[dpdk-dev,v6,5/5] net/mlx4: add loopback Tx from VF
Checks
Commit Message
From: Moti Haimovsky <motih@mellanox.com>
This patch adds loopback functionality used when the chip is a VF in order
to enable packet transmission between VFs and PF.
Signed-off-by: Moti Haimovsky <motih@mellanox.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
---
drivers/net/mlx4/mlx4_rxtx.c | 33 +++++++++++++++++++++------------
drivers/net/mlx4/mlx4_rxtx.h | 1 +
drivers/net/mlx4/mlx4_txq.c | 2 ++
3 files changed, 24 insertions(+), 12 deletions(-)
@@ -311,10 +311,13 @@ mlx4_post_send(struct txq *txq, struct rte_mbuf *pkt)
struct mlx4_wqe_data_seg *dseg;
struct mlx4_sq *sq = &txq->msq;
struct rte_mbuf *buf;
+ union {
+ uint32_t flags;
+ uint16_t flags16[2];
+ } srcrb;
uint32_t head_idx = sq->head & sq->txbb_cnt_mask;
uint32_t lkey;
uintptr_t addr;
- uint32_t srcrb_flags;
uint32_t owner_opcode = MLX4_OPCODE_SEND;
uint32_t byte_count;
int wqe_real_size;
@@ -414,22 +417,16 @@ mlx4_post_send(struct txq *txq, struct rte_mbuf *pkt)
/* Fill the control parameters for this packet. */
ctrl->fence_size = (wqe_real_size >> 4) & 0x3f;
/*
- * The caller should prepare "imm" in advance in order to support
- * VF to VF communication (when the device is a virtual-function
- * device (VF)).
- */
- ctrl->imm = 0;
- /*
* For raw Ethernet, the SOLICIT flag is used to indicate that no ICRC
* should be calculated.
*/
txq->elts_comp_cd -= nr_txbbs;
if (unlikely(txq->elts_comp_cd <= 0)) {
txq->elts_comp_cd = txq->elts_comp_cd_init;
- srcrb_flags = RTE_BE32(MLX4_WQE_CTRL_SOLICIT |
+ srcrb.flags = RTE_BE32(MLX4_WQE_CTRL_SOLICIT |
MLX4_WQE_CTRL_CQ_UPDATE);
} else {
- srcrb_flags = RTE_BE32(MLX4_WQE_CTRL_SOLICIT);
+ srcrb.flags = RTE_BE32(MLX4_WQE_CTRL_SOLICIT);
}
/* Enable HW checksum offload if requested */
if (txq->csum &&
@@ -443,14 +440,26 @@ mlx4_post_send(struct txq *txq, struct rte_mbuf *pkt)
owner_opcode |= MLX4_WQE_CTRL_IIP_HDR_CSUM |
MLX4_WQE_CTRL_IL4_HDR_CSUM;
if (pkt->ol_flags & PKT_TX_OUTER_IP_CKSUM)
- srcrb_flags |=
+ srcrb.flags |=
RTE_BE32(MLX4_WQE_CTRL_IP_HDR_CSUM);
} else {
- srcrb_flags |= RTE_BE32(MLX4_WQE_CTRL_IP_HDR_CSUM |
+ srcrb.flags |= RTE_BE32(MLX4_WQE_CTRL_IP_HDR_CSUM |
MLX4_WQE_CTRL_TCP_UDP_CSUM);
}
}
- ctrl->srcrb_flags = srcrb_flags;
+ if (txq->lb) {
+ /*
+ * Copy destination MAC address to the WQE, this allows
+ * loopback in eSwitch, so that VFs and PF can communicate
+ * with each other.
+ */
+ srcrb.flags16[0] = *(rte_pktmbuf_mtod(pkt, uint16_t *));
+ ctrl->imm = *(rte_pktmbuf_mtod_offset(pkt, uint32_t *,
+ sizeof(uint16_t)));
+ } else {
+ ctrl->imm = 0;
+ }
+ ctrl->srcrb_flags = srcrb.flags;
/*
* Make sure descriptor is fully written before
* setting ownership bit (because HW can start
@@ -128,6 +128,7 @@ struct txq {
uint32_t max_inline; /**< Max inline send size. */
uint32_t csum:1; /**< Enable checksum offloading. */
uint32_t csum_l2tun:1; /**< Same for L2 tunnels. */
+ uint32_t lb:1; /**< Whether packets should be looped back by eSwitch. */
uint8_t *bounce_buf;
/**< Memory used for storing the first DWORD of data TXBBs. */
struct {
@@ -278,6 +278,8 @@ mlx4_tx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
RTE_MIN(MLX4_PMD_TX_PER_COMP_REQ, desc / 4),
.csum = priv->hw_csum,
.csum_l2tun = priv->hw_csum_l2tun,
+ /* Enable Tx loopback for VF devices. */
+ .lb = !!priv->vf,
.bounce_buf = bounce_buf,
};
txq->cq = ibv_create_cq(priv->ctx, desc, NULL, NULL, 0);