netkit: Add tstats per-CPU traffic counters

Add dev->tstats traffic accounting to netkit. The latter contains per-CPU
RX and TX counters.

The dev's TX counters are bumped upon pass/unspec as well as redirect
verdicts, in other words, on everything except for drops.

The dev's RX counters are bumped upon successful __netif_rx(), as well
as from skb_do_redirect() (not part of this commit here).

Using dev->lstats with having just a single packets/bytes counter and
inferring one another's RX counters from the peer dev's lstats is not
possible given skb_do_redirect() can also bump the device's stats.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20231114004220.6495-4-daniel@iogearbox.netSigned-off-by: Martin KaFai Lau <martin.lau@kernel.org>

drivers/net/netkit.c

@@ -68,6 +68,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev)
 	netdev_tx_t ret_dev = NET_XMIT_SUCCESS;
 	const struct bpf_mprog_entry *entry;
 	struct net_device *peer;
+	int len = skb->len;
 
 	rcu_read_lock();
 	peer = rcu_dereference(nk->peer);
@@ -85,15 +86,22 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev)
 	case NETKIT_PASS:
 		skb->protocol = eth_type_trans(skb, skb->dev);
 		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
-		__netif_rx(skb);
+		if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) {
+			dev_sw_netstats_tx_add(dev, 1, len);
+			dev_sw_netstats_rx_add(peer, len);
+		} else {
+			goto drop_stats;
+		}
 		break;
 	case NETKIT_REDIRECT:
+		dev_sw_netstats_tx_add(dev, 1, len);
 		skb_do_redirect(skb);
 		break;
 	case NETKIT_DROP:
 	default:
 drop:
 		kfree_skb(skb);
+drop_stats:
 		dev_core_stats_tx_dropped_inc(dev);
 		ret_dev = NET_XMIT_DROP;
 		break;
@@ -174,6 +182,13 @@ static struct net_device *netkit_peer_dev(struct net_device *dev)
 	return rcu_dereference(netkit_priv(dev)->peer);
 }
 
+static void netkit_get_stats(struct net_device *dev,
+			     struct rtnl_link_stats64 *stats)
+{
+	dev_fetch_sw_netstats(stats, dev->tstats);
+	stats->tx_dropped = DEV_STATS_READ(dev, tx_dropped);
+}
+
 static void netkit_uninit(struct net_device *dev);
 
 static const struct net_device_ops netkit_netdev_ops = {
@@ -184,6 +199,7 @@ static const struct net_device_ops netkit_netdev_ops = {
 	.ndo_set_rx_headroom	= netkit_set_headroom,
 	.ndo_get_iflink		= netkit_get_iflink,
 	.ndo_get_peer_dev	= netkit_peer_dev,
+	.ndo_get_stats64	= netkit_get_stats,
 	.ndo_uninit		= netkit_uninit,
 	.ndo_features_check	= passthru_features_check,
 };
@@ -218,6 +234,7 @@ static void netkit_setup(struct net_device *dev)
 
 	ether_setup(dev);
 	dev->max_mtu = ETH_MAX_MTU;
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 
 	dev->flags |= IFF_NOARP;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;