Merge branch 'net-core-unify-dstats-with-tstats-and-lstats-implement-generic-dstats-collection'

Jeremy Kerr says:

====================
net: core: Unify dstats with tstats and lstats, implement generic dstats collection

The struct pcpu_dstats ("dstats") has a few variations from the other
two stats types (struct pcpu_sw_netstats and struct pcpu_lstats), and
doesn't have generic helpers for collecting the per-cpu stats into a
struct rtnl_link_stats64.

This change unifies dstats with the other types, adds a collection
implementation to the core, and updates the single driver (vrf) to use
this generic implementation.

Of course, questions/comments/etc are most welcome!

v3: https://lore.kernel.org/r/20240605-dstats-v2-0-7fae03f813f3@codeconstruct.com.au
v2: v1: https://lore.kernel.org/r/20240605-dstats-v1-0-1024396e1670@codeconstruct.com.au
====================

Link: https://lore.kernel.org/r/20240607-dstats-v3-0-cc781fe116f7@codeconstruct.com.auSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/vrf.c

@@ -126,8 +126,8 @@ static void vrf_rx_stats(struct net_device *dev, int len)
 	struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
 
 	u64_stats_update_begin(&dstats->syncp);
-	dstats->rx_packets++;
-	dstats->rx_bytes += len;
+	u64_stats_inc(&dstats->rx_packets);
+	u64_stats_add(&dstats->rx_bytes, len);
 	u64_stats_update_end(&dstats->syncp);
 }
 
@@ -137,33 +137,6 @@ static void vrf_tx_error(struct net_device *vrf_dev, struct sk_buff *skb)
 	kfree_skb(skb);
 }
 
-static void vrf_get_stats64(struct net_device *dev,
-			    struct rtnl_link_stats64 *stats)
-{
-	int i;
-
-	for_each_possible_cpu(i) {
-		const struct pcpu_dstats *dstats;
-		u64 tbytes, tpkts, tdrops, rbytes, rpkts;
-		unsigned int start;
-
-		dstats = per_cpu_ptr(dev->dstats, i);
-		do {
-			start = u64_stats_fetch_begin(&dstats->syncp);
-			tbytes = dstats->tx_bytes;
-			tpkts = dstats->tx_packets;
-			tdrops = dstats->tx_drops;
-			rbytes = dstats->rx_bytes;
-			rpkts = dstats->rx_packets;
-		} while (u64_stats_fetch_retry(&dstats->syncp, start));
-		stats->tx_bytes += tbytes;
-		stats->tx_packets += tpkts;
-		stats->tx_dropped += tdrops;
-		stats->rx_bytes += rbytes;
-		stats->rx_packets += rpkts;
-	}
-}
-
 static struct vrf_map *netns_vrf_map(struct net *net)
 {
 	struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id);
@@ -408,10 +381,15 @@ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	skb->protocol = eth_type_trans(skb, dev);
 
-	if (likely(__netif_rx(skb) == NET_RX_SUCCESS))
+	if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) {
 		vrf_rx_stats(dev, len);
-	else
-		this_cpu_inc(dev->dstats->rx_drops);
+	} else {
+		struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
+
+		u64_stats_update_begin(&dstats->syncp);
+		u64_stats_inc(&dstats->rx_drops);
+		u64_stats_update_end(&dstats->syncp);
+	}
 
 	return NETDEV_TX_OK;
 }
@@ -599,19 +577,20 @@ static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
 
 static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
+
 	int len = skb->len;
 	netdev_tx_t ret = is_ip_tx_frame(skb, dev);
 
+	u64_stats_update_begin(&dstats->syncp);
 	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
-		struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
 
-		u64_stats_update_begin(&dstats->syncp);
-		dstats->tx_packets++;
-		dstats->tx_bytes += len;
-		u64_stats_update_end(&dstats->syncp);
+		u64_stats_inc(&dstats->tx_packets);
+		u64_stats_add(&dstats->tx_bytes, len);
 	} else {
-		this_cpu_inc(dev->dstats->tx_drops);
+		u64_stats_inc(&dstats->tx_drops);
 	}
+	u64_stats_update_end(&dstats->syncp);
 
 	return ret;
 }
@@ -1195,7 +1174,6 @@ static const struct net_device_ops vrf_netdev_ops = {
 	.ndo_uninit		= vrf_dev_uninit,
 	.ndo_start_xmit		= vrf_xmit,
 	.ndo_set_mac_address	= eth_mac_addr,
-	.ndo_get_stats64	= vrf_get_stats64,
 	.ndo_add_slave		= vrf_add_slave,
 	.ndo_del_slave		= vrf_del_slave,
 };

include/linux/netdevice.h

@@ -2731,12 +2731,12 @@ struct pcpu_sw_netstats {
 } __aligned(4 * sizeof(u64));
 
 struct pcpu_dstats {
-	u64			rx_packets;
-	u64			rx_bytes;
-	u64			rx_drops;
-	u64			tx_packets;
-	u64			tx_bytes;
-	u64			tx_drops;
+	u64_stats_t		rx_packets;
+	u64_stats_t		rx_bytes;
+	u64_stats_t		rx_drops;
+	u64_stats_t		tx_packets;
+	u64_stats_t		tx_bytes;
+	u64_stats_t		tx_drops;
 	struct u64_stats_sync	syncp;
 } __aligned(8 * sizeof(u64));
 

net/core/dev.c

@@ -10703,6 +10703,54 @@ void netdev_run_todo(void)
 		wake_up(&netdev_unregistering_wq);
 }
 
+/* Collate per-cpu network dstats statistics
+ *
+ * Read per-cpu network statistics from dev->dstats and populate the related
+ * fields in @s.
+ */
+static void dev_fetch_dstats(struct rtnl_link_stats64 *s,
+			     const struct pcpu_dstats __percpu *dstats)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		u64 rx_packets, rx_bytes, rx_drops;
+		u64 tx_packets, tx_bytes, tx_drops;
+		const struct pcpu_dstats *stats;
+		unsigned int start;
+
+		stats = per_cpu_ptr(dstats, cpu);
+		do {
+			start = u64_stats_fetch_begin(&stats->syncp);
+			rx_packets = u64_stats_read(&stats->rx_packets);
+			rx_bytes   = u64_stats_read(&stats->rx_bytes);
+			rx_drops   = u64_stats_read(&stats->rx_drops);
+			tx_packets = u64_stats_read(&stats->tx_packets);
+			tx_bytes   = u64_stats_read(&stats->tx_bytes);
+			tx_drops   = u64_stats_read(&stats->tx_drops);
+		} while (u64_stats_fetch_retry(&stats->syncp, start));
+
+		s->rx_packets += rx_packets;
+		s->rx_bytes   += rx_bytes;
+		s->rx_dropped += rx_drops;
+		s->tx_packets += tx_packets;
+		s->tx_bytes   += tx_bytes;
+		s->tx_dropped += tx_drops;
+	}
+}
+
+/* ndo_get_stats64 implementation for dtstats-based accounting.
+ *
+ * Populate @s from dev->stats and dev->dstats. This is used internally by the
+ * core for NETDEV_PCPU_STAT_DSTAT-type stats collection.
+ */
+static void dev_get_dstats64(const struct net_device *dev,
+			     struct rtnl_link_stats64 *s)
+{
+	netdev_stats_to_stats64(s, &dev->stats);
+	dev_fetch_dstats(s, dev->dstats);
+}
+
 /* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has
  * all the same fields in the same order as net_device_stats, with only
  * the type differing, but rtnl_link_stats64 may have additional fields
@@ -10779,6 +10827,8 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 		netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev));
 	} else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_TSTATS) {
 		dev_get_tstats64(dev, storage);
+	} else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_DSTATS) {
+		dev_get_dstats64(dev, storage);
 	} else {
 		netdev_stats_to_stats64(storage, &dev->stats);
 	}