[PATCH v5 34/35] net/idpf: enable simple Tx function

[Bruce Richardson]

The common "simple Tx" function - in some ways a scalar version of the
vector Tx functions - can be used by the idpf driver as well as i40e and
ice, so add support for it to the driver.

Signed-off-by: Bruce Richardson <bruce.richardson at intel.com>
---
 drivers/net/intel/idpf/idpf_common_device.h   |  1 +
 drivers/net/intel/idpf/idpf_common_rxtx.c     | 19 ++++++++++
 drivers/net/intel/idpf/idpf_common_rxtx.h     |  3 ++
 .../net/intel/idpf/idpf_common_rxtx_avx512.c  |  1 -
 drivers/net/intel/idpf/idpf_rxtx.c            | 38 ++++++++++++++++---
 5 files changed, 56 insertions(+), 6 deletions(-)

diff --git a/drivers/net/intel/idpf/idpf_common_device.h b/drivers/net/intel/idpf/idpf_common_device.h
index 31915a03d4..bbc969c734 100644
--- a/drivers/net/intel/idpf/idpf_common_device.h
+++ b/drivers/net/intel/idpf/idpf_common_device.h
@@ -78,6 +78,7 @@ enum idpf_rx_func_type {
 enum idpf_tx_func_type {
 	IDPF_TX_DEFAULT,
 	IDPF_TX_SINGLEQ,
+	IDPF_TX_SINGLEQ_SIMPLE,
 	IDPF_TX_SINGLEQ_AVX2,
 	IDPF_TX_AVX512,
 	IDPF_TX_SINGLEQ_AVX512,
diff --git a/drivers/net/intel/idpf/idpf_common_rxtx.c b/drivers/net/intel/idpf/idpf_common_rxtx.c
index f14a20d6ec..b8f6418d4a 100644
--- a/drivers/net/intel/idpf/idpf_common_rxtx.c
+++ b/drivers/net/intel/idpf/idpf_common_rxtx.c
@@ -1347,6 +1347,15 @@ idpf_dp_singleq_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 			idpf_set_tso_ctx, NULL, NULL);
 }
 
+RTE_EXPORT_INTERNAL_SYMBOL(idpf_dp_singleq_xmit_pkts_simple)
+uint16_t
+idpf_dp_singleq_xmit_pkts_simple(void *tx_queue, struct rte_mbuf **tx_pkts,
+				   uint16_t nb_pkts)
+{
+	return ci_xmit_pkts_simple(tx_queue, tx_pkts, nb_pkts);
+}
+
+
 /* TX prep functions */
 RTE_EXPORT_INTERNAL_SYMBOL(idpf_dp_prep_pkts)
 uint16_t
@@ -1532,6 +1541,16 @@ const struct ci_tx_path_info idpf_tx_path_infos[] = {
 			.single_queue = true
 		}
 	},
+	[IDPF_TX_SINGLEQ_SIMPLE] = {
+		.pkt_burst = idpf_dp_singleq_xmit_pkts_simple,
+		.info = "Single Queue Scalar Simple",
+		.features = {
+			.tx_offloads = IDPF_TX_VECTOR_OFFLOADS,
+			.single_queue = true,
+			.simple_tx = true,
+		}
+	},
+
 #ifdef RTE_ARCH_X86
 	[IDPF_TX_SINGLEQ_AVX2] = {
 		.pkt_burst = idpf_dp_singleq_xmit_pkts_avx2,
diff --git a/drivers/net/intel/idpf/idpf_common_rxtx.h b/drivers/net/intel/idpf/idpf_common_rxtx.h
index fe7094d434..914cab0f25 100644
--- a/drivers/net/intel/idpf/idpf_common_rxtx.h
+++ b/drivers/net/intel/idpf/idpf_common_rxtx.h
@@ -221,6 +221,9 @@ __rte_internal
 uint16_t idpf_dp_singleq_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 				   uint16_t nb_pkts);
 __rte_internal
+uint16_t idpf_dp_singleq_xmit_pkts_simple(void *tx_queue, struct rte_mbuf **tx_pkts,
+				   uint16_t nb_pkts);
+__rte_internal
 uint16_t idpf_dp_prep_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 			   uint16_t nb_pkts);
 __rte_internal
diff --git a/drivers/net/intel/idpf/idpf_common_rxtx_avx512.c b/drivers/net/intel/idpf/idpf_common_rxtx_avx512.c
index 666ad1a4dd..c5f2018924 100644
--- a/drivers/net/intel/idpf/idpf_common_rxtx_avx512.c
+++ b/drivers/net/intel/idpf/idpf_common_rxtx_avx512.c
@@ -1365,6 +1365,5 @@ idpf_qc_tx_vec_avx512_setup(struct ci_tx_queue *txq)
 	if (!txq)
 		return 0;
 
-	txq->use_vec_entry = true;
 	return 0;
 }
diff --git a/drivers/net/intel/idpf/idpf_rxtx.c b/drivers/net/intel/idpf/idpf_rxtx.c
index 9420200f6d..6317112353 100644
--- a/drivers/net/intel/idpf/idpf_rxtx.c
+++ b/drivers/net/intel/idpf/idpf_rxtx.c
@@ -833,21 +833,39 @@ idpf_set_rx_function(struct rte_eth_dev *dev)
 
 }
 
+static bool
+idpf_tx_simple_allowed(struct rte_eth_dev *dev)
+{
+	struct idpf_vport *vport = dev->data->dev_private;
+	struct ci_tx_queue *txq;
+
+	if (vport->txq_model != VIRTCHNL2_QUEUE_MODEL_SINGLE)
+		return false;
+
+	for (int i = 0; i < dev->data->nb_tx_queues; i++) {
+		txq = dev->data->tx_queues[i];
+		if (txq == NULL)
+			continue;
+		if (txq->offloads != (txq->offloads & RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE) ||
+				txq->tx_rs_thresh < IDPF_VPMD_TX_MAX_BURST)
+			return false;
+	}
+	return true;
+}
+
 void
 idpf_set_tx_function(struct rte_eth_dev *dev)
 {
 	struct idpf_vport *vport = dev->data->dev_private;
-#ifdef RTE_ARCH_X86
-#ifdef CC_AVX512_SUPPORT
 	struct ci_tx_queue *txq;
 	int i;
-#endif /* CC_AVX512_SUPPORT */
-#endif /* RTE_ARCH_X86 */
 	struct idpf_adapter *ad = vport->adapter;
+	bool simple_allowed = idpf_tx_simple_allowed(dev);
 	struct ci_tx_path_features req_features = {
 		.tx_offloads = dev->data->dev_conf.txmode.offloads,
 		.simd_width = RTE_VECT_SIMD_DISABLED,
-		.single_queue = (vport->txq_model == VIRTCHNL2_QUEUE_MODEL_SINGLE)
+		.single_queue = (vport->txq_model == VIRTCHNL2_QUEUE_MODEL_SINGLE),
+		.simple_tx = simple_allowed
 	};
 
 	/* The primary process selects the tx path for all processes. */
@@ -864,6 +882,16 @@ idpf_set_tx_function(struct rte_eth_dev *dev)
 					IDPF_TX_MAX,
 					IDPF_TX_DEFAULT);
 
+	/* Set use_vec_entry for single queue mode - only IDPF_TX_SINGLEQ uses regular entries */
+	if (vport->txq_model == VIRTCHNL2_QUEUE_MODEL_SINGLE) {
+		for (i = 0; i < dev->data->nb_tx_queues; i++) {
+			txq = dev->data->tx_queues[i];
+			if (txq == NULL)
+				continue;
+			txq->use_vec_entry = (ad->tx_func_type != IDPF_TX_SINGLEQ);
+		}
+	}
+
 out:
 	dev->tx_pkt_burst = idpf_tx_path_infos[ad->tx_func_type].pkt_burst;
 	dev->tx_pkt_prepare = idpf_dp_prep_pkts;
-- 
2.51.0