net/mlx4_en: Add ethtool statistics for XDP cases

XDP statistics are reported in ethtool, in total and per ring,
as follows:
- xdp_drop: the number of packets dropped by xdp.
- xdp_tx: the number of packets forwarded by xdp.
- xdp_tx_full: the number of times an xdp forward failed
	due to a full tx xdp ring.

In addition, all packets that are dropped/forwarded by XDP
are no longer accounted in rx_packets/rx_bytes of the ring,
so that they count traffic that is passed to the stack.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx4/en_ethtool.c

@@ -195,6 +195,10 @@ static const char main_strings[][ETH_GSTRING_LEN] = {
 	"tx_prio_7_packets", "tx_prio_7_bytes",
 	"tx_novlan_packets", "tx_novlan_bytes",
 
+	/* xdp statistics */
+	"rx_xdp_drop",
+	"rx_xdp_tx",
+	"rx_xdp_tx_full",
 };
 
 static const char mlx4_en_test_names[][ETH_GSTRING_LEN]= {
@@ -340,7 +344,7 @@ static int mlx4_en_get_sset_count(struct net_device *dev, int sset)
 	case ETH_SS_STATS:
 		return bitmap_iterator_count(&it) +
 			(priv->tx_ring_num[TX] * 2) +
-			(priv->rx_ring_num * 3);
+			(priv->rx_ring_num * (3 + NUM_XDP_STATS));
 	case ETH_SS_TEST:
 		return MLX4_EN_NUM_SELF_TEST - !(priv->mdev->dev->caps.flags
 					& MLX4_DEV_CAP_FLAG_UC_LOOPBACK) * 2;
@@ -400,6 +404,10 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev,
 		if (bitmap_iterator_test(&it))
 			data[index++] = ((unsigned long *)&priv->pkstats)[i];
 
+	for (i = 0; i < NUM_XDP_STATS; i++, bitmap_iterator_inc(&it))
+		if (bitmap_iterator_test(&it))
+			data[index++] = ((unsigned long *)&priv->xdp_stats)[i];
+
 	for (i = 0; i < priv->tx_ring_num[TX]; i++) {
 		data[index++] = priv->tx_ring[TX][i]->packets;
 		data[index++] = priv->tx_ring[TX][i]->bytes;
@@ -408,6 +416,9 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev,
 		data[index++] = priv->rx_ring[i]->packets;
 		data[index++] = priv->rx_ring[i]->bytes;
 		data[index++] = priv->rx_ring[i]->dropped;
+		data[index++] = priv->rx_ring[i]->xdp_drop;
+		data[index++] = priv->rx_ring[i]->xdp_tx;
+		data[index++] = priv->rx_ring[i]->xdp_tx_full;
 	}
 	spin_unlock_bh(&priv->stats_lock);
 
@@ -470,6 +481,12 @@ static void mlx4_en_get_strings(struct net_device *dev,
 				strcpy(data + (index++) * ETH_GSTRING_LEN,
 				       main_strings[strings]);
 
+		for (i = 0; i < NUM_XDP_STATS; i++, strings++,
+		     bitmap_iterator_inc(&it))
+			if (bitmap_iterator_test(&it))
+				strcpy(data + (index++) * ETH_GSTRING_LEN,
+				       main_strings[strings]);
+
 		for (i = 0; i < priv->tx_ring_num[TX]; i++) {
 			sprintf(data + (index++) * ETH_GSTRING_LEN,
 				"tx%d_packets", i);
@@ -483,6 +500,12 @@ static void mlx4_en_get_strings(struct net_device *dev,
 				"rx%d_bytes", i);
 			sprintf(data + (index++) * ETH_GSTRING_LEN,
 				"rx%d_dropped", i);
+			sprintf(data + (index++) * ETH_GSTRING_LEN,
+				"rx%d_xdp_drop", i);
+			sprintf(data + (index++) * ETH_GSTRING_LEN,
+				"rx%d_xdp_tx", i);
+			sprintf(data + (index++) * ETH_GSTRING_LEN,
+				"rx%d_xdp_tx_full", i);
 		}
 		break;
 	case ETH_SS_PRIV_FLAGS:

drivers/net/ethernet/mellanox/mlx4/en_netdev.c

@@ -3125,6 +3125,10 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev,
 
 	if (!mlx4_is_slave(dev))
 		bitmap_set(stats_bitmap->bitmap, last_i, NUM_PKT_STATS);
+	last_i += NUM_PKT_STATS;
+
+	bitmap_set(stats_bitmap->bitmap, last_i, NUM_XDP_STATS);
+	last_i += NUM_XDP_STATS;
 }
 
 int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,

drivers/net/ethernet/mellanox/mlx4/en_port.c

@@ -179,6 +179,9 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	priv->port_stats.rx_chksum_good = 0;
 	priv->port_stats.rx_chksum_none = 0;
 	priv->port_stats.rx_chksum_complete = 0;
+	priv->xdp_stats.rx_xdp_drop    = 0;
+	priv->xdp_stats.rx_xdp_tx      = 0;
+	priv->xdp_stats.rx_xdp_tx_full = 0;
 	for (i = 0; i < priv->rx_ring_num; i++) {
 		stats->rx_packets += priv->rx_ring[i]->packets;
 		stats->rx_bytes += priv->rx_ring[i]->bytes;
@@ -186,6 +189,9 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 		priv->port_stats.rx_chksum_good += priv->rx_ring[i]->csum_ok;
 		priv->port_stats.rx_chksum_none += priv->rx_ring[i]->csum_none;
 		priv->port_stats.rx_chksum_complete += priv->rx_ring[i]->csum_complete;
+		priv->xdp_stats.rx_xdp_drop    += priv->rx_ring[i]->xdp_drop;
+		priv->xdp_stats.rx_xdp_tx      += priv->rx_ring[i]->xdp_tx;
+		priv->xdp_stats.rx_xdp_tx_full += priv->rx_ring[i]->xdp_tx_full;
 	}
 	stats->tx_packets = 0;
 	stats->tx_bytes = 0;

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -875,8 +875,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		 */
 		length = be32_to_cpu(cqe->byte_cnt);
 		length -= ring->fcs_del;
-		ring->bytes += length;
-		ring->packets++;
 		l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
 			(cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
 
@@ -902,22 +900,26 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			case XDP_PASS:
 				break;
 			case XDP_TX:
-				if (likely(!mlx4_en_xmit_frame(frags, dev,
+				if (likely(!mlx4_en_xmit_frame(ring, frags, dev,
 							length, cq->ring,
 							&doorbell_pending)))
 					goto consumed;
-				goto xdp_drop; /* Drop on xmit failure */
+				goto xdp_drop_no_cnt; /* Drop on xmit failure */
 			default:
 				bpf_warn_invalid_xdp_action(act);
 			case XDP_ABORTED:
 			case XDP_DROP:
-xdp_drop:
+				ring->xdp_drop++;
+xdp_drop_no_cnt:
 				if (likely(mlx4_en_rx_recycle(ring, frags)))
 					goto consumed;
 				goto next;
 			}
 		}
 
+		ring->bytes += length;
+		ring->packets++;
+
 		if (likely(dev->features & NETIF_F_RXCSUM)) {
 			if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
 						      MLX4_CQE_STATUS_UDP)) {

drivers/net/ethernet/mellanox/mlx4/en_tx.c

@@ -1079,7 +1079,8 @@ tx_drop:
 	return NETDEV_TX_OK;
 }
 
-netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
+netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
+			       struct mlx4_en_rx_alloc *frame,
 			       struct net_device *dev, unsigned int length,
 			       int tx_ind, int *doorbell_pending)
 {
@@ -1154,8 +1155,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
 		((ring->prod & ring->size) ?
 		 cpu_to_be32(MLX4_EN_BIT_DESC_OWN) : 0);
 
-	ring->packets++;
-	ring->bytes += tx_info->nr_bytes;
+	rx_ring->xdp_tx++;
 	AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, length);
 
 	ring->prod += nr_txbb;
@@ -1179,7 +1179,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
 	return NETDEV_TX_OK;
 
 tx_drop_count:
-	ring->tx_dropped++;
+	rx_ring->xdp_tx_full++;
 tx_drop:
 	return NETDEV_TX_BUSY;
 }

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -350,6 +350,9 @@ struct mlx4_en_rx_ring {
 	unsigned long csum_ok;
 	unsigned long csum_none;
 	unsigned long csum_complete;
+	unsigned long xdp_drop;
+	unsigned long xdp_tx;
+	unsigned long xdp_tx_full;
 	unsigned long dropped;
 	int hwtstamp_rx_filter;
 	cpumask_var_t affinity_mask;
@@ -599,6 +602,7 @@ struct mlx4_en_priv {
 	struct mlx4_en_flow_stats_rx rx_flowstats;
 	struct mlx4_en_flow_stats_tx tx_flowstats;
 	struct mlx4_en_port_stats port_stats;
+	struct mlx4_en_xdp_stats xdp_stats;
 	struct mlx4_en_stats_bitmap stats_bitmap;
 	struct list_head mc_list;
 	struct list_head curr_list;
@@ -687,7 +691,8 @@ void mlx4_en_tx_irq(struct mlx4_cq *mcq);
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
 			 void *accel_priv, select_queue_fallback_t fallback);
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
-netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
+netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
+			       struct mlx4_en_rx_alloc *frame,
 			       struct net_device *dev, unsigned int length,
 			       int tx_ind, int *doorbell_pending);
 void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring);

drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h

@@ -55,6 +55,13 @@ struct mlx4_en_perf_stats {
 #define NUM_PERF_COUNTERS		6
 };
 
+struct mlx4_en_xdp_stats {
+	unsigned long rx_xdp_drop;
+	unsigned long rx_xdp_tx;
+	unsigned long rx_xdp_tx_full;
+#define NUM_XDP_STATS		3
+};
+
 #define NUM_MAIN_STATS	21
 
 #define MLX4_NUM_PRIORITIES	8
@@ -107,7 +114,8 @@ enum {
 };
 
 #define NUM_ALL_STATS	(NUM_MAIN_STATS + NUM_PORT_STATS + NUM_PKT_STATS + \
-			 NUM_FLOW_STATS + NUM_PERF_STATS + NUM_PF_STATS)
+			 NUM_FLOW_STATS + NUM_PERF_STATS + NUM_PF_STATS + \
+			 NUM_XDP_STATS)
 
 #define MLX4_FIND_NETDEV_STAT(n) (offsetof(struct net_device_stats, n) / \
 				  sizeof(((struct net_device_stats *)0)->n))