Received-SPF: pass (google.com: domain of linux-kernel+bounces-155969-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
Date: Tue, 23 Apr 2024 12:42:13 -1000
From: Joe Damato <jdamato@fastly.com>
To: linux-kernel@vger.kernel.org, netdev@vger.kernel.org, tariqt@nvidia.com,
	saeedm@nvidia.com
Cc: mkarsten@uwaterloo.ca, gal@nvidia.com, nalramli@fastly.com,
	"David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	"open list:MELLANOX MLX4 core VPI driver" <linux-rdma@vger.kernel.org>
Subject: Re: [PATCH net-next 3/3] net/mlx4: support per-queue statistics via
 netlink
Message-ID: <Zig5RZOkzhGITL7V@LQ3V64L9R2>
References: <20240423194931.97013-1-jdamato@fastly.com>
 <20240423194931.97013-4-jdamato@fastly.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20240423194931.97013-4-jdamato@fastly.com>

On Tue, Apr 23, 2024 at 07:49:30PM +0000, Joe Damato wrote:
> Make mlx4 compatible with the newly added netlink queue stats API.
> 
> Signed-off-by: Joe Damato <jdamato@fastly.com>
> Tested-by: Martin Karsten <mkarsten@uwaterloo.ca>
> ---
>  .../net/ethernet/mellanox/mlx4/en_netdev.c    | 91 +++++++++++++++++++
>  1 file changed, 91 insertions(+)
> 
> diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
> index 5d3fde63b273..c7f04d4820c6 100644
> --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
> +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
> @@ -43,6 +43,7 @@
>  #include <net/vxlan.h>
>  #include <net/devlink.h>
>  #include <net/rps.h>
> +#include <net/netdev_queues.h>
>  
>  #include <linux/mlx4/driver.h>
>  #include <linux/mlx4/device.h>
> @@ -3099,6 +3100,95 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev,
>  	last_i += NUM_PHY_STATS;
>  }
>  
> +static void mlx4_get_queue_stats_rx(struct net_device *dev, int i,
> +				    struct netdev_queue_stats_rx *stats)
> +{
> +	struct mlx4_en_priv *priv = netdev_priv(dev);
> +	const struct mlx4_en_rx_ring *ring;
> +
> +	stats->packets = 0xff;
> +	stats->bytes = 0xff;
> +	stats->alloc_fail = 0xff;
> +
> +	spin_lock_bh(&priv->stats_lock);
> +
> +	if (!priv->port_up || mlx4_is_master(priv->mdev->dev))
> +		goto out_unlock;
> +
> +	ring = priv->rx_ring[i];
> +	stats->packets = READ_ONCE(ring->packets);
> +	stats->bytes   = READ_ONCE(ring->bytes);
> +	stats->alloc_fail = READ_ONCE(ring->dropped);
> +
> +out_unlock:
> +	spin_unlock_bh(&priv->stats_lock);
> +}
> +
> +static void mlx4_get_queue_stats_tx(struct net_device *dev, int i,
> +				    struct netdev_queue_stats_tx *stats)
> +{
> +	struct mlx4_en_priv *priv = netdev_priv(dev);
> +	const struct mlx4_en_tx_ring *ring;
> +
> +	stats->packets = 0xff;
> +	stats->bytes = 0xff;
> +
> +	spin_lock_bh(&priv->stats_lock);
> +
> +	if (!priv->port_up || mlx4_is_master(priv->mdev->dev))
> +		goto out_unlock;
> +
> +	ring = priv->tx_ring[TX][i];
> +	stats->packets = READ_ONCE(ring->packets);
> +	stats->bytes   = READ_ONCE(ring->bytes);
> +
> +out_unlock:
> +	spin_unlock_bh(&priv->stats_lock);
> +}
> +
> +static void mlx4_get_base_stats(struct net_device *dev,
> +				struct netdev_queue_stats_rx *rx,
> +				struct netdev_queue_stats_tx *tx)
> +{
> +	struct mlx4_en_priv *priv = netdev_priv(dev);
> +	int i;
> +
> +	rx->packets = 0xff;
> +	rx->bytes = 0xff;
> +	rx->alloc_fail = 0xff;
> +	tx->packets = 0xff;
> +	tx->bytes = 0xff;
> +
> +	spin_lock_bh(&priv->stats_lock);
> +
> +	if (!priv->port_up || mlx4_is_master(priv->mdev->dev))
> +		goto out_unlock;

I realized in this case, I'll need to set the fields initialized to 0xff
above to 0 before doing the increments below.

Sorry about that; just realized that now and will fix that in the v2 (along
with any other feedback I get), probably something:

  if (priv->rx_ring_num) {
          rx->packets = 0;
          rx->bytes = 0;
          rx->alloc_fail = 0;
  }

Here for the RX side and see below for the TX side.

> +	for (i = 0; i < priv->rx_ring_num; i++) {
> +		const struct mlx4_en_rx_ring *ring = priv->rx_ring[i];
> +
> +		rx->packets += READ_ONCE(ring->packets);
> +		rx->bytes += READ_ONCE(ring->bytes);
> +		rx->alloc_fail += READ_ONCE(ring->dropped);
> +	}

Similar to above, probably will fix with something like this here:

  if (priv->tx_ring_num[TX]) {
          tx->packets = 0;
          tx->bytes = 0;
  }

Sorry for the noise, I should have noticed this before sending it out.

> +	for (i = 0; i < priv->tx_ring_num[TX]; i++) {
> +		const struct mlx4_en_tx_ring *ring = priv->tx_ring[TX][i];
> +
> +		tx->packets += READ_ONCE(ring->packets);
> +		tx->bytes   += READ_ONCE(ring->bytes);
> +	}
> +
> +out_unlock:
> +	spin_unlock_bh(&priv->stats_lock);
> +}
> +
> +static const struct netdev_stat_ops mlx4_stat_ops = {
> +	.get_queue_stats_rx     = mlx4_get_queue_stats_rx,
> +	.get_queue_stats_tx     = mlx4_get_queue_stats_tx,
> +	.get_base_stats         = mlx4_get_base_stats,
> +};
> +
>  int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
>  			struct mlx4_en_port_profile *prof)
>  {
> @@ -3262,6 +3352,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
>  	netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]);
>  	netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
>  
> +	dev->stat_ops = &mlx4_stat_ops;
>  	dev->ethtool_ops = &mlx4_en_ethtool_ops;
>  
>  	/*
> -- 
> 2.25.1
>