net: add a core netdev->rx_dropped counter

In various situations, a device provides a packet to our stack and we
drop it before it enters protocol stack :
- softnet backlog full (accounted in /proc/net/softnet_stat)
- bad vlan tag (not accounted)
- unknown/unregistered protocol (not accounted)

We can handle a per-device counter of such dropped frames at core level,
and automatically adds it to the device provided stats (rx_dropped), so
that standard tools can be used (ifconfig, ip link, cat /proc/net/dev)

This is a generalization of commit 8990f46 (net: rx_dropped
accounting), thus reverting it.

Signed-off-by: Eric Dumazet <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

drivers/net/loopback.c

@@ -64,7 +64,6 @@ struct pcpu_lstats {
 	u64			packets;
 	u64			bytes;
 	struct u64_stats_sync	syncp;
-	unsigned long		drops;
 };
 
 /*
@@ -90,8 +89,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb,
 		lb_stats->bytes += len;
 		lb_stats->packets++;
 		u64_stats_update_end(&lb_stats->syncp);
-	} else
-		lb_stats->drops++;
+	}
 
 	return NETDEV_TX_OK;
 }
@@ -101,7 +99,6 @@ static struct rtnl_link_stats64 *loopback_get_stats64(struct net_device *dev,
 {
 	u64 bytes = 0;
 	u64 packets = 0;
-	u64 drops = 0;
 	int i;
 
 	for_each_possible_cpu(i) {
@@ -115,14 +112,11 @@ static struct rtnl_link_stats64 *loopback_get_stats64(struct net_device *dev,
 			tbytes = lb_stats->bytes;
 			tpackets = lb_stats->packets;
 		} while (u64_stats_fetch_retry(&lb_stats->syncp, start));
-		drops   += lb_stats->drops;
 		bytes   += tbytes;
 		packets += tpackets;
 	}
 	stats->rx_packets = packets;
 	stats->tx_packets = packets;
-	stats->rx_dropped = drops;
-	stats->rx_errors  = drops;
 	stats->rx_bytes   = bytes;
 	stats->tx_bytes   = bytes;
 	return stats;

include/linux/netdevice.h

@@ -884,6 +884,9 @@ struct net_device {
 	int			iflink;
 
 	struct net_device_stats	stats;
+	atomic_long_t		rx_dropped; /* dropped packets by core network
+					     * Do not use this in drivers.
+					     */
 
 #ifdef CONFIG_WIRELESS_EXT
 	/* List of functions to handle Wireless Extensions (instead of ioctl).

net/8021q/vlan.h

@@ -25,15 +25,13 @@ struct vlan_priority_tci_mapping {
  *	@rx_multicast: number of received multicast packets
  *	@syncp: synchronization point for 64bit counters
  *	@rx_errors: number of errors
- *	@rx_dropped: number of dropped packets
  */
 struct vlan_rx_stats {
 	u64			rx_packets;
 	u64			rx_bytes;
 	u64			rx_multicast;
 	struct u64_stats_sync	syncp;
 	unsigned long		rx_errors;
-	unsigned long		rx_dropped;
 };
 
 /**

net/8021q/vlan_core.c

@@ -33,6 +33,7 @@ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
 	return polling ? netif_receive_skb(skb) : netif_rx(skb);
 
 drop:
+	atomic_long_inc(&skb->dev->rx_dropped);
 	dev_kfree_skb_any(skb);
 	return NET_RX_DROP;
 }
@@ -123,6 +124,7 @@ vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp,
 	return dev_gro_receive(napi, skb);
 
 drop:
+	atomic_long_inc(&skb->dev->rx_dropped);
 	return GRO_DROP;
 }
 

net/8021q/vlan_dev.c

@@ -225,16 +225,15 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
-	if (unlikely(netif_rx(skb) == NET_RX_DROP)) {
-		if (rx_stats)
-			rx_stats->rx_dropped++;
-	}
+	netif_rx(skb);
+
 	rcu_read_unlock();
 	return NET_RX_SUCCESS;
 
 err_unlock:
 	rcu_read_unlock();
 err_free:
+	atomic_long_inc(&dev->rx_dropped);
 	kfree_skb(skb);
 	return NET_RX_DROP;
 }
@@ -846,15 +845,13 @@ static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, st
 			accum.rx_packets += rxpackets;
 			accum.rx_bytes   += rxbytes;
 			accum.rx_multicast += rxmulticast;
-			/* rx_errors, rx_dropped are ulong, not protected by syncp */
+			/* rx_errors is ulong, not protected by syncp */
 			accum.rx_errors  += p->rx_errors;
-			accum.rx_dropped += p->rx_dropped;
 		}
 		stats->rx_packets = accum.rx_packets;
 		stats->rx_bytes   = accum.rx_bytes;
 		stats->rx_errors  = accum.rx_errors;
 		stats->multicast  = accum.rx_multicast;
-		stats->rx_dropped = accum.rx_dropped;
 	}
 	return stats;
 }

net/core/dev.c

@@ -1483,8 +1483,9 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 	skb_orphan(skb);
 	nf_reset(skb);
 
-	if (!(dev->flags & IFF_UP) ||
-	    (skb->len > (dev->mtu + dev->hard_header_len))) {
+	if (unlikely(!(dev->flags & IFF_UP) ||
+		     (skb->len > (dev->mtu + dev->hard_header_len)))) {
+		atomic_long_inc(&dev->rx_dropped);
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
@@ -2548,6 +2549,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 
 	local_irq_restore(flags);
 
+	atomic_long_inc(&skb->dev->rx_dropped);
 	kfree_skb(skb);
 	return NET_RX_DROP;
 }
@@ -2995,6 +2997,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	if (pt_prev) {
 		ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
 	} else {
+		atomic_long_inc(&skb->dev->rx_dropped);
 		kfree_skb(skb);
 		/* Jamal, now you will not able to escape explaining
 		 * me how you were going to use this. :-)
@@ -5429,14 +5432,14 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 
 	if (ops->ndo_get_stats64) {
 		memset(storage, 0, sizeof(*storage));
-		return ops->ndo_get_stats64(dev, storage);
-	}
-	if (ops->ndo_get_stats) {
+		ops->ndo_get_stats64(dev, storage);
+	} else if (ops->ndo_get_stats) {
 		netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev));
-		return storage;
+	} else {
+		netdev_stats_to_stats64(storage, &dev->stats);
+		dev_txq_stats_fold(dev, storage);
 	}
-	netdev_stats_to_stats64(storage, &dev->stats);
-	dev_txq_stats_fold(dev, storage);
+	storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
 	return storage;
 }
 EXPORT_SYMBOL(dev_get_stats);

net/ipv4/ip_gre.c

@@ -679,8 +679,7 @@ static int ipgre_rcv(struct sk_buff *skb)
 		skb_reset_network_header(skb);
 		ipgre_ecn_decapsulate(iph, skb);
 
-		if (netif_rx(skb) == NET_RX_DROP)
-			tunnel->dev->stats.rx_dropped++;
+		netif_rx(skb);
 
 		rcu_read_unlock();
 		return 0;

net/ipv4/ipip.c

@@ -414,8 +414,7 @@ static int ipip_rcv(struct sk_buff *skb)
 
 		ipip_ecn_decapsulate(iph, skb);
 
-		if (netif_rx(skb) == NET_RX_DROP)
-			tunnel->dev->stats.rx_dropped++;
+		netif_rx(skb);
 
 		rcu_read_unlock();
 		return 0;

net/ipv6/ip6_tunnel.c

@@ -768,8 +768,7 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
 
 		dscp_ecn_decapsulate(t, ipv6h, skb);
 
-		if (netif_rx(skb) == NET_RX_DROP)
-			t->dev->stats.rx_dropped++;
+		netif_rx(skb);
 
 		rcu_read_unlock();
 		return 0;

net/ipv6/ip6mr.c

@@ -666,8 +666,7 @@ static int pim6_rcv(struct sk_buff *skb)
 
 	skb_tunnel_rx(skb, reg_dev);
 
-	if (netif_rx(skb) == NET_RX_DROP)
-		reg_dev->stats.rx_dropped++;
+	netif_rx(skb);
 
 	dev_put(reg_dev);
 	return 0;

net/ipv6/sit.c

@@ -600,8 +600,7 @@ static int ipip6_rcv(struct sk_buff *skb)
 
 		ipip6_ecn_decapsulate(iph, skb);
 
-		if (netif_rx(skb) == NET_RX_DROP)
-			tunnel->dev->stats.rx_dropped++;
+		netif_rx(skb);
 
 		rcu_read_unlock();
 		return 0;