ravb: Add Rx checksum offload support for GbEth

TOE has hardware support for calculating IP header and TCP/UDP/ICMP
checksum for both IPv4 and IPv6.

Add Rx checksum offload supported by TOE for IPv4 and TCP/UDP protocols.

For Rx, the 4-byte result of checksum calculation is attached to the
Ethernet frames.First 2-bytes is result of IPv4 header checksum and next
2-bytes is TCP/UDP/ICMP checksum.

If a frame does not have checksum error, 0x0000 is attached as checksum
calculation result. For unsupported frames 0xFFFF is attached as checksum
calculation result. In case of an IPv6 packet, IPv4 checksum is always set
to 0xFFFF.

We can test this functionality by the below commands

ethtool -K eth0 rx on --> to turn on Rx checksum offload
ethtool -K eth0 rx off --> to turn off Rx checksum offload
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Link: https://lore.kernel.org/r/20240207092838.160627-2-biju.das.jz@bp.renesas.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/renesas/ravb.h

@@ -205,7 +205,10 @@ enum ravb_reg {
 	TLFRCR	= 0x0758,
 	RFCR	= 0x0760,
 	MAFCR	= 0x0778,
-	CSR0    = 0x0800,	/* RZ/G2L only */
+
+	/* TOE registers (RZ/G2L only) */
+	CSR0    = 0x0800,
+	CSR2    = 0x0808,
 };
 
 
@@ -978,6 +981,20 @@ enum CSR0_BIT {
 	CSR0_RPE	= 0x00000020,
 };
 
+enum CSR2_BIT {
+	CSR2_RIP4	= 0x00000001,
+	CSR2_RTCP4	= 0x00000010,
+	CSR2_RUDP4	= 0x00000020,
+	CSR2_RICMP4	= 0x00000040,
+	CSR2_RTCP6	= 0x00100000,
+	CSR2_RUDP6	= 0x00200000,
+	CSR2_RICMP6	= 0x00400000,
+	CSR2_RHOP	= 0x01000000,
+	CSR2_RROUT	= 0x02000000,
+	CSR2_RAHD	= 0x04000000,
+	CSR2_RDHD	= 0x08000000,
+};
+
 #define DBAT_ENTRY_NUM	22
 #define RX_QUEUE_OFFSET	4
 #define NUM_RX_QUEUE	2

drivers/net/ethernet/renesas/ravb_main.c

@@ -512,6 +512,24 @@ static int ravb_ring_init(struct net_device *ndev, int q)
 	return -ENOMEM;
 }
 
+static void ravb_csum_init_gbeth(struct net_device *ndev)
+{
+	if (!(ndev->features & NETIF_F_RXCSUM))
+		goto done;
+
+	ravb_write(ndev, 0, CSR0);
+	if (ravb_wait(ndev, CSR0, CSR0_RPE, 0)) {
+		netdev_err(ndev, "Timeout enabling hardware checksum\n");
+		ndev->features &= ~NETIF_F_RXCSUM;
+	} else {
+		ravb_write(ndev, CSR2_RIP4 | CSR2_RTCP4 | CSR2_RUDP4 | CSR2_RICMP4,
+			   CSR2);
+	}
+
+done:
+	ravb_write(ndev, CSR0_TPE | CSR0_RPE, CSR0);
+}
+
 static void ravb_emac_init_gbeth(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
@@ -543,7 +561,8 @@ static void ravb_emac_init_gbeth(struct net_device *ndev)
 
 	/* E-MAC status register clear */
 	ravb_write(ndev, ECSR_ICD | ECSR_LCHNG | ECSR_PFRI, ECSR);
-	ravb_write(ndev, CSR0_TPE | CSR0_RPE, CSR0);
+
+	ravb_csum_init_gbeth(ndev);
 
 	/* E-MAC interrupt enable register */
 	ravb_write(ndev, ECSIPR_ICDIP, ECSIPR);
@@ -724,6 +743,30 @@ static void ravb_get_tx_tstamp(struct net_device *ndev)
 	}
 }
 
+static void ravb_rx_csum_gbeth(struct sk_buff *skb)
+{
+	__wsum csum_ip_hdr, csum_proto;
+	u8 *hw_csum;
+
+	/* The hardware checksum status is contained in sizeof(__sum16) * 2 = 4
+	 * bytes appended to packet data. First 2 bytes is ip header checksum
+	 * and last 2 bytes is protocol checksum.
+	 */
+	if (unlikely(skb->len < sizeof(__sum16) * 2))
+		return;
+
+	hw_csum = skb_tail_pointer(skb) - sizeof(__sum16);
+	csum_proto = csum_unfold((__force __sum16)get_unaligned_le16(hw_csum));
+
+	hw_csum -= sizeof(__sum16);
+	csum_ip_hdr = csum_unfold((__force __sum16)get_unaligned_le16(hw_csum));
+	skb_trim(skb, skb->len - 2 * sizeof(__sum16));
+
+	/* TODO: IPV6 Rx checksum */
+	if (skb->protocol == htons(ETH_P_IP) && !csum_ip_hdr && !csum_proto)
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+}
+
 static void ravb_rx_csum(struct sk_buff *skb)
 {
 	u8 *hw_csum;
@@ -809,6 +852,8 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
 				skb = ravb_get_skb_gbeth(ndev, entry, desc);
 				skb_put(skb, pkt_len);
 				skb->protocol = eth_type_trans(skb, ndev);
+				if (ndev->features & NETIF_F_RXCSUM)
+					ravb_rx_csum_gbeth(skb);
 				napi_gro_receive(&priv->napi[q], skb);
 				stats->rx_packets++;
 				stats->rx_bytes += pkt_len;
@@ -836,6 +881,8 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
 				dev_kfree_skb(skb);
 				priv->rx_1st_skb->protocol =
 					eth_type_trans(priv->rx_1st_skb, ndev);
+				if (ndev->features & NETIF_F_RXCSUM)
+					ravb_rx_csum_gbeth(skb);
 				napi_gro_receive(&priv->napi[q],
 						 priv->rx_1st_skb);
 				stats->rx_packets++;
@@ -2389,11 +2436,48 @@ static void ravb_set_rx_csum(struct net_device *ndev, bool enable)
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
+static int ravb_endisable_csum_gbeth(struct net_device *ndev, enum ravb_reg reg,
+				     u32 val, u32 mask)
+{
+	u32 csr0 = CSR0_TPE | CSR0_RPE;
+	int ret;
+
+	ravb_write(ndev, csr0 & ~mask, CSR0);
+	ret = ravb_wait(ndev, CSR0, mask, 0);
+	if (!ret)
+		ravb_write(ndev, val, reg);
+
+	ravb_write(ndev, csr0, CSR0);
+
+	return ret;
+}
+
 static int ravb_set_features_gbeth(struct net_device *ndev,
 				   netdev_features_t features)
 {
-	/* Place holder */
-	return 0;
+	netdev_features_t changed = ndev->features ^ features;
+	struct ravb_private *priv = netdev_priv(ndev);
+	unsigned long flags;
+	int ret = 0;
+	u32 val;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	if (changed & NETIF_F_RXCSUM) {
+		if (features & NETIF_F_RXCSUM)
+			val = CSR2_RIP4 | CSR2_RTCP4 | CSR2_RUDP4 | CSR2_RICMP4;
+		else
+			val = 0;
+
+		ret = ravb_endisable_csum_gbeth(ndev, CSR2, val, CSR0_RPE);
+		if (ret)
+			goto done;
+	}
+
+	ndev->features = features;
+done:
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return ret;
 }
 
 static int ravb_set_features_rcar(struct net_device *ndev,
@@ -2573,6 +2657,8 @@ static const struct ravb_hw_info gbeth_hw_info = {
 	.emac_init = ravb_emac_init_gbeth,
 	.gstrings_stats = ravb_gstrings_stats_gbeth,
 	.gstrings_size = sizeof(ravb_gstrings_stats_gbeth),
+	.net_hw_features = NETIF_F_RXCSUM,
+	.net_features = NETIF_F_RXCSUM,
 	.stats_len = ARRAY_SIZE(ravb_gstrings_stats_gbeth),
 	.max_rx_len = ALIGN(GBETH_RX_BUFF_MAX, RAVB_ALIGN),
 	.tccr_mask = TCCR_TSRQ0,