net/mlx5e: Unify reserving space for WQEs

In our fast-path design, a WQE (Work Queue Element) must not cross the
page boundary. To enforce that, for WQEs consisting of more than one BB
(Basic Block), the driver checks the available contiguous space in the
WQ in advance, and if it's not enough, it pads it with NOPs.

This patch modifies the code that calculates the position of next WQE,
considering the padding, and prepares the WQE. This code is common for
all SQ types. In this patch it's reorganized in a way that makes the
usage pattern unified for all SQ types, and makes the implementations
self-contained and look almost the same, preparing the repeating code to
further attempts to deduplicate it.

One place is left as is: mlx5e_sq_xmit and mlx5e_fill_sq_frag_edge call
inside, because it is special in a way that it may also copy WQE's cseg
and eseg when reserving space. This will be eliminated in one of the
following patches, and this place will be converted to the new approach,
too.

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

1 files changed, 26 insertions, 5 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index cf089520c031..c4a7fb4ecd14 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -178,21 +178,42 @@ xdp_abort:
 	}
 }
 
-static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
+static u16 mlx5e_xdpsq_get_next_pi(struct mlx5e_xdpsq *sq, u16 size)
 {
-	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
-	struct mlx5e_xdpsq_stats *stats = sq->stats;
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	u16 pi, contig_wqebbs;
 
 	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 	contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+	if (unlikely(contig_wqebbs < size)) {
+		struct mlx5e_xdp_wqe_info *wi, *edge_wi;
+
+		wi = &sq->db.wqe_info[pi];
+		edge_wi = wi + contig_wqebbs;
+
+		/* Fill SQ frag edge with NOPs to avoid WQE wrapping two pages. */
+		for (; wi < edge_wi; wi++) {
+			*wi = (struct mlx5e_xdp_wqe_info) {
+				.num_wqebbs = 1,
+				.num_pkts = 0,
+			};
+			mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+		}
+		sq->stats->nops += contig_wqebbs;
 
-	if (unlikely(contig_wqebbs < MLX5_SEND_WQE_MAX_WQEBBS)) {
-		mlx5e_fill_xdpsq_frag_edge(sq, wq, pi, contig_wqebbs);
 		pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 	}
 
+	return pi;
+}
+
+static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5e_xdpsq_stats *stats = sq->stats;
+	u16 pi;
+
+	pi = mlx5e_xdpsq_get_next_pi(sq, MLX5_SEND_WQE_MAX_WQEBBS);
 	session->wqe = MLX5E_TX_FETCH_WQE(sq, pi);
 
 	prefetchw(session->wqe->data);