1 files changed, 191 insertions, 47 deletions

diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx.c
index 1217e5a6..6032d554 100644
--- a/drivers/net/i40e/i40e_rxtx.c
+++ b/drivers/net/i40e/i40e_rxtx.c
@@ -40,9 +40,6 @@
 /* Base address of the HW descriptor ring should be 128B aligned. */
 #define I40E_RING_BASE_ALIGN	128
 
-#define I40E_SIMPLE_FLAGS ((uint32_t)ETH_TXQ_FLAGS_NOMULTSEGS | \
-					ETH_TXQ_FLAGS_NOOFFLOADS)
-
 #define I40E_TXD_CMD (I40E_TX_DESC_CMD_EOP | I40E_TX_DESC_CMD_RS)
 
 #ifdef RTE_LIBRTE_IEEE1588
@@ -1240,7 +1237,7 @@ i40e_tx_free_bufs(struct i40e_tx_queue *txq)
 	for (i = 0; i < txq->tx_rs_thresh; i++)
 		rte_prefetch0((txep + i)->mbuf);
 
-	if (txq->txq_flags & (uint32_t)ETH_TXQ_FLAGS_NOREFCOUNT) {
+	if (txq->offloads & DEV_TX_OFFLOAD_MBUF_FAST_FREE) {
 		for (i = 0; i < txq->tx_rs_thresh; ++i, ++txep) {
 			rte_mempool_put(txep->mbuf->pool, txep->mbuf);
 			txep->mbuf = NULL;
@@ -1692,6 +1689,75 @@ i40e_dev_supported_ptypes_get(struct rte_eth_dev *dev)
 	return NULL;
 }
 
+static int
+i40e_dev_first_queue(uint16_t idx, void **queues, int num)
+{
+	uint16_t i;
+
+	for (i = 0; i < num; i++) {
+		if (i != idx && queues[i])
+			return 0;
+	}
+
+	return 1;
+}
+
+static int
+i40e_dev_rx_queue_setup_runtime(struct rte_eth_dev *dev,
+				struct i40e_rx_queue *rxq)
+{
+	struct i40e_adapter *ad =
+		I40E_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
+	int use_def_burst_func =
+		check_rx_burst_bulk_alloc_preconditions(rxq);
+	uint16_t buf_size =
+		(uint16_t)(rte_pktmbuf_data_room_size(rxq->mp) -
+			   RTE_PKTMBUF_HEADROOM);
+	int use_scattered_rx =
+		((rxq->max_pkt_len + 2 * I40E_VLAN_TAG_SIZE) > buf_size);
+
+	if (i40e_rx_queue_init(rxq) != I40E_SUCCESS) {
+		PMD_DRV_LOG(ERR,
+			    "Failed to do RX queue initialization");
+		return -EINVAL;
+	}
+
+	if (i40e_dev_first_queue(rxq->queue_id,
+				 dev->data->rx_queues,
+				 dev->data->nb_rx_queues)) {
+		/**
+		 * If it is the first queue to setup,
+		 * set all flags to default and call
+		 * i40e_set_rx_function.
+		 */
+		ad->rx_bulk_alloc_allowed = true;
+		ad->rx_vec_allowed = true;
+		dev->data->scattered_rx = use_scattered_rx;
+		if (use_def_burst_func)
+			ad->rx_bulk_alloc_allowed = false;
+		i40e_set_rx_function(dev);
+		return 0;
+	}
+
+	/* check bulk alloc conflict */
+	if (ad->rx_bulk_alloc_allowed && use_def_burst_func) {
+		PMD_DRV_LOG(ERR, "Can't use default burst.");
+		return -EINVAL;
+	}
+	/* check scatterred conflict */
+	if (!dev->data->scattered_rx && use_scattered_rx) {
+		PMD_DRV_LOG(ERR, "Scattered rx is required.");
+		return -EINVAL;
+	}
+	/* check vector conflict */
+	if (ad->rx_vec_allowed && i40e_rxq_vec_setup(rxq)) {
+		PMD_DRV_LOG(ERR, "Failed vector rx setup.");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 int
 i40e_dev_rx_queue_setup(struct rte_eth_dev *dev,
 			uint16_t queue_idx,
@@ -1712,6 +1778,9 @@ i40e_dev_rx_queue_setup(struct rte_eth_dev *dev,
 	uint16_t len, i;
 	uint16_t reg_idx, base, bsf, tc_mapping;
 	int q_offset, use_def_burst_func = 1;
+	uint64_t offloads;
+
+	offloads = rx_conf->offloads | dev->data->dev_conf.rxmode.offloads;
 
 	if (hw->mac.type == I40E_MAC_VF || hw->mac.type == I40E_MAC_X722_VF) {
 		vf = I40EVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
@@ -1760,11 +1829,12 @@ i40e_dev_rx_queue_setup(struct rte_eth_dev *dev,
 	rxq->queue_id = queue_idx;
 	rxq->reg_idx = reg_idx;
 	rxq->port_id = dev->data->port_id;
-	rxq->crc_len = (uint8_t) ((dev->data->dev_conf.rxmode.hw_strip_crc) ?
-							0 : ETHER_CRC_LEN);
+	rxq->crc_len = (uint8_t)((dev->data->dev_conf.rxmode.offloads &
+			DEV_RX_OFFLOAD_CRC_STRIP) ? 0 : ETHER_CRC_LEN);
 	rxq->drop_en = rx_conf->rx_drop_en;
 	rxq->vsi = vsi;
 	rxq->rx_deferred_start = rx_conf->rx_deferred_start;
+	rxq->offloads = offloads;
 
 	/* Allocate the maximun number of RX ring hardware descriptor. */
 	len = I40E_MAX_RING_DESC;
@@ -1808,25 +1878,6 @@ i40e_dev_rx_queue_setup(struct rte_eth_dev *dev,
 
 	i40e_reset_rx_queue(rxq);
 	rxq->q_set = TRUE;
-	dev->data->rx_queues[queue_idx] = rxq;
-
-	use_def_burst_func = check_rx_burst_bulk_alloc_preconditions(rxq);
-
-	if (!use_def_burst_func) {
-#ifdef RTE_LIBRTE_I40E_RX_ALLOW_BULK_ALLOC
-		PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions are "
-			     "satisfied. Rx Burst Bulk Alloc function will be "
-			     "used on port=%d, queue=%d.",
-			     rxq->port_id, rxq->queue_id);
-#endif /* RTE_LIBRTE_I40E_RX_ALLOW_BULK_ALLOC */
-	} else {
-		PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions are "
-			     "not satisfied, Scattered Rx is requested, "
-			     "or RTE_LIBRTE_I40E_RX_ALLOW_BULK_ALLOC is "
-			     "not enabled on port=%d, queue=%d.",
-			     rxq->port_id, rxq->queue_id);
-		ad->rx_bulk_alloc_allowed = false;
-	}
 
 	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
 		if (!(vsi->enabled_tc & (1 << i)))
@@ -1841,6 +1892,34 @@ i40e_dev_rx_queue_setup(struct rte_eth_dev *dev,
 			rxq->dcb_tc = i;
 	}
 
+	if (dev->data->dev_started) {
+		if (i40e_dev_rx_queue_setup_runtime(dev, rxq)) {
+			i40e_dev_rx_queue_release(rxq);
+			return -EINVAL;
+		}
+	} else {
+		use_def_burst_func =
+			check_rx_burst_bulk_alloc_preconditions(rxq);
+		if (!use_def_burst_func) {
+#ifdef RTE_LIBRTE_I40E_RX_ALLOW_BULK_ALLOC
+			PMD_INIT_LOG(DEBUG,
+			  "Rx Burst Bulk Alloc Preconditions are "
+			  "satisfied. Rx Burst Bulk Alloc function will be "
+			  "used on port=%d, queue=%d.",
+			  rxq->port_id, rxq->queue_id);
+#endif /* RTE_LIBRTE_I40E_RX_ALLOW_BULK_ALLOC */
+		} else {
+			PMD_INIT_LOG(DEBUG,
+			  "Rx Burst Bulk Alloc Preconditions are "
+			  "not satisfied, Scattered Rx is requested, "
+			  "or RTE_LIBRTE_I40E_RX_ALLOW_BULK_ALLOC is "
+			  "not enabled on port=%d, queue=%d.",
+			  rxq->port_id, rxq->queue_id);
+			ad->rx_bulk_alloc_allowed = false;
+		}
+	}
+
+	dev->data->rx_queues[queue_idx] = rxq;
 	return 0;
 }
 
@@ -1972,6 +2051,52 @@ i40e_dev_tx_descriptor_status(void *tx_queue, uint16_t offset)
 	return RTE_ETH_TX_DESC_FULL;
 }
 
+static int
+i40e_dev_tx_queue_setup_runtime(struct rte_eth_dev *dev,
+				struct i40e_tx_queue *txq)
+{
+	struct i40e_adapter *ad =
+		I40E_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
+
+	if (i40e_tx_queue_init(txq) != I40E_SUCCESS) {
+		PMD_DRV_LOG(ERR,
+			    "Failed to do TX queue initialization");
+		return -EINVAL;
+	}
+
+	if (i40e_dev_first_queue(txq->queue_id,
+				 dev->data->tx_queues,
+				 dev->data->nb_tx_queues)) {
+		/**
+		 * If it is the first queue to setup,
+		 * set all flags and call
+		 * i40e_set_tx_function.
+		 */
+		i40e_set_tx_function_flag(dev, txq);
+		i40e_set_tx_function(dev);
+		return 0;
+	}
+
+	/* check vector conflict */
+	if (ad->tx_vec_allowed) {
+		if (txq->tx_rs_thresh > RTE_I40E_TX_MAX_FREE_BUF_SZ ||
+		    i40e_txq_vec_setup(txq)) {
+			PMD_DRV_LOG(ERR, "Failed vector tx setup.");
+			return -EINVAL;
+		}
+	}
+	/* check simple tx conflict */
+	if (ad->tx_simple_allowed) {
+		if (txq->offloads != 0 ||
+				txq->tx_rs_thresh < RTE_PMD_I40E_TX_MAX_BURST) {
+			PMD_DRV_LOG(ERR, "No-simple tx is required.");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 int
 i40e_dev_tx_queue_setup(struct rte_eth_dev *dev,
 			uint16_t queue_idx,
@@ -1989,6 +2114,9 @@ i40e_dev_tx_queue_setup(struct rte_eth_dev *dev,
 	uint16_t tx_rs_thresh, tx_free_thresh;
 	uint16_t reg_idx, i, base, bsf, tc_mapping;
 	int q_offset;
+	uint64_t offloads;
+
+	offloads = tx_conf->offloads | dev->data->dev_conf.txmode.offloads;
 
 	if (hw->mac.type == I40E_MAC_VF || hw->mac.type == I40E_MAC_X722_VF) {
 		vf = I40EVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
@@ -2123,7 +2251,7 @@ i40e_dev_tx_queue_setup(struct rte_eth_dev *dev,
 	txq->queue_id = queue_idx;
 	txq->reg_idx = reg_idx;
 	txq->port_id = dev->data->port_id;
-	txq->txq_flags = tx_conf->txq_flags;
+	txq->offloads = offloads;
 	txq->vsi = vsi;
 	txq->tx_deferred_start = tx_conf->tx_deferred_start;
 
@@ -2144,10 +2272,6 @@ i40e_dev_tx_queue_setup(struct rte_eth_dev *dev,
 
 	i40e_reset_tx_queue(txq);
 	txq->q_set = TRUE;
-	dev->data->tx_queues[queue_idx] = txq;
-
-	/* Use a simple TX queue without offloads or multi segs if possible */
-	i40e_set_tx_function_flag(dev, txq);
 
 	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
 		if (!(vsi->enabled_tc & (1 << i)))
@@ -2162,6 +2286,20 @@ i40e_dev_tx_queue_setup(struct rte_eth_dev *dev,
 			txq->dcb_tc = i;
 	}
 
+	if (dev->data->dev_started) {
+		if (i40e_dev_tx_queue_setup_runtime(dev, txq)) {
+			i40e_dev_tx_queue_release(txq);
+			return -EINVAL;
+		}
+	} else {
+		/**
+		 * Use a simple TX queue without offloads or
+		 * multi segs if possible
+		 */
+		i40e_set_tx_function_flag(dev, txq);
+	}
+	dev->data->tx_queues[queue_idx] = txq;
+
 	return 0;
 }
 
@@ -2189,8 +2327,8 @@ i40e_memzone_reserve(const char *name, uint32_t len, int socket_id)
 	if (mz)
 		return mz;
 
-	mz = rte_memzone_reserve_aligned(name, len,
-					 socket_id, 0, I40E_RING_BASE_ALIGN);
+	mz = rte_memzone_reserve_aligned(name, len, socket_id,
+			RTE_MEMZONE_IOVA_CONTIG, I40E_RING_BASE_ALIGN);
 	return mz;
 }
 
@@ -2469,7 +2607,7 @@ i40e_rx_queue_config(struct i40e_rx_queue *rxq)
 
 	len = hw->func_caps.rx_buf_chain_len * rxq->rx_buf_len;
 	rxq->max_pkt_len = RTE_MIN(len, data->dev_conf.rxmode.max_rx_pkt_len);
-	if (data->dev_conf.rxmode.jumbo_frame == 1) {
+	if (data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
 		if (rxq->max_pkt_len <= ETHER_MAX_LEN ||
 			rxq->max_pkt_len > I40E_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must "
@@ -2747,6 +2885,7 @@ i40e_rxq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
 	qinfo->conf.rx_free_thresh = rxq->rx_free_thresh;
 	qinfo->conf.rx_drop_en = rxq->drop_en;
 	qinfo->conf.rx_deferred_start = rxq->rx_deferred_start;
+	qinfo->conf.offloads = rxq->offloads;
 }
 
 void
@@ -2765,8 +2904,8 @@ i40e_txq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
 
 	qinfo->conf.tx_free_thresh = txq->tx_free_thresh;
 	qinfo->conf.tx_rs_thresh = txq->tx_rs_thresh;
-	qinfo->conf.txq_flags = txq->txq_flags;
 	qinfo->conf.tx_deferred_start = txq->tx_deferred_start;
+	qinfo->conf.offloads = txq->offloads;
 }
 
 void __attribute__((cold))
@@ -2889,19 +3028,24 @@ i40e_set_tx_function_flag(struct rte_eth_dev *dev, struct i40e_tx_queue *txq)
 	struct i40e_adapter *ad =
 		I40E_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
 
-	/* Use a simple Tx queue (no offloads, no multi segs) if possible */
-	if (((txq->txq_flags & I40E_SIMPLE_FLAGS) == I40E_SIMPLE_FLAGS)
-			&& (txq->tx_rs_thresh >= RTE_PMD_I40E_TX_MAX_BURST)) {
-		if (txq->tx_rs_thresh <= RTE_I40E_TX_MAX_FREE_BUF_SZ) {
-			PMD_INIT_LOG(DEBUG, "Vector tx"
-				     " can be enabled on this txq.");
-
-		} else {
-			ad->tx_vec_allowed = false;
-		}
-	} else {
-		ad->tx_simple_allowed = false;
-	}
+	/* Use a simple Tx queue if possible (only fast free is allowed) */
+	ad->tx_simple_allowed =
+		(txq->offloads ==
+		 (txq->offloads & DEV_TX_OFFLOAD_MBUF_FAST_FREE) &&
+		 txq->tx_rs_thresh >= RTE_PMD_I40E_TX_MAX_BURST);
+	ad->tx_vec_allowed = (ad->tx_simple_allowed &&
+			txq->tx_rs_thresh <= RTE_I40E_TX_MAX_FREE_BUF_SZ);
+
+	if (ad->tx_vec_allowed)
+		PMD_INIT_LOG(DEBUG, "Vector Tx can be enabled on Tx queue %u.",
+				txq->queue_id);
+	else if (ad->tx_simple_allowed)
+		PMD_INIT_LOG(DEBUG, "Simple Tx can be enabled on Tx queue %u.",
+				txq->queue_id);
+	else
+		PMD_INIT_LOG(DEBUG,
+				"Neither simple nor vector Tx enabled on Tx queue %u\n",
+				txq->queue_id);
 }
 
 void __attribute__((cold))