[PATCH v2 36/36] net/idpf: enable simple Tx function

[Bruce Richardson <bruce.richardson@intel.com>]

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@intel.com>
---
 drivers/net/intel/idpf/idpf_common_device.h |  2 ++
 drivers/net/intel/idpf/idpf_common_rxtx.c   | 19 +++++++++++++++
 drivers/net/intel/idpf/idpf_common_rxtx.h   |  3 +++
 drivers/net/intel/idpf/idpf_rxtx.c          | 26 ++++++++++++++++++++-
 4 files changed, 49 insertions(+), 1 deletion(-)

diff --git a/drivers/net/intel/idpf/idpf_common_device.h b/drivers/net/intel/idpf/idpf_common_device.h
index 31915a03d4..527aa9b3dc 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,
@@ -100,6 +101,7 @@ struct idpf_adapter {
 
 	bool is_tx_singleq; /* true - single queue model, false - split queue model */
 	bool is_rx_singleq; /* true - single queue model, false - split queue model */
+	bool tx_simple_allowed; /* true if all queues support simple TX */
 
 	/* For timestamp */
 	uint64_t time_hw;
diff --git a/drivers/net/intel/idpf/idpf_common_rxtx.c b/drivers/net/intel/idpf/idpf_common_rxtx.c
index 781310e564..bf2e9363d4 100644
--- a/drivers/net/intel/idpf/idpf_common_rxtx.c
+++ b/drivers/net/intel/idpf/idpf_common_rxtx.c
@@ -1348,6 +1348,15 @@ 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
@@ -1533,6 +1542,16 @@ 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_rxtx.c b/drivers/net/intel/idpf/idpf_rxtx.c
index 5c2516f556..a2bb4b766d 100644
--- a/drivers/net/intel/idpf/idpf_rxtx.c
+++ b/drivers/net/intel/idpf/idpf_rxtx.c
@@ -497,6 +497,22 @@ idpf_tx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx,
 	txq->q_set = true;
 	dev->data->tx_queues[queue_idx] = txq;
 
+	/* Set tx_simple_allowed flag based on queue configuration.
+	 * For queue 0: explicitly set the flag based on its configuration.
+	 * For other queues: only set to false if this queue cannot use simple_tx.
+	 */
+	if (vport->txq_model == VIRTCHNL2_QUEUE_MODEL_SPLIT)
+		goto out;
+
+	/* for first queue, default to true, disable later if any queue can't meet conditions */
+	if (queue_idx == 0)
+		adapter->tx_simple_allowed = true;
+
+	if ((txq->offloads != (txq->offloads & RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE)) ||
+			txq->tx_rs_thresh < IDPF_VPMD_TX_MAX_BURST)
+		adapter->tx_simple_allowed = false;
+
+out:
 	return 0;
 
 err_complq_setup:
@@ -639,6 +655,7 @@ int
 idpf_tx_queue_start(struct rte_eth_dev *dev, uint16_t tx_queue_id)
 {
 	struct idpf_vport *vport = dev->data->dev_private;
+	struct idpf_adapter *ad = vport->adapter;
 	struct ci_tx_queue *txq = dev->data->tx_queues[tx_queue_id];
 	int err = 0;
 
@@ -655,6 +672,12 @@ idpf_tx_queue_start(struct rte_eth_dev *dev, uint16_t tx_queue_id)
 		return err;
 	}
 
+	/* Record what kind of descriptor cleanup we need on teardown.
+	 * For single queue mode, vector or simple tx paths use vec entry format.
+	 */
+	if (vport->txq_model == VIRTCHNL2_QUEUE_MODEL_SINGLE)
+		txq->use_vec_entry = ad->tx_simple_allowed;
+
 	/* Ready to switch the queue on */
 	err = idpf_vc_queue_switch(vport, tx_queue_id, false, true,
 							VIRTCHNL2_QUEUE_TYPE_TX);
@@ -835,7 +858,8 @@ idpf_set_tx_function(struct rte_eth_dev *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 = ad->tx_simple_allowed
 	};
 
 	/* The primary process selects the tx path for all processes. */
-- 
2.51.0