Merge branch 'sfc-further-ef100-encap-tso-features'

Edward Cree says:

====================
sfc: further EF100 encap TSO features

This series adds support for GRE and GRE_CSUM TSO on EF100 NICs, as
well as improving the handling of UDP tunnel TSO.
====================

Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

drivers/net/ethernet/sfc/bitfield.h

···
 				 field14, value14,			\
 				 field15, value15,			\
 				 field16, value16,			\
-				 field17, value17)			\
+				 field17, value17,			\
+				 field18, value18,			\
+				 field19, value19)			\
 	(EFX_INSERT_FIELD_NATIVE((min), (max), field1, (value1)) |	\
 	 EFX_INSERT_FIELD_NATIVE((min), (max), field2, (value2)) |	\
 	 EFX_INSERT_FIELD_NATIVE((min), (max), field3, (value3)) |	\
···
 	 EFX_INSERT_FIELD_NATIVE((min), (max), field14, (value14)) |	\
 	 EFX_INSERT_FIELD_NATIVE((min), (max), field15, (value15)) |	\
 	 EFX_INSERT_FIELD_NATIVE((min), (max), field16, (value16)) |	\
-	 EFX_INSERT_FIELD_NATIVE((min), (max), field17, (value17)))
+	 EFX_INSERT_FIELD_NATIVE((min), (max), field17, (value17)) |	\
+	 EFX_INSERT_FIELD_NATIVE((min), (max), field18, (value18)) |	\
+	 EFX_INSERT_FIELD_NATIVE((min), (max), field19, (value19)))
 
 #define EFX_INSERT_FIELDS64(...)				\
 	cpu_to_le64(EFX_INSERT_FIELDS_NATIVE(__VA_ARGS__))
···
 #endif
 
 /* Populate an octword field with various numbers of arguments */
-#define EFX_POPULATE_OWORD_17 EFX_POPULATE_OWORD
+#define EFX_POPULATE_OWORD_19 EFX_POPULATE_OWORD
+#define EFX_POPULATE_OWORD_18(oword, ...) \
+	EFX_POPULATE_OWORD_19(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_OWORD_17(oword, ...) \
+	EFX_POPULATE_OWORD_18(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
 #define EFX_POPULATE_OWORD_16(oword, ...) \
 	EFX_POPULATE_OWORD_17(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
 #define EFX_POPULATE_OWORD_15(oword, ...) \
···
 			     EFX_DWORD_3, 0xffffffff)
 
 /* Populate a quadword field with various numbers of arguments */
-#define EFX_POPULATE_QWORD_17 EFX_POPULATE_QWORD
+#define EFX_POPULATE_QWORD_19 EFX_POPULATE_QWORD
+#define EFX_POPULATE_QWORD_18(qword, ...) \
+	EFX_POPULATE_QWORD_19(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_QWORD_17(qword, ...) \
+	EFX_POPULATE_QWORD_18(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
 #define EFX_POPULATE_QWORD_16(qword, ...) \
 	EFX_POPULATE_QWORD_17(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
 #define EFX_POPULATE_QWORD_15(qword, ...) \
···
 			     EFX_DWORD_1, 0xffffffff)
 
 /* Populate a dword field with various numbers of arguments */
-#define EFX_POPULATE_DWORD_17 EFX_POPULATE_DWORD
+#define EFX_POPULATE_DWORD_19 EFX_POPULATE_DWORD
+#define EFX_POPULATE_DWORD_18(dword, ...) \
+	EFX_POPULATE_DWORD_19(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_DWORD_17(dword, ...) \
+	EFX_POPULATE_DWORD_18(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
 #define EFX_POPULATE_DWORD_16(dword, ...) \
 	EFX_POPULATE_DWORD_17(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
 #define EFX_POPULATE_DWORD_15(dword, ...) \

drivers/net/ethernet/sfc/ef100_nic.c

···
 	if (efx_ef100_has_cap(nic_data->datapath_caps2, TX_TSO_V3)) {
 		struct net_device *net_dev = efx->net_dev;
 		netdev_features_t tso = NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_PARTIAL |
-					NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM;
+					NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM |
+					NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM;
 
 		net_dev->features |= tso;
 		net_dev->hw_features |= tso;
 		net_dev->hw_enc_features |= tso;
-		net_dev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM;
+		/* EF100 HW can only offload outer checksums if they are UDP,
+		 * so for GRE_CSUM we have to use GSO_PARTIAL.
+		 */
+		net_dev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
 	}
 	efx->num_mac_stats = MCDI_WORD(outbuf,
 				       GET_CAPABILITIES_V4_OUT_MAC_STATS_NUM_STATS);

drivers/net/ethernet/sfc/ef100_tx.c

···
 	u16 vlan_tci = skb_vlan_tag_get(skb);
 	u32 mss = skb_shinfo(skb)->gso_size;
 	bool encap = skb->encapsulation;
+	bool udp_encap = false;
 	u16 vlan_enable = 0;
 	struct tcphdr *tcp;
+	bool outer_csum;
 	u32 paylen;
 
 	if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID)
···
 		outer_l4_offset = skb_transport_offset(skb);
 		ip_offset = skb_inner_network_offset(skb);
 		tcp_offset = skb_inner_transport_offset(skb);
+		if (skb_shinfo(skb)->gso_type &
+		    (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM))
+			udp_encap = true;
 	} else {
 		ip_offset =  skb_network_offset(skb);
 		tcp_offset = skb_transport_offset(skb);
 		outer_ip_offset = outer_l4_offset = 0;
 	}
+	outer_csum = skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM;
 
 	/* subtract TCP payload length from inner checksum */
 	tcp = (void *)skb->data + tcp_offset;
 	paylen = skb->len - tcp_offset;
 	csum_replace_by_diff(&tcp->check, (__force __wsum)htonl(paylen));
 
-	EFX_POPULATE_OWORD_17(*txd,
+	EFX_POPULATE_OWORD_19(*txd,
 			      ESF_GZ_TX_DESC_TYPE, ESE_GZ_TX_DESC_TYPE_TSO,
 			      ESF_GZ_TX_TSO_MSS, mss,
 			      ESF_GZ_TX_TSO_HDR_NUM_SEGS, 1,
 			      ESF_GZ_TX_TSO_PAYLOAD_NUM_SEGS, payload_segs,
 			      ESF_GZ_TX_TSO_HDR_LEN_W, buffer->len >> 1,
 			      ESF_GZ_TX_TSO_PAYLOAD_LEN, len,
+			      ESF_GZ_TX_TSO_CSO_OUTER_L4, outer_csum,
 			      ESF_GZ_TX_TSO_CSO_INNER_L4, 1,
 			      ESF_GZ_TX_TSO_INNER_L3_OFF_W, ip_offset >> 1,
 			      ESF_GZ_TX_TSO_INNER_L4_OFF_W, tcp_offset >> 1,
···
 			      ESF_GZ_TX_TSO_ED_INNER_IP_LEN, 1,
 			      ESF_GZ_TX_TSO_OUTER_L3_OFF_W, outer_ip_offset >> 1,
 			      ESF_GZ_TX_TSO_OUTER_L4_OFF_W, outer_l4_offset >> 1,
-			      ESF_GZ_TX_TSO_ED_OUTER_UDP_LEN, encap && !gso_partial,
+			      ESF_GZ_TX_TSO_ED_OUTER_UDP_LEN, udp_encap && !gso_partial,
+			      ESF_GZ_TX_TSO_ED_OUTER_IP_LEN, encap && !gso_partial,
 			      ESF_GZ_TX_TSO_ED_OUTER_IP4_ID, encap ? mangleid :
 								     ESE_GZ_TX_DESC_IP4_ID_NO_OP,
 			      ESF_GZ_TX_TSO_VLAN_INSERT_EN, vlan_enable,