Re: [dpdk-stable] [dpdk-dev] [PATCH] net/mlx5: fix order of items in neon scatter func

[Shahaf Shuler <shahafs@mellanox.com>]

Wednesday, May 15, 2019 1:08 PM, Dekel Peled:
> Subject: [dpdk-dev] [PATCH] net/mlx5: fix order of items in neon scatter
> func
> 
> Previous patch added handling of metadata for multi-segment packet.
> Function txq_scatter_v in file mlx5_rxtx_vec_neon.h was updated
> incorrectly, items were inserted into WQE in wrong order.
> 
> This patch fixes the issue, inserting items into WQE correctly.
> 
> Fixes: 7f4019d370f6 ("net/mlx5: fix Tx metadata for multi-segment packet")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Dekel Peled <dekelp@mellanox.com>
> ---
>  drivers/net/mlx5/mlx5_rxtx_vec_neon.h | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
> b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
> index 38e915c..b1e0e8f 100644
> --- a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
> +++ b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
> @@ -171,7 +171,7 @@
>  		/* Fill ESEG in the header. */
>  		vst1q_u32((void *)(t_wqe + 1),
>  			  ((uint32x4_t){ 0,
> -					 cs_flags << 16 |
> rte_cpu_to_be_16(len),
> +					 rte_cpu_to_be_16(len) << 16 |
> cs_flags,

It was probably not introduced by the previous patch, but since you touch this area:
Why do you set the mss (len)? This function handles only non-TSO packets. 

>  					 metadata, 0 }));
>  		txq->wqe_ci = wqe_ci;
>  	}
> --
> 1.8.3.1