[dpdk-dev] [PATCH v4 3/4] net: add arm64 neon version of CRC compute APIs

[Jianbo Liu]

On 9 May 2017 at 17:53, Ashwin Sekhar T K
<ashwin.sekhar at caviumnetworks.com> wrote:
> Added CRC compute APIs for arm64 utilizing the pmull
> capability
>
> Added new file net_crc_neon.h to hold the arm64 pmull
> CRC implementation
>
> Verified the changes with crc_autotest unit test case
>
> Signed-off-by: Ashwin Sekhar T K <ashwin.sekhar at caviumnetworks.com>
> ---
> v2:
> * Fixed merge conflict in MAINTAINERS
>
> v3:
> * Moved feature detection changes and GCC_VERSION definition
>   changes to separate commit
> * Replaced usage of assert() with RTE_ASSERT()
> * Made the comments in rte_vect.h more positive in sense
>
> v4:
> * Rebased on top of latest commit
>
>  MAINTAINERS                                       |   1 +
>  lib/librte_eal/common/include/arch/arm/rte_vect.h |  28 ++
>  lib/librte_net/net_crc_neon.h                     | 357 ++++++++++++++++++++++
>  lib/librte_net/rte_net_crc.c                      |  34 ++-
>  lib/librte_net/rte_net_crc.h                      |   2 +
>  5 files changed, 416 insertions(+), 6 deletions(-)
>  create mode 100644 lib/librte_net/net_crc_neon.h
>
> diff --git a/MAINTAINERS b/MAINTAINERS
> index b6495d2..66d64c2 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -147,6 +147,7 @@ F: lib/librte_eal/common/include/arch/arm/*_64.h
>  F: lib/librte_acl/acl_run_neon.*
>  F: lib/librte_lpm/rte_lpm_neon.h
>  F: lib/librte_hash/rte*_arm64.h
> +F: lib/librte_net/net_crc_neon.h
>  F: drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
>  F: drivers/net/i40e/i40e_rxtx_vec_neon.c
>  F: drivers/net/virtio/virtio_rxtx_simple_neon.c
> diff --git a/lib/librte_eal/common/include/arch/arm/rte_vect.h b/lib/librte_eal/common/include/arch/arm/rte_vect.h
> index 4107c99..b215cc9 100644
> --- a/lib/librte_eal/common/include/arch/arm/rte_vect.h
> +++ b/lib/librte_eal/common/include/arch/arm/rte_vect.h
> @@ -35,6 +35,7 @@
>
>  #include <stdint.h>
>  #include "generic/rte_vect.h"
> +#include "rte_debug.h"
>  #include "arm_neon.h"
>
>  #ifdef __cplusplus
> @@ -78,6 +79,33 @@ vqtbl1q_u8(uint8x16_t a, uint8x16_t b)
>  }
>  #endif
>
> +#if (GCC_VERSION < 70000)
> +/* NEON intrinsic vreinterpretq_u64_p128() is supported since GCC version 7 */
> +static inline uint64x2_t
> +vreinterpretq_u64_p128(poly128_t x)
> +{
> +       return (uint64x2_t)x;
> +}
> +
> +/* NEON intrinsic vreinterpretq_p64_u64() is supported since GCC version 7 */
> +static inline poly64x2_t
> +vreinterpretq_p64_u64(uint64x2_t x)
> +{
> +       return (poly64x2_t)x;
> +}
> +
> +/* NEON intrinsic vgetq_lane_p64() is supported since GCC version 7 */
> +static inline poly64_t
> +vgetq_lane_p64(poly64x2_t x, const int lane)
> +{
> +       RTE_ASSERT(lane >= 0 && lane <= 1);
> +
> +       poly64_t *p = (poly64_t *)&x;
> +
> +       return p[lane];
> +}
> +#endif
> +
>  #ifdef __cplusplus
>  }
>  #endif
> diff --git a/lib/librte_net/net_crc_neon.h b/lib/librte_net/net_crc_neon.h
> new file mode 100644
> index 0000000..05120a7
> --- /dev/null
> +++ b/lib/librte_net/net_crc_neon.h
> @@ -0,0 +1,357 @@
> +/*
> + *   BSD LICENSE
> + *
> + *   Copyright (C) Cavium networks Ltd. 2017.
> + *
> + *   Redistribution and use in source and binary forms, with or without
> + *   modification, are permitted provided that the following conditions
> + *   are met:
> + *
> + *     * Redistributions of source code must retain the above copyright
> + *       notice, this list of conditions and the following disclaimer.
> + *     * Redistributions in binary form must reproduce the above copyright
> + *       notice, this list of conditions and the following disclaimer in
> + *       the documentation and/or other materials provided with the
> + *       distribution.
> + *     * Neither the name of Cavium networks nor the names of its
> + *       contributors may be used to endorse or promote products derived
> + *       from this software without specific prior written permission.
> + *
> + *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
> + *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
> + *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
> + *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
> + *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
> + *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
> + *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
> + *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
> + *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
> + *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
> + *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
> + */
> +
> +#ifndef _NET_CRC_NEON_H_
> +#define _NET_CRC_NEON_H_
> +
> +#include <rte_branch_prediction.h>
> +#include <rte_net_crc.h>
> +#include <rte_vect.h>
> +#include <rte_cpuflags.h>
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +/** PMULL CRC computation context structure */
> +struct crc_pmull_ctx {
> +       uint64x2_t rk1_rk2;
> +       uint64x2_t rk5_rk6;
> +       uint64x2_t rk7_rk8;
> +};
> +
> +struct crc_pmull_ctx crc32_eth_pmull __rte_aligned(16);
> +struct crc_pmull_ctx crc16_ccitt_pmull __rte_aligned(16);
> +
> +static inline uint8x16_t
> +extract_vector(uint8x16_t v0, uint8x16_t v1, const int n)
> +{
> +       switch (n) {
> +       case 0: return vextq_u8(v0, v1, 0);
> +       case 1: return vextq_u8(v0, v1, 1);
> +       case 2: return vextq_u8(v0, v1, 2);
> +       case 3: return vextq_u8(v0, v1, 3);
> +       case 4: return vextq_u8(v0, v1, 4);
> +       case 5: return vextq_u8(v0, v1, 5);
> +       case 6: return vextq_u8(v0, v1, 6);
> +       case 7: return vextq_u8(v0, v1, 7);
> +       case 8: return vextq_u8(v0, v1, 8);
> +       case 9: return vextq_u8(v0, v1, 9);
> +       case 10: return vextq_u8(v0, v1, 10);
> +       case 11: return vextq_u8(v0, v1, 11);
> +       case 12: return vextq_u8(v0, v1, 12);
> +       case 13: return vextq_u8(v0, v1, 13);
> +       case 14: return vextq_u8(v0, v1, 14);
> +       case 15: return vextq_u8(v0, v1, 15);
> +       }
> +       return v1;
> +}
> +
> +/**
> + * Shifts right 128 bit register by specified number of bytes
> + *
> + * @param reg 128 bit value
> + * @param num number of bytes to shift reg by (0-16)
> + *
> + * @return reg << (num * 8)
> + */
> +static inline uint64x2_t
> +shift_bytes_right(uint64x2_t reg, const unsigned int num)
> +{
> +       /* Right Shift */
> +       return vreinterpretq_u64_u8(extract_vector(
> +                               vreinterpretq_u8_u64(reg),
> +                               vdupq_n_u8(0),
> +                               num));
> +}
> +
> +/**
> + * Shifts left 128 bit register by specified number of bytes
> + *
> + * @param reg 128 bit value
> + * @param num number of bytes to shift reg by (0-16)
> + *
> + * @return reg << (num * 8)
> + */
> +static inline uint64x2_t
> +shift_bytes_left(uint64x2_t reg, const unsigned int num)
> +{
> +       /* Left Shift */
> +       return vreinterpretq_u64_u8(extract_vector(
> +                               vdupq_n_u8(0),
> +                               vreinterpretq_u8_u64(reg),
> +                               16 - num));
> +}
> +

Can you move shift_bytes_right/shift_bytes_left to rte_vect.h because
they are common functions?