[RFC 3/5] net/mlx5: add Tx datapath tracing

[Viacheslav Ovsiienko <viacheslavo@nvidia.com>]

The patch adds tracing capability to Tx datapath.
To engage this tracing capability the following steps
should be taken:

- meson option -Denable_trace_fp=true
- meson option -Dc_args='-DALLOW_EXPERIMENTAL_API'
- EAL command line parameter --trace=pmd.net.mlx5.tx.*

The Tx datapath tracing allows to get information how packets
are pushed into hardware descriptors, time stamping for
scheduled wait and send completions, etc.

To provide the human readable form of trace results the
dedicated post-processing script is presumed.

Signed-off-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
---
 drivers/net/mlx5/mlx5_rx.h   | 19 -------------------
 drivers/net/mlx5/mlx5_rxtx.h | 19 +++++++++++++++++++
 drivers/net/mlx5/mlx5_tx.c   |  9 +++++++++
 drivers/net/mlx5/mlx5_tx.h   | 25 +++++++++++++++++++++++--
 4 files changed, 51 insertions(+), 21 deletions(-)

diff --git a/drivers/net/mlx5/mlx5_rx.h b/drivers/net/mlx5/mlx5_rx.h
index 8b87adad36..1b5f110ccc 100644
--- a/drivers/net/mlx5/mlx5_rx.h
+++ b/drivers/net/mlx5/mlx5_rx.h
@@ -376,25 +376,6 @@ mlx5_rx_mb2mr(struct mlx5_rxq_data *rxq, struct rte_mbuf *mb)
 	return mlx5_mr_mempool2mr_bh(mr_ctrl, mb->pool, addr);
 }
 
-/**
- * Convert timestamp from HW format to linear counter
- * from Packet Pacing Clock Queue CQE timestamp format.
- *
- * @param sh
- *   Pointer to the device shared context. Might be needed
- *   to convert according current device configuration.
- * @param ts
- *   Timestamp from CQE to convert.
- * @return
- *   UTC in nanoseconds
- */
-static __rte_always_inline uint64_t
-mlx5_txpp_convert_rx_ts(struct mlx5_dev_ctx_shared *sh, uint64_t ts)
-{
-	RTE_SET_USED(sh);
-	return (ts & UINT32_MAX) + (ts >> 32) * NS_PER_S;
-}
-
 /**
  * Set timestamp in mbuf dynamic field.
  *
diff --git a/drivers/net/mlx5/mlx5_rxtx.h b/drivers/net/mlx5/mlx5_rxtx.h
index 876aa14ae6..b109d50758 100644
--- a/drivers/net/mlx5/mlx5_rxtx.h
+++ b/drivers/net/mlx5/mlx5_rxtx.h
@@ -43,4 +43,23 @@ int mlx5_queue_state_modify_primary(struct rte_eth_dev *dev,
 int mlx5_queue_state_modify(struct rte_eth_dev *dev,
 			    struct mlx5_mp_arg_queue_state_modify *sm);
 
+/**
+ * Convert timestamp from HW format to linear counter
+ * from Packet Pacing Clock Queue CQE timestamp format.
+ *
+ * @param sh
+ *   Pointer to the device shared context. Might be needed
+ *   to convert according current device configuration.
+ * @param ts
+ *   Timestamp from CQE to convert.
+ * @return
+ *   UTC in nanoseconds
+ */
+static __rte_always_inline uint64_t
+mlx5_txpp_convert_rx_ts(struct mlx5_dev_ctx_shared *sh, uint64_t ts)
+{
+	RTE_SET_USED(sh);
+	return (ts & UINT32_MAX) + (ts >> 32) * NS_PER_S;
+}
+
 #endif /* RTE_PMD_MLX5_RXTX_H_ */
diff --git a/drivers/net/mlx5/mlx5_tx.c b/drivers/net/mlx5/mlx5_tx.c
index 14e1487e59..1fe9521dfc 100644
--- a/drivers/net/mlx5/mlx5_tx.c
+++ b/drivers/net/mlx5/mlx5_tx.c
@@ -232,6 +232,15 @@ mlx5_tx_handle_completion(struct mlx5_txq_data *__rte_restrict txq,
 		MLX5_ASSERT((txq->fcqs[txq->cq_ci & txq->cqe_m] >> 16) ==
 			    cqe->wqe_counter);
 #endif
+		if (__rte_trace_point_fp_is_enabled()) {
+			uint64_t ts = rte_be_to_cpu_64(cqe->timestamp);
+			uint16_t wqe_id = rte_be_to_cpu_16(cqe->wqe_counter);
+
+			if (txq->rt_timestamp)
+				ts = mlx5_txpp_convert_rx_ts(NULL, ts);
+			rte_pmd_mlx5_trace_tx_complete(txq->port_id, txq->idx,
+						       wqe_id, ts);
+		}
 		ring_doorbell = true;
 		++txq->cq_ci;
 		last_cqe = cqe;
diff --git a/drivers/net/mlx5/mlx5_tx.h b/drivers/net/mlx5/mlx5_tx.h
index cc8f7e98aa..7f624de58e 100644
--- a/drivers/net/mlx5/mlx5_tx.h
+++ b/drivers/net/mlx5/mlx5_tx.h
@@ -19,6 +19,8 @@
 
 #include "mlx5.h"
 #include "mlx5_autoconf.h"
+#include "mlx5_trace.h"
+#include "mlx5_rxtx.h"
 
 /* TX burst subroutines return codes. */
 enum mlx5_txcmp_code {
@@ -764,6 +766,9 @@ mlx5_tx_cseg_init(struct mlx5_txq_data *__rte_restrict txq,
 	cs->flags = RTE_BE32(MLX5_COMP_ONLY_FIRST_ERR <<
 			     MLX5_COMP_MODE_OFFSET);
 	cs->misc = RTE_BE32(0);
+	if (__rte_trace_point_fp_is_enabled() && !loc->pkts_sent)
+		rte_pmd_mlx5_trace_tx_entry(txq->port_id, txq->idx);
+	rte_pmd_mlx5_trace_tx_wqe((txq->wqe_ci << 8) | opcode);
 }
 
 /**
@@ -1692,6 +1697,7 @@ mlx5_tx_schedule_send(struct mlx5_txq_data *restrict txq,
 		if (txq->wait_on_time) {
 			/* The wait on time capability should be used. */
 			ts -= sh->txpp.skew;
+			rte_pmd_mlx5_trace_tx_wait(ts);
 			mlx5_tx_cseg_init(txq, loc, wqe,
 					  1 + sizeof(struct mlx5_wqe_wseg) /
 					      MLX5_WSEG_SIZE,
@@ -1706,6 +1712,7 @@ mlx5_tx_schedule_send(struct mlx5_txq_data *restrict txq,
 			if (unlikely(wci < 0))
 				return MLX5_TXCMP_CODE_SINGLE;
 			/* Build the WAIT WQE with specified completion. */
+			rte_pmd_mlx5_trace_tx_wait(ts - sh->txpp.skew);
 			mlx5_tx_cseg_init(txq, loc, wqe,
 					  1 + sizeof(struct mlx5_wqe_qseg) /
 					      MLX5_WSEG_SIZE,
@@ -1810,6 +1817,7 @@ mlx5_tx_packet_multi_tso(struct mlx5_txq_data *__rte_restrict txq,
 	wqe = txq->wqes + (txq->wqe_ci & txq->wqe_m);
 	loc->wqe_last = wqe;
 	mlx5_tx_cseg_init(txq, loc, wqe, 0, MLX5_OPCODE_TSO, olx);
+	rte_pmd_mlx5_trace_tx_push(loc->mbuf, txq->wqe_ci);
 	ds = mlx5_tx_mseg_build(txq, loc, wqe, vlan, inlen, 1, olx);
 	wqe->cseg.sq_ds = rte_cpu_to_be_32(txq->qp_num_8s | ds);
 	txq->wqe_ci += (ds + 3) / 4;
@@ -1892,6 +1900,7 @@ mlx5_tx_packet_multi_send(struct mlx5_txq_data *__rte_restrict txq,
 	wqe = txq->wqes + (txq->wqe_ci & txq->wqe_m);
 	loc->wqe_last = wqe;
 	mlx5_tx_cseg_init(txq, loc, wqe, ds, MLX5_OPCODE_SEND, olx);
+	rte_pmd_mlx5_trace_tx_push(loc->mbuf, txq->wqe_ci);
 	mlx5_tx_eseg_none(txq, loc, wqe, olx);
 	dseg = &wqe->dseg[0];
 	do {
@@ -2115,6 +2124,7 @@ mlx5_tx_packet_multi_inline(struct mlx5_txq_data *__rte_restrict txq,
 	wqe = txq->wqes + (txq->wqe_ci & txq->wqe_m);
 	loc->wqe_last = wqe;
 	mlx5_tx_cseg_init(txq, loc, wqe, 0, MLX5_OPCODE_SEND, olx);
+	rte_pmd_mlx5_trace_tx_push(loc->mbuf, txq->wqe_ci);
 	ds = mlx5_tx_mseg_build(txq, loc, wqe, vlan, inlen, 0, olx);
 	wqe->cseg.sq_ds = rte_cpu_to_be_32(txq->qp_num_8s | ds);
 	txq->wqe_ci += (ds + 3) / 4;
@@ -2318,8 +2328,8 @@ mlx5_tx_burst_tso(struct mlx5_txq_data *__rte_restrict txq,
 		 */
 		wqe = txq->wqes + (txq->wqe_ci & txq->wqe_m);
 		loc->wqe_last = wqe;
-		mlx5_tx_cseg_init(txq, loc, wqe, ds,
-				  MLX5_OPCODE_TSO, olx);
+		mlx5_tx_cseg_init(txq, loc, wqe, ds, MLX5_OPCODE_TSO, olx);
+		rte_pmd_mlx5_trace_tx_push(loc->mbuf, txq->wqe_ci);
 		dseg = mlx5_tx_eseg_data(txq, loc, wqe, vlan, hlen, 1, olx);
 		dptr = rte_pktmbuf_mtod(loc->mbuf, uint8_t *) + hlen - vlan;
 		dlen -= hlen - vlan;
@@ -2688,6 +2698,7 @@ mlx5_tx_burst_empw_simple(struct mlx5_txq_data *__rte_restrict txq,
 			/* Update sent data bytes counter. */
 			slen += dlen;
 #endif
+			rte_pmd_mlx5_trace_tx_push(loc->mbuf, txq->wqe_ci);
 			mlx5_tx_dseg_ptr
 				(txq, loc, dseg,
 				 rte_pktmbuf_mtod(loc->mbuf, uint8_t *),
@@ -2926,6 +2937,7 @@ mlx5_tx_burst_empw_inline(struct mlx5_txq_data *__rte_restrict txq,
 				tlen += sizeof(struct rte_vlan_hdr);
 				if (room < tlen)
 					break;
+				rte_pmd_mlx5_trace_tx_push(loc->mbuf, txq->wqe_ci);
 				dseg = mlx5_tx_dseg_vlan(txq, loc, dseg,
 							 dptr, dlen, olx);
 #ifdef MLX5_PMD_SOFT_COUNTERS
@@ -2935,6 +2947,7 @@ mlx5_tx_burst_empw_inline(struct mlx5_txq_data *__rte_restrict txq,
 			} else {
 				if (room < tlen)
 					break;
+				rte_pmd_mlx5_trace_tx_push(loc->mbuf, txq->wqe_ci);
 				dseg = mlx5_tx_dseg_empw(txq, loc, dseg,
 							 dptr, dlen, olx);
 			}
@@ -2980,6 +2993,7 @@ mlx5_tx_burst_empw_inline(struct mlx5_txq_data *__rte_restrict txq,
 			if (MLX5_TXOFF_CONFIG(VLAN))
 				MLX5_ASSERT(!(loc->mbuf->ol_flags &
 					    RTE_MBUF_F_TX_VLAN));
+			rte_pmd_mlx5_trace_tx_push(loc->mbuf, txq->wqe_ci);
 			mlx5_tx_dseg_ptr(txq, loc, dseg, dptr, dlen, olx);
 			/* We have to store mbuf in elts.*/
 			txq->elts[txq->elts_head++ & txq->elts_m] = loc->mbuf;
@@ -3194,6 +3208,7 @@ mlx5_tx_burst_single_send(struct mlx5_txq_data *__rte_restrict txq,
 				loc->wqe_last = wqe;
 				mlx5_tx_cseg_init(txq, loc, wqe, seg_n,
 						  MLX5_OPCODE_SEND, olx);
+				rte_pmd_mlx5_trace_tx_push(loc->mbuf, txq->wqe_ci);
 				mlx5_tx_eseg_data(txq, loc, wqe,
 						  vlan, inlen, 0, olx);
 				txq->wqe_ci += wqe_n;
@@ -3256,6 +3271,7 @@ mlx5_tx_burst_single_send(struct mlx5_txq_data *__rte_restrict txq,
 				loc->wqe_last = wqe;
 				mlx5_tx_cseg_init(txq, loc, wqe, ds,
 						  MLX5_OPCODE_SEND, olx);
+				rte_pmd_mlx5_trace_tx_push(loc->mbuf, txq->wqe_ci);
 				dseg = mlx5_tx_eseg_data(txq, loc, wqe, vlan,
 							 txq->inlen_mode,
 							 0, olx);
@@ -3297,6 +3313,7 @@ mlx5_tx_burst_single_send(struct mlx5_txq_data *__rte_restrict txq,
 				loc->wqe_last = wqe;
 				mlx5_tx_cseg_init(txq, loc, wqe, 4,
 						  MLX5_OPCODE_SEND, olx);
+				rte_pmd_mlx5_trace_tx_push(loc->mbuf, txq->wqe_ci);
 				mlx5_tx_eseg_dmin(txq, loc, wqe, vlan, olx);
 				dptr = rte_pktmbuf_mtod(loc->mbuf, uint8_t *) +
 				       MLX5_ESEG_MIN_INLINE_SIZE - vlan;
@@ -3338,6 +3355,7 @@ mlx5_tx_burst_single_send(struct mlx5_txq_data *__rte_restrict txq,
 			loc->wqe_last = wqe;
 			mlx5_tx_cseg_init(txq, loc, wqe, 3,
 					  MLX5_OPCODE_SEND, olx);
+			rte_pmd_mlx5_trace_tx_push(loc->mbuf, txq->wqe_ci);
 			mlx5_tx_eseg_none(txq, loc, wqe, olx);
 			mlx5_tx_dseg_ptr
 				(txq, loc, &wqe->dseg[0],
@@ -3707,6 +3725,9 @@ mlx5_tx_burst_tmpl(struct mlx5_txq_data *__rte_restrict txq,
 #endif
 	if (MLX5_TXOFF_CONFIG(INLINE) && loc.mbuf_free)
 		__mlx5_tx_free_mbuf(txq, pkts, loc.mbuf_free, olx);
+	/* Trace productive bursts only. */
+	if (__rte_trace_point_fp_is_enabled() && loc.pkts_sent)
+		rte_pmd_mlx5_trace_tx_exit(loc.pkts_sent, pkts_n);
 	return loc.pkts_sent;
 }
 
-- 
2.18.1