id, uint32_t pages)
+{
+	char z_name[RTE_MEMZONE_NAMESIZE];
+	struct gve_queue_page_list *qpl;
+	const struct rte_memzone *mz;
+	dma_addr_t page_bus;
+	uint32_t i;
+
+	if (priv->num_registered_pages + pages >
+	    priv->max_registered_pages) {
+		PMD_DRV_LOG(ERR, "Pages %" PRIu64 " > max registered pages %" PRIu64,
+			    priv->num_registered_pages + pages,
+			    priv->max_registered_pages);
+		return -EINVAL;
+	}
+	qpl = &priv->qpl[id];
+	snprintf(z_name, sizeof(z_name), "gve_%s_qpl%d", priv->pci_dev->device.name, id);
+	mz = rte_memzone_reserve_aligned(z_name, pages * PAGE_SIZE,
+					 rte_socket_id(),
+					 RTE_MEMZONE_IOVA_CONTIG, PAGE_SIZE);
+	if (mz == NULL) {
+		PMD_DRV_LOG(ERR, "Failed to alloc %s.", z_name);
+		return -ENOMEM;
+	}
+	qpl->page_buses = rte_zmalloc("qpl page buses", pages * sizeof(dma_addr_t), 0);
+	if (qpl->page_buses == NULL) {
+		PMD_DRV_LOG(ERR, "Failed to alloc qpl %u page buses", id);
+		return -ENOMEM;
+	}
+	page_bus = mz->iova;
+	for (i = 0; i < pages; i++) {
+		qpl->page_buses[i] = page_bus;
+		page_bus += PAGE_SIZE;
+	}
+	qpl->id = id;
+	qpl->mz = mz;
+	qpl->num_entries = pages;
+
+	priv->num_registered_pages += pages;
+
+	return 0;
+}
+
+static void
+gve_free_qpls(struct gve_priv *priv)
+{
+	uint16_t nb_txqs = priv->max_nb_txq;
+	uint16_t nb_rxqs = priv->max_nb_rxq;
+	uint32_t i;
+
+	for (i = 0; i < nb_txqs + nb_rxqs; i++) {
+		if (priv->qpl[i].mz != NULL)
+			rte_memzone_free(priv->qpl[i].mz);
+		if (priv->qpl[i].page_buses != NULL)
+			rte_free(priv->qpl[i].page_buses);
+	}
+
+	if (priv->qpl != NULL)
+		rte_free(priv->qpl);
+}
+
 static int
 gve_dev_configure(struct rte_eth_dev *dev)
 {
@@ -42,6 +104,43 @@ gve_dev_configure(struct rte_eth_dev *dev)
 	return 0;
 }
 
+static int
+gve_refill_pages(struct gve_rx_queue *rxq)
+{
+	struct rte_mbuf *nmb;
+	uint16_t i;
+	int diag;
+
+	diag = rte_pktmbuf_alloc_bulk(rxq->mpool, &rxq->sw_ring[0], rxq->nb_rx_desc);
+	if (diag < 0) {
+		for (i = 0; i < rxq->nb_rx_desc - 1; i++) {
+			nmb = rte_pktmbuf_alloc(rxq->mpool);
+			if (!nmb)
+				break;
+			rxq->sw_ring[i] = nmb;
+		}
+		if (i < rxq->nb_rx_desc - 1)
+			return -ENOMEM;
+	}
+	rxq->nb_avail = 0;
+	rxq->next_avail = rxq->nb_rx_desc - 1;
+
+	for (i = 0; i < rxq->nb_rx_desc; i++) {
+		if (rxq->is_gqi_qpl) {
+			rxq->rx_data_ring[i].addr = rte_cpu_to_be_64(i * PAGE_SIZE);
+		} else {
+			if (i == rxq->nb_rx_desc - 1)
+				break;
+			nmb = rxq->sw_ring[i];
+			rxq->rx_data_ring[i].addr = rte_cpu_to_be_64(rte_mbuf_data_iova(nmb));
+		}
+	}
+
+	rte_write32(rte_cpu_to_be_32(rxq->next_avail), rxq->qrx_tail);
+
+	return 0;
+}
+
 static int
 gve_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complete)
 {
@@ -73,16 +172,70 @@ gve_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complete)
 static int
 gve_dev_start(struct rte_eth_dev *dev)
 {
+	uint16_t num_queues = dev->data->nb_tx_queues;
+	struct gve_priv *priv = dev->data->dev_private;
+	struct gve_tx_queue *txq;
+	struct gve_rx_queue *rxq;
+	uint16_t i;
+	int err;
+
+	priv->txqs = (struct gve_tx_queue **)dev->data->tx_queues;
+	err = gve_adminq_create_tx_queues(priv, num_queues);
+	if (err) {
+		PMD_DRV_LOG(ERR, "failed to create %u tx queues.", num_queues);
+		return err;
+	}
+	for (i = 0; i < num_queues; i++) {
+		txq = priv->txqs[i];
+		txq->qtx_tail =
+		&priv->db_bar2[rte_be_to_cpu_32(txq->qres->db_index)];
+		txq->qtx_head =
+		&priv->cnt_array[rte_be_to_cpu_32(txq->qres->counter_index)];
+
+		rte_write32(rte_cpu_to_be_32(GVE_IRQ_MASK), txq->ntfy_addr);
+	}
+
+	num_queues = dev->data->nb_rx_queues;
+	priv->rxqs = (struct gve_rx_queue **)dev->data->rx_queues;
+	err = gve_adminq_create_rx_queues(priv, num_queues);
+	if (err) {
+		PMD_DRV_LOG(ERR, "failed to create %u rx queues.", num_queues);
+		goto err_tx;
+	}
+	for (i = 0; i < num_queues; i++) {
+		rxq = priv->rxqs[i];
+		rxq->qrx_tail =
+		&priv->db_bar2[rte_be_to_cpu_32(rxq->qres->db_index)];
+
+		rte_write32(rte_cpu_to_be_32(GVE_IRQ_MASK), rxq->ntfy_addr);
+
+		err = gve_refill_pages(rxq);
+		if (err) {
+			PMD_DRV_LOG(ERR, "Failed to refill for RX");
+			goto err_rx;
+		}
+	}
+
 	dev->data->dev_started = 1;
 	gve_link_update(dev, 0);
 
 	return 0;
+
+err_rx:
+	gve_stop_rx_queues(dev);
+err_tx:
+	gve_stop_tx_queues(dev);
+	return err;
 }
 
 static int
 gve_dev_stop(struct rte_eth_dev *dev)
 {
 	dev->data->dev_link.link_status = RTE_ETH_LINK_DOWN;
+
+	gve_stop_tx_queues(dev);
+	gve_stop_rx_queues(dev);
+
 	dev->data->dev_started = 0;
 
 	return 0;
@@ -91,7 +244,11 @@ gve_dev_stop(struct rte_eth_dev *dev)
 static int
 gve_dev_close(struct rte_eth_dev *dev)
 {
+	struct gve_priv *priv = dev->data->dev_private;
+	struct gve_tx_queue *txq;
+	struct gve_rx_queue *rxq;
 	int err = 0;
+	uint16_t i;
 
 	if (dev->data->dev_started) {
 		err = gve_dev_stop(dev);
@@ -99,6 +256,19 @@ gve_dev_close(struct rte_eth_dev *dev)
 			PMD_DRV_LOG(ERR, "Failed to stop dev.");
 	}
 
+	for (i = 0; i < dev->data->nb_tx_queues; i++) {
+		txq = dev->data->tx_queues[i];
+		gve_tx_queue_release(txq);
+	}
+
+	for (i = 0; i < dev->data->nb_rx_queues; i++) {
+		rxq = dev->data->rx_queues[i];
+		gve_rx_queue_release(rxq);
+	}
+
+	gve_free_qpls(priv);
+	rte_free(priv->adminq);
+
 	dev->data->mac_addrs = NULL;
 
 	return err;
@@ -185,6 +355,8 @@ static const struct eth_dev_ops gve_eth_dev_ops = {
 	.dev_stop             = gve_dev_stop,
 	.dev_close            = gve_dev_close,
 	.dev_infos_get        = gve_dev_info_get,
+	.rx_queue_setup       = gve_rx_queue_setup,
+	.tx_queue_setup       = gve_tx_queue_setup,
 	.link_update          = gve_link_update,
 	.mtu_set              = gve_dev_mtu_set,
 };
@@ -322,7 +494,9 @@ gve_setup_device_resources(struct gve_priv *priv)
 static int
 gve_init_priv(struct gve_priv *priv, bool skip_describe_device)
 {
+	uint16_t pages;
 	int num_ntfy;
+	uint32_t i;
 	int err;
 
 	/* Set up the adminq */
@@ -373,10 +547,40 @@ gve_init_priv(struct gve_priv *priv, bool skip_describe_device)
 	PMD_DRV_LOG(INFO, "Max TX queues %d, Max RX queues %d",
 		    priv->max_nb_txq, priv->max_nb_rxq);
 
+	/* In GQI_QPL queue format:
+	 * Allocate queue page lists according to max queue number
+	 * tx qpl id should start from 0 while rx qpl id should start
+	 * from priv->max_nb_txq
+	 */
+	if (priv->queue_format == GVE_GQI_QPL_FORMAT) {
+		priv->qpl = rte_zmalloc("gve_qpl",
+					(priv->max_nb_txq + priv->max_nb_rxq) *
+					sizeof(struct gve_queue_page_list), 0);
+		if (priv->qpl == NULL) {
+			PMD_DRV_LOG(ERR, "Failed to alloc qpl.");
+			err = -ENOMEM;
+			goto free_adminq;
+		}
+
+		for (i = 0; i < priv->max_nb_txq + priv->max_nb_rxq; i++) {
+			if (i < priv->max_nb_txq)
+				pages = priv->tx_pages_per_qpl;
+			else
+				pages = priv->rx_data_slot_cnt;
+			err = gve_alloc_queue_page_list(priv, i, pages);
+			if (err != 0) {
+				PMD_DRV_LOG(ERR, "Failed to alloc qpl %u.", i);
+				goto err_qpl;
+			}
+		}
+	}
+
 setup_device:
 	err = gve_setup_device_resources(priv);
 	if (!err)
 		return 0;
+err_qpl:
+	gve_free_qpls(priv);
 free_adminq:
 	gve_adminq_free(priv);
 	return err;
diff --git a/drivers/net/gve/gve_ethdev.h b/drivers/net/gve/gve_ethdev.h
index 57c29374b5..00c69d1b88 100644
--- a/drivers/net/gve/gve_ethdev.h
+++ b/drivers/net/gve/gve_ethdev.h
@@ -37,15 +37,35 @@ union gve_tx_desc {
 	struct gve_tx_seg_desc seg; /* subsequent descs for a packet */
 };
 
+struct gve_tx_iovec {
+	uint32_t iov_base; /* offset in fifo */
+	uint32_t iov_len;
+};
+
 struct gve_tx_queue {
 	volatile union gve_tx_desc *tx_desc_ring;
 	const struct rte_memzone *mz;
 	uint64_t tx_ring_phys_addr;
+	struct rte_mbuf **sw_ring;
+	volatile rte_be32_t *qtx_tail;
+	volatile rte_be32_t *qtx_head;
 
+	uint32_t tx_tail;
 	uint16_t nb_tx_desc;
+	uint16_t nb_free;
+	uint32_t next_to_clean;
+	uint16_t free_thresh;
 
 	/* Only valid for DQO_QPL queue format */
+	uint16_t sw_tail;
+	uint16_t sw_ntc;
+	uint16_t sw_nb_free;
+	uint32_t fifo_size;
+	uint32_t fifo_head;
+	uint32_t fifo_avail;
+	uint64_t fifo_base;
 	struct gve_queue_page_list *qpl;
+	struct gve_tx_iovec *iov_ring;
 
 	uint16_t port_id;
 	uint16_t queue_id;
@@ -59,6 +79,8 @@ struct gve_tx_queue {
 
 	/* Only valid for DQO_RDA queue format */
 	struct gve_tx_queue *complq;
+
+	uint8_t is_gqi_qpl;
 };
 
 struct gve_rx_queue {
@@ -67,9 +89,17 @@ struct gve_rx_queue {
 	const struct rte_memzone *mz;
 	const struct rte_memzone *data_mz;
 	uint64_t rx_ring_phys_addr;
+	struct rte_mbuf **sw_ring;
+	struct rte_mempool *mpool;
 
+	uint16_t rx_tail;
 	uint16_t nb_rx_desc;
+	uint16_t expected_seqno; /* the next expected seqno */
+	uint16_t free_thresh;
+	uint32_t next_avail;
+	uint32_t nb_avail;
 
+	volatile rte_be32_t *qrx_tail;
 	volatile rte_be32_t *ntfy_addr;
 
 	/* only valid for GQI_QPL queue format */
@@ -86,6 +116,8 @@ struct gve_rx_queue {
 
 	/* Only valid for DQO_RDA queue format */
 	struct gve_rx_queue *bufq;
+
+	uint8_t is_gqi_qpl;
 };
 
 struct gve_priv {
@@ -225,4 +257,24 @@ gve_clear_device_rings_ok(struct gve_priv *priv)
 				&priv->state_flags);
 }
 
+int
+gve_rx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_id, uint16_t nb_desc,
+		   unsigned int socket_id, const struct rte_eth_rxconf *conf,
+		   struct rte_mempool *pool);
+int
+gve_tx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_id, uint16_t nb_desc,
+		   unsigned int socket_id, const struct rte_eth_txconf *conf);
+
+void
+gve_tx_queue_release(void *txq);
+
+void
+gve_rx_queue_release(void *rxq);
+
+void
+gve_stop_tx_queues(struct rte_eth_dev *dev);
+
+void
+gve_stop_rx_queues(struct rte_eth_dev *dev);
+
 #endif /* _GVE_ETHDEV_H_ */
diff --git a/drivers/net/gve/gve_rx.c b/drivers/net/gve/gve_rx.c
new file mode 100644
index 0000000000..e64a461253
--- /dev/null
+++ b/drivers/net/gve/gve_rx.c
@@ -0,0 +1,212 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(C) 2022 Intel Corporation
+ */
+
+#include "gve_ethdev.h"
+#include "base/gve_adminq.h"
+
+static inline void
+gve_reset_rxq(struct gve_rx_queue *rxq)
+{
+	struct rte_mbuf **sw_ring = rxq->sw_ring;
+	uint32_t size, i;
+
+	if (rxq == NULL) {
+		PMD_DRV_LOG(ERR, "pointer to rxq is NULL");
+		return;
+	}
+
+	size = rxq->nb_rx_desc * sizeof(struct gve_rx_desc);
+	for (i = 0; i < size; i++)
+		((volatile char *)rxq->rx_desc_ring)[i] = 0;
+
+	size = rxq->nb_rx_desc * sizeof(union gve_rx_data_slot);
+	for (i = 0; i < size; i++)
+		((volatile char *)rxq->rx_data_ring)[i] = 0;
+
+	for (i = 0; i < rxq->nb_rx_desc; i++)
+		sw_ring[i] = NULL;
+
+	rxq->rx_tail = 0;
+	rxq->next_avail = 0;
+	rxq->nb_avail = rxq->nb_rx_desc;
+	rxq->expected_seqno = 1;
+}
+
+static inline void
+gve_release_rxq_mbufs(struct gve_rx_queue *rxq)
+{
+	uint16_t i;
+
+	for (i = 0; i < rxq->nb_rx_desc; i++) {
+		if (rxq->sw_ring[i]) {
+			rte_pktmbuf_free_seg(rxq->sw_ring[i]);
+			rxq->sw_ring[i] = NULL;
+		}
+	}
+
+	rxq->nb_avail = rxq->nb_rx_desc;
+}
+
+void
+gve_rx_queue_release(void *rxq)
+{
+	struct gve_rx_queue *q = rxq;
+
+	if (!q)
+		return;
+
+	if (q->is_gqi_qpl) {
+		gve_adminq_unregister_page_list(q->hw, q->qpl->id);
+		q->qpl = NULL;
+	}
+
+	gve_release_rxq_mbufs(q);
+	rte_free(q->sw_ring);
+	rte_memzone_free(q->data_mz);
+	rte_memzone_free(q->mz);
+	rte_memzone_free(q->qres_mz);
+	q->qres = NULL;
+	rte_free(q);
+}
+
+int
+gve_rx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_id,
+		uint16_t nb_desc, unsigned int socket_id,
+		const struct rte_eth_rxconf *conf, struct rte_mempool *pool)
+{
+	struct gve_priv *hw = dev->data->dev_private;
+	const struct rte_memzone *mz;
+	struct gve_rx_queue *rxq;
+	uint16_t free_thresh;
+	int err = 0;
+
+	if (nb_desc != hw->rx_desc_cnt) {
+		PMD_DRV_LOG(WARNING, "gve doesn't support nb_desc config, use hw nb_desc %u.",
+			    hw->rx_desc_cnt);
+	}
+	nb_desc = hw->rx_desc_cnt;
+
+	/* Free memory if needed. */
+	if (dev->data->rx_queues[queue_id]) {
+		gve_rx_queue_release(dev->data->rx_queues[queue_id]);
+		dev->data->rx_queues[queue_id] = NULL;
+	}
+
+	/* Allocate the RX queue data structure. */
+	rxq = rte_zmalloc_socket("gve rxq",
+				 sizeof(struct gve_rx_queue),
+				 RTE_CACHE_LINE_SIZE,
+				 socket_id);
+	if (!rxq) {
+		PMD_DRV_LOG(ERR, "Failed to allocate memory for rx queue structure");
+		err = -ENOMEM;
+		goto err_rxq;
+	}
+
+	free_thresh = conf->rx_free_thresh ? conf->rx_free_thresh : GVE_DEFAULT_RX_FREE_THRESH;
+	if (free_thresh >= nb_desc) {
+		PMD_DRV_LOG(ERR, "rx_free_thresh (%u) must be less than nb_desc (%u) minus 3.",
+			    free_thresh, rxq->nb_rx_desc);
+		err = -EINVAL;
+		goto err_rxq;
+	}
+
+	rxq->nb_rx_desc = nb_desc;
+	rxq->free_thresh = free_thresh;
+	rxq->queue_id = queue_id;
+	rxq->port_id = dev->data->port_id;
+	rxq->ntfy_id = hw->num_ntfy_blks / 2 + queue_id;
+	rxq->is_gqi_qpl = hw->queue_format == GVE_GQI_QPL_FORMAT;
+	rxq->mpool = pool;
+	rxq->hw = hw;
+	rxq->ntfy_addr = &hw->db_bar2[rte_be_to_cpu_32(hw->irq_dbs[rxq->ntfy_id].id)];
+
+	rxq->rx_buf_len = rte_pktmbuf_data_room_size(rxq->mpool) - RTE_PKTMBUF_HEADROOM;
+
+	/* Allocate software ring */
+	rxq->sw_ring = rte_zmalloc_socket("gve rx sw ring", sizeof(struct rte_mbuf *) * nb_desc,
+					  RTE_CACHE_LINE_SIZE, socket_id);
+	if (!rxq->sw_ring) {
+		PMD_DRV_LOG(ERR, "Failed to allocate memory for SW RX ring");
+		err = -ENOMEM;
+		goto err_rxq;
+	}
+
+	mz = rte_eth_dma_zone_reserve(dev, "rx_ring", queue_id,
+				      nb_desc * sizeof(struct gve_rx_desc),
+				      PAGE_SIZE, socket_id);
+	if (mz == NULL) {
+		PMD_DRV_LOG(ERR, "Failed to reserve DMA memory for RX");
+		err = -ENOMEM;
+		goto err_sw_ring;
+	}
+	rxq->rx_desc_ring = (struct gve_rx_desc *)mz->addr;
+	rxq->rx_ring_phys_addr = mz->iova;
+	rxq->mz = mz;
+
+	mz = rte_eth_dma_zone_reserve(dev, "gve rx data ring", queue_id,
+				      sizeof(union gve_rx_data_slot) * nb_desc,
+				      PAGE_SIZE, socket_id);
+	if (mz == NULL) {
+		PMD_DRV_LOG(ERR, "Failed to allocate memory for RX data ring");
+		err = -ENOMEM;
+		goto err_rx_ring;
+	}
+	rxq->rx_data_ring = (union gve_rx_data_slot *)mz->addr;
+	rxq->data_mz = mz;
+	if (rxq->is_gqi_qpl) {
+		rxq->qpl = &hw->qpl[rxq->ntfy_id];
+		err = gve_adminq_register_page_list(hw, rxq->qpl);
+		if (err != 0) {
+			PMD_DRV_LOG(ERR, "Failed to register qpl %u", queue_id);
+			goto err_data_ring;
+		}
+	}
+
+	mz = rte_eth_dma_zone_reserve(dev, "rxq_res", queue_id,
+				      sizeof(struct gve_queue_resources),
+				      PAGE_SIZE, socket_id);
+	if (mz == NULL) {
+		PMD_DRV_LOG(ERR, "Failed to reserve DMA memory for RX resource");
+		err = -ENOMEM;
+		goto err_data_ring;
+	}
+	rxq->qres = (struct gve_queue_resources *)mz->addr;
+	rxq->qres_mz = mz;
+
+	gve_reset_rxq(rxq);
+
+	dev->data->rx_queues[queue_id] = rxq;
+
+	return 0;
+
+err_data_ring:
+	rte_memzone_free(rxq->data_mz);
+err_rx_ring:
+	rte_memzone_free(rxq->mz);
+err_sw_ring:
+	rte_free(rxq->sw_ring);
+err_rxq:
+	rte_free(rxq);
+	return err;
+}
+
+void
+gve_stop_rx_queues(struct rte_eth_dev *dev)
+{
+	struct gve_priv *hw = dev->data->dev_private;
+	struct gve_rx_queue *rxq;
+	uint16_t i;
+	int err;
+
+	err = gve_adminq_destroy_rx_queues(hw, dev->data->nb_rx_queues);
+	if (err != 0)
+		PMD_DRV_LOG(WARNING, "failed to destroy rxqs");
+
+	for (i = 0; i < dev->data->nb_rx_queues; i++) {
+		rxq = dev->data->rx_queues[i];
+		gve_release_rxq_mbufs(rxq);
+		gve_reset_rxq(rxq);
+	}
+}
diff --git a/drivers/net/gve/gve_tx.c b/drivers/net/gve/gve_tx.c
new file mode 100644
index 0000000000..b706b62e71
--- /dev/null
+++ b/drivers/net/gve/gve_tx.c
@@ -0,0 +1,214 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(C) 2022 Intel Corporation
+ */
+
+#include "gve_ethdev.h"
+#include "base/gve_adminq.h"
+
+static inline void
+gve_reset_txq(struct gve_tx_queue *txq)
+{
+	struct rte_mbuf **sw_ring = txq->sw_ring;
+	uint32_t size, i;
+
+	if (txq == NULL) {
+		PMD_DRV_LOG(ERR, "Pointer to txq is NULL");
+		return;
+	}
+
+	size = txq->nb_tx_desc * sizeof(union gve_tx_desc);
+	for (i = 0; i < size; i++)
+		((volatile char *)txq->tx_desc_ring)[i] = 0;
+
+	for (i = 0; i < txq->nb_tx_desc; i++) {
+		sw_ring[i] = NULL;
+		if (txq->is_gqi_qpl) {
+			txq->iov_ring[i].iov_base = 0;
+			txq->iov_ring[i].iov_len = 0;
+		}
+	}
+
+	txq->tx_tail = 0;
+	txq->nb_free = txq->nb_tx_desc - 1;
+	txq->next_to_clean = 0;
+
+	if (txq->is_gqi_qpl) {
+		txq->fifo_size = PAGE_SIZE * txq->hw->tx_pages_per_qpl;
+		txq->fifo_avail = txq->fifo_size;
+		txq->fifo_head = 0;
+		txq->fifo_base = (uint64_t)(txq->qpl->mz->addr);
+
+		txq->sw_tail = 0;
+		txq->sw_nb_free = txq->nb_tx_desc - 1;
+		txq->sw_ntc = 0;
+	}
+}
+
+static inline void
+gve_release_txq_mbufs(struct gve_tx_queue *txq)
+{
+	uint16_t i;
+
+	for (i = 0; i < txq->nb_tx_desc; i++) {
+		if (txq->sw_ring[i]) {
+			rte_pktmbuf_free_seg(txq->sw_ring[i]);
+			txq->sw_ring[i] = NULL;
+		}
+	}
+}
+
+void
+gve_tx_queue_release(void *txq)
+{
+	struct gve_tx_queue *q = txq;
+
+	if (!q)
+		return;
+
+	if (q->is_gqi_qpl) {
+		gve_adminq_unregister_page_list(q->hw, q->qpl->id);
+		rte_free(q->iov_ring);
+		q->qpl = NULL;
+	}
+
+	gve_release_txq_mbufs(q);
+	rte_free(q->sw_ring);
+	rte_memzone_free(q->mz);
+	rte_memzone_free(q->qres_mz);
+	q->qres = NULL;
+	rte_free(q);
+}
+
+int
+gve_tx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_id, uint16_t nb_desc,
+		   unsigned int socket_id, const struct rte_eth_txconf *conf)
+{
+	struct gve_priv *hw = dev->data->dev_private;
+	const struct rte_memzone *mz;
+	struct gve_tx_queue *txq;
+	uint16_t free_thresh;
+	int err = 0;
+
+	if (nb_desc != hw->tx_desc_cnt) {
+		PMD_DRV_LOG(WARNING, "gve doesn't support nb_desc config, use hw nb_desc %u.",
+			    hw->tx_desc_cnt);
+	}
+	nb_desc = hw->tx_desc_cnt;
+
+	/* Free memory if needed. */
+	if (dev->data->tx_queues[queue_id]) {
+		gve_tx_queue_release(dev->data->tx_queues[queue_id]);
+		dev->data->tx_queues[queue_id] = NULL;
+	}
+
+	/* Allocate the TX queue data structure. */
+	txq = rte_zmalloc_socket("gve txq", sizeof(struct gve_tx_queue),
+				 RTE_CACHE_LINE_SIZE, socket_id);
+	if (!txq) {
+		PMD_DRV_LOG(ERR, "Failed to allocate memory for tx queue structure");
+		err = -ENOMEM;
+		goto err_txq;
+	}
+
+	free_thresh = conf->tx_free_thresh ? conf->tx_free_thresh : GVE_DEFAULT_TX_FREE_THRESH;
+	if (free_thresh >= nb_desc - 3) {
+		PMD_DRV_LOG(ERR, "tx_free_thresh (%u) must be less than nb_desc (%u) minus 3.",
+			    free_thresh, txq->nb_tx_desc);
+		err = -EINVAL;
+		goto err_txq;
+	}
+
+	txq->nb_tx_desc = nb_desc;
+	txq->free_thresh = free_thresh;
+	txq->queue_id = queue_id;
+	txq->port_id = dev->data->port_id;
+	txq->ntfy_id = queue_id;
+	txq->is_gqi_qpl = hw->queue_format == GVE_GQI_QPL_FORMAT;
+	txq->hw = hw;
+	txq->ntfy_addr = &hw->db_bar2[rte_be_to_cpu_32(hw->irq_dbs[txq->ntfy_id].id)];
+
+	/* Allocate software ring */
+	txq->sw_ring = rte_zmalloc_socket("gve tx sw ring",
+					  sizeof(struct rte_mbuf *) * nb_desc,
+					  RTE_CACHE_LINE_SIZE, socket_id);
+	if (!txq->sw_ring) {
+		PMD_DRV_LOG(ERR, "Failed to allocate memory for SW TX ring");
+		err = -ENOMEM;
+		goto err_txq;
+	}
+
+	mz = rte_eth_dma_zone_reserve(dev, "tx_ring", queue_id,
+				      nb_desc * sizeof(union gve_tx_desc),
+				      PAGE_SIZE, socket_id);
+	if (mz == NULL) {
+		PMD_DRV_LOG(ERR, "Failed to reserve DMA memory for TX");
+		err = -ENOMEM;
+		goto err_sw_ring;
+	}
+	txq->tx_desc_ring = (union gve_tx_desc *)mz->addr;
+	txq->tx_ring_phys_addr = mz->iova;
+	txq->mz = mz;
+
+	if (txq->is_gqi_qpl) {
+		txq->iov_ring = rte_zmalloc_socket("gve tx iov ring",
+						   sizeof(struct gve_tx_iovec) * nb_desc,
+						   RTE_CACHE_LINE_SIZE, socket_id);
+		if (!txq->iov_ring) {
+			PMD_DRV_LOG(ERR, "Failed to allocate memory for SW TX ring");
+			err = -ENOMEM;
+			goto err_tx_ring;
+		}
+		txq->qpl = &hw->qpl[queue_id];
+		err = gve_adminq_register_page_list(hw, txq->qpl);
+		if (err != 0) {
+			PMD_DRV_LOG(ERR, "Failed to register qpl %u", queue_id);
+			goto err_iov_ring;
+		}
+	}
+
+	mz = rte_eth_dma_zone_reserve(dev, "txq_res", queue_id, sizeof(struct gve_queue_resources),
+				      PAGE_SIZE, socket_id);
+	if (mz == NULL) {
+		PMD_DRV_LOG(ERR, "Failed to reserve DMA memory for TX resource");
+		err = -ENOMEM;
+		goto err_iov_ring;
+	}
+	txq->qres = (struct gve_queue_resources *)mz->addr;
+	txq->qres_mz = mz;
+
+	gve_reset_txq(txq);
+
+	dev->data->tx_queues[queue_id] = txq;
+
+	return 0;
+
+err_iov_ring:
+	if (txq->is_gqi_qpl)
+		rte_free(txq->iov_ring);
+err_tx_ring:
+	rte_memzone_free(txq->mz);
+err_sw_ring:
+	rte_free(txq->sw_ring);
+err_txq:
+	rte_free(txq);
+	return err;
+}
+
+void
+gve_stop_tx_queues(struct rte_eth_dev *dev)
+{
+	struct gve_priv *hw = dev->data->dev_private;
+	struct gve_tx_queue *txq;
+	uint16_t i;
+	int err;
+
+	err = gve_adminq_destroy_tx_queues(hw, dev->data->nb_tx_queues);
+	if (err != 0)
+		PMD_DRV_LOG(WARNING, "failed to destroy txqs");
+
+	for (i = 0; i < dev->data->nb_tx_queues; i++) {
+		txq = dev->data->tx_queues[i];
+		gve_release_txq_mbufs(txq);
+		gve_reset_txq(txq);
+	}
+}
diff --git a/drivers/net/gve/meson.build b/drivers/net/gve/meson.build
index d8ec64b3a3..af0010c01c 100644
--- a/drivers/net/gve/meson.build
+++ b/drivers/net/gve/meson.build
@@ -9,6 +9,8 @@ endif
 
 sources = files(
         'base/gve_adminq.c',
+        'gve_rx.c',
+        'gve_tx.c',
         'gve_ethdev.c',
 )
 includes += include_directories('base')
-- 
2.34.1