net/mlx5e: Fix wrong calculation of header index in HW_GRO

The HW doesn't wrap the CQE.shampo.header_index field according to the
headers buffer size, instead it always increases it until reaching overflow
of u16 size.

Thus the mlx5e_handle_rx_cqe_mpwrq_shampo handler should mask the
CQE header_index field to find the actual header index in the headers buffer.

Fixes: f97d5c2a ("net/mlx5e: Add handle SHAMPO cqe support")
Signed-off-by: Khalid Manaa <khalidm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h

@@ -167,6 +167,11 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size)
 	return pi;
 }
 
+static inline u16 mlx5e_shampo_get_cqe_header_index(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+{
+	return be16_to_cpu(cqe->shampo.header_entry_index) & (rq->mpwqe.shampo->hd_per_wq - 1);
+}
+
 struct mlx5e_shampo_umr {
 	u16 len;
 };

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

@@ -1117,7 +1117,7 @@ static void mlx5e_shampo_update_ipv6_udp_hdr(struct mlx5e_rq *rq, struct ipv6hdr
 static void mlx5e_shampo_update_fin_psh_flags(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 					      struct tcphdr *skb_tcp_hd)
 {
-	u16 header_index = be16_to_cpu(cqe->shampo.header_entry_index);
+	u16 header_index = mlx5e_shampo_get_cqe_header_index(rq, cqe);
 	struct tcphdr *last_tcp_hd;
 	void *last_hd_addr;
 
@@ -1973,7 +1973,7 @@ mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index)
 static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
 	u16 data_bcnt		= mpwrq_get_cqe_byte_cnt(cqe) - cqe->shampo.header_size;
-	u16 header_index	= be16_to_cpu(cqe->shampo.header_entry_index);
+	u16 header_index	= mlx5e_shampo_get_cqe_header_index(rq, cqe);
 	u32 wqe_offset		= be32_to_cpu(cqe->shampo.data_offset);
 	u16 cstrides		= mpwrq_get_cqe_consumed_strides(cqe);
 	u32 data_offset		= wqe_offset & (PAGE_SIZE - 1);