vmxnet3: Make ethtool handlers multiqueue aware

Show per-queue stats in ethtool -S output for vmxnet3 interface. Register dump
of ethtool should dump registers for all tx and rx queues.

Signed-off-by: Shreyas N Bhatewara <sbhatewara@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/vmxnet3/vmxnet3_ethtool.c

@@ -68,6 +68,7 @@ vmxnet3_set_rx_csum(struct net_device *netdev, u32 val)
 static const struct vmxnet3_stat_desc
 vmxnet3_tq_dev_stats[] = {
 	/* description,         offset */
+	{ "Tx Queue#",        0 },
 	{ "  TSO pkts tx",	offsetof(struct UPT1_TxStats, TSOPktsTxOK) },
 	{ "  TSO bytes tx",	offsetof(struct UPT1_TxStats, TSOBytesTxOK) },
 	{ "  ucast pkts tx",	offsetof(struct UPT1_TxStats, ucastPktsTxOK) },
@@ -107,6 +108,7 @@ vmxnet3_tq_driver_stats[] = {
 /* per rq stats maintained by the device */
 static const struct vmxnet3_stat_desc
 vmxnet3_rq_dev_stats[] = {
+	{ "Rx Queue#",        0 },
 	{ "  LRO pkts rx",	offsetof(struct UPT1_RxStats, LROPktsRxOK) },
 	{ "  LRO byte rx",	offsetof(struct UPT1_RxStats, LROBytesRxOK) },
 	{ "  ucast pkts rx",	offsetof(struct UPT1_RxStats, ucastPktsRxOK) },
@@ -115,7 +117,7 @@ vmxnet3_rq_dev_stats[] = {
 	{ "  mcast bytes rx",	offsetof(struct UPT1_RxStats, mcastBytesRxOK) },
 	{ "  bcast pkts rx",	offsetof(struct UPT1_RxStats, bcastPktsRxOK) },
 	{ "  bcast bytes rx",	offsetof(struct UPT1_RxStats, bcastBytesRxOK) },
-	{ "pkts rx out of buf", offsetof(struct UPT1_RxStats, pktsRxOutOfBuf) },
+	{ "  pkts rx OOB",	offsetof(struct UPT1_RxStats, pktsRxOutOfBuf) },
 	{ "  pkts rx err",	offsetof(struct UPT1_RxStats, pktsRxError) },
 };
 
@@ -193,12 +195,15 @@ vmxnet3_get_stats(struct net_device *netdev)
 static int
 vmxnet3_get_sset_count(struct net_device *netdev, int sset)
 {
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	switch (sset) {
 	case ETH_SS_STATS:
-		return ARRAY_SIZE(vmxnet3_tq_dev_stats) +
+		return (ARRAY_SIZE(vmxnet3_tq_dev_stats) +
-			ARRAY_SIZE(vmxnet3_tq_driver_stats) +
+			ARRAY_SIZE(vmxnet3_tq_driver_stats)) *
-			ARRAY_SIZE(vmxnet3_rq_dev_stats) +
+		       adapter->num_tx_queues +
-			ARRAY_SIZE(vmxnet3_rq_driver_stats) +
+		       (ARRAY_SIZE(vmxnet3_rq_dev_stats) +
+			ARRAY_SIZE(vmxnet3_rq_driver_stats)) *
+		       adapter->num_rx_queues +
 			ARRAY_SIZE(vmxnet3_global_stats);
 	default:
 		return -EOPNOTSUPP;
@@ -206,10 +211,16 @@ vmxnet3_get_sset_count(struct net_device *netdev, int sset)
 }
 
 
+/* Should be multiple of 4 */
+#define NUM_TX_REGS	8
+#define NUM_RX_REGS	12
+
 static int
 vmxnet3_get_regs_len(struct net_device *netdev)
 {
-	return 20 * sizeof(u32);
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+	return (adapter->num_tx_queues * NUM_TX_REGS * sizeof(u32) +
+		adapter->num_rx_queues * NUM_RX_REGS * sizeof(u32));
 }
 
 
@@ -240,29 +251,37 @@ vmxnet3_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 static void
 vmxnet3_get_strings(struct net_device *netdev, u32 stringset, u8 *buf)
 {
+	 struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	if (stringset == ETH_SS_STATS) {
-		int i;
+		int i, j;
-
+		for (j = 0; j < adapter->num_tx_queues; j++) {
 			for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_dev_stats); i++) {
 				memcpy(buf, vmxnet3_tq_dev_stats[i].desc,
 				       ETH_GSTRING_LEN);
 				buf += ETH_GSTRING_LEN;
 			}
-		for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_driver_stats); i++) {
+			for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_driver_stats);
+			     i++) {
 				memcpy(buf, vmxnet3_tq_driver_stats[i].desc,
 				       ETH_GSTRING_LEN);
 				buf += ETH_GSTRING_LEN;
 			}
+		}
+
+		for (j = 0; j < adapter->num_rx_queues; j++) {
 			for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_dev_stats); i++) {
 				memcpy(buf, vmxnet3_rq_dev_stats[i].desc,
 				       ETH_GSTRING_LEN);
 				buf += ETH_GSTRING_LEN;
 			}
-		for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_driver_stats); i++) {
+			for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_driver_stats);
+			     i++) {
 				memcpy(buf, vmxnet3_rq_driver_stats[i].desc,
 				       ETH_GSTRING_LEN);
 				buf += ETH_GSTRING_LEN;
 			}
+		}
+
 		for (i = 0; i < ARRAY_SIZE(vmxnet3_global_stats); i++) {
 			memcpy(buf, vmxnet3_global_stats[i].desc,
 				ETH_GSTRING_LEN);
@@ -310,23 +329,31 @@ vmxnet3_get_ethtool_stats(struct net_device *netdev,
 	VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_STATS);
 
 	/* this does assume each counter is 64-bit wide */
-/* TODO change this for multiple queues */
+	for (j = 0; j < adapter->num_tx_queues; j++) {
-
 		base = (u8 *)&adapter->tqd_start[j].stats;
-	for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_dev_stats); i++)
+		*buf++ = (u64)j;
-		*buf++ = *(u64 *)(base + vmxnet3_tq_dev_stats[i].offset);
+		for (i = 1; i < ARRAY_SIZE(vmxnet3_tq_dev_stats); i++)
+			*buf++ = *(u64 *)(base +
+					  vmxnet3_tq_dev_stats[i].offset);
 
 		base = (u8 *)&adapter->tx_queue[j].stats;
 		for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_driver_stats); i++)
-		*buf++ = *(u64 *)(base + vmxnet3_tq_driver_stats[i].offset);
+			*buf++ = *(u64 *)(base +
+					  vmxnet3_tq_driver_stats[i].offset);
+	}
 
+	for (j = 0; j < adapter->num_tx_queues; j++) {
 		base = (u8 *)&adapter->rqd_start[j].stats;
-	for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_dev_stats); i++)
+		*buf++ = (u64) j;
-		*buf++ = *(u64 *)(base + vmxnet3_rq_dev_stats[i].offset);
+		for (i = 1; i < ARRAY_SIZE(vmxnet3_rq_dev_stats); i++)
+			*buf++ = *(u64 *)(base +
+					  vmxnet3_rq_dev_stats[i].offset);
 
 		base = (u8 *)&adapter->rx_queue[j].stats;
 		for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_driver_stats); i++)
-		*buf++ = *(u64 *)(base + vmxnet3_rq_driver_stats[i].offset);
+			*buf++ = *(u64 *)(base +
+					  vmxnet3_rq_driver_stats[i].offset);
+	}
 
 	base = (u8 *)adapter;
 	for (i = 0; i < ARRAY_SIZE(vmxnet3_global_stats); i++)
@@ -339,7 +366,7 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	u32 *buf = p;
-	int i = 0;
+	int i = 0, j = 0;
 
 	memset(p, 0, vmxnet3_get_regs_len(netdev));
 
@@ -348,31 +375,35 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
 	/* Update vmxnet3_get_regs_len if we want to dump more registers */
 
 	/* make each ring use multiple of 16 bytes */
-/* TODO change this for multiple queues */
+	for (i = 0; i < adapter->num_tx_queues; i++) {
-	buf[0] = adapter->tx_queue[i].tx_ring.next2fill;
+		buf[j++] = adapter->tx_queue[i].tx_ring.next2fill;
-	buf[1] = adapter->tx_queue[i].tx_ring.next2comp;
+		buf[j++] = adapter->tx_queue[i].tx_ring.next2comp;
-	buf[2] = adapter->tx_queue[i].tx_ring.gen;
+		buf[j++] = adapter->tx_queue[i].tx_ring.gen;
-	buf[3] = 0;
+		buf[j++] = 0;
 
-	buf[4] = adapter->tx_queue[i].comp_ring.next2proc;
+		buf[j++] = adapter->tx_queue[i].comp_ring.next2proc;
-	buf[5] = adapter->tx_queue[i].comp_ring.gen;
+		buf[j++] = adapter->tx_queue[i].comp_ring.gen;
-	buf[6] = adapter->tx_queue[i].stopped;
+		buf[j++] = adapter->tx_queue[i].stopped;
-	buf[7] = 0;
+		buf[j++] = 0;
+	}
 
-	buf[8] = adapter->rx_queue[i].rx_ring[0].next2fill;
+	for (i = 0; i < adapter->num_rx_queues; i++) {
-	buf[9] = adapter->rx_queue[i].rx_ring[0].next2comp;
+		buf[j++] = adapter->rx_queue[i].rx_ring[0].next2fill;
-	buf[10] = adapter->rx_queue[i].rx_ring[0].gen;
+		buf[j++] = adapter->rx_queue[i].rx_ring[0].next2comp;
-	buf[11] = 0;
+		buf[j++] = adapter->rx_queue[i].rx_ring[0].gen;
+		buf[j++] = 0;
 
-	buf[12] = adapter->rx_queue[i].rx_ring[1].next2fill;
+		buf[j++] = adapter->rx_queue[i].rx_ring[1].next2fill;
-	buf[13] = adapter->rx_queue[i].rx_ring[1].next2comp;
+		buf[j++] = adapter->rx_queue[i].rx_ring[1].next2comp;
-	buf[14] = adapter->rx_queue[i].rx_ring[1].gen;
+		buf[j++] = adapter->rx_queue[i].rx_ring[1].gen;
-	buf[15] = 0;
+		buf[j++] = 0;
+
+		buf[j++] = adapter->rx_queue[i].comp_ring.next2proc;
+		buf[j++] = adapter->rx_queue[i].comp_ring.gen;
+		buf[j++] = 0;
+		buf[j++] = 0;
+	}
 
-	buf[16] = adapter->rx_queue[i].comp_ring.next2proc;
-	buf[17] = adapter->rx_queue[i].comp_ring.gen;
-	buf[18] = 0;
-	buf[19] = 0;
 }