Implement netdev_stat_ops to provide standardized per-queue
statistics via the Netlink API.

The implementation was verified using the ynl tool:

$ ./cli.py --spec netlink/specs/netdev.yaml --dump \
    qstats-get --json '{"ifindex":5, "scope":"queue"}'

[{'ifindex': 5, 'queue-id': 0, 'queue-type': 'rx',
  'rx-alloc-fail': 0, 'rx-bytes': 1024, 'rx-packets': 10},
 {'ifindex': 5, 'queue-id': 1, 'queue-type': 'rx',
  'rx-alloc-fail': 0, 'rx-bytes': 2048, 'rx-packets': 20},
 {'ifindex': 5, 'queue-id': 0, 'queue-type': 'tx',
  'tx-bytes': 512,  'tx-packets': 5},
 {'ifindex': 5, 'queue-id': 1, 'queue-type': 'tx',
  'tx-bytes': 1536, 'tx-packets': 15}]

Signed-off-by: Bhargava Marreddy <bhargava.marreddy@broadcom.com>
Reviewed-by: Vikas Gupta <vikas.gupta@broadcom.com>
---
 .../net/ethernet/broadcom/bnge/bnge_netdev.c  | 71 +++++++++++++++++++
 1 file changed, 71 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c
index ec0a8c5e28d..9710113b51f 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c
@@ -3089,6 +3089,76 @@ void bnge_get_ring_err_stats(struct bnge_net *bn,
 					    &bn->bnapi[i]->nq_ring);
 }
 
+static void bnge_get_queue_stats_rx(struct net_device *dev, int i,
+				    struct netdev_queue_stats_rx *stats)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+	struct bnge_nq_ring_info *nqr;
+	u64 *sw;
+
+	if (!bn->bnapi)
+		return;
+
+	nqr = &bn->bnapi[i]->nq_ring;
+	sw = nqr->stats.sw_stats;
+
+	stats->packets = 0;
+	stats->packets += BNGE_GET_RING_STATS64(sw, rx_ucast_pkts);
+	stats->packets += BNGE_GET_RING_STATS64(sw, rx_mcast_pkts);
+	stats->packets += BNGE_GET_RING_STATS64(sw, rx_bcast_pkts);
+
+	stats->bytes = 0;
+	stats->bytes += BNGE_GET_RING_STATS64(sw, rx_ucast_bytes);
+	stats->bytes += BNGE_GET_RING_STATS64(sw, rx_mcast_bytes);
+	stats->bytes += BNGE_GET_RING_STATS64(sw, rx_bcast_bytes);
+
+	stats->alloc_fail = nqr->sw_stats->rx.rx_oom_discards;
+}
+
+static void bnge_get_queue_stats_tx(struct net_device *dev, int i,
+				    struct netdev_queue_stats_tx *stats)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+	struct bnge_napi *bnapi;
+	u64 *sw;
+
+	if (!bn->tx_ring)
+		return;
+
+	bnapi = bn->tx_ring[bn->tx_ring_map[i]].bnapi;
+	sw = bnapi->nq_ring.stats.sw_stats;
+
+	stats->packets = 0;
+	stats->packets += BNGE_GET_RING_STATS64(sw, tx_ucast_pkts);
+	stats->packets += BNGE_GET_RING_STATS64(sw, tx_mcast_pkts);
+	stats->packets += BNGE_GET_RING_STATS64(sw, tx_bcast_pkts);
+
+	stats->bytes = 0;
+	stats->bytes += BNGE_GET_RING_STATS64(sw, tx_ucast_bytes);
+	stats->bytes += BNGE_GET_RING_STATS64(sw, tx_mcast_bytes);
+	stats->bytes += BNGE_GET_RING_STATS64(sw, tx_bcast_bytes);
+}
+
+static void bnge_get_base_stats(struct net_device *dev,
+				struct netdev_queue_stats_rx *rx,
+				struct netdev_queue_stats_tx *tx)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+
+	rx->packets = bn->net_stats_prev.rx_packets;
+	rx->bytes = bn->net_stats_prev.rx_bytes;
+	rx->alloc_fail = bn->ring_err_stats_prev.rx_total_oom_discards;
+
+	tx->packets = bn->net_stats_prev.tx_packets;
+	tx->bytes = bn->net_stats_prev.tx_bytes;
+}
+
+static const struct netdev_stat_ops bnge_stat_ops = {
+	.get_queue_stats_rx	= bnge_get_queue_stats_rx,
+	.get_queue_stats_tx	= bnge_get_queue_stats_tx,
+	.get_base_stats		= bnge_get_base_stats,
+};
+
 static const struct net_device_ops bnge_netdev_ops = {
 	.ndo_open		= bnge_open,
 	.ndo_stop		= bnge_close,
@@ -3252,6 +3322,7 @@ int bnge_netdev_alloc(struct bnge_dev *bd, int max_irqs)
 	bd->netdev = netdev;
 
 	netdev->netdev_ops = &bnge_netdev_ops;
+	netdev->stat_ops = &bnge_stat_ops;
 
 	bnge_set_ethtool_ops(netdev);
 
-- 
2.47.3