From: Jakub Kicinski <kuba@kernel.org>

bnxt seems to be able to aggregate data up to 32kB without any issue.
The driver is already capable of doing this for systems with higher
order pages. While for systems with 4k pages we historically preferred
to stick to small buffers because they are easier to allocate, the
zero-copy APIs remove the allocation problem. The ZC mem is
pre-allocated and fixed size.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     |  3 ++-
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 21 ++++++++++++++++++-
 2 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index ac841d02d7ad..56aafae568f8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -758,7 +758,8 @@ struct nqe_cn {
 #define BNXT_RX_PAGE_SHIFT PAGE_SHIFT
 #endif
 
-#define BNXT_RX_PAGE_SIZE (1 << BNXT_RX_PAGE_SHIFT)
+#define BNXT_MAX_RX_PAGE_SIZE	(1 << 15)
+#define BNXT_RX_PAGE_SIZE	(1 << BNXT_RX_PAGE_SHIFT)
 
 #define BNXT_MAX_MTU		9500
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 1b37612b1c01..2e130eeeabe5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -835,6 +835,8 @@ static void bnxt_get_ringparam(struct net_device *dev,
 	ering->rx_jumbo_pending = bp->rx_agg_ring_size;
 	ering->tx_pending = bp->tx_ring_size;
 
+	kernel_ering->rx_buf_len_max = BNXT_MAX_RX_PAGE_SIZE;
+	kernel_ering->rx_buf_len = bp->rx_page_size;
 	kernel_ering->hds_thresh_max = BNXT_HDS_THRESHOLD_MAX;
 }
 
@@ -862,6 +864,21 @@ static int bnxt_set_ringparam(struct net_device *dev,
 		return -EINVAL;
 	}
 
+	if (!kernel_ering->rx_buf_len)	/* Zero means restore default */
+		kernel_ering->rx_buf_len = BNXT_RX_PAGE_SIZE;
+
+	if (kernel_ering->rx_buf_len != bp->rx_page_size &&
+	    !(bp->flags & BNXT_FLAG_CHIP_P5_PLUS)) {
+		NL_SET_ERR_MSG_MOD(extack, "changing rx-buf-len not supported");
+		return -EINVAL;
+	}
+	if (!is_power_of_2(kernel_ering->rx_buf_len) ||
+	    kernel_ering->rx_buf_len < BNXT_RX_PAGE_SIZE ||
+	    kernel_ering->rx_buf_len > BNXT_MAX_RX_PAGE_SIZE) {
+		NL_SET_ERR_MSG_MOD(extack, "rx-buf-len out of range, or not power of 2");
+		return -ERANGE;
+	}
+
 	if (netif_running(dev))
 		bnxt_close_nic(bp, false, false);
 
@@ -874,6 +891,7 @@ static int bnxt_set_ringparam(struct net_device *dev,
 
 	bp->rx_ring_size = ering->rx_pending;
 	bp->tx_ring_size = ering->tx_pending;
+	bp->rx_page_size = kernel_ering->rx_buf_len;
 	bnxt_set_ring_params(bp);
 
 	if (netif_running(dev))
@@ -5489,7 +5507,8 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 				     ETHTOOL_COALESCE_STATS_BLOCK_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX |
 				     ETHTOOL_COALESCE_USE_CQE,
-	.supported_ring_params	= ETHTOOL_RING_USE_TCP_DATA_SPLIT |
+	.supported_ring_params	= ETHTOOL_RING_USE_RX_BUF_LEN |
+				  ETHTOOL_RING_USE_TCP_DATA_SPLIT |
 				  ETHTOOL_RING_USE_HDS_THRS,
 	.get_link_ksettings	= bnxt_get_link_ksettings,
 	.set_link_ksettings	= bnxt_set_link_ksettings,
-- 
2.49.0

On Mon, Aug 18, 2025 at 6:56 AM Pavel Begunkov <asml.silence@gmail.com> wrote:
>
> From: Jakub Kicinski <kuba@kernel.org>
>
> bnxt seems to be able to aggregate data up to 32kB without any issue.
> The driver is already capable of doing this for systems with higher
> order pages. While for systems with 4k pages we historically preferred
> to stick to small buffers because they are easier to allocate, the
> zero-copy APIs remove the allocation problem. The ZC mem is
> pre-allocated and fixed size.
>
> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
> Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
> ---
>  drivers/net/ethernet/broadcom/bnxt/bnxt.h     |  3 ++-
>  .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 21 ++++++++++++++++++-
>  2 files changed, 22 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
> index ac841d02d7ad..56aafae568f8 100644
> --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
> +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
> @@ -758,7 +758,8 @@ struct nqe_cn {
>  #define BNXT_RX_PAGE_SHIFT PAGE_SHIFT
>  #endif
>
> -#define BNXT_RX_PAGE_SIZE (1 << BNXT_RX_PAGE_SHIFT)
> +#define BNXT_MAX_RX_PAGE_SIZE  (1 << 15)
> +#define BNXT_RX_PAGE_SIZE      (1 << BNXT_RX_PAGE_SHIFT)
>
>  #define BNXT_MAX_MTU           9500
>
> diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
> index 1b37612b1c01..2e130eeeabe5 100644
> --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
> +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
> @@ -835,6 +835,8 @@ static void bnxt_get_ringparam(struct net_device *dev,
>         ering->rx_jumbo_pending = bp->rx_agg_ring_size;
>         ering->tx_pending = bp->tx_ring_size;
>
> +       kernel_ering->rx_buf_len_max = BNXT_MAX_RX_PAGE_SIZE;
> +       kernel_ering->rx_buf_len = bp->rx_page_size;
>         kernel_ering->hds_thresh_max = BNXT_HDS_THRESHOLD_MAX;
>  }
>
> @@ -862,6 +864,21 @@ static int bnxt_set_ringparam(struct net_device *dev,
>                 return -EINVAL;
>         }
>
> +       if (!kernel_ering->rx_buf_len)  /* Zero means restore default */
> +               kernel_ering->rx_buf_len = BNXT_RX_PAGE_SIZE;
> +

I wonder if things should be refactored a bit such that not every
driver needs to do this 0 special handling, and core does it instead.
I notice patch 4 does the same thing for otx2. But this is fine too.

hns3 changes are missing, but assuming Jakub knows what he's doing
with hns3, the changes here look good to me.

Reviewed-by: Mina Almasry <almasrymina@google.com>

-- 
Thanks,
Mina