Thread (6 messages) 6 messages, 1 author, 4d ago
COOLING4d REVIEWED: 1 (0M)

[PATCH net-next 1/5] net/mlx5: HWS, Print more details for bad completion

From: Tariq Toukan <tariqt@nvidia.com>
Date: 2026-07-23 09:54:43
Also in: linux-rdma, lkml
Subsystem: mellanox mlx5 core vpi driver, networking drivers, the rest · Maintainers: Saeed Mahameed, Leon Romanovsky, Tariq Toukan, Mark Bloch, Andrew Lunn, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Linus Torvalds

From: Yevgeny Kliteynik <redacted>

When polling for completion returned completion with error,
parse some more details: QP number and WQE count.
Also, extract all the long value-to-string if conditions
to a short value-to-string functions: do it for rule
resize state, rule status, and syndrome.

Signed-off-by: Yevgeny Kliteynik <redacted>
Reviewed-by: Erez Shitrit <redacted>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../mellanox/mlx5/core/steering/hws/send.c    | 68 +++++++++++++------
 1 file changed, 49 insertions(+), 19 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
index aed009aec4fe..1c9206f74aaa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
@@ -344,6 +344,36 @@ hws_send_engine_update_rule_resize(struct mlx5hws_send_engine *queue,
 	}
 }
 
+static const char *hws_rule_status_to_string(enum mlx5hws_rule_status status)
+{
+	switch (status) {
+	case MLX5HWS_RULE_STATUS_CREATING: return "CREATING";
+	case MLX5HWS_RULE_STATUS_UPDATING: return "UPDATING";
+	case MLX5HWS_RULE_STATUS_DELETING: return "DELETING";
+	case MLX5HWS_RULE_STATUS_FAILING: return "FAILING";
+	default: return "NA";
+	}
+}
+
+static const char *hws_rule_resize_state_to_string(u8 state)
+{
+	switch (state) {
+	case MLX5HWS_RULE_RESIZE_STATE_IDLE: return "IDLE";
+	case MLX5HWS_RULE_RESIZE_STATE_WRITING: return "WRITING";
+	case MLX5HWS_RULE_RESIZE_STATE_DELETING: return "DELETING";
+	default: return "UNKNOWN";
+	}
+}
+
+static const char *hws_gta_syndrome_to_string(u8 syndrome)
+{
+	switch (syndrome) {
+	case 1: return "SET_FLOW_FAIL";
+	case 2: return "DISABLE_FLOW_FAIL";
+	default: return "UNKNOWN";
+	}
+}
+
 static void hws_send_engine_dump_error_cqe(struct mlx5hws_send_engine *queue,
 					   struct mlx5hws_send_ring_priv *priv,
 					   struct mlx5_cqe64 *cqe)
@@ -352,6 +382,7 @@ static void hws_send_engine_dump_error_cqe(struct mlx5hws_send_engine *queue,
 	struct mlx5hws_context *ctx = priv->rule->matcher->tbl->ctx;
 	u32 opcode = cqe ? get_cqe_opcode(cqe) : 0;
 	struct mlx5hws_rule *rule = priv->rule;
+	u8 syndrome;
 
 	/* If something bad happens and lots of rules are failing, we don't
 	 * want to pollute dmesg. Print only the first bad cqe per engine,
@@ -364,26 +395,17 @@ static void hws_send_engine_dump_error_cqe(struct mlx5hws_send_engine *queue,
 
 	if (mlx5hws_rule_move_in_progress(rule))
 		mlx5hws_err(ctx,
-			    "--- rule 0x%08llx: error completion moving rule: phase %s, wqes left %d\n",
+			    "--- rule 0x%08llx: error completion moving rule: phase %s (%d), wqes left %d\n",
 			    HWS_PTR_TO_ID(rule),
-			    rule->resize_info->state ==
-			    MLX5HWS_RULE_RESIZE_STATE_WRITING ? "WRITING" :
-			    rule->resize_info->state ==
-			    MLX5HWS_RULE_RESIZE_STATE_DELETING ? "DELETING" :
-			    "UNKNOWN",
+			    hws_rule_resize_state_to_string
+				(rule->resize_info->state),
+			    rule->resize_info->state,
 			    rule->pending_wqes);
 	else
 		mlx5hws_err(ctx,
 			    "--- rule 0x%08llx: error completion %s (%d), wqes left %d\n",
 			    HWS_PTR_TO_ID(rule),
-			    rule->status ==
-			    MLX5HWS_RULE_STATUS_CREATING ? "CREATING" :
-			    rule->status ==
-			    MLX5HWS_RULE_STATUS_DELETING ? "DELETING" :
-			    rule->status ==
-			    MLX5HWS_RULE_STATUS_FAILING ? "FAILING" :
-			    rule->status ==
-			    MLX5HWS_RULE_STATUS_UPDATING ? "UPDATING" : "NA",
+			    hws_rule_status_to_string(rule->status),
 			    rule->status,
 			    rule->pending_wqes);
 
@@ -423,6 +445,15 @@ static void hws_send_engine_dump_error_cqe(struct mlx5hws_send_engine *queue,
 			    "    rule 0x%08llx:  |--- syndrome = 0x%x\n",
 			    HWS_PTR_TO_ID(rule),
 			    err_cqe->syndrome);
+		mlx5hws_err(ctx,
+			    "    rule 0x%08llx:  |--- QPN = 0x%x\n",
+			    HWS_PTR_TO_ID(rule),
+			    be32_to_cpu(err_cqe->s_wqe_opcode_qpn) &
+					0xffffff);
+		mlx5hws_err(ctx,
+			    "    rule 0x%08llx:  |--- WQE_CNT = 0x%04x\n",
+			    HWS_PTR_TO_ID(rule),
+			    (u32)be16_to_cpu(err_cqe->wqe_counter));
 	}
 
 	mlx5hws_err(ctx,
@@ -433,13 +464,12 @@ static void hws_send_engine_dump_error_cqe(struct mlx5hws_send_engine *queue,
 		    HWS_PTR_TO_ID(rule),
 		    (be32_to_cpu(cqe->byte_cnt) & 0x80000000) ?
 		    "FAILURE" : "SUCCESS");
+	/* syndrome is in the lower 2 bits of byte_cnt */
+	syndrome = be32_to_cpu(cqe->byte_cnt) & 3;
 	mlx5hws_err(ctx,
-		    "    rule 0x%08llx:  |------- SYNDROME = %s\n",
+		    "    rule 0x%08llx:  |------- SYNDROME = %s (%u)\n",
 		    HWS_PTR_TO_ID(rule),
-		    ((be32_to_cpu(cqe->byte_cnt) & 0x00000003) == 1) ?
-		    "SET_FLOW_FAIL" :
-		    ((be32_to_cpu(cqe->byte_cnt) & 0x00000003) == 2) ?
-		    "DISABLE_FLOW_FAIL" : "UNKNOWN");
+		    hws_gta_syndrome_to_string(syndrome), syndrome);
 	mlx5hws_err(ctx,
 		    "    rule 0x%08llx: cqe->sop_drop_qpn  = 0x%08x\n",
 		    HWS_PTR_TO_ID(rule), be32_to_cpu(cqe->sop_drop_qpn));
-- 
2.44.0
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help