net/mlx5e: Fix calculated checksum offloads counters

Instead of calculating the offloads counters, count them explicitly.
The calculations done for these counters would result in bugs in some
cases, for example:
When running TCP traffic over a VXLAN tunnel with TSO enabled the following
counters would increase:
       tx_csum_partial: 1,333,284
       tx_csum_partial_inner: 29,286
       tx4_csum_partial_inner: 384
       tx7_csum_partial_inner: 8
       tx9_csum_partial_inner: 34
       tx10_csum_partial_inner: 26,807
       tx11_csum_partial_inner: 287
       tx12_csum_partial_inner: 27
       tx16_csum_partial_inner: 6
       tx25_csum_partial_inner: 1,733

Seems like tx_csum_partial increased out of nowhere.
The issue is in the following calculation in mlx5e_update_sw_counters:
s->tx_csum_partial = s->tx_packets - tx_offload_none - s->tx_csum_partial_inner;

While tx_packets increases by the number of GSO segments for each SKB,
tx_csum_partial_inner will only increase by one, resulting in wrong
tx_csum_partial counter.

Fixes: bfe6d8d1d4 ("net/mlx5e: Reorganize ethtool statistics")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

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

@@ -184,7 +184,6 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 	struct mlx5e_sw_stats temp, *s = &temp;
 	struct mlx5e_rq_stats *rq_stats;
 	struct mlx5e_sq_stats *sq_stats;
-	u64 tx_offload_none = 0;
 	int i, j;
 
 	memset(s, 0, sizeof(*s));
@@ -199,6 +198,7 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 		s->rx_lro_bytes	+= rq_stats->lro_bytes;
 		s->rx_csum_none	+= rq_stats->csum_none;
 		s->rx_csum_complete += rq_stats->csum_complete;
+		s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
 		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
 		s->rx_xdp_drop += rq_stats->xdp_drop;
 		s->rx_xdp_tx += rq_stats->xdp_tx;
@@ -229,14 +229,11 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 			s->tx_queue_dropped	+= sq_stats->dropped;
 			s->tx_xmit_more		+= sq_stats->xmit_more;
 			s->tx_csum_partial_inner += sq_stats->csum_partial_inner;
-			tx_offload_none		+= sq_stats->csum_none;
+			s->tx_csum_none		+= sq_stats->csum_none;
+			s->tx_csum_partial	+= sq_stats->csum_partial;
 		}
 	}
 
-	/* Update calculated offload counters */
-	s->tx_csum_partial = s->tx_packets - tx_offload_none - s->tx_csum_partial_inner;
-	s->rx_csum_unnecessary = s->rx_packets - s->rx_csum_none - s->rx_csum_complete;
-
 	s->link_down_events_phy = MLX5_GET(ppcnt_reg,
 				priv->stats.pport.phy_counters,
 				counter_set.phys_layer_cntrs.link_down_events);

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

@@ -627,6 +627,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 
 	if (lro) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		rq->stats.csum_unnecessary++;
 		return;
 	}
 
@@ -644,7 +645,9 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 			skb->csum_level = 1;
 			skb->encapsulation = 1;
 			rq->stats.csum_unnecessary_inner++;
+			return;
 		}
+		rq->stats.csum_unnecessary++;
 		return;
 	}
 csum_none:

drivers/net/ethernet/mellanox/mlx5/core/en_stats.h

@@ -68,6 +68,7 @@ struct mlx5e_sw_stats {
 	u64 rx_xdp_drop;
 	u64 rx_xdp_tx;
 	u64 rx_xdp_tx_full;
+	u64 tx_csum_none;
 	u64 tx_csum_partial;
 	u64 tx_csum_partial_inner;
 	u64 tx_queue_stopped;
@@ -108,6 +109,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) },
@@ -339,6 +341,7 @@ struct mlx5e_rq_stats {
 	u64 packets;
 	u64 bytes;
 	u64 csum_complete;
+	u64 csum_unnecessary;
 	u64 csum_unnecessary_inner;
 	u64 csum_none;
 	u64 lro_packets;
@@ -363,6 +366,7 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) },
@@ -392,6 +396,7 @@ struct mlx5e_sq_stats {
 	u64 tso_bytes;
 	u64 tso_inner_packets;
 	u64 tso_inner_bytes;
+	u64 csum_partial;
 	u64 csum_partial_inner;
 	u64 nop;
 	/* less likely accessed in data path */
@@ -408,6 +413,7 @@ static const struct counter_desc sq_stats_desc[] = {
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_bytes) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_packets) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) },

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

@@ -193,6 +193,7 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct
 			sq->stats.csum_partial_inner++;
 		} else {
 			eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
+			sq->stats.csum_partial++;
 		}
 	} else
 		sq->stats.csum_none++;