net/mlx5e: Rx, Check ip headers sanity

[mirror_ubuntu-bionic-kernel.git] / drivers / net / ethernet / mellanox / mlx5 / core / en_rx.c

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 7d49062c74f8579e4b20a2922e991414ec52bec3..6a3cb9e6aa57b7d6535307196f04c0dffb43f934 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -37,6 +37,7 @@
 #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"
@@ -628,12 +629,36 @@ 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);
 
-       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)
@@ -647,6 +672,16 @@ static u32 mlx5e_get_fcs(const struct sk_buff *skb)
        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,
@@ -654,6 +689,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
                                     bool   lro)
 {
        int network_depth = 0;
+       __be16 proto;
 
        if (unlikely(!(netdev->features & NETIF_F_RXCSUM)))
                goto csum_none;
@@ -664,7 +700,25 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
                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)
@@ -683,6 +737,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
                return;
        }
 
+csum_unnecessary:
        if (likely((cqe->hds_ip_ext & CQE_L3_OK) &&
                   (cqe->hds_ip_ext & CQE_L4_OK))) {
                skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -700,6 +755,8 @@ csum_none:
        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,
@@ -739,6 +796,10 @@ 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);
 }