@@ -98,7 +98,15 @@ static struct ibmveth_stat ibmveth_stats[] = {
 	{ "fw_enabled_ipv6_csum", IBMVETH_STAT_OFF(fw_ipv6_csum_support) },
 	{ "tx_large_packets", IBMVETH_STAT_OFF(tx_large_packets) },
 	{ "rx_large_packets", IBMVETH_STAT_OFF(rx_large_packets) },
-	{ "fw_enabled_large_send", IBMVETH_STAT_OFF(fw_large_send_support) }
+	{ "fw_enabled_large_send", IBMVETH_STAT_OFF(fw_large_send_support) },
+	{ "hcall_reg_lan_queue", IBMVETH_STAT_OFF(hcall_stats.reg_lan_queue) },
+	{ "hcall_reg_lan", IBMVETH_STAT_OFF(hcall_stats.reg_lan) },
+	{ "hcall_add_bufs_queue", IBMVETH_STAT_OFF(hcall_stats.add_bufs_queue) },
+	{ "hcall_add_bufs", IBMVETH_STAT_OFF(hcall_stats.add_bufs) },
+	{ "hcall_add_buf", IBMVETH_STAT_OFF(hcall_stats.add_buf) },
+	{ "hcall_free_lan_queue", IBMVETH_STAT_OFF(hcall_stats.free_lan_queue) },
+	{ "hcall_free_lan", IBMVETH_STAT_OFF(hcall_stats.free_lan) },
+	{ "hcall_send_lan", IBMVETH_STAT_OFF(hcall_stats.send_lan) },
 };
 
 /* simple methods of getting data from the current rxq entry */

@@ -244,6 +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

@@ -847,6 +882,8 @@ static void ibmveth_update_rx_no_buffer(struct ibmveth_adapter *adapter)
 		__be64 *p = adapter->buffer_list_addr[i] + 4096 - 8;
 		u64 drops = be64_to_cpup(p);
 
+		if (adapter->rx_qstats)
+			adapter->rx_qstats[i].no_buffer_drops = drops;
 		if (i == 0)
 			adapter->rx_no_buffer = drops;
 	}

@@ -1618,6 +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");

@@ -1658,6 +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);

@@ -1925,22 +1967,107 @@ static int ibmveth_set_features(struct net_device *dev,
 	return rc1 ? rc1 : rc2;
 }
 
+/**
+ * ibmveth_aggregate_rx_qstats - Sum per-queue RX 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_rx_qstats(struct ibmveth_adapter *adapter)
+{
+	u64 total_invalid = 0;
+	u64 total_large = 0;
+	int i;
+
+	if (!adapter->rx_qstats)
+		return;
+
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		total_invalid += adapter->rx_qstats[i].invalid_buffers;
+		total_large += adapter->rx_qstats[i].large_packets;
+	}
+
+	adapter->rx_invalid_buffer = total_invalid;
+	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);
+	u8 *p = data;
 	int i;
 
 	if (stringset != ETH_SS_STATS)
 		return;
 
-	for (i = 0; i < ARRAY_SIZE(ibmveth_stats); i++, data += ETH_GSTRING_LEN)
-		memcpy(data, ibmveth_stats[i].name, ETH_GSTRING_LEN);
+	for (i = 0; i < ARRAY_SIZE(ibmveth_stats); i++) {
+		memcpy(p, ibmveth_stats[i].name, ETH_GSTRING_LEN);
+		p += ETH_GSTRING_LEN;
+	}
+
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		ethtool_sprintf(&p, "rx%d_packets", i);
+		ethtool_sprintf(&p, "rx%d_bytes", i);
+		ethtool_sprintf(&p, "rx%d_interrupts", i);
+		ethtool_sprintf(&p, "rx%d_polls", i);
+		ethtool_sprintf(&p, "rx%d_large_packets", i);
+		ethtool_sprintf(&p, "rx%d_invalid_buffers", i);
+		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);
+		ethtool_sprintf(&p, "pool%d_available", i);
+	}
 }
 
 static int ibmveth_get_sset_count(struct net_device *dev, int sset)
 {
+	struct ibmveth_adapter *adapter = netdev_priv(dev);
+
 	switch (sset) {
 	case ETH_SS_STATS:
-		return ARRAY_SIZE(ibmveth_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;
 	}

@@ -1949,21 +2076,62 @@ static int ibmveth_get_sset_count(struct net_device *dev, int sset)
 static void ibmveth_get_ethtool_stats(struct net_device *dev,
 				      struct ethtool_stats *stats, u64 *data)
 {
-	int i;
 	struct ibmveth_adapter *adapter = netdev_priv(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);
+
+	for (j = 0; j < adapter->num_rx_queues; j++) {
+		if (adapter->rx_qstats) {
+			data[i++] = adapter->rx_qstats[j].packets;
+			data[i++] = adapter->rx_qstats[j].bytes;
+			data[i++] = adapter->rx_qstats[j].interrupts;
+			data[i++] = adapter->rx_qstats[j].polls;
+			data[i++] = adapter->rx_qstats[j].large_packets;
+			data[i++] = adapter->rx_qstats[j].invalid_buffers;
+			data[i++] = adapter->rx_qstats[j].no_buffer_drops;
+		} else {
+			i += IBMVETH_NUM_RX_QSTATS;
+		}
+	}
+
+	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;
+		data[i++] = atomic_read(&adapter->rx_buff_pool[0][j].available);
+	}
 }
 
 static void ibmveth_get_channels(struct net_device *netdev,
 				 struct ethtool_channels *channels)
 {
+	struct ibmveth_adapter *adapter = netdev_priv(netdev);
+
 	channels->max_tx = ibmveth_real_max_tx_queues();
 	channels->tx_count = netdev->real_num_tx_queues;
 
-	channels->max_rx = netdev->real_num_rx_queues;
-	channels->rx_count = netdev->real_num_rx_queues;
+	if (adapter->multi_queue)
+		channels->max_rx = IBMVETH_MAX_RX_QUEUES;
+	else
+		channels->max_rx = 1;
+	channels->rx_count = adapter->num_rx_queues;
 }
 
 static int ibmveth_set_channels(struct net_device *netdev,

@@ -2061,12 +2229,15 @@ static int ibmveth_send(struct ibmveth_adapter *adapter,
 		return 1;
 	}
 
+	adapter->hcall_stats.send_lan++;
 	return 0;
 }
 
 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;
 

@@ -2074,7 +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;
 	}
 

@@ -2090,7 +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 &&

@@ -2101,7 +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;
 	}
 

@@ -2113,6 +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;

@@ -2124,7 +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

@@ -2133,7 +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++;
 		}
 	}
 

@@ -2141,7 +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));

@@ -2158,7 +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;

@@ -2167,11 +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:

@@ -2311,6 +2485,9 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
 	if (WARN_ON(queue_index < 0 || queue_index >= adapter->num_rx_queues))
 		return 0;
 
+	if (adapter->rx_qstats)
+		adapter->rx_qstats[queue_index].polls++;
+
 restart_poll:
 	while (frames_processed < budget) {
 		if (!ibmveth_rxq_pending_buffer(adapter, queue_index))

@@ -2319,7 +2496,10 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
 		smp_rmb();
 		if (!ibmveth_rxq_buffer_valid(adapter, queue_index)) {
 			wmb(); /* suggested by larson1 */
-			adapter->rx_invalid_buffer++;
+			if (adapter->rx_qstats)
+				adapter->rx_qstats[queue_index].invalid_buffers++;
+			else
+				adapter->rx_invalid_buffer++;
 			netdev_dbg(netdev, "recycling invalid buffer\n");
 			rc = ibmveth_rxq_harvest_buffer(adapter, queue_index, true);
 			if (unlikely(rc))

@@ -2384,7 +2564,10 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
 			if ((length > netdev->mtu + ETH_HLEN) ||
 			    lrg_pkt || iph_check == 0xffff) {
 				ibmveth_rx_mss_helper(skb, mss, lrg_pkt);
-				adapter->rx_large_packets++;
+				if (adapter->rx_qstats)
+					adapter->rx_qstats[queue_index].large_packets++;
+				else
+					adapter->rx_large_packets++;
 			}
 
 			if (csum_good) {

@@ -2394,8 +2577,11 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
 
 			napi_gro_receive(napi, skb);	/* send it up */
 
-			netdev->stats.rx_packets++;
-			netdev->stats.rx_bytes += length;
+			if (adapter->rx_qstats) {
+				adapter->rx_qstats[queue_index].packets++;
+				adapter->rx_qstats[queue_index].bytes += length;
+			}
+
 			frames_processed++;
 		}
 	}

@@ -2444,6 +2630,9 @@ static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance)
 	if (WARN_ON(qindex < 0 || qindex >= adapter->num_rx_queues))
 		return IRQ_NONE;
 
+	if (adapter->rx_qstats)
+		adapter->rx_qstats[qindex].interrupts++;
+
 	if (napi_schedule_prep(napi)) {
 		lpar_rc = ibmveth_disable_irq(adapter, qindex);
 		WARN_ON(lpar_rc != H_SUCCESS);

@@ -2656,6 +2845,39 @@ static netdev_features_t ibmveth_features_check(struct sk_buff *skb,
 	return vlan_features_check(skb, features);
 }
 
+/**
+ * ibmveth_get_stats64 - Return aggregated per-queue statistics
+ * @dev: network device
+ * @stats: rtnl link statistics storage
+ *
+ * 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)
+{
+	struct ibmveth_adapter *adapter = netdev_priv(dev);
+	int i;
+
+	if (adapter->rx_qstats) {
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			stats->rx_packets += adapter->rx_qstats[i].packets;
+			stats->rx_bytes += adapter->rx_qstats[i].bytes;
+		}
+	}
+
+	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;
+}
+
 static const struct net_device_ops ibmveth_netdev_ops = {
 	.ndo_open		= ibmveth_open,
 	.ndo_stop		= ibmveth_close,

@@ -2668,6 +2890,7 @@ static const struct net_device_ops ibmveth_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address    = ibmveth_set_mac_addr,
 	.ndo_features_check	= ibmveth_features_check,
+	.ndo_get_stats64	= ibmveth_get_stats64,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= ibmveth_poll_controller,
 #endif

@@ -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;