[dpdk-stable] [PATCH] net/mlx5: fix Tx doorbell

[Nelio Laranjeiro]

From: Nélio Laranjeiro <nelio.laranjeiro at 6wind.com>

[ backported from upstream commit 8cfdff62b00eccb59506c79e439a6a5aba03901c ]

Too much data is uselessly written to the Tx doorbell.

Fixes: 1d88ba171942 ("net/mlx5: refactor Tx data path")

Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro at 6wind.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil at 6wind.com>
---
 drivers/net/mlx5/mlx5_rxtx.c | 27 ++++++++++++++-------------
 drivers/net/mlx5/mlx5_rxtx.h |  2 --
 drivers/net/mlx5/mlx5_txq.c  |  2 --
 3 files changed, 14 insertions(+), 17 deletions(-)

diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c
index 79f7fa9..8088ed6 100644
--- a/drivers/net/mlx5/mlx5_rxtx.c
+++ b/drivers/net/mlx5/mlx5_rxtx.c
@@ -69,6 +69,10 @@
 #include "mlx5_defs.h"
 #include "mlx5_prm.h"
 
+static inline void
+mlx5_tx_dbrec(struct txq *txq, volatile union mlx5_wqe *wqe)
+	__attribute__((always_inline));
+
 #ifndef NDEBUG
 
 /**
@@ -394,23 +398,20 @@ use_dseg:
  *
  * @param txq
  *   Pointer to TX queue structure.
+ * @param wqe
+ *   Pointer to the last WQE posted in the NIC.
  */
 static inline void
-mlx5_tx_dbrec(struct txq *txq)
+mlx5_tx_dbrec(struct txq *txq, volatile union mlx5_wqe *wqe)
 {
-	uint8_t *dst = (uint8_t *)((uintptr_t)txq->bf_reg + txq->bf_offset);
-	uint32_t data[4] = {
-		htonl((txq->wqe_ci << 8) | MLX5_OPCODE_SEND),
-		htonl(txq->qp_num_8s),
-		0,
-		0,
-	};
+	uint64_t *dst = (uint64_t *)((uintptr_t)txq->bf_reg);
+	volatile uint64_t *src = ((volatile uint64_t *)wqe);
+
 	rte_wmb();
 	*txq->qp_db = htonl(txq->wqe_ci);
 	/* Ensure ordering between DB record and BF copy. */
 	rte_wmb();
-	rte_mov16(dst, (uint8_t *)data);
-	txq->bf_offset ^= txq->bf_buf_size;
+	*dst = *src;
 }
 
 /**
@@ -586,7 +587,7 @@ skip_segs:
 	txq->stats.opackets += i;
 #endif
 	/* Ring QP doorbell. */
-	mlx5_tx_dbrec(txq);
+	mlx5_tx_dbrec(txq, (volatile union mlx5_wqe *)wqe);
 	txq->elts_head = elts_head;
 	return i;
 }
@@ -793,7 +794,7 @@ mlx5_tx_burst_mpw(void *dpdk_txq, struct rte_mbuf **pkts, uint16_t pkts_n)
 	/* Ring QP doorbell. */
 	if (mpw.state == MLX5_MPW_STATE_OPENED)
 		mlx5_mpw_close(txq, &mpw);
-	mlx5_tx_dbrec(txq);
+	mlx5_tx_dbrec(txq, mpw.wqe);
 	txq->elts_head = elts_head;
 	return i;
 }
@@ -1058,7 +1059,7 @@ mlx5_tx_burst_mpw_inline(void *dpdk_txq, struct rte_mbuf **pkts,
 		mlx5_mpw_inline_close(txq, &mpw);
 	else if (mpw.state == MLX5_MPW_STATE_OPENED)
 		mlx5_mpw_close(txq, &mpw);
-	mlx5_tx_dbrec(txq);
+	mlx5_tx_dbrec(txq, mpw.wqe);
 	txq->elts_head = elts_head;
 	return i;
 }
diff --git a/drivers/net/mlx5/mlx5_rxtx.h b/drivers/net/mlx5/mlx5_rxtx.h
index 05779ef..1db1cc2 100644
--- a/drivers/net/mlx5/mlx5_rxtx.h
+++ b/drivers/net/mlx5/mlx5_rxtx.h
@@ -247,8 +247,6 @@ struct txq {
 	uint16_t cqe_n; /* Number of CQ elements. */
 	uint16_t wqe_ci; /* Consumer index for work queue. */
 	uint16_t wqe_n; /* Number of WQ elements. */
-	uint16_t bf_offset; /* Blueflame offset. */
-	uint16_t bf_buf_size; /* Blueflame size. */
 	uint16_t max_inline; /* Multiple of RTE_CACHE_LINE_SIZE to inline. */
 	uint32_t qp_num_8s; /* QP number shifted by 8. */
 	volatile struct mlx5_cqe (*cqes)[]; /* Completion queue. */
diff --git a/drivers/net/mlx5/mlx5_txq.c b/drivers/net/mlx5/mlx5_txq.c
index e4510ef..579cf9e 100644
--- a/drivers/net/mlx5/mlx5_txq.c
+++ b/drivers/net/mlx5/mlx5_txq.c
@@ -220,8 +220,6 @@ txq_setup(struct txq_ctrl *tmpl, struct txq_ctrl *txq_ctrl)
 	tmpl->txq.wqe_n = qp->sq.wqe_cnt;
 	tmpl->txq.qp_db = &qp->gen_data.db[MLX5_SND_DBR];
 	tmpl->txq.bf_reg = qp->gen_data.bf->reg;
-	tmpl->txq.bf_offset = qp->gen_data.bf->offset;
-	tmpl->txq.bf_buf_size = qp->gen_data.bf->buf_size;
 	tmpl->txq.cq_db = cq->dbrec;
 	tmpl->txq.cqes =
 		(volatile struct mlx5_cqe (*)[])
-- 
2.1.4