[PATCH 3/4] net/mlx5: fix Tx tracing to use single clock source

[Viacheslav Ovsiienko]

From: Tim Martin <timothym at nvidia.com>

The prior commit introduced tracing for mlx5, but there is a mixture of
two unrelated clocks used: the TSC for host work submission timestamps
and the NIC HW clock for CQE completion times. It is necessary to have
timestamps from a single common clock, and the NIC HW clock is the
better choice since it can be used with externally synchronized clocks.

This patch adds the NIC HW clock as an additional logged parameter for
trace_tx_entry, trace_tx_exit, and trace_tx_wqe.  The included trace
analysis python script is also updated to use the new clock when
it is available.

Fixes: a1e910f5b8d4 ("net/mlx5: introduce tracepoints")
Fixes: 9725191a7e14 ("net/mlx5: add Tx datapath trace analyzing script")
Cc: stable at dpdk.org

Signed-off-by: Tim Martin <timothym at nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo at nvidia.com>
---
 drivers/net/mlx5/mlx5_trace.h        |  9 ++++++---
 drivers/net/mlx5/tools/mlx5_trace.py | 12 +++++++++---
 2 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/net/mlx5/mlx5_trace.h b/drivers/net/mlx5/mlx5_trace.h
index 888d96f60b..656dbb1a4f 100644
--- a/drivers/net/mlx5/mlx5_trace.h
+++ b/drivers/net/mlx5/mlx5_trace.h
@@ -22,21 +22,24 @@ extern "C" {
 /* TX burst subroutines trace points. */
 RTE_TRACE_POINT_FP(
 	rte_pmd_mlx5_trace_tx_entry,
-	RTE_TRACE_POINT_ARGS(uint16_t port_id, uint16_t queue_id),
+	RTE_TRACE_POINT_ARGS(uint64_t real_time, uint16_t port_id, uint16_t queue_id),
+	rte_trace_point_emit_u64(real_time);
 	rte_trace_point_emit_u16(port_id);
 	rte_trace_point_emit_u16(queue_id);
 )
 
 RTE_TRACE_POINT_FP(
 	rte_pmd_mlx5_trace_tx_exit,
-	RTE_TRACE_POINT_ARGS(uint16_t nb_sent, uint16_t nb_req),
+	RTE_TRACE_POINT_ARGS(uint64_t real_time, uint16_t nb_sent, uint16_t nb_req),
+	rte_trace_point_emit_u64(real_time);
 	rte_trace_point_emit_u16(nb_sent);
 	rte_trace_point_emit_u16(nb_req);
 )
 
 RTE_TRACE_POINT_FP(
 	rte_pmd_mlx5_trace_tx_wqe,
-	RTE_TRACE_POINT_ARGS(uint32_t opcode),
+	RTE_TRACE_POINT_ARGS(uint64_t real_time, uint32_t opcode),
+	rte_trace_point_emit_u64(real_time);
 	rte_trace_point_emit_u32(opcode);
 )
 
diff --git a/drivers/net/mlx5/tools/mlx5_trace.py b/drivers/net/mlx5/tools/mlx5_trace.py
index 67461520a9..5eb634a490 100755
--- a/drivers/net/mlx5/tools/mlx5_trace.py
+++ b/drivers/net/mlx5/tools/mlx5_trace.py
@@ -174,7 +174,9 @@ def do_tx_entry(msg, trace):
         return
     # allocate the new burst and append to the queue
     burst = MlxBurst()
-    burst.call_ts = msg.default_clock_snapshot.ns_from_origin
+    burst.call_ts = event["real_time"]
+    if burst.call_ts == 0:
+        burst.call_ts = msg.default_clock_snapshot.ns_from_origin
     trace.tx_blst[cpu_id] = burst
     pq_id = event["port_id"] << 16 | event["queue_id"]
     queue = trace.tx_qlst.get(pq_id)
@@ -194,7 +196,9 @@ def do_tx_exit(msg, trace):
     burst = trace.tx_blst.get(cpu_id)
     if burst is None:
         return
-    burst.done_ts = msg.default_clock_snapshot.ns_from_origin
+    burst.done_ts = event["real_time"]
+    if burst.done_ts == 0:
+        burst.done_ts = msg.default_clock_snapshot.ns_from_origin
     burst.req = event["nb_req"]
     burst.done = event["nb_sent"]
     trace.tx_blst.pop(cpu_id)
@@ -210,7 +214,9 @@ def do_tx_wqe(msg, trace):
     wqe = MlxWqe()
     wqe.wait_ts = trace.tx_wlst.get(cpu_id)
     if wqe.wait_ts is None:
-        wqe.wait_ts = msg.default_clock_snapshot.ns_from_origin
+        wqe.wait_ts = event["real_time"]
+        if wqe.wait_ts == 0:
+            wqe.wait_ts = msg.default_clock_snapshot.ns_from_origin
     wqe.opcode = event["opcode"]
     burst.wqes.append(wqe)
 
-- 
2.34.1