net/mlx5e: RX, Use cyclic WQ in legacy RQ

Now that LRO is not supported for Legacy RQ, there is no source of
out-of-order completions in the WQ, and we can use a cyclic one.
This has multiple advantages:
- reduces the WQE size (smaller PCI transactions).
- lower overhead in datapath (no handling of 'next' pointers).
- no reserved WQE for the WQ head (was need in linked-list).
- allows using a constant map between frag and dma_info struct, in downstream patch.

Performance tests:
ConnectX-4, single core, single RX ring.
Major gain in packet rate of single ring XDP drop.
Bottleneck is shifted form HW (at 16Mpps) to SW (at 20Mpps).

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

1 files changed, 7 insertions, 3 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index f2f2dcf6b23c..af521dd52993 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -186,9 +186,13 @@ struct mlx5e_tx_wqe {
 	struct mlx5_wqe_data_seg data[0];
 };
 
-struct mlx5e_rx_wqe {
+struct mlx5e_rx_wqe_ll {
 	struct mlx5_wqe_srq_next_seg  next;
-	struct mlx5_wqe_data_seg      data;
+	struct mlx5_wqe_data_seg      data[0];
+};
+
+struct mlx5e_rx_wqe_cyc {
+	struct mlx5_wqe_data_seg      data[0];
 };
 
 struct mlx5e_umr_wqe {
@@ -500,7 +504,7 @@ struct mlx5e_rq {
 	/* data path */
 	union {
 		struct {
-			struct mlx5_wq_ll      wq;
+			struct mlx5_wq_cyc     wq;
 			struct mlx5e_wqe_frag_info *frag_info;
 			u32 frag_sz;	/* max possible skb frag_sz */
 			union {