ENETC rev 4.1 supports TCP and UDP checksum offload for receive, the bit
108 of the Rx BD will be set if the TCP/UDP checksum is correct. Since
this capability is not defined in register, the rx_csum bit is added to
struct enetc_drvdata to indicate whether the device supports Rx checksum
offload.

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
---
v2: no changes
v3: no changes
v4: no changes
v5: no changes
v6: no changes
---
 drivers/net/ethernet/freescale/enetc/enetc.c       | 14 ++++++++++----
 drivers/net/ethernet/freescale/enetc/enetc.h       |  2 ++
 drivers/net/ethernet/freescale/enetc/enetc_hw.h    |  2 ++
 .../net/ethernet/freescale/enetc/enetc_pf_common.c |  3 +++
 4 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 35634c516e26..3137b6ee62d3 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -1011,10 +1011,15 @@ static void enetc_get_offloads(struct enetc_bdr *rx_ring,
 
 	/* TODO: hashing */
 	if (rx_ring->ndev->features & NETIF_F_RXCSUM) {
-		u16 inet_csum = le16_to_cpu(rxbd->r.inet_csum);
-
-		skb->csum = csum_unfold((__force __sum16)~htons(inet_csum));
-		skb->ip_summed = CHECKSUM_COMPLETE;
+		if (priv->active_offloads & ENETC_F_RXCSUM &&
+		    le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_L4_CSUM_OK) {
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+		} else {
+			u16 inet_csum = le16_to_cpu(rxbd->r.inet_csum);
+
+			skb->csum = csum_unfold((__force __sum16)~htons(inet_csum));
+			skb->ip_summed = CHECKSUM_COMPLETE;
+		}
 	}
 
 	if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_VLAN) {
@@ -3281,6 +3286,7 @@ static const struct enetc_drvdata enetc_pf_data = {
 static const struct enetc_drvdata enetc4_pf_data = {
 	.sysclk_freq = ENETC_CLK_333M,
 	.pmac_offset = ENETC4_PMAC_OFFSET,
+	.rx_csum = 1,
 	.eth_ops = &enetc4_pf_ethtool_ops,
 };
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 72fa03dbc2dd..5b65f79e05be 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -234,6 +234,7 @@ enum enetc_errata {
 
 struct enetc_drvdata {
 	u32 pmac_offset; /* Only valid for PSI which supports 802.1Qbu */
+	u8 rx_csum:1;
 	u64 sysclk_freq;
 	const struct ethtool_ops *eth_ops;
 };
@@ -341,6 +342,7 @@ enum enetc_active_offloads {
 	ENETC_F_QBV			= BIT(9),
 	ENETC_F_QCI			= BIT(10),
 	ENETC_F_QBU			= BIT(11),
+	ENETC_F_RXCSUM			= BIT(12),
 };
 
 enum enetc_flags_bit {
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 7c3285584f8a..4b8fd1879005 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -645,6 +645,8 @@ union enetc_rx_bd {
 #define ENETC_RXBD_LSTATUS(flags)	((flags) << 16)
 #define ENETC_RXBD_FLAG_VLAN	BIT(9)
 #define ENETC_RXBD_FLAG_TSTMP	BIT(10)
+/* UDP and TCP checksum offload, for ENETC 4.1 and later */
+#define ENETC_RXBD_FLAG_L4_CSUM_OK	BIT(12)
 #define ENETC_RXBD_FLAG_TPID	GENMASK(1, 0)
 
 #define ENETC_MAC_ADDR_FILT_CNT	8 /* # of supported entries per port */
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
index 0eecfc833164..91e79582a541 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
@@ -119,6 +119,9 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 
 	ndev->priv_flags |= IFF_UNICAST_FLT;
 
+	if (si->drvdata->rx_csum)
+		priv->active_offloads |= ENETC_F_RXCSUM;
+
 	/* TODO: currently, i.MX95 ENETC driver does not support advanced features */
 	if (!is_enetc_rev1(si)) {
 		ndev->hw_features &= ~(NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK);
-- 
2.34.1

On Wed, Dec 04, 2024 at 01:29:28PM +0800, Wei Fang wrote:
> ENETC rev 4.1 supports TCP and UDP checksum offload for receive, the bit
> 108 of the Rx BD will be set if the TCP/UDP checksum is correct. Since
> this capability is not defined in register, the rx_csum bit is added to
> struct enetc_drvdata to indicate whether the device supports Rx checksum
> offload.
> 
> Signed-off-by: Wei Fang <wei.fang@nxp.com>
> Reviewed-by: Frank Li <Frank.Li@nxp.com>
> Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
> ---
> v2: no changes
> v3: no changes
> v4: no changes
> v5: no changes
> v6: no changes
> ---
>  drivers/net/ethernet/freescale/enetc/enetc.c       | 14 ++++++++++----
>  drivers/net/ethernet/freescale/enetc/enetc.h       |  2 ++
>  drivers/net/ethernet/freescale/enetc/enetc_hw.h    |  2 ++
>  .../net/ethernet/freescale/enetc/enetc_pf_common.c |  3 +++
>  4 files changed, 17 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
> index 35634c516e26..3137b6ee62d3 100644
> --- a/drivers/net/ethernet/freescale/enetc/enetc.c
> +++ b/drivers/net/ethernet/freescale/enetc/enetc.c
> @@ -1011,10 +1011,15 @@ static void enetc_get_offloads(struct enetc_bdr *rx_ring,
>  
>  	/* TODO: hashing */
>  	if (rx_ring->ndev->features & NETIF_F_RXCSUM) {
> -		u16 inet_csum = le16_to_cpu(rxbd->r.inet_csum);
> -
> -		skb->csum = csum_unfold((__force __sum16)~htons(inet_csum));
> -		skb->ip_summed = CHECKSUM_COMPLETE;
> +		if (priv->active_offloads & ENETC_F_RXCSUM &&
> +		    le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_L4_CSUM_OK) {
> +			skb->ip_summed = CHECKSUM_UNNECESSARY;
> +		} else {
> +			u16 inet_csum = le16_to_cpu(rxbd->r.inet_csum);
> +
> +			skb->csum = csum_unfold((__force __sum16)~htons(inet_csum));
> +			skb->ip_summed = CHECKSUM_COMPLETE;
> +		}
>  	}

Hi Wei,

I am wondering about the relationship between the above and
hardware support for CHECKSUM_COMPLETE.

Prior to this patch CHECKSUM_COMPLETE was always used, which seems
desirable. But with this patch, CHECKSUM_UNNECESSARY is conditionally used.

If those cases don't work with CHECKSUM_COMPLETE then is this a bug-fix?

Or, alternatively, if those cases do work with CHECKSUM_COMPLETE, then
I'm unsure why this change is necessary or desirable. It's my understanding
that from the Kernel's perspective CHECKSUM_COMPLETE is preferable to
CHECKSUM_UNNECESSARY.

...