net/mlx5e: Add per queue netdev-genl stats

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

...snip

 {'ifindex': 7,
  'queue-id': 62,
  'queue-type': 'rx',
  'rx-alloc-fail': 0,
  'rx-bytes': 105965251,
  'rx-packets': 179790},
 {'ifindex': 7,
  'queue-id': 0,
  'queue-type': 'tx',
  'tx-bytes': 9402665,
  'tx-packets': 17551},

...snip

Also tested with the script tools/testing/selftests/drivers/net/stats.py
in several scenarios to ensure stats tallying was correct:

- on boot (default queue counts)
- adjusting queue count up or down (ethtool -L eth0 combined ...)

The tools/testing/selftests/drivers/net/stats.py brings the device up,
so to test with the device down, I did the following:

$ ip link show eth4
7: eth4: <BROADCAST,MULTICAST> mtu 9000 qdisc mq state DOWN [..snip..]
  [..snip..]

$ cat /proc/net/dev | grep eth4
eth4: 235710489  434811 [..snip rx..] 2878744 21227  [..snip tx..]

$ ./cli.py --spec ../../../Documentation/netlink/specs/netdev.yaml \
           --dump qstats-get --json '{"ifindex": 7}'
[{'ifindex': 7,
  'rx-alloc-fail': 0,
  'rx-bytes': 235710489,
  'rx-packets': 434811,
  'tx-bytes': 2878744,
  'tx-packets': 21227}]

Compare the values in /proc/net/dev match the output of cli for the same
device, even while the device is down.

Note that while the device is down, per queue stats output nothing
(because the device is down there are no queues):

$ ./cli.py --spec ../../../Documentation/netlink/specs/netdev.yaml \
           --dump qstats-get --json '{"scope": "queue", "ifindex": 7}'
[]

Signed-off-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 445bd0f8c6a2d67ac3402d3c96569e1d3a6bf7e4..0eba4c5bb2ecb3b8c246db0adc328ecd58665570 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -39,6 +39,7 @@
 #include <linux/debugfs.h>
 #include <linux/if_bridge.h>
 #include <linux/filter.h>
+#include <net/netdev_queues.h>
 #include <net/page_pool/types.h>
 #include <net/pkt_sched.h>
 #include <net/xdp_sock_drv.h>
@@ -5298,6 +5299,136 @@ static bool mlx5e_tunnel_any_tx_proto_supported(struct mlx5_core_dev *mdev)
        return (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev));
 }
 
+static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i,
+                                    struct netdev_queue_stats_rx *stats)
+{
+       struct mlx5e_priv *priv = netdev_priv(dev);
+       struct mlx5e_channel_stats *channel_stats;
+       struct mlx5e_rq_stats *xskrq_stats;
+       struct mlx5e_rq_stats *rq_stats;
+
+       ASSERT_RTNL();
+       if (mlx5e_is_uplink_rep(priv))
+               return;
+
+       channel_stats = priv->channel_stats[i];
+       xskrq_stats = &channel_stats->xskrq;
+       rq_stats = &channel_stats->rq;
+
+       stats->packets = rq_stats->packets + xskrq_stats->packets;
+       stats->bytes = rq_stats->bytes + xskrq_stats->bytes;
+       stats->alloc_fail = rq_stats->buff_alloc_err +
+                           xskrq_stats->buff_alloc_err;
+}
+
+static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i,
+                                    struct netdev_queue_stats_tx *stats)
+{
+       struct mlx5e_priv *priv = netdev_priv(dev);
+       struct mlx5e_sq_stats *sq_stats;
+
+       ASSERT_RTNL();
+       /* no special case needed for ptp htb etc since txq2sq_stats is kept up
+        * to date for active sq_stats, otherwise get_base_stats takes care of
+        * inactive sqs.
+        */
+       sq_stats = priv->txq2sq_stats[i];
+       stats->packets = sq_stats->packets;
+       stats->bytes = sq_stats->bytes;
+}
+
+static void mlx5e_get_base_stats(struct net_device *dev,
+                                struct netdev_queue_stats_rx *rx,
+                                struct netdev_queue_stats_tx *tx)
+{
+       struct mlx5e_priv *priv = netdev_priv(dev);
+       struct mlx5e_ptp *ptp_channel;
+       int i, tc;
+
+       ASSERT_RTNL();
+       if (!mlx5e_is_uplink_rep(priv)) {
+               rx->packets = 0;
+               rx->bytes = 0;
+               rx->alloc_fail = 0;
+
+               for (i = priv->channels.params.num_channels; i < priv->stats_nch; i++) {
+                       struct netdev_queue_stats_rx rx_i = {0};
+
+                       mlx5e_get_queue_stats_rx(dev, i, &rx_i);
+
+                       rx->packets += rx_i.packets;
+                       rx->bytes += rx_i.bytes;
+                       rx->alloc_fail += rx_i.alloc_fail;
+               }
+
+               /* always report PTP RX stats from base as there is no
+                * corresponding channel to report them under in
+                * mlx5e_get_queue_stats_rx.
+                */
+               if (priv->rx_ptp_opened) {
+                       struct mlx5e_rq_stats *rq_stats = &priv->ptp_stats.rq;
+
+                       rx->packets += rq_stats->packets;
+                       rx->bytes += rq_stats->bytes;
+               }
+       }
+
+       tx->packets = 0;
+       tx->bytes = 0;
+
+       for (i = 0; i < priv->stats_nch; i++) {
+               struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i];
+
+               /* handle two cases:
+                *
+                *  1. channels which are active. In this case,
+                *     report only deactivated TCs on these channels.
+                *
+                *  2. channels which were deactivated
+                *     (i > priv->channels.params.num_channels)
+                *     must have all of their TCs [0 .. priv->max_opened_tc)
+                *     examined because deactivated channels will not be in the
+                *     range of [0..real_num_tx_queues) and will not have their
+                *     stats reported by mlx5e_get_queue_stats_tx.
+                */
+               if (i < priv->channels.params.num_channels)
+                       tc = mlx5e_get_dcb_num_tc(&priv->channels.params);
+               else
+                       tc = 0;
+
+               for (; tc < priv->max_opened_tc; tc++) {
+                       struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[tc];
+
+                       tx->packets += sq_stats->packets;
+                       tx->bytes += sq_stats->bytes;
+               }
+       }
+
+       /* if PTP TX was opened at some point and has since either:
+        *    -  been shutdown and set to NULL, or
+        *    -  simply disabled (bit unset)
+        *
+        * report stats directly from the ptp_stats structures as these queues
+        * are now unavailable and there is no txq index to retrieve these
+        * stats via calls to mlx5e_get_queue_stats_tx.
+        */
+       ptp_channel = priv->channels.ptp;
+       if (priv->tx_ptp_opened && (!ptp_channel || !test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state))) {
+               for (tc = 0; tc < priv->max_opened_tc; tc++) {
+                       struct mlx5e_sq_stats *sq_stats = &priv->ptp_stats.sq[tc];
+
+                       tx->packets += sq_stats->packets;
+                       tx->bytes   += sq_stats->bytes;
+               }
+       }
+}
+
+static const struct netdev_stat_ops mlx5e_stat_ops = {
+       .get_queue_stats_rx  = mlx5e_get_queue_stats_rx,
+       .get_queue_stats_tx  = mlx5e_get_queue_stats_tx,
+       .get_base_stats      = mlx5e_get_base_stats,
+};
+
 static void mlx5e_build_nic_netdev(struct net_device *netdev)
 {
        struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -5315,6 +5446,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 
        netdev->watchdog_timeo    = 15 * HZ;
 
+       netdev->stat_ops          = &mlx5e_stat_ops;
        netdev->ethtool_ops       = &mlx5e_ethtool_ops;
 
        netdev->vlan_features    |= NETIF_F_SG;