Re: [PATCH net-next v11 4/7] r8169: enable new interrupt mapping

From: Javen Xu <redacted>

This patch enables new interrupt mapping for RTL8127 and add error pkts
counter per ring.

Signed-off-by: Javen Xu <redacted>
---
Changes in v2:
  - no changes

Changes in v3:
  - no changes

Changes in v4:
  - no changes

Changes in v5:
  - no changes

Changes in v6:
  - no changes

Changes in v7:
  - no changes

Changes in v8:
  - no changes

Changes in v9:
  - no changes

Changes in v10:
  - no changes

Changes in v11:
  - add error pkts counter per ring
---
  drivers/net/ethernet/realtek/r8169_main.c | 80 +++++++++++++++++++----
  1 file changed, 68 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index b30f0a31d7c7..aa72c42c374d 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c

@@ -29,6 +29,7 @@
  #include <linux/prefetch.h>
  #include <linux/ipv6.h>
  #include <linux/unaligned.h>
+#include <linux/u64_stats_sync.h>
  #include <net/ip6_checksum.h>
  #include <net/netdev_queues.h>
  #include <net/phy/realtek_phy.h>

@@ -754,6 +755,15 @@ struct rtl8169_rx_ring {
  	dma_addr_t rx_desc_phy_addr[NUM_RX_DESC];
  	dma_addr_t rx_phy_addr;
  	struct page *rx_databuff[NUM_RX_DESC];
+
+	struct {
+		u64 rx_errors;
+		u64 rx_dropped;
+		u64 rx_length_errors;
+		u64 rx_crc_errors;
+		u64 multicast;
+		struct u64_stats_sync syncp;
+	} stats;
  };
  
  struct rtl8169_private {

@@ -3939,6 +3949,15 @@ DECLARE_RTL_COND(rtl_mac_ocp_e00e_cond)
  	return r8168_mac_ocp_read(tp, 0xe00e) & BIT(13);
  }
  
+static void rtl8169_hw_enable_vec_mapping(struct rtl8169_private *tp)
+{
+	u8 tmp;
+
+	tmp = RTL_R8(tp, INT_CFG0_8125);
+	tmp |= INT_CFG0_ENABLE_8125;
+	RTL_W8(tp, INT_CFG0_8125, tmp);
+}
+
  static void rtl_hw_start_8125_common(struct rtl8169_private *tp)
  {
  	rtl_pcie_state_l2l3_disable(tp);

@@ -3947,6 +3966,9 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp)
  	RTL_W32(tp, RSS_CTRL_8125, 0);
  	RTL_W16(tp, Q_NUM_CTRL_8125, 0);
  
+	if (tp->irq_nvecs > 1)
+		rtl8169_hw_enable_vec_mapping(tp);
+
  	/* disable UPS */
  	r8168_mac_ocp_modify(tp, 0xd40a, 0x0010, 0x0000);
  

@@ -4347,7 +4369,7 @@ static int rtl8169_init_ring(struct rtl8169_private *tp)
  
  	memset(tp->tx_skb, 0, sizeof(tp->tx_skb));
  
-	for (i = 0; i < tp->num_rx_rings; i++) {
+	for (int i = 0; i < tp->num_rx_rings; i++) {

  		struct rtl8169_rx_ring *ring = &tp->rx_ring[i];
  
  		memset(ring->rx_databuff, 0, sizeof(ring->rx_databuff));

@@ -4926,15 +4948,16 @@ static inline void rtl8169_rx_csum(struct sk_buff *skb,
  		skb_checksum_none_assert(skb);
  }
  
-static bool rtl8169_check_rx_desc_error(struct net_device *dev,
-					struct rtl8169_private *tp,
+static bool rtl8169_check_rx_desc_error(struct rtl8169_rx_ring *ring,
  					u32 status)
  {
  	if (unlikely(status & RxRES)) {
+		u64_stats_update_begin(&ring->stats.syncp);
  		if (status & (RxRWT | RxRUNT))
-			dev->stats.rx_length_errors++;
+			ring->stats.rx_length_errors++;
  		if (status & RxCRC)
-			dev->stats.rx_crc_errors++;
+			ring->stats.rx_crc_errors++;
+		u64_stats_update_end(&ring->stats.syncp);
  		return true;
  	}
  	return false;

@@ -4965,11 +4988,13 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp,
  		 */
  		dma_rmb();
  
-		if (rtl8169_check_rx_desc_error(dev, tp, status)) {
+		if (rtl8169_check_rx_desc_error(ring, status)) {
  			if (net_ratelimit())
  				netdev_warn(dev, "Rx ERROR. status = %08x\n",
  					    status);
-			dev->stats.rx_errors++;
+			u64_stats_update_begin(&ring->stats.syncp);
+			ring->stats.rx_errors++;
+			u64_stats_update_end(&ring->stats.syncp);
  
  			if (!(dev->features & NETIF_F_RXALL))
  				goto release_descriptor;

@@ -4985,14 +5010,18 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp,
  		 * They are seen as a symptom of over-mtu sized frames.
  		 */
  		if (unlikely(rtl8169_fragmented_frame(status))) {
-			dev->stats.rx_dropped++;
-			dev->stats.rx_length_errors++;
+			u64_stats_update_begin(&ring->stats.syncp);
+			ring->stats.rx_dropped++;
+			ring->stats.rx_length_errors++;
+			u64_stats_update_end(&ring->stats.syncp);
  			goto release_descriptor;
  		}
  
  		skb = napi_alloc_skb(napi, pkt_size);
  		if (unlikely(!skb)) {
-			dev->stats.rx_dropped++;
+			u64_stats_update_begin(&ring->stats.syncp);
+			ring->stats.rx_dropped++;
+			u64_stats_update_end(&ring->stats.syncp);
  			goto release_descriptor;
  		}
  

@@ -5011,8 +5040,11 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp,
  
  		rtl8169_rx_vlan_tag(desc, skb);
  
-		if (skb->pkt_type == PACKET_MULTICAST)
-			dev->stats.multicast++;
+		if (skb->pkt_type == PACKET_MULTICAST) {
+			u64_stats_update_begin(&ring->stats.syncp);
+			ring->stats.multicast++;
+			u64_stats_update_end(&ring->stats.syncp);
+		}
  
  		napi_gro_receive(napi, skb);
  

@@ -5428,6 +5460,27 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
  	netdev_stats_to_stats64(stats, &dev->stats);
  	dev_fetch_sw_netstats(stats, dev->tstats);
  
+	for (int i = 0; i < tp->num_rx_rings; i++) {
+		u64 errors, dropped, length_errors, crc_errors, multicast;
+		struct rtl8169_rx_ring *ring = &tp->rx_ring[i];
+		unsigned int start;
+
+		do {
+			start = u64_stats_fetch_begin(&ring->stats.syncp);
+			errors = ring->stats.rx_errors;
+			dropped = ring->stats.rx_dropped;
+			length_errors = ring->stats.rx_length_errors;
+			crc_errors = ring->stats.rx_crc_errors;
+			multicast = ring->stats.multicast;
+		} while (u64_stats_fetch_retry(&ring->stats.syncp, start));
+
+		stats->rx_errors += errors;
+		stats->rx_dropped += dropped;
+		stats->rx_length_errors += length_errors;
+		stats->rx_crc_errors += crc_errors;
+		stats->multicast += multicast;
+	}
+
  	/*
  	 * Fetch additional counter values missing in stats collected by driver
  	 * from tally counters.

@@ -6166,6 +6219,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
  	if (!tp->rx_ring)
  		return -ENOMEM;
  
+	for (int i = 0; i < tp->num_rx_rings; i++)
+		u64_stats_init(&tp->rx_ring[i].stats.syncp);
+
  	tp->rtl8169_napi = kcalloc(tp->irq_nvecs, sizeof(struct napi_struct),
  				   GFP_KERNEL);
  	if (!tp->rtl8169_napi) {