net/mlx5e: Set ECN for received packets using CQE indication

In multi-host (MH) NIC scheme, a single HW port serves multiple hosts
or sockets on the same host.
The HW uses a mechanism in the PCIe buffer which monitors
the amount of consumed PCIe buffers per host.
On a certain configuration, under congestion,
the HW emulates a switch doing ECN marking on packets using ECN
indication on the completion descriptor (CQE).

The driver needs to set the ECN bits on the packet SKB,
such that the network stack can react on that, this commit does that.

Signed-off-by: Natali Shechtman <natali@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

drivers/net/ethernet/mellanox/mlx5/core/en_rx.c

@@ -37,6 +37,7 @@
 #include <net/busy_poll.h>
 #include <net/ip6_checksum.h>
 #include <net/page_pool.h>
+#include <net/inet_ecn.h>
 #include "en.h"
 #include "en_tc.h"
 #include "eswitch.h"
@@ -690,12 +691,29 @@ static inline void mlx5e_skb_set_hash(struct mlx5_cqe64 *cqe,
 	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);
+	return (*proto == htons(ETH_P_IP) || *proto == htons(ETH_P_IPV6));
+}
+
+static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
+{
+	int network_depth = 0;
+	__be16 proto;
+	void *ip;
+	int rc;
 
-	ethertype = __vlan_get_protocol(skb, ethertype, network_depth);
-	return (ethertype == htons(ETH_P_IP) || ethertype == htons(ETH_P_IPV6));
+	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 __be32 mlx5e_get_fcs(struct sk_buff *skb)
@@ -745,6 +763,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 {
 	struct mlx5e_rq_stats *stats = rq->stats;
 	int network_depth = 0;
+	__be16 proto;
 
 	if (unlikely(!(netdev->features & NETIF_F_RXCSUM)))
 		goto csum_none;
@@ -755,7 +774,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		return;
 	}
 
-	if (likely(is_last_ethertype_ip(skb, &network_depth))) {
+	if (likely(is_last_ethertype_ip(skb, &network_depth, &proto))) {
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
 		if (network_depth > ETH_HLEN)
@@ -790,6 +809,8 @@ csum_none:
 	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,
@@ -834,6 +855,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 	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);
 }
 

drivers/net/ethernet/mellanox/mlx5/core/en_stats.c

@@ -53,6 +53,7 @@ static const struct counter_desc sw_stats_desc[] = {
 
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_ecn_mark) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_removed_vlan_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) },
@@ -144,6 +145,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_bytes	+= rq_stats->bytes;
 		s->rx_lro_packets += rq_stats->lro_packets;
 		s->rx_lro_bytes	+= rq_stats->lro_bytes;
+		s->rx_ecn_mark	+= rq_stats->ecn_mark;
 		s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets;
 		s->rx_csum_none	+= rq_stats->csum_none;
 		s->rx_csum_complete += rq_stats->csum_complete;
@@ -1144,6 +1146,7 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_redirect) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, ecn_mark) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) },

drivers/net/ethernet/mellanox/mlx5/core/en_stats.h

@@ -66,6 +66,7 @@ struct mlx5e_sw_stats {
 	u64 tx_nop;
 	u64 rx_lro_packets;
 	u64 rx_lro_bytes;
+	u64 rx_ecn_mark;
 	u64 rx_removed_vlan_packets;
 	u64 rx_csum_unnecessary;
 	u64 rx_csum_none;
@@ -184,6 +185,7 @@ struct mlx5e_rq_stats {
 	u64 csum_none;
 	u64 lro_packets;
 	u64 lro_bytes;
+	u64 ecn_mark;
 	u64 removed_vlan_packets;
 	u64 xdp_drop;
 	u64 xdp_redirect;