net/mlx5: fix vectorized mini-CQE prefetching

  There was an optimization work to prefetch all the CQEs before
their invalidation. It allowed us to speed up the mini-CQE
decompression process by preheating the cache in the vectorized
Rx routine.

Prefetching of the next mini-CQE, on the other hand, showed
no difference in the performance on x86 platform. So, that was
removed. Unfortunately this caused the performance drop on ARM.

Prefetch the mini-CQE as well as well as the all the soon to be
invalidated CQEs to get both CQE and mini-CQE on the hot path.

Fixes: 28a4b9632 ("net/mlx5: prefetch CQEs for a faster decompression")
Cc: stable@dpdk.org

Signed-off-by: Alexander Kozyrev <akozyrev@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
---
 drivers/net/mlx5/mlx5_rxtx_vec_altivec.h | 3 ++-
 drivers/net/mlx5/mlx5_rxtx_vec_neon.h    | 3 +++
 drivers/net/mlx5/mlx5_rxtx_vec_sse.h     | 3 ++-
 3 files changed, 7 insertions(+), 2 deletions(-)
  

Hi,

> -----Original Message-----
> From: Alexander Kozyrev <akozyrev@mellanox.com>
> Sent: Wednesday, July 22, 2020 11:33 PM
> To: dev@dpdk.org
> Cc: stable@dpdk.org; Raslan Darawsheh <rasland@mellanox.com>; Slava
> Ovsiienko <viacheslavo@mellanox.com>
> Subject: [PATCH] net/mlx5: fix vectorized mini-CQE prefetching
> 
> There was an optimization work to prefetch all the CQEs before
> their invalidation. It allowed us to speed up the mini-CQE
> decompression process by preheating the cache in the vectorized
> Rx routine.
> 
> Prefetching of the next mini-CQE, on the other hand, showed
> no difference in the performance on x86 platform. So, that was
> removed. Unfortunately this caused the performance drop on ARM.
> 
> Prefetch the mini-CQE as well as well as the all the soon to be
> invalidated CQEs to get both CQE and mini-CQE on the hot path.
> 
> Fixes: 28a4b9632 ("net/mlx5: prefetch CQEs for a faster decompression")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Alexander Kozyrev <akozyrev@mellanox.com>
> Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
> ---
>  drivers/net/mlx5/mlx5_rxtx_vec_altivec.h | 3 ++-
>  drivers/net/mlx5/mlx5_rxtx_vec_neon.h    | 3 +++
>  drivers/net/mlx5/mlx5_rxtx_vec_sse.h     | 3 ++-
>  3 files changed, 7 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h
> b/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h
> index f5414eebad..cb4ce1a099 100644
> --- a/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h
> +++ b/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h
> @@ -158,7 +158,6 @@ rxq_cq_decompress_v(struct mlx5_rxq_data *rxq,
> volatile struct mlx5_cqe *cq,
>  		for (i = 0; i < MLX5_VPMD_DESCS_PER_LOOP; ++i)
>  			if (likely(pos + i < mcqe_n))
>  				rte_prefetch0((void *)(cq + pos + i));
> -
>  		/* A.1 load mCQEs into a 128bit register. */
>  		mcqe1 = (vector unsigned char)vec_vsx_ld(0,
>  			(signed int const *)&mcq[pos % 8]);
> @@ -287,6 +286,8 @@ rxq_cq_decompress_v(struct mlx5_rxq_data *rxq,
> volatile struct mlx5_cqe *cq,
>  		pos += MLX5_VPMD_DESCS_PER_LOOP;
>  		/* Move to next CQE and invalidate consumed CQEs. */
>  		if (!(pos & 0x7) && pos < mcqe_n) {
> +			if (pos + 8 < mcqe_n)
> +				rte_prefetch0((void *)(cq + pos + 8));
>  			mcq = (void *)&(cq + pos)->pkt_info;
>  			for (i = 0; i < 8; ++i)
>  				cq[inv++].op_own =
> MLX5_CQE_INVALIDATE;
> diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
> b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
> index 555c342626..6c3149523e 100644
> --- a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
> +++ b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
> @@ -145,6 +145,7 @@ rxq_cq_decompress_v(struct mlx5_rxq_data *rxq,
> volatile struct mlx5_cqe *cq,
>  				    -1UL << ((mcqe_n - pos) *
>  					     sizeof(uint16_t) * 8) : 0);
>  #endif
> +
>  		for (i = 0; i < MLX5_VPMD_DESCS_PER_LOOP; ++i)
>  			if (likely(pos + i < mcqe_n))
>  				rte_prefetch0((void *)(cq + pos + i));
> @@ -227,6 +228,8 @@ rxq_cq_decompress_v(struct mlx5_rxq_data *rxq,
> volatile struct mlx5_cqe *cq,
>  		pos += MLX5_VPMD_DESCS_PER_LOOP;
>  		/* Move to next CQE and invalidate consumed CQEs. */
>  		if (!(pos & 0x7) && pos < mcqe_n) {
> +			if (pos + 8 < mcqe_n)
> +				rte_prefetch0((void *)(cq + pos + 8));
>  			mcq = (void *)&(cq + pos)->pkt_info;
>  			for (i = 0; i < 8; ++i)
>  				cq[inv++].op_own =
> MLX5_CQE_INVALIDATE;
> diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
> b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
> index 34e3397115..554924d7fc 100644
> --- a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
> +++ b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
> @@ -135,7 +135,6 @@ rxq_cq_decompress_v(struct mlx5_rxq_data *rxq,
> volatile struct mlx5_cqe *cq,
>  		for (i = 0; i < MLX5_VPMD_DESCS_PER_LOOP; ++i)
>  			if (likely(pos + i < mcqe_n))
>  				rte_prefetch0((void *)(cq + pos + i));
> -
>  		/* A.1 load mCQEs into a 128bit register. */
>  		mcqe1 = _mm_loadu_si128((__m128i *)&mcq[pos % 8]);
>  		mcqe2 = _mm_loadu_si128((__m128i *)&mcq[pos % 8 + 2]);
> @@ -214,6 +213,8 @@ rxq_cq_decompress_v(struct mlx5_rxq_data *rxq,
> volatile struct mlx5_cqe *cq,
>  		pos += MLX5_VPMD_DESCS_PER_LOOP;
>  		/* Move to next CQE and invalidate consumed CQEs. */
>  		if (!(pos & 0x7) && pos < mcqe_n) {
> +			if (pos + 8 < mcqe_n)
> +				rte_prefetch0((void *)(cq + pos + 8));
>  			mcq = (void *)(cq + pos);
>  			for (i = 0; i < 8; ++i)
>  				cq[inv++].op_own =
> MLX5_CQE_INVALIDATE;
> --
> 2.24.1

Patch applied to next-net-mlx,

Kindest regards,
Raslan Darawsheh