[PATCH net-next 0/5] net/mlx5e: Report more netdev stats

[PATCH net-next 0/5] net/mlx5e: Report more netdev stats

[Tariq Toukan]

Hi,

This series by Gal extends the set of counters reported in netdev stats,
by adding:
- hw_gso_packets/bytes
- hw_gro_packets/bytes
- TX/RX csum
- TX queue stop/wake

Regards,
Tariq

Gal Pressman (5):
  net/mlx5e: Report hw_gso_packets and hw_gso_bytes netdev stats
  net/mlx5e: Report hw_gro_packets and hw_gro_bytes netdev stats
  net/mlx5e: Report TX csum netdev stats
  net/mlx5e: Report RX csum netdev stats
  net/mlx5e: Report stop and wake TX queue stats

 .../net/ethernet/mellanox/mlx5/core/en_main.c | 64 +++++++++++++++++++
 1 file changed, 64 insertions(+)


base-commit: 9a9424c756feee9ee6e717405a9d6fa7bacdef08
-- 
2.44.0

[PATCH net-next 1/5] net/mlx5e: Report hw_gso_packets and hw_gso_bytes netdev stats

[Tariq Toukan]

From: Gal Pressman <gal@nvidia.com>

Report hardware GSO statistics via the netdev queue stats API by mapping
the existing TSO counters to hw_gso_packets and hw_gso_bytes fields.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 96dc6a6dc737..0e955568c2f4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5550,6 +5550,10 @@ static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i,
 	sq_stats = priv->txq2sq_stats[i];
 	stats->packets = sq_stats->packets;
 	stats->bytes = sq_stats->bytes;
+
+	stats->hw_gso_packets =
+		sq_stats->tso_packets + sq_stats->tso_inner_packets;
+	stats->hw_gso_bytes = sq_stats->tso_bytes + sq_stats->tso_inner_bytes;
 }
 
 static void mlx5e_get_base_stats(struct net_device *dev,
@@ -5589,6 +5593,8 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 
 	tx->packets = 0;
 	tx->bytes = 0;
+	tx->hw_gso_packets = 0;
+	tx->hw_gso_bytes = 0;
 
 	for (i = 0; i < priv->stats_nch; i++) {
 		struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i];
@@ -5615,6 +5621,10 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 
 			tx->packets += sq_stats->packets;
 			tx->bytes += sq_stats->bytes;
+			tx->hw_gso_packets += sq_stats->tso_packets +
+					      sq_stats->tso_inner_packets;
+			tx->hw_gso_bytes += sq_stats->tso_bytes +
+					    sq_stats->tso_inner_bytes;
 		}
 	}
 
@@ -5633,6 +5643,10 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 
 			tx->packets += sq_stats->packets;
 			tx->bytes   += sq_stats->bytes;
+			tx->hw_gso_packets += sq_stats->tso_packets +
+					      sq_stats->tso_inner_packets;
+			tx->hw_gso_bytes += sq_stats->tso_bytes +
+					    sq_stats->tso_inner_bytes;
 		}
 	}
 }
-- 
2.44.0

[PATCH net-next 2/5] net/mlx5e: Report hw_gro_packets and hw_gro_bytes netdev stats

[Tariq Toukan]

From: Gal Pressman <gal@nvidia.com>

Report RX hardware GRO statistics via the netdev queue stats API by
mapping the existing gro_packets and gro_bytes counters to the
hw_gro_packets and hw_gro_bytes fields.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0e955568c2f4..774a2e32d5f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5532,6 +5532,10 @@ static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i,
 	stats->bytes = rq_stats->bytes + xskrq_stats->bytes;
 	stats->alloc_fail = rq_stats->buff_alloc_err +
 			    xskrq_stats->buff_alloc_err;
+
+	stats->hw_gro_packets =
+		rq_stats->gro_packets + xskrq_stats->gro_packets;
+	stats->hw_gro_bytes = rq_stats->gro_bytes + xskrq_stats->gro_bytes;
 }
 
 static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i,
@@ -5568,6 +5572,8 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 		rx->packets = 0;
 		rx->bytes = 0;
 		rx->alloc_fail = 0;
+		rx->hw_gro_packets = 0;
+		rx->hw_gro_bytes = 0;
 
 		for (i = priv->channels.params.num_channels; i < priv->stats_nch; i++) {
 			struct netdev_queue_stats_rx rx_i = {0};
@@ -5577,6 +5583,8 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 			rx->packets += rx_i.packets;
 			rx->bytes += rx_i.bytes;
 			rx->alloc_fail += rx_i.alloc_fail;
+			rx->hw_gro_packets += rx_i.hw_gro_packets;
+			rx->hw_gro_bytes += rx_i.hw_gro_bytes;
 		}
 
 		/* always report PTP RX stats from base as there is no
@@ -5588,6 +5596,8 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 
 			rx->packets += rq_stats->packets;
 			rx->bytes += rq_stats->bytes;
+			rx->hw_gro_packets += rq_stats->gro_packets;
+			rx->hw_gro_bytes += rq_stats->gro_bytes;
 		}
 	}
 
-- 
2.44.0

[PATCH net-next 3/5] net/mlx5e: Report TX csum netdev stats

[Tariq Toukan]

From: Gal Pressman <gal@nvidia.com>

Report TX checksum statistics via the netdev queue stats API by mapping
the existing csum_none and csum_partial counters to the csum_none and
needs_csum fields.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 774a2e32d5f9..8c4ab3f81bbc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5558,6 +5558,10 @@ static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i,
 	stats->hw_gso_packets =
 		sq_stats->tso_packets + sq_stats->tso_inner_packets;
 	stats->hw_gso_bytes = sq_stats->tso_bytes + sq_stats->tso_inner_bytes;
+
+	stats->csum_none = sq_stats->csum_none;
+	stats->needs_csum =
+		sq_stats->csum_partial + sq_stats->csum_partial_inner;
 }
 
 static void mlx5e_get_base_stats(struct net_device *dev,
@@ -5605,6 +5609,8 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 	tx->bytes = 0;
 	tx->hw_gso_packets = 0;
 	tx->hw_gso_bytes = 0;
+	tx->csum_none = 0;
+	tx->needs_csum = 0;
 
 	for (i = 0; i < priv->stats_nch; i++) {
 		struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i];
@@ -5635,6 +5641,9 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 					      sq_stats->tso_inner_packets;
 			tx->hw_gso_bytes += sq_stats->tso_bytes +
 					    sq_stats->tso_inner_bytes;
+			tx->csum_none += sq_stats->csum_none;
+			tx->needs_csum += sq_stats->csum_partial +
+					  sq_stats->csum_partial_inner;
 		}
 	}
 
@@ -5657,6 +5666,9 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 					      sq_stats->tso_inner_packets;
 			tx->hw_gso_bytes += sq_stats->tso_bytes +
 					    sq_stats->tso_inner_bytes;
+			tx->csum_none += sq_stats->csum_none;
+			tx->needs_csum += sq_stats->csum_partial +
+					  sq_stats->csum_partial_inner;
 		}
 	}
 }
-- 
2.44.0

[PATCH net-next 4/5] net/mlx5e: Report RX csum netdev stats

[Tariq Toukan]

From: Gal Pressman <gal@nvidia.com>

Report RX checksum statistics via the netdev queue stats API by mapping
the existing csum_complete, csum_unnecessary, csum_unnecessary_inner,
and csum_none counters to the csum_complete, csum_unnecessary and
csum_none fields.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 8c4ab3f81bbc..036587123a6a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5536,6 +5536,14 @@ static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i,
 	stats->hw_gro_packets =
 		rq_stats->gro_packets + xskrq_stats->gro_packets;
 	stats->hw_gro_bytes = rq_stats->gro_bytes + xskrq_stats->gro_bytes;
+
+	stats->csum_complete =
+		rq_stats->csum_complete + xskrq_stats->csum_complete;
+	stats->csum_unnecessary = rq_stats->csum_unnecessary +
+				  xskrq_stats->csum_unnecessary +
+				  rq_stats->csum_unnecessary_inner +
+				  xskrq_stats->csum_unnecessary_inner;
+	stats->csum_none = rq_stats->csum_none + xskrq_stats->csum_none;
 }
 
 static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i,
@@ -5578,6 +5586,9 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 		rx->alloc_fail = 0;
 		rx->hw_gro_packets = 0;
 		rx->hw_gro_bytes = 0;
+		rx->csum_complete = 0;
+		rx->csum_unnecessary = 0;
+		rx->csum_none = 0;
 
 		for (i = priv->channels.params.num_channels; i < priv->stats_nch; i++) {
 			struct netdev_queue_stats_rx rx_i = {0};
@@ -5589,6 +5600,9 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 			rx->alloc_fail += rx_i.alloc_fail;
 			rx->hw_gro_packets += rx_i.hw_gro_packets;
 			rx->hw_gro_bytes += rx_i.hw_gro_bytes;
+			rx->csum_complete += rx_i.csum_complete;
+			rx->csum_unnecessary += rx_i.csum_unnecessary;
+			rx->csum_none += rx_i.csum_none;
 		}
 
 		/* always report PTP RX stats from base as there is no
@@ -5602,6 +5616,11 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 			rx->bytes += rq_stats->bytes;
 			rx->hw_gro_packets += rq_stats->gro_packets;
 			rx->hw_gro_bytes += rq_stats->gro_bytes;
+			rx->csum_complete += rq_stats->csum_complete;
+			rx->csum_unnecessary +=
+				rq_stats->csum_unnecessary +
+				rq_stats->csum_unnecessary_inner;
+			rx->csum_none += rq_stats->csum_none;
 		}
 	}
 
-- 
2.44.0

[PATCH net-next 5/5] net/mlx5e: Report stop and wake TX queue stats

[Tariq Toukan]

From: Gal Pressman <gal@nvidia.com>

Report TX queue stop and wake statistics via the netdev queue stats API
by mapping the existing stopped and wake counters to the stop and wake
fields.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 036587123a6a..4ed0449a27bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5570,6 +5570,9 @@ static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i,
 	stats->csum_none = sq_stats->csum_none;
 	stats->needs_csum =
 		sq_stats->csum_partial + sq_stats->csum_partial_inner;
+
+	stats->stop = sq_stats->stopped;
+	stats->wake = sq_stats->wake;
 }
 
 static void mlx5e_get_base_stats(struct net_device *dev,
@@ -5630,6 +5633,8 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 	tx->hw_gso_bytes = 0;
 	tx->csum_none = 0;
 	tx->needs_csum = 0;
+	tx->stop = 0;
+	tx->wake = 0;
 
 	for (i = 0; i < priv->stats_nch; i++) {
 		struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i];
@@ -5663,6 +5668,8 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 			tx->csum_none += sq_stats->csum_none;
 			tx->needs_csum += sq_stats->csum_partial +
 					  sq_stats->csum_partial_inner;
+			tx->stop += sq_stats->stopped;
+			tx->wake += sq_stats->wake;
 		}
 	}
 
@@ -5688,6 +5695,8 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 			tx->csum_none += sq_stats->csum_none;
 			tx->needs_csum += sq_stats->csum_partial +
 					  sq_stats->csum_partial_inner;
+			tx->stop += sq_stats->stopped;
+			tx->wake += sq_stats->wake;
 		}
 	}
 }
-- 
2.44.0

Re: [PATCH net-next 2/5] net/mlx5e: Report hw_gro_packets and hw_gro_bytes netdev stats

[Jakub Kicinski]

On Wed, 4 Feb 2026 21:33:12 +0200 Tariq Toukan wrote:
> +	stats->hw_gro_packets =
> +		rq_stats->gro_packets + xskrq_stats->gro_packets;
> +	stats->hw_gro_bytes = rq_stats->gro_bytes + xskrq_stats->gro_bytes;

Doesn't look right.. 

mlx5e_shampo_flush_skb(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, bool match) 
{                                                                               
        struct sk_buff *skb = rq->hw_gro_data->skb;                             
        struct mlx5e_rq_stats *stats = rq->stats;                               
        u16 gro_count = NAPI_GRO_CB(skb)->count;                                
                                                                                
        if (likely(skb_shinfo(skb)->nr_frags))                                  
                mlx5e_shampo_align_fragment(skb, rq->mpwqe.log_stride_sz);      
        if (gro_count > 1) {                                                    
                stats->gro_skbs++;                                              
                stats->gro_packets += gro_count;       

And:
      -
        name: rx-hw-gro-packets
        doc: |
          Number of packets that were coalesced from smaller packets by the
          device. Counts only packets coalesced with the HW-GRO netdevice
          feature, LRO-coalesced packets are not counted.

      -
        name: rx-hw-gro-wire-packets
        doc: |
          Number of packets that were coalesced to bigger packetss with the
          HW-GRO netdevice feature. LRO-coalesced packets are not counted.
        type: uint

Your gro_packets are "gro-wire-packets" and "gro-packets" are your
gro_skbs.

I really wish the AI was clever enough to catch uAPI mis-reading :(
-- 
pw-bot: cr

Re: [PATCH net-next 2/5] net/mlx5e: Report hw_gro_packets and hw_gro_bytes netdev stats

[Gal Pressman]

On 05/02/2026 7:23, Jakub Kicinski wrote:
> On Wed, 4 Feb 2026 21:33:12 +0200 Tariq Toukan wrote:
>> +	stats->hw_gro_packets =
>> +		rq_stats->gro_packets + xskrq_stats->gro_packets;
>> +	stats->hw_gro_bytes = rq_stats->gro_bytes + xskrq_stats->gro_bytes;
> 
> Doesn't look right.. 
> 
> mlx5e_shampo_flush_skb(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, bool match) 
> {                                                                               
>         struct sk_buff *skb = rq->hw_gro_data->skb;                             
>         struct mlx5e_rq_stats *stats = rq->stats;                               
>         u16 gro_count = NAPI_GRO_CB(skb)->count;                                
>                                                                                 
>         if (likely(skb_shinfo(skb)->nr_frags))                                  
>                 mlx5e_shampo_align_fragment(skb, rq->mpwqe.log_stride_sz);      
>         if (gro_count > 1) {                                                    
>                 stats->gro_skbs++;                                              
>                 stats->gro_packets += gro_count;       
> 
> And:
>       -
>         name: rx-hw-gro-packets
>         doc: |
>           Number of packets that were coalesced from smaller packets by the
>           device. Counts only packets coalesced with the HW-GRO netdevice
>           feature, LRO-coalesced packets are not counted.
> 
>       -
>         name: rx-hw-gro-wire-packets
>         doc: |
>           Number of packets that were coalesced to bigger packetss with the
>           HW-GRO netdevice feature. LRO-coalesced packets are not counted.
>         type: uint
> 
> Your gro_packets are "gro-wire-packets" and "gro-packets" are your
> gro_skbs.

You're absolutely right, thanks Jakub!

> 
> I really wish the AI was clever enough to catch uAPI mis-reading :(