net/mlx5e: Re-add support for TX timeout when TX reporter is not valid

When TX reporter was introduced, it took ownership over TX timeout error
handling. this introduced a regression in case TX reporter is not valid
(NET_DEVLINK is not set, or devlink_health_reporter_create failure).

Fix mlx5e_tx_reporter_timeout function so it can be called at all times.

In addition, remove a warning print that indicates that a TX timeout won't
be handled in case of no valid TX reporter.

Fixes: 7d91126 ("net/mlx5e: Add tx timeout support for mlx5e tx reporter")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

Author: Eran Ben Elisha

drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c

@@ -113,6 +113,18 @@ static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq)
 	return 0;
 }
 
+static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter,
+				 char *err_str,
+				 struct mlx5e_tx_err_ctx *err_ctx)
+{
+	if (IS_ERR_OR_NULL(tx_reporter)) {
+		netdev_err(err_ctx->sq->channel->netdev, err_str);
+		return err_ctx->recover(err_ctx->sq);
+	}
+
+	return devlink_health_report(tx_reporter, err_str, err_ctx);
+}
+
 void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq)
 {
 	char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
@@ -122,7 +134,7 @@ void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq)
 	err_ctx.recover  = mlx5e_tx_reporter_err_cqe_recover;
 	sprintf(err_str, "ERR CQE on SQ: 0x%x", sq->sqn);
 
-	devlink_health_report(sq->channel->priv->tx_reporter, err_str,
+	mlx5_tx_health_report(sq->channel->priv->tx_reporter, err_str,
 			      &err_ctx);
 }
 
@@ -160,7 +172,7 @@ int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq)
 		sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
 		jiffies_to_usecs(jiffies - sq->txq->trans_start));
 
-	return devlink_health_report(sq->channel->priv->tx_reporter, err_str,
+	return mlx5_tx_health_report(sq->channel->priv->tx_reporter, err_str,
 				     &err_ctx);
 }
 

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -4173,12 +4173,6 @@ static void mlx5e_tx_timeout(struct net_device *dev)
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
 	netdev_err(dev, "TX timeout detected\n");
-
-	if (IS_ERR_OR_NULL(priv->tx_reporter)) {
-		netdev_err_once(priv->netdev, "tx timeout will not be handled, no valid tx reporter\n");
-		return;
-	}
-
 	queue_work(priv->wq, &priv->tx_timeout_work);
 }
 

drivers/net/ethernet/mellanox/mlx5/core/en_tx.c

@@ -519,9 +519,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 					      &sq->state)) {
 				mlx5e_dump_error_cqe(sq,
 						     (struct mlx5_err_cqe *)cqe);
-				if (!IS_ERR_OR_NULL(cq->channel->priv->tx_reporter))
-					queue_work(cq->channel->priv->wq,
-						   &sq->recover_work);
+				queue_work(cq->channel->priv->wq,
+					   &sq->recover_work);
 			}
 			stats->cqe_err++;
 		}