@@ -252,6 +252,33 @@ static void ibmveth_free_rx_qstats(struct ibmveth_adapter *adapter)
 	adapter->rx_qstats = NULL;
 }
 
+/**
+ * ibmveth_alloc_tx_qstats - Allocate per-queue TX statistics
+ * @adapter: ibmveth adapter structure
+ *
+ * Return: 0 on success, -ENOMEM on failure
+ */
+static int ibmveth_alloc_tx_qstats(struct ibmveth_adapter *adapter)
+{
+	adapter->tx_qstats = kcalloc(IBMVETH_MAX_QUEUES,
+				     sizeof(struct ibmveth_tx_queue_stats),
+				     GFP_KERNEL);
+	if (!adapter->tx_qstats)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/**
+ * ibmveth_free_tx_qstats - Free per-queue TX statistics
+ * @adapter: ibmveth adapter structure
+ */
+static void ibmveth_free_tx_qstats(struct ibmveth_adapter *adapter)
+{
+	kfree(adapter->tx_qstats);
+	adapter->tx_qstats = NULL;
+}
+
 /**
  * ibmveth_alloc_rx_queues - Allocate per-queue RX resources
  * @adapter: ibmveth adapter structure

@@ -1628,6 +1655,10 @@ static int ibmveth_open(struct net_device *netdev)
 	if (rc)
 		goto out_cleanup_rx_interrupts;
 
+	rc = ibmveth_alloc_tx_qstats(adapter);
+	if (rc)
+		goto out_free_tx_resources;
+
 	netif_tx_start_all_queues(netdev);
 
 	netdev_dbg(netdev, "open complete\n");

@@ -1668,6 +1699,7 @@ static int ibmveth_close(struct net_device *netdev)
 		}
 	}
 
+	ibmveth_free_tx_qstats(adapter);
 	ibmveth_free_tx_resources(adapter);
 	ibmveth_cleanup_rx_interrupts(adapter);
 	ibmveth_update_rx_no_buffer(adapter);

@@ -1960,6 +1992,32 @@ static void ibmveth_aggregate_rx_qstats(struct ibmveth_adapter *adapter)
 	adapter->rx_large_packets = total_large;
 }
 
+/**
+ * ibmveth_aggregate_tx_qstats - Sum per-queue TX stats into globals
+ * @adapter: ibmveth adapter
+ *
+ * Cold path only (ethtool). Keeps legacy global counters meaningful for
+ * tools that read the adapter-level fields in ibmveth_stats[].
+ */
+static void ibmveth_aggregate_tx_qstats(struct ibmveth_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	u64 total_large = 0;
+	u64 total_send_failed = 0;
+	int i;
+
+	if (!adapter->tx_qstats)
+		return;
+
+	for (i = 0; i < netdev->real_num_tx_queues; i++) {
+		total_large += adapter->tx_qstats[i].large_packets;
+		total_send_failed += adapter->tx_qstats[i].send_failures;
+	}
+
+	adapter->tx_large_packets = total_large;
+	adapter->tx_send_failed = total_send_failed;
+}
+
 static void ibmveth_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 {
 	struct ibmveth_adapter *adapter = netdev_priv(dev);

@@ -1984,6 +2042,15 @@ static void ibmveth_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 		ethtool_sprintf(&p, "rx%d_no_buffer_drops", i);
 	}
 
+	for (i = 0; i < dev->real_num_tx_queues; i++) {
+		ethtool_sprintf(&p, "tx%d_packets", i);
+		ethtool_sprintf(&p, "tx%d_bytes", i);
+		ethtool_sprintf(&p, "tx%d_large_packets", i);
+		ethtool_sprintf(&p, "tx%d_dropped_packets", i);
+		ethtool_sprintf(&p, "tx%d_send_failures", i);
+		ethtool_sprintf(&p, "tx%d_checksum_offload", i);
+	}
+
 	for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
 		ethtool_sprintf(&p, "pool%d_size", i);
 		ethtool_sprintf(&p, "pool%d_active", i);

@@ -1999,6 +2066,7 @@ static int ibmveth_get_sset_count(struct net_device *dev, int sset)
 	case ETH_SS_STATS:
 		return ARRAY_SIZE(ibmveth_stats) +
 		       adapter->num_rx_queues * IBMVETH_NUM_RX_QSTATS +
+		       dev->real_num_tx_queues * IBMVETH_NUM_TX_QSTATS +
 		       IBMVETH_NUM_BUFF_POOLS * 3;
 	default:
 		return -EOPNOTSUPP;

@@ -2012,6 +2080,7 @@ static void ibmveth_get_ethtool_stats(struct net_device *dev,
 	int i, j;
 
 	ibmveth_aggregate_rx_qstats(adapter);
+	ibmveth_aggregate_tx_qstats(adapter);
 
 	for (i = 0; i < ARRAY_SIZE(ibmveth_stats); i++)
 		data[i] = IBMVETH_GET_STAT(adapter, ibmveth_stats[i].offset);

@@ -2030,6 +2099,19 @@ static void ibmveth_get_ethtool_stats(struct net_device *dev,
 		}
 	}
 
+	for (j = 0; j < dev->real_num_tx_queues; j++) {
+		if (adapter->tx_qstats) {
+			data[i++] = adapter->tx_qstats[j].packets;
+			data[i++] = adapter->tx_qstats[j].bytes;
+			data[i++] = adapter->tx_qstats[j].large_packets;
+			data[i++] = adapter->tx_qstats[j].dropped_packets;
+			data[i++] = adapter->tx_qstats[j].send_failures;
+			data[i++] = adapter->tx_qstats[j].checksum_offload;
+		} else {
+			i += IBMVETH_NUM_TX_QSTATS;
+		}
+	}
+
 	for (j = 0; j < IBMVETH_NUM_BUFF_POOLS; j++) {
 		data[i++] = adapter->rx_buff_pool[0][j].size;
 		data[i++] = adapter->rx_buff_pool[0][j].active;

@@ -2152,8 +2234,10 @@ static int ibmveth_send(struct ibmveth_adapter *adapter,
 }
 
 static int ibmveth_is_packet_unsupported(struct sk_buff *skb,
-					 struct net_device *netdev)
+					 struct ibmveth_adapter *adapter,
+					 int queue_num)
 {
+	struct net_device *netdev = adapter->netdev;
 	struct ethhdr *ether_header;
 	int ret = 0;
 

@@ -2161,7 +2245,8 @@ static int ibmveth_is_packet_unsupported(struct sk_buff *skb,
 
 	if (ether_addr_equal(ether_header->h_dest, netdev->dev_addr)) {
 		netdev_dbg(netdev, "veth doesn't support loopback packets, dropping packet.\n");
-		netdev->stats.tx_dropped++;
+		if (adapter->tx_qstats)
+			adapter->tx_qstats[queue_num].dropped_packets++;
 		ret = -EOPNOTSUPP;
 	}
 

@@ -2177,7 +2262,7 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 	int i, queue_num = skb_get_queue_mapping(skb);
 	unsigned long mss = 0;
 
-	if (ibmveth_is_packet_unsupported(skb, netdev))
+	if (ibmveth_is_packet_unsupported(skb, adapter, queue_num))
 		goto out;
 	/* veth can't checksum offload UDP */
 	if (skb->ip_summed == CHECKSUM_PARTIAL &&

@@ -2188,7 +2273,7 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 	    skb_checksum_help(skb)) {
 
 		netdev_err(netdev, "tx: failed to checksum packet\n");
-		netdev->stats.tx_dropped++;
+		adapter->tx_qstats[queue_num].dropped_packets++;
 		goto out;
 	}
 

@@ -2200,6 +2285,8 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 
 		desc_flags |= (IBMVETH_BUF_NO_CSUM | IBMVETH_BUF_CSUM_GOOD);
 
+		adapter->tx_qstats[queue_num].checksum_offload++;
+
 		/* Need to zero out the checksum */
 		buf[0] = 0;
 		buf[1] = 0;

@@ -2211,7 +2298,7 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 	if (skb->ip_summed == CHECKSUM_PARTIAL && skb_is_gso(skb)) {
 		if (adapter->fw_large_send_support) {
 			mss = (unsigned long)skb_shinfo(skb)->gso_size;
-			adapter->tx_large_packets++;
+			adapter->tx_qstats[queue_num].large_packets++;
 		} else if (!skb_is_gso_v6(skb)) {
 			/* Put -1 in the IP checksum to tell phyp it
 			 * is a largesend packet. Put the mss in

@@ -2220,7 +2307,7 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 			ip_hdr(skb)->check = 0xffff;
 			tcp_hdr(skb)->check =
 				cpu_to_be16(skb_shinfo(skb)->gso_size);
-			adapter->tx_large_packets++;
+			adapter->tx_qstats[queue_num].large_packets++;
 		}
 	}
 

@@ -2228,7 +2315,7 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 	if (unlikely(skb->len > adapter->tx_ltb_size)) {
 		netdev_err(adapter->netdev, "tx: packet size (%u) exceeds ltb (%u)\n",
 			   skb->len, adapter->tx_ltb_size);
-		netdev->stats.tx_dropped++;
+		adapter->tx_qstats[queue_num].dropped_packets++;
 		goto out;
 	}
 	memcpy(adapter->tx_ltb_ptr[queue_num], skb->data, skb_headlen(skb));

@@ -2245,7 +2332,7 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 	if (unlikely(total_bytes != skb->len)) {
 		netdev_err(adapter->netdev, "tx: incorrect packet len copied into ltb (%u != %u)\n",
 			   skb->len, total_bytes);
-		netdev->stats.tx_dropped++;
+		adapter->tx_qstats[queue_num].dropped_packets++;
 		goto out;
 	}
 	desc.fields.flags_len = desc_flags | skb->len;

@@ -2254,11 +2341,11 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 	dma_wmb();
 
 	if (ibmveth_send(adapter, desc.desc, mss)) {
-		adapter->tx_send_failed++;
-		netdev->stats.tx_dropped++;
+		adapter->tx_qstats[queue_num].send_failures++;
+		adapter->tx_qstats[queue_num].dropped_packets++;
 	} else {
-		netdev->stats.tx_packets++;
-		netdev->stats.tx_bytes += skb->len;
+		adapter->tx_qstats[queue_num].packets++;
+		adapter->tx_qstats[queue_num].bytes += skb->len;
 	}
 
 out:

@@ -2759,12 +2846,13 @@ static netdev_features_t ibmveth_features_check(struct sk_buff *skb,
 }
 
 /**
- * ibmveth_get_stats64 - Return aggregated per-queue RX statistics
+ * ibmveth_get_stats64 - Return aggregated per-queue statistics
  * @dev: network device
  * @stats: rtnl link statistics storage
  *
- * Sums per-queue rx_qstats into rx_packets/rx_bytes for multi-queue mode.
- * TX counters continue to come from netdev->stats (updated in start_xmit).
+ * Sums per-queue rx_qstats and tx_qstats into the rtnl counters.
+ * Callers use ndo_get_stats64(); avoid updating netdev->stats on the
+ * xmit/poll paths to keep per-queue counters off the hot cache line.
  */
 static void ibmveth_get_stats64(struct net_device *dev,
 				struct rtnl_link_stats64 *stats)

@@ -2779,9 +2867,14 @@ static void ibmveth_get_stats64(struct net_device *dev,
 		}
 	}
 
-	stats->tx_packets = dev->stats.tx_packets;
-	stats->tx_bytes = dev->stats.tx_bytes;
-	stats->tx_dropped = dev->stats.tx_dropped;
+	if (adapter->tx_qstats) {
+		for (i = 0; i < dev->real_num_tx_queues; i++) {
+			stats->tx_packets += adapter->tx_qstats[i].packets;
+			stats->tx_bytes += adapter->tx_qstats[i].bytes;
+			stats->tx_dropped += adapter->tx_qstats[i].dropped_packets;
+		}
+	}
+
 	stats->tx_errors = dev->stats.tx_errors;
 }
 

@@ -316,9 +316,21 @@ struct ibmveth_rx_queue_stats {
 	u64 no_buffer_drops;
 };
 
+struct ibmveth_tx_queue_stats {
+	u64 packets;
+	u64 bytes;
+	u64 large_packets;
+	u64 dropped_packets;
+	u64 send_failures;
+	u64 checksum_offload;
+};
+
 #define IBMVETH_NUM_RX_QSTATS \
 	(sizeof(struct ibmveth_rx_queue_stats) / sizeof(u64))
 
+#define IBMVETH_NUM_TX_QSTATS \
+	(sizeof(struct ibmveth_tx_queue_stats) / sizeof(u64))
+
 struct ibmveth_buff_pool {
     u32 size;
     u32 index;

@@ -386,6 +398,7 @@ struct ibmveth_adapter {
 	/* Multi-queue statistics */
 	struct ibmveth_hcall_stats hcall_stats;
 	struct ibmveth_rx_queue_stats *rx_qstats;
+	struct ibmveth_tx_queue_stats *tx_qstats;
 
 	/* Ethtool settings */
 	u8 duplex;