The device can fully segment 4-in-6 and 6-in-6 packet types. Add mpnic_features_check_encap_gso() to check the skb for some additional constraints, such as ip6 non-atomic frag ext header. Signed-off-by: Daniel Zahka --- v2: - derive inner L3 header length from csum_start rather than inner_transport_header, which can be stale for DODGY skbs - check the outer header is IPv6 in mpnic_ipxip6_gso_ok(), since SKB_GSO_IPXIP6 can be set by a nested tunnel under an IPv4 outer - move hw_enc_features setup to the Tx checksum offload patch --- drivers/net/ethernet/meta/mpnic/mpnic_csr.h | 3 ++ drivers/net/ethernet/meta/mpnic/mpnic_netdev.c | 1 + drivers/net/ethernet/meta/mpnic/mpnic_txrx.c | 53 ++++++++++++++++++++++++-- 3 files changed, 53 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_csr.h b/drivers/net/ethernet/meta/mpnic/mpnic_csr.h index 2cd627d62bf5..63282916eb13 100644 --- a/drivers/net/ethernet/meta/mpnic/mpnic_csr.h +++ b/drivers/net/ethernet/meta/mpnic/mpnic_csr.h @@ -14,6 +14,7 @@ /* Transmit Work Descriptor Format */ #define MPNIC_TWD_L2_HLEN DESC_GENMASK(5, 0) +#define MPNIC_TWD_L3_OHLEN DESC_GENMASK(15, 8) #define MPNIC_TWD_L3_IHLEN DESC_GENMASK(23, 16) #define MPNIC_TWD_CSUM_OFFSET DESC_GENMASK(27, 24) #define MPNIC_TWD_L4_HLEN DESC_GENMASK(31, 28) @@ -30,6 +31,8 @@ enum { enum { MPNIC_TWD_L3_TYPE_IPV4 = 1, MPNIC_TWD_L3_TYPE_IPV6 = 2, + MPNIC_TWD_L3_TYPE_V6V6 = 3, + MPNIC_TWD_L3_TYPE_V6V4 = 4, }; #define MPNIC_TWD_FLAG_DEST_MAC DESC_BIT(43) diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c b/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c index bf3b459ba5be..032a5ee92a08 100644 --- a/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c +++ b/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c @@ -323,6 +323,7 @@ struct net_device *mpnic_netdev_alloc(struct mpnic_dev *mpd) mpn->num_napi = queues; netdev->features |= + NETIF_F_GSO_IPXIP6 | NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM | diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c index 2a0560b7dd19..839feb4716b6 100644 --- a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c +++ b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c @@ -22,6 +22,7 @@ struct mpnic_xmit_cb { struct mpnic_tx_hdrs { unsigned int i3len; + unsigned int o3len; unsigned int l3_type; unsigned int l4_type; }; @@ -218,6 +219,9 @@ mpnic_tx_map(struct mpnic_ring *ring, struct sk_buff *skb, __le64 *meta) static void mpnic_tx_fill_hdrs(struct sk_buff *skb, struct mpnic_tx_hdrs *hdrs) { + unsigned int net_off = skb_network_offset(skb); + unsigned int inner_off; + if (!skb_is_gso(skb)) { hdrs->i3len = skb_checksum_start(skb) - skb_network_header(skb); return; @@ -228,9 +232,17 @@ static void mpnic_tx_fill_hdrs(struct sk_buff *skb, struct mpnic_tx_hdrs *hdrs) 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; + if (!skb->encapsulation) { + hdrs->i3len = skb_transport_offset(skb) - net_off; + hdrs->l3_type = ip_hdr(skb)->version == 4 ? + MPNIC_TWD_L3_TYPE_IPV4 : MPNIC_TWD_L3_TYPE_IPV6; + } else { + inner_off = skb_inner_network_offset(skb); + hdrs->o3len = inner_off - net_off; + hdrs->i3len = skb_checksum_start_offset(skb) - inner_off; + hdrs->l3_type = inner_ip_hdr(skb)->version == 4 ? + MPNIC_TWD_L3_TYPE_V6V4 : MPNIC_TWD_L3_TYPE_V6V6; + } } static bool @@ -304,6 +316,7 @@ mpnic_tx_offloads(struct mpnic_ring *ring, struct sk_buff *skb, __le64 *meta) *meta |= cpu_to_le64(FIELD_PREP(MPNIC_TWD_L2_HLEN, skb_mac_header_len(skb) / 2) | FIELD_PREP(MPNIC_TWD_L3_IHLEN, hdrs.i3len / 2) | + FIELD_PREP(MPNIC_TWD_L3_OHLEN, hdrs.o3len / 2) | FIELD_PREP(MPNIC_TWD_L3_TYPE, hdrs.l3_type) | FIELD_PREP(MPNIC_TWD_L4_TYPE, hdrs.l4_type)); @@ -362,6 +375,35 @@ netdev_tx_t mpnic_xmit_frame(struct sk_buff *skb, struct net_device *dev) return mpnic_xmit_frame_ring(skb, mpn->tx[skb_get_queue_mapping(skb)]); } +static bool mpnic_ipxip6_gso_ok(struct sk_buff *skb) +{ + struct ipv6hdr *ip6h; + __be16 frag_off; + u8 nexthdr; + int start; + + ip6h = ipv6_hdr(skb); + if (ip6h->version != 6) + return false; + + nexthdr = ip6h->nexthdr; + start = skb_network_offset(skb) + sizeof(*ip6h); + start = ipv6_skip_exthdr(skb, start, &nexthdr, &frag_off); + + return !frag_off && start == skb_inner_network_offset(skb) && + (nexthdr == IPPROTO_IPV6 || nexthdr == IPPROTO_IPIP); +} + +static netdev_features_t +mpnic_features_check_encap_gso(struct sk_buff *skb, netdev_features_t features) +{ + if (skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP6 && + mpnic_ipxip6_gso_ok(skb)) + return features; + + return features & ~NETIF_F_GSO_IPXIP6; +} + netdev_features_t mpnic_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) @@ -388,7 +430,10 @@ netdev_features_t mpnic_features_check(struct sk_buff *skb, !FIELD_FIT(MPNIC_TWD_MSS, skb_shinfo(skb)->gso_size))) return features & ~NETIF_F_GSO_MASK; - return features; + if (!skb->encapsulation || !skb_is_gso(skb)) + return features; + + return mpnic_features_check_encap_gso(skb, features); } static void mpnic_clean_twq0(struct mpnic_napi_vector *nv, int napi_budget, -- 2.52.0