[PATCH net-next 4/6] eth: mpnic: UDP segmentation offload

[Daniel Zahka <daniel.zahka@gmail.com>]

Support segmentation of non-encapsulated udp4/udp6 packets. Like for
tcp, the segmentation engine expects the udp csum to be seeded with 0
length.

The HW inverts UDP checksums computed as 0 during segmentation.

Signed-off-by: Daniel Zahka <daniel.zahka@gmail.com>
---
 drivers/net/ethernet/meta/mpnic/mpnic_csr.h    |  2 ++
 drivers/net/ethernet/meta/mpnic/mpnic_init.c   |  1 +
 drivers/net/ethernet/meta/mpnic/mpnic_netdev.c |  3 ++-
 drivers/net/ethernet/meta/mpnic/mpnic_txrx.c   | 33 +++++++++++++++++++-------
 4 files changed, 29 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_csr.h b/drivers/net/ethernet/meta/mpnic/mpnic_csr.h
index 672ce0a98c22..2cd627d62bf5 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_csr.h
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_csr.h
@@ -20,6 +20,7 @@
 #define MPNIC_TWD_L4_TYPE		DESC_GENMASK(33, 32)
 enum {
 	MPNIC_TWD_L4_TYPE_TCP	= 1,
+	MPNIC_TWD_L4_TYPE_UDP	= 2,
 };
 
 #define MPNIC_TWD_FLAG_REQ_LSO		DESC_BIT(35)
@@ -335,6 +336,7 @@ enum {
 
 #define MPNIC_TOF_MODE_IPV4_ZERO_CSUM		CSR_BIT(1)
 #define MPNIC_TOF_MODE_TCP_ZERO_CSUM		CSR_BIT(2)
+#define MPNIC_TOF_MODE_UDP_ZERO_CSUM		CSR_BIT(3)
 #define MPNIC_TOF_MODE_L4_ZERO_CSUM		CSR_BIT(4)
 #define MPNIC_TOF_TCP_FLAG_CLR		0x7e3030		/* 0x1f8c0c0 */
 #define MPNIC_TOF_TCP_FLAG_CLR_FIRST_SEGMENT	CSR_GENMASK(8, 0)
diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_init.c b/drivers/net/ethernet/meta/mpnic/mpnic_init.c
index b9a41656f8f7..ab832ec5de0e 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_init.c
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_init.c
@@ -304,6 +304,7 @@ static void mpnic_txglb_init(struct mpnic_dev *mpd)
 			      MPNIC_IPV4_ID_MODE_INCREMENT) |
 		   FIELD_PREP(MPNIC_TOF_MODE_IPV4_ZERO_CSUM, 1) |
 		   FIELD_PREP(MPNIC_TOF_MODE_TCP_ZERO_CSUM, 1) |
+		   FIELD_PREP(MPNIC_TOF_MODE_UDP_ZERO_CSUM, 0) |
 		   FIELD_PREP(MPNIC_TOF_MODE_L4_ZERO_CSUM, 0));
 	mpnic_wr64(mpd, MPNIC_TOF_TCP_FLAG_CLR,
 		   FIELD_PREP(MPNIC_TOF_TCP_FLAG_CLR_FIRST_SEGMENT,
diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c b/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c
index 3a4aa5be57a1..83be45031a30 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c
@@ -331,7 +331,8 @@ struct net_device *mpnic_netdev_alloc(struct mpnic_dev *mpd)
 		NETIF_F_RXCSUM |
 		NETIF_F_TSO |
 		NETIF_F_TSO_ECN |
-		NETIF_F_TSO6;
+		NETIF_F_TSO6 |
+		NETIF_F_GSO_UDP_L4;
 
 	netdev->hw_features |= netdev->features;
 	netdev->vlan_features |= netdev->features;
diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c
index e2e6ab6d3c59..9dd61b6d374c 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c
@@ -223,29 +223,44 @@ static void mpnic_tx_fill_hdrs(struct sk_buff *skb, struct mpnic_tx_hdrs *hdrs)
 		return;
 	}
 
-	hdrs->l4_type = MPNIC_TWD_L4_TYPE_TCP;
+	if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))
+		hdrs->l4_type = MPNIC_TWD_L4_TYPE_TCP;
+	else
+		hdrs->l4_type = MPNIC_TWD_L4_TYPE_UDP;
+
 	hdrs->i3len = skb_transport_offset(skb) - skb_network_offset(skb);
 	hdrs->l3_type = ip_hdr(skb)->version == 4 ?
 			MPNIC_TWD_L3_TYPE_IPV4 : MPNIC_TWD_L3_TYPE_IPV6;
 }
 
 static bool
-mpnic_tx_lso(struct mpnic_ring *ring, struct sk_buff *skb, __le64 *meta)
+mpnic_tx_lso(struct mpnic_ring *ring, struct sk_buff *skb, __le64 *meta,
+	     const struct mpnic_tx_hdrs *hdrs)
 {
 	struct skb_shared_info *shinfo;
 	unsigned int l4len, hdrlen;
-	struct tcphdr *tcph;
-	__be16 payload_len;
+	unsigned char *l4hdr;
 
 	if (skb_cow_head(skb, 0))
 		return true;
 
 	shinfo = skb_shinfo(skb);
+	l4hdr = skb_checksum_start(skb);
+
+	if (hdrs->l4_type == MPNIC_TWD_L4_TYPE_TCP) {
+		struct tcphdr *tcph = (struct tcphdr *)l4hdr;
+		__be16 payload_len;
 
-	tcph = (struct tcphdr *)skb_checksum_start(skb);
-	l4len = __tcp_hdrlen(tcph);
-	payload_len = cpu_to_be16(skb->len - skb_checksum_start_offset(skb));
-	csum_replace_by_diff(&tcph->check, (__force __wsum)payload_len);
+		l4len = __tcp_hdrlen(tcph);
+		payload_len = cpu_to_be16(skb->len -
+					  skb_checksum_start_offset(skb));
+		csum_replace_by_diff(&tcph->check, (__force __wsum)payload_len);
+	} else {
+		struct udphdr *udph = (struct udphdr *)l4hdr;
+
+		l4len = sizeof(*udph);
+		csum_replace_by_diff(&udph->check, (__force __wsum)udph->len);
+	}
 
 	*meta |= cpu_to_le64(FIELD_PREP(MPNIC_TWD_L4_HLEN, l4len / 4) |
 			     FIELD_PREP(MPNIC_TWD_MSS, shinfo->gso_size) |
@@ -277,7 +292,7 @@ mpnic_tx_offloads(struct mpnic_ring *ring, struct sk_buff *skb, __le64 *meta)
 					skb->csum_offset / 2));
 
 	if (skb_is_gso(skb)) {
-		if (mpnic_tx_lso(ring, skb, meta))
+		if (mpnic_tx_lso(ring, skb, meta, &hdrs))
 			return true;
 	} else {
 		*meta |= cpu_to_le64(MPNIC_TWD_FLAG_REQ_CSO);

-- 
2.52.0