#include <linux/tcp.h>
#include <linux/bpf_trace.h>
#include <net/busy_poll.h>
+#include <net/ip6_checksum.h>
+#include <net/inet_ecn.h>
#include "en.h"
#include "en_tc.h"
#include "eswitch.h"
return true;
}
+static void mlx5e_lro_update_tcp_hdr(struct mlx5_cqe64 *cqe, struct tcphdr *tcp)
+{
+ u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
+ u8 tcp_ack = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) ||
+ (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA);
+
+ tcp->check = 0;
+ tcp->psh = get_cqe_lro_tcppsh(cqe);
+
+ if (tcp_ack) {
+ tcp->ack = 1;
+ tcp->ack_seq = cqe->lro_ack_seq_num;
+ tcp->window = cqe->lro_tcp_win;
+ }
+}
+
static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
u32 cqe_bcnt)
{
struct ethhdr *eth = (struct ethhdr *)(skb->data);
struct tcphdr *tcp;
int network_depth = 0;
+ __wsum check;
__be16 proto;
u16 tot_len;
void *ip_p;
- u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
- u8 tcp_ack = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) ||
- (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA);
-
proto = __vlan_get_protocol(skb, eth->h_proto, &network_depth);
tot_len = cqe_bcnt - network_depth;
ipv4->check = 0;
ipv4->check = ip_fast_csum((unsigned char *)ipv4,
ipv4->ihl);
+
+ mlx5e_lro_update_tcp_hdr(cqe, tcp);
+ check = csum_partial(tcp, tcp->doff * 4,
+ csum_unfold((__force __sum16)cqe->check_sum));
+ /* Almost done, don't forget the pseudo header */
+ tcp->check = csum_tcpudp_magic(ipv4->saddr, ipv4->daddr,
+ tot_len - sizeof(struct iphdr),
+ IPPROTO_TCP, check);
} else {
+ u16 payload_len = tot_len - sizeof(struct ipv6hdr);
struct ipv6hdr *ipv6 = ip_p;
tcp = ip_p + sizeof(struct ipv6hdr);
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
ipv6->hop_limit = cqe->lro_min_ttl;
- ipv6->payload_len = cpu_to_be16(tot_len -
- sizeof(struct ipv6hdr));
- }
-
- tcp->psh = get_cqe_lro_tcppsh(cqe);
-
- if (tcp_ack) {
- tcp->ack = 1;
- tcp->ack_seq = cqe->lro_ack_seq_num;
- tcp->window = cqe->lro_tcp_win;
+ ipv6->payload_len = cpu_to_be16(payload_len);
+
+ mlx5e_lro_update_tcp_hdr(cqe, tcp);
+ check = csum_partial(tcp, tcp->doff * 4,
+ csum_unfold((__force __sum16)cqe->check_sum));
+ /* Almost done, don't forget the pseudo header */
+ tcp->check = csum_ipv6_magic(&ipv6->saddr, &ipv6->daddr, payload_len,
+ IPPROTO_TCP, check);
}
}
skb_set_hash(skb, be32_to_cpu(cqe->rss_hash_result), ht);
}
-static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth)
+static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth,
+ __be16 *proto)
{
- __be16 ethertype = ((struct ethhdr *)skb->data)->h_proto;
+ *proto = ((struct ethhdr *)skb->data)->h_proto;
+ *proto = __vlan_get_protocol(skb, *proto, network_depth);
- ethertype = __vlan_get_protocol(skb, ethertype, network_depth);
- return (ethertype == htons(ETH_P_IP) || ethertype == htons(ETH_P_IPV6));
+ if (*proto == htons(ETH_P_IP))
+ return pskb_may_pull(skb, *network_depth + sizeof(struct iphdr));
+
+ if (*proto == htons(ETH_P_IPV6))
+ return pskb_may_pull(skb, *network_depth + sizeof(struct ipv6hdr));
+
+ return false;
}
+static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
+{
+ int network_depth = 0;
+ __be16 proto;
+ void *ip;
+ int rc;
+
+ if (unlikely(!is_last_ethertype_ip(skb, &network_depth, &proto)))
+ return;
+
+ ip = skb->data + network_depth;
+ rc = ((proto == htons(ETH_P_IP)) ? IP_ECN_set_ce((struct iphdr *)ip) :
+ IP6_ECN_set_ce(skb, (struct ipv6hdr *)ip));
+
+ rq->stats.ecn_mark += !!rc;
+}
+
+static u32 mlx5e_get_fcs(const struct sk_buff *skb)
+{
+ const void *fcs_bytes;
+ u32 _fcs_bytes;
+
+ fcs_bytes = skb_header_pointer(skb, skb->len - ETH_FCS_LEN,
+ ETH_FCS_LEN, &_fcs_bytes);
+
+ return __get_unaligned_cpu32(fcs_bytes);
+}
+
+static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
+{
+ void *ip_p = skb->data + network_depth;
+
+ return (proto == htons(ETH_P_IP)) ? ((struct iphdr *)ip_p)->protocol :
+ ((struct ipv6hdr *)ip_p)->nexthdr;
+}
+
+#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
+
static inline void mlx5e_handle_csum(struct net_device *netdev,
struct mlx5_cqe64 *cqe,
struct mlx5e_rq *rq,
bool lro)
{
int network_depth = 0;
+ __be16 proto;
if (unlikely(!(netdev->features & NETIF_F_RXCSUM)))
goto csum_none;
return;
}
- if (is_last_ethertype_ip(skb, &network_depth)) {
+ /* True when explicitly set via priv flag, or XDP prog is loaded */
+ if (test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state))
+ goto csum_unnecessary;
+
+ /* CQE csum doesn't cover padding octets in short ethernet
+ * frames. And the pad field is appended prior to calculating
+ * and appending the FCS field.
+ *
+ * Detecting these padded frames requires to verify and parse
+ * IP headers, so we simply force all those small frames to be
+ * CHECKSUM_UNNECESSARY even if they are not padded.
+ */
+ if (short_frame(skb->len))
+ goto csum_unnecessary;
+
+ if (likely(is_last_ethertype_ip(skb, &network_depth, &proto))) {
+ if (unlikely(get_ip_proto(skb, network_depth, proto) == IPPROTO_SCTP))
+ goto csum_unnecessary;
+
skb->ip_summed = CHECKSUM_COMPLETE;
skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
if (network_depth > ETH_HLEN)
skb->csum = csum_partial(skb->data + ETH_HLEN,
network_depth - ETH_HLEN,
skb->csum);
+ if (unlikely(netdev->features & NETIF_F_RXFCS))
+ skb->csum = csum_block_add(skb->csum,
+ (__force __wsum)mlx5e_get_fcs(skb),
+ skb->len - ETH_FCS_LEN);
rq->stats.csum_complete++;
return;
}
+csum_unnecessary:
if (likely((cqe->hds_ip_ext & CQE_L3_OK) &&
(cqe->hds_ip_ext & CQE_L4_OK))) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
rq->stats.csum_none++;
}
+#define MLX5E_CE_BIT_MASK 0x80
+
static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
u32 cqe_bcnt,
struct mlx5e_rq *rq,
skb->mark = be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK;
mlx5e_handle_csum(netdev, cqe, rq, skb, !!lro_num_seg);
+ /* checking CE bit in cqe - MSB in ml_path field */
+ if (unlikely(cqe->ml_path & MLX5E_CE_BIT_MASK))
+ mlx5e_enable_ecn(rq, skb);
+
skb->protocol = eth_type_trans(skb, netdev);
}
int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
{
struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
- struct mlx5e_xdpsq *xdpsq;
+ struct mlx5e_xdpsq *xdpsq = &rq->xdpsq;
struct mlx5_cqe64 *cqe;
int work_done = 0;
work_done += mlx5e_decompress_cqes_cont(rq, cq, 0, budget);
cqe = mlx5_cqwq_get_cqe(&cq->wq);
- if (!cqe)
+ if (!cqe) {
+ if (unlikely(work_done))
+ goto out;
return 0;
-
- xdpsq = &rq->xdpsq;
+ }
do {
if (mlx5_get_cqe_format(cqe) == MLX5_COMPRESSED) {
rq->handle_rx_cqe(rq, cqe);
} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
+out:
if (xdpsq->db.doorbell) {
mlx5e_xmit_xdp_doorbell(xdpsq);
xdpsq->db.doorbell = false;
u32 cqe_bcnt,
struct sk_buff *skb)
{
+ struct hwtstamp_config *tstamp;
struct net_device *netdev;
+ struct mlx5e_priv *priv;
char *pseudo_header;
u32 qpn;
u8 *dgid;
return;
}
+ priv = mlx5i_epriv(netdev);
+ tstamp = &priv->tstamp;
+
g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3;
dgid = skb->data + MLX5_IB_GRH_DGID_OFFSET;
if ((!g) || dgid[0] != 0xff)
skb->ip_summed = CHECKSUM_COMPLETE;
skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
- if (unlikely(mlx5e_rx_hw_stamp(rq->tstamp)))
+ if (unlikely(mlx5e_rx_hw_stamp(tstamp)))
skb_hwtstamps(skb)->hwtstamp =
mlx5_timecounter_cyc2time(rq->clock, get_cqe_ts(cqe));