[v3,2/2] net/mlx5: fix instruction hotspot on replenishing Rx buffer
Checks
Commit Message
On replenishing Rx buffers for vectorized Rx, mbuf->buf_addr isn't needed
to be accessed as it is static and easily calculated from the mbuf address.
Accessing the mbuf content causes unnecessary load stall and it is worsened
on ARM.
Fixes: 545b884b1da3 ("net/mlx5: fix buffer address posting in SSE Rx")
Cc: stable@dpdk.org
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
---
v3:
* rte_mbuf_buf_addr_default() -> rte_mbuf_buf_addr()
v2:
* use the newly introduced API - rte_mbuf_buf_addr_default()
* fix error in assert
drivers/net/mlx5/mlx5_rxtx_vec.h | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
Comments
Thursday, January 10, 2019 8:35 PM, Yongseok Koh:
> Subject: [dpdk-dev] [PATCH v3 2/2] net/mlx5: fix instruction hotspot on
> replenishing Rx buffer
>
> On replenishing Rx buffers for vectorized Rx, mbuf->buf_addr isn't needed to
> be accessed as it is static and easily calculated from the mbuf address.
> Accessing the mbuf content causes unnecessary load stall and it is worsened on
> ARM.
>
> Fixes: 545b884b1da3 ("net/mlx5: fix buffer address posting in SSE Rx")
> Cc: stable@dpdk.org
>
> Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
> ---
>
> v3:
> * rte_mbuf_buf_addr_default() -> rte_mbuf_buf_addr()
>
> v2:
> * use the newly introduced API - rte_mbuf_buf_addr_default()
> * fix error in assert
>
> drivers/net/mlx5/mlx5_rxtx_vec.h | 6 ++++--
> 1 file changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/mlx5/mlx5_rxtx_vec.h
> b/drivers/net/mlx5/mlx5_rxtx_vec.h
> index fda7004e2d..989a1fdce5 100644
> --- a/drivers/net/mlx5/mlx5_rxtx_vec.h
> +++ b/drivers/net/mlx5/mlx5_rxtx_vec.h
> @@ -102,8 +102,10 @@ mlx5_rx_replenish_bulk_mbuf(struct mlx5_rxq_data
> *rxq, uint16_t n)
> return;
> }
> for (i = 0; i < n; ++i) {
> - wq[i].addr = rte_cpu_to_be_64((uintptr_t)elts[i]->buf_addr +
> - RTE_PKTMBUF_HEADROOM);
> + void *buf_addr = rte_mbuf_buf_addr(elts[i], rxq->mp);
> +
> + assert(buf_addr == elts[i]->buf_addr);
> + wq[i].addr = rte_cpu_to_be_64((uintptr_t)buf_addr +
> +RTE_PKTMBUF_HEADROOM);
> /* If there's only one MR, no need to replace LKey in WQE. */
> if (unlikely(mlx5_mr_btree_len(&rxq->mr_ctrl.cache_bh) > 1))
> wq[i].lkey = mlx5_rx_mb2mr(rxq, elts[i]);
> --
> 2.11.0
@@ -102,8 +102,10 @@ mlx5_rx_replenish_bulk_mbuf(struct mlx5_rxq_data *rxq, uint16_t n)
return;
}
for (i = 0; i < n; ++i) {
- wq[i].addr = rte_cpu_to_be_64((uintptr_t)elts[i]->buf_addr +
- RTE_PKTMBUF_HEADROOM);
+ void *buf_addr = rte_mbuf_buf_addr(elts[i], rxq->mp);
+
+ assert(buf_addr == elts[i]->buf_addr);
+ wq[i].addr = rte_cpu_to_be_64((uintptr_t)buf_addr + RTE_PKTMBUF_HEADROOM);
/* If there's only one MR, no need to replace LKey in WQE. */
if (unlikely(mlx5_mr_btree_len(&rxq->mr_ctrl.cache_bh) > 1))
wq[i].lkey = mlx5_rx_mb2mr(rxq, elts[i]);