r8169: use struct pcpu_sw_netstats for rx/tx packet/byte counters

Switch to the net core rx/tx byte/packet counter infrastructure.
This simplifies the code, only small drawback is some memory overhead
because we use just one queue, but allocate the counters per cpu.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/realtek/r8169_main.c

@@ -4417,6 +4417,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp,
 	if (tp->dirty_tx != dirty_tx) {
 		netdev_completed_queue(dev, pkts_compl, bytes_compl);
 
+		dev_sw_netstats_tx_add(dev, pkts_compl, bytes_compl);
 		rtl_inc_priv_stats(&tp->tx_stats, pkts_compl, bytes_compl);
 
 		tp->dirty_tx = dirty_tx;
@@ -4539,6 +4540,7 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget
 
 		napi_gro_receive(&tp->napi, skb);
 
+		dev_sw_netstats_rx_add(dev, pkt_size);
 		rtl_inc_priv_stats(&tp->rx_stats, 1, pkt_size);
 release_descriptor:
 		rtl8169_mark_to_asic(desc);
@@ -4790,9 +4792,7 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	pm_runtime_get_noresume(&pdev->dev);
 
 	netdev_stats_to_stats64(stats, &dev->stats);
-
-	rtl_get_priv_stats(&tp->rx_stats, &stats->rx_packets, &stats->rx_bytes);
-	rtl_get_priv_stats(&tp->tx_stats, &stats->tx_packets, &stats->tx_bytes);
+	dev_fetch_sw_netstats(stats, dev->tstats);
 
 	/*
 	 * Fetch additional counter values missing in stats collected by driver
@@ -5263,6 +5263,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	tp->eee_adv = -1;
 	tp->ocp_base = OCP_STD_PHY_BASE;
 
+	dev->tstats = devm_netdev_alloc_pcpu_stats(&pdev->dev,
+						   struct pcpu_sw_netstats);
+	if (!dev->tstats)
+		return -ENOMEM;
+
 	/* Get the *optional* external "ether_clk" used on some boards */
 	rc = rtl_get_ether_clk(tp);
 	if (rc)