[v3,2/5] net/ixgbe: fix vector rx burst for ixgbe

  The limitation of burst size in vector rx was removed, since it should
retrieve as much received packets as possible. And also the scattered
receive path should use a wrapper function to achieve the goal of
burst maximizing. And do some code cleaning for vector rx path.

Signed-off-by: Jeff Guo <jia.guo@intel.com>
---
 drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c | 77 +++++++++++++------------
 drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c  | 61 +++++++++++---------
 2 files changed, 76 insertions(+), 62 deletions(-)
  

Hi, Jeff

> From: dev <dev-bounces@dpdk.org> On Behalf Of Jeff Guo
> Sent: Wednesday, September 9, 2020 2:37 PM
> To: qiming.yang@intel.com; beilei.xing@intel.com; wei.zhao1@intel.com;
> qi.z.zhang@intel.com; jingjing.wu@intel.com
> Cc: bruce.richardson@intel.com; dev@dpdk.org; jia.guo@intel.com;
> helin.zhang@intel.com; mb@smartsharesystems.com; ferruh.yigit@intel.com;
> haiyue.wang@intel.com; stephen@networkplumber.org; barbette@kth.se
> Subject: [dpdk-dev] [PATCH v3 2/5] net/ixgbe: fix vector rx burst for ixgbe
> 
> The limitation of burst size in vector rx was removed, since it should retrieve as
> much received packets as possible. And also the scattered receive path should
> use a wrapper function to achieve the goal of burst maximizing. And do some
> code cleaning for vector rx path.
> 
> Signed-off-by: Jeff Guo <jia.guo@intel.com>
> ---
>  drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c | 77 +++++++++++++------------
This patch has passed the test on aarch64 platform with neon path.
Tested-by: Feifei Wang <Feifei.wang2@arm.com>
> drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c  | 61 +++++++++++---------
>  2 files changed, 76 insertions(+), 62 deletions(-)
> 
> diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
> b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
> index aa27ee177..7692c5d59 100644
> --- a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
> +++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
> @@ -130,17 +130,6 @@ desc_to_olflags_v(uint8x16x2_t sterr_tmp1,
> uint8x16x2_t sterr_tmp2,  rx_pkts[3]->ol_flags = vol.e[3];  }
> 
> -/*
> - * vPMD raw receive routine, only accept(nb_pkts >=
> RTE_IXGBE_DESCS_PER_LOOP)
> - *
> - * Notice:
> - * - nb_pkts < RTE_IXGBE_DESCS_PER_LOOP, just return no packet
> - * - nb_pkts > RTE_IXGBE_MAX_RX_BURST, only scan
> RTE_IXGBE_MAX_RX_BURST
> - *   numbers of DD bit
> - * - floor align nb_pkts to a RTE_IXGBE_DESC_PER_LOOP power-of-two
> - * - don't support ol_flags for rss and csum err
> - */
> -
>  #define IXGBE_VPMD_DESC_EOP_MASK0x02020202
>  #define IXGBE_UINT8_BIT(CHAR_BIT * sizeof(uint8_t))
> 
> @@ -206,6 +195,13 @@ desc_to_ptype_v(uint64x2_t descs[4], uint16_t
> pkt_type_mask,  vgetq_lane_u32(tunnel_check, 3));  }
> 
> +/**
> + * vPMD raw receive routine, only accept(nb_pkts >=
> +RTE_IXGBE_DESCS_PER_LOOP)
> + *
> + * Notice:
> + * - nb_pkts < RTE_IXGBE_DESCS_PER_LOOP, just return no packet
> + * - floor align nb_pkts to a RTE_IXGBE_DESC_PER_LOOP power-of-two  */
>  static inline uint16_t
>  _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
>     uint16_t nb_pkts, uint8_t *split_packet) @@ -226,9 +222,6 @@
> _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
> uint16x8_t crc_adjust = {0, 0, rxq->crc_len, 0,
>   rxq->crc_len, 0, 0, 0};
> 
> -/* nb_pkts shall be less equal than RTE_IXGBE_MAX_RX_BURST */ -nb_pkts =
> RTE_MIN(nb_pkts, RTE_IXGBE_MAX_RX_BURST);
> -
>  /* nb_pkts has to be floor-aligned to RTE_IXGBE_DESCS_PER_LOOP */  nb_pkts
> = RTE_ALIGN_FLOOR(nb_pkts, RTE_IXGBE_DESCS_PER_LOOP);
> 
> @@ -382,16 +375,6 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq,
> struct rte_mbuf **rx_pkts,  return nb_pkts_recd;  }
> 
> -/*
> - * vPMD receive routine, only accept(nb_pkts >=
> RTE_IXGBE_DESCS_PER_LOOP)
> - *
> - * Notice:
> - * - nb_pkts < RTE_IXGBE_DESCS_PER_LOOP, just return no packet
> - * - nb_pkts > RTE_IXGBE_MAX_RX_BURST, only scan
> RTE_IXGBE_MAX_RX_BURST
> - *   numbers of DD bit
> - * - floor align nb_pkts to a RTE_IXGBE_DESC_PER_LOOP power-of-two
> - * - don't support ol_flags for rss and csum err
> - */
>  uint16_t
>  ixgbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,  uint16_t
> nb_pkts) @@ -399,23 +382,19 @@ ixgbe_recv_pkts_vec(void *rx_queue, struct
> rte_mbuf **rx_pkts,  return _recv_raw_pkts_vec(rx_queue, rx_pkts, nb_pkts,
> NULL);  }
> 
> -/*
> - * vPMD receive routine that reassembles scattered packets
> - *
> - * Notice:
> - * - don't support ol_flags for rss and csum err
> - * - nb_pkts < RTE_IXGBE_DESCS_PER_LOOP, just return no packet
> - * - nb_pkts > RTE_IXGBE_MAX_RX_BURST, only scan
> RTE_IXGBE_MAX_RX_BURST
> - *   numbers of DD bit
> - * - floor align nb_pkts to a RTE_IXGBE_DESC_PER_LOOP power-of-two
> +/**
> + * vPMD receive routine that reassembles single burst of 32 scattered
> +packets
>   */
> -uint16_t
> -ixgbe_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts, -
> uint16_t nb_pkts)
> +static uint16_t
> +ixgbe_recv_scattered_burst_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
> +       uint16_t nb_pkts)
>  {
>  struct ixgbe_rx_queue *rxq = rx_queue;
>  uint8_t split_flags[RTE_IXGBE_MAX_RX_BURST] = {0};
> 
> +/* split_flags only can support max of RTE_IXGBE_MAX_RX_BURST */
> +nb_pkts = RTE_MIN(nb_pkts, RTE_IXGBE_MAX_RX_BURST);
> +
>  /* get some new buffers */
>  uint16_t nb_bufs = _recv_raw_pkts_vec(rxq, rx_pkts, nb_pkts,  split_flags);
> @@ -443,6 +422,32 @@ ixgbe_recv_scattered_pkts_vec(void *rx_queue, struct
> rte_mbuf **rx_pkts,  &split_flags[i]);  }
> 
> +/**
> + * vPMD receive routine that reassembles scattered packets.
> + */
> +uint16_t
> +ixgbe_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
> +      uint16_t nb_pkts)
> +{
> +uint16_t retval = 0;
> +
> +while (nb_pkts > RTE_IXGBE_MAX_RX_BURST) { uint16_t burst;
> +
> +burst = ixgbe_recv_scattered_burst_vec(rx_queue,
> +       rx_pkts + retval,
> +       RTE_IXGBE_MAX_RX_BURST);
> +retval += burst;
> +nb_pkts -= burst;
> +if (burst < RTE_IXGBE_MAX_RX_BURST)
> +return retval;
> +}
> +
> +return retval + ixgbe_recv_scattered_burst_vec(rx_queue,
> +       rx_pkts + retval,
> +       nb_pkts);
> +}
> +
>  static inline void
>  vtx1(volatile union ixgbe_adv_tx_desc *txdp,  struct rte_mbuf *pkt, uint64_t
> flags) diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
> b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
> index 517ca3166..cf54ff128 100644
> --- a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
> +++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
> @@ -302,13 +302,11 @@ desc_to_ptype_v(__m128i descs[4], uint16_t
> pkt_type_mask,  get_packet_type(3, pkt_info, etqf_check, tunnel_check);  }
> 
> -/*
> +/**
>   * vPMD raw receive routine, only accept(nb_pkts >=
> RTE_IXGBE_DESCS_PER_LOOP)
>   *
>   * Notice:
>   * - nb_pkts < RTE_IXGBE_DESCS_PER_LOOP, just return no packet
> - * - nb_pkts > RTE_IXGBE_MAX_RX_BURST, only scan
> RTE_IXGBE_MAX_RX_BURST
> - *   numbers of DD bit
>   * - floor align nb_pkts to a RTE_IXGBE_DESC_PER_LOOP power-of-two
>   */
>  static inline uint16_t
> @@ -344,9 +342,6 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct
> rte_mbuf **rx_pkts,  __m128i mbuf_init;  uint8_t vlan_flags;
> 
> -/* nb_pkts shall be less equal than RTE_IXGBE_MAX_RX_BURST */ -nb_pkts =
> RTE_MIN(nb_pkts, RTE_IXGBE_MAX_RX_BURST);
> -
>  /* nb_pkts has to be floor-aligned to RTE_IXGBE_DESCS_PER_LOOP */  nb_pkts
> = RTE_ALIGN_FLOOR(nb_pkts, RTE_IXGBE_DESCS_PER_LOOP);
> 
> @@ -556,15 +551,6 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq,
> struct rte_mbuf **rx_pkts,  return nb_pkts_recd;  }
> 
> -/*
> - * vPMD receive routine, only accept(nb_pkts >=
> RTE_IXGBE_DESCS_PER_LOOP)
> - *
> - * Notice:
> - * - nb_pkts < RTE_IXGBE_DESCS_PER_LOOP, just return no packet
> - * - nb_pkts > RTE_IXGBE_MAX_RX_BURST, only scan
> RTE_IXGBE_MAX_RX_BURST
> - *   numbers of DD bit
> - * - floor align nb_pkts to a RTE_IXGBE_DESC_PER_LOOP power-of-two
> - */
>  uint16_t
>  ixgbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,  uint16_t
> nb_pkts) @@ -572,22 +558,19 @@ ixgbe_recv_pkts_vec(void *rx_queue, struct
> rte_mbuf **rx_pkts,  return _recv_raw_pkts_vec(rx_queue, rx_pkts, nb_pkts,
> NULL);  }
> 
> -/*
> - * vPMD receive routine that reassembles scattered packets
> - *
> - * Notice:
> - * - nb_pkts < RTE_IXGBE_DESCS_PER_LOOP, just return no packet
> - * - nb_pkts > RTE_IXGBE_MAX_RX_BURST, only scan
> RTE_IXGBE_MAX_RX_BURST
> - *   numbers of DD bit
> - * - floor align nb_pkts to a RTE_IXGBE_DESC_PER_LOOP power-of-two
> +/**
> + * vPMD receive routine that reassembles single burst of 32 scattered
> +packets
>   */
> -uint16_t
> -ixgbe_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts, -
> uint16_t nb_pkts)
> +static uint16_t
> +ixgbe_recv_scattered_burst_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
> +       uint16_t nb_pkts)
>  {
>  struct ixgbe_rx_queue *rxq = rx_queue;
>  uint8_t split_flags[RTE_IXGBE_MAX_RX_BURST] = {0};
> 
> +/* split_flags only can support max of RTE_IXGBE_MAX_RX_BURST */
> +nb_pkts = RTE_MIN(nb_pkts, RTE_IXGBE_MAX_RX_BURST);
> +
>  /* get some new buffers */
>  uint16_t nb_bufs = _recv_raw_pkts_vec(rxq, rx_pkts, nb_pkts,  split_flags);
> @@ -615,6 +598,32 @@ ixgbe_recv_scattered_pkts_vec(void *rx_queue, struct
> rte_mbuf **rx_pkts,  &split_flags[i]);  }
> 
> +/**
> + * vPMD receive routine that reassembles scattered packets.
> + */
> +uint16_t
> +ixgbe_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
> +      uint16_t nb_pkts)
> +{
> +uint16_t retval = 0;
> +
> +while (nb_pkts > RTE_IXGBE_MAX_RX_BURST) { uint16_t burst;
> +
> +burst = ixgbe_recv_scattered_burst_vec(rx_queue,
> +       rx_pkts + retval,
> +       RTE_IXGBE_MAX_RX_BURST);
> +retval += burst;
> +nb_pkts -= burst;
> +if (burst < RTE_IXGBE_MAX_RX_BURST)
> +return retval;
> +}
> +
> +return retval + ixgbe_recv_scattered_burst_vec(rx_queue,
> +       rx_pkts + retval,
> +       nb_pkts);
> +}
> +
>  static inline void
>  vtx1(volatile union ixgbe_adv_tx_desc *txdp,  struct rte_mbuf *pkt, uint64_t
> flags)
> --
> 2.20.1
>