> -----Original Message-----
> From: dev <dev-boun...@dpdk.org> On Behalf Of Mairtin o Loingsigh
> Sent: Friday, October 9, 2020 9:51 PM
> To: jasvinder.si...@intel.com; bruce.richard...@intel.com;
> pablo.de.lara.gua...@intel.com; konstantin.anan...@intel.com
> Cc: dev@dpdk.org; brendan.r...@intel.com; mairtin.oloings...@intel.com;
> david.co...@intel.com
> Subject: [dpdk-dev] [PATCH v5 1/2] net: add run-time architecture specific
> CRC selection
>
> This patch adds support for run-time selection of the optimal architecture-
> specific CRC path, based on the supported instruction set(s) of the CPU.
>
> The compiler option checks have been moved from the C files to the meson
> script. The rte_cpu_get_flag_enabled function is called automatically by the
> library at process initialization time to determine which instructions the CPU
> supports, with the most optimal supported CRC path ultimately selected.
>
> Signed-off-by: Mairtin o Loingsigh <mairtin.oloings...@intel.com>
> Signed-off-by: David Coyle <david.co...@intel.com>
> Acked-by: Konstantin Ananyev <konstantin.anan...@intel.com>
> ---
> doc/guides/rel_notes/release_20_11.rst | 4 +
> lib/librte_net/meson.build | 34 ++++++-
> lib/librte_net/net_crc.h | 34 +++++++
> lib/librte_net/{net_crc_neon.h => net_crc_neon.c} | 26 ++---
> lib/librte_net/{net_crc_sse.h => net_crc_sse.c} | 34 ++-----
> lib/librte_net/rte_net_crc.c | 116
> +++++++++++++++-------
> 6 files changed, 168 insertions(+), 80 deletions(-) create mode 100644
> lib/librte_net/net_crc.h rename lib/librte_net/{net_crc_neon.h =>
> net_crc_neon.c} (95%) rename lib/librte_net/{net_crc_sse.h =>
> net_crc_sse.c} (94%)
>
> diff --git a/doc/guides/rel_notes/release_20_11.rst
> b/doc/guides/rel_notes/release_20_11.rst
> index 808bdc4e5..b77297f7e 100644
> --- a/doc/guides/rel_notes/release_20_11.rst
> +++ b/doc/guides/rel_notes/release_20_11.rst
> @@ -55,6 +55,10 @@ New Features
> Also, make sure to start the actual text at the margin.
> =======================================================
>
> +* **Updated CRC modules of rte_net library.**
> +
> + * Added run-time selection of the optimal architecture-specific CRC path.
> +
> * **Updated Broadcom bnxt driver.**
>
> Updated the Broadcom bnxt driver with new features and improvements,
> including:
> diff --git a/lib/librte_net/meson.build b/lib/librte_net/meson.build index
> 24ed8253b..fa439b9e5 100644
> --- a/lib/librte_net/meson.build
> +++ b/lib/librte_net/meson.build
> @@ -1,5 +1,5 @@
> # SPDX-License-Identifier: BSD-3-Clause -# Copyright(c) 2017 Intel
> Corporation
> +# Copyright(c) 2017-2020 Intel Corporation
>
> headers = files('rte_ip.h',
> 'rte_tcp.h',
> @@ -20,3 +20,35 @@ headers = files('rte_ip.h',
>
> sources = files('rte_arp.c', 'rte_ether.c', 'rte_net.c', 'rte_net_crc.c')
> deps +=
> ['mbuf']
> +
> +if dpdk_conf.has('RTE_ARCH_X86_64')
> + net_crc_sse42_cpu_support = (
> + cc.get_define('__PCLMUL__', args: machine_args) != '')
> + net_crc_sse42_cc_support = (
> + cc.has_argument('-mpclmul') and cc.has_argument('-maes'))
> +
> + build_static_net_crc_sse42_lib = 0
> +
> + if net_crc_sse42_cpu_support == true
> + sources += files('net_crc_sse.c')
> + cflags += ['-DCC_X86_64_SSE42_PCLMULQDQ_SUPPORT']
> + elif net_crc_sse42_cc_support == true
> + build_static_net_crc_sse42_lib = 1
> + net_crc_sse42_lib_cflags = ['-mpclmul', '-maes']
> + cflags += ['-DCC_X86_64_SSE42_PCLMULQDQ_SUPPORT']
> + endif
> +
> + if build_static_net_crc_sse42_lib == 1
> + net_crc_sse42_lib = static_library(
> + 'net_crc_sse42_lib',
> + 'net_crc_sse.c',
> + dependencies: static_rte_eal,
> + c_args: [cflags,
> + net_crc_sse42_lib_cflags])
> + objs += net_crc_sse42_lib.extract_objects('net_crc_sse.c')
> + endif
> +elif (dpdk_conf.has('RTE_ARCH_ARM64') and
> + cc.get_define('__ARM_FEATURE_CRYPTO', args:
> machine_args) != '')
> + sources += files('net_crc_neon.c')
> + cflags += ['-DCC_ARM64_NEON_PMULL_SUPPORT'] endif
> diff --git a/lib/librte_net/net_crc.h b/lib/librte_net/net_crc.h new file mode
> 100644 index 000000000..a1578a56c
> --- /dev/null
> +++ b/lib/librte_net/net_crc.h
> @@ -0,0 +1,34 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2020 Intel Corporation
> + */
> +
> +#ifndef _NET_CRC_H_
> +#define _NET_CRC_H_
> +
> +/*
> + * Different implementations of CRC
> + */
> +
> +/* SSE4.2 */
> +
> +void
> +rte_net_crc_sse42_init(void);
> +
> +uint32_t
> +rte_crc16_ccitt_sse42_handler(const uint8_t *data, uint32_t data_len);
> +
> +uint32_t
> +rte_crc32_eth_sse42_handler(const uint8_t *data, uint32_t data_len);
> +
> +/* NEON */
> +
> +void
> +rte_net_crc_neon_init(void);
> +
> +uint32_t
> +rte_crc16_ccitt_neon_handler(const uint8_t *data, uint32_t data_len);
> +
> +uint32_t
> +rte_crc32_eth_neon_handler(const uint8_t *data, uint32_t data_len);
> +
> +#endif /* _NET_CRC_H_ */
> diff --git a/lib/librte_net/net_crc_neon.h b/lib/librte_net/net_crc_neon.c
> similarity index 95% rename from lib/librte_net/net_crc_neon.h rename to
> lib/librte_net/net_crc_neon.c index 63fa1d4a1..f61d75a8c 100644
> --- a/lib/librte_net/net_crc_neon.h
> +++ b/lib/librte_net/net_crc_neon.c
> @@ -2,17 +2,15 @@
> * Copyright(c) 2017 Cavium, Inc
> */
>
> -#ifndef _NET_CRC_NEON_H_
> -#define _NET_CRC_NEON_H_
> +#include <string.h>
>
> +#include <rte_common.h>
> #include <rte_branch_prediction.h>
> #include <rte_net_crc.h>
> #include <rte_vect.h>
> #include <rte_cpuflags.h>
>
> -#ifdef __cplusplus
> -extern "C" {
> -#endif
> +#include "net_crc.h"
>
> /** PMULL CRC computation context structure */ struct crc_pmull_ctx
> { @@ -218,7 +216,7 @@ crc32_eth_calc_pmull(
> return n;
> }
>
> -static inline void
> +void
> rte_net_crc_neon_init(void)
> {
> /* Initialize CRC16 data */
> @@ -242,9 +240,8 @@ rte_net_crc_neon_init(void)
> crc32_eth_pmull.rk7_rk8 = vld1q_u64(eth_k7_k8); }
>
> -static inline uint32_t
> -rte_crc16_ccitt_neon_handler(const uint8_t *data,
> - uint32_t data_len)
> +uint32_t
> +rte_crc16_ccitt_neon_handler(const uint8_t *data, uint32_t data_len)
> {
> return (uint16_t)~crc32_eth_calc_pmull(data,
> data_len,
> @@ -252,18 +249,11 @@ rte_crc16_ccitt_neon_handler(const uint8_t *data,
> &crc16_ccitt_pmull);
> }
>
> -static inline uint32_t
> -rte_crc32_eth_neon_handler(const uint8_t *data,
> - uint32_t data_len)
> +uint32_t
> +rte_crc32_eth_neon_handler(const uint8_t *data, uint32_t data_len)
> {
> return ~crc32_eth_calc_pmull(data,
> data_len,
> 0xffffffffUL,
> &crc32_eth_pmull);
> }
> -
> -#ifdef __cplusplus
> -}
> -#endif
> -
> -#endif /* _NET_CRC_NEON_H_ */
> diff --git a/lib/librte_net/net_crc_sse.h b/lib/librte_net/net_crc_sse.c
> similarity index 94% rename from lib/librte_net/net_crc_sse.h rename to
> lib/librte_net/net_crc_sse.c index 1c7b7a548..053b54b39 100644
> --- a/lib/librte_net/net_crc_sse.h
> +++ b/lib/librte_net/net_crc_sse.c
> @@ -1,18 +1,16 @@
> /* SPDX-License-Identifier: BSD-3-Clause
> - * Copyright(c) 2017 Intel Corporation
> + * Copyright(c) 2017-2020 Intel Corporation
> */
>
> -#ifndef _RTE_NET_CRC_SSE_H_
> -#define _RTE_NET_CRC_SSE_H_
> +#include <string.h>
>
> +#include <rte_common.h>
> #include <rte_branch_prediction.h>
> +#include <rte_cpuflags.h>
>
> -#include <x86intrin.h>
> -#include <cpuid.h>
> +#include "net_crc.h"
>
> -#ifdef __cplusplus
> -extern "C" {
> -#endif
> +#include <x86intrin.h>
>
> /** PCLMULQDQ CRC computation context structure */ struct
> crc_pclmulqdq_ctx { @@ -259,8 +257,7 @@ crc32_eth_calc_pclmulqdq(
> return n;
> }
>
> -
> -static inline void
> +void
> rte_net_crc_sse42_init(void)
> {
> uint64_t k1, k2, k5, k6;
> @@ -303,12 +300,10 @@ rte_net_crc_sse42_init(void)
> * use other data types such as float, double, etc.
> */
> _mm_empty();
> -
> }
>
> -static inline uint32_t
> -rte_crc16_ccitt_sse42_handler(const uint8_t *data,
> - uint32_t data_len)
> +uint32_t
> +rte_crc16_ccitt_sse42_handler(const uint8_t *data, uint32_t data_len)
> {
> /** return 16-bit CRC value */
> return (uint16_t)~crc32_eth_calc_pclmulqdq(data,
> @@ -317,18 +312,11 @@ rte_crc16_ccitt_sse42_handler(const uint8_t *data,
> &crc16_ccitt_pclmulqdq);
> }
>
> -static inline uint32_t
> -rte_crc32_eth_sse42_handler(const uint8_t *data,
> - uint32_t data_len)
> +uint32_t
> +rte_crc32_eth_sse42_handler(const uint8_t *data, uint32_t data_len)
> {
> return ~crc32_eth_calc_pclmulqdq(data,
> data_len,
> 0xffffffffUL,
> &crc32_eth_pclmulqdq);
> }
> -
> -#ifdef __cplusplus
> -}
> -#endif
> -
> -#endif /* _RTE_NET_CRC_SSE_H_ */
> diff --git a/lib/librte_net/rte_net_crc.c b/lib/librte_net/rte_net_crc.c index
> 4f5b9e828..d271d5205 100644
> --- a/lib/librte_net/rte_net_crc.c
> +++ b/lib/librte_net/rte_net_crc.c
> @@ -1,5 +1,5 @@
> /* SPDX-License-Identifier: BSD-3-Clause
> - * Copyright(c) 2017 Intel Corporation
> + * Copyright(c) 2017-2020 Intel Corporation
> */
>
> #include <stddef.h>
> @@ -10,17 +10,7 @@
> #include <rte_common.h>
> #include <rte_net_crc.h>
>
> -#if defined(RTE_ARCH_X86_64) && defined(__PCLMUL__)
> -#define X86_64_SSE42_PCLMULQDQ 1
> -#elif defined(RTE_ARCH_ARM64) && defined(__ARM_FEATURE_CRYPTO)
> -#define ARM64_NEON_PMULL 1
> -#endif
> -
> -#ifdef X86_64_SSE42_PCLMULQDQ
> -#include <net_crc_sse.h>
> -#elif defined ARM64_NEON_PMULL
> -#include <net_crc_neon.h>
> -#endif
> +#include "net_crc.h"
>
> /** CRC polynomials */
> #define CRC32_ETH_POLYNOMIAL 0x04c11db7UL @@ -41,25 +31,27 @@
> rte_crc32_eth_handler(const uint8_t *data, uint32_t data_len); typedef
> uint32_t (*rte_net_crc_handler)(const uint8_t *data, uint32_t data_len);
>
> -static rte_net_crc_handler *handlers;
> +static const rte_net_crc_handler *handlers;
>
> -static rte_net_crc_handler handlers_scalar[] = {
> +static const rte_net_crc_handler handlers_scalar[] = {
> [RTE_NET_CRC16_CCITT] = rte_crc16_ccitt_handler,
> [RTE_NET_CRC32_ETH] = rte_crc32_eth_handler, };
> -
> -#ifdef X86_64_SSE42_PCLMULQDQ
> -static rte_net_crc_handler handlers_sse42[] = {
> +#ifdef CC_X86_64_SSE42_PCLMULQDQ_SUPPORT static const
> +rte_net_crc_handler handlers_sse42[] = {
> [RTE_NET_CRC16_CCITT] = rte_crc16_ccitt_sse42_handler,
> [RTE_NET_CRC32_ETH] = rte_crc32_eth_sse42_handler, }; -#elif
> defined ARM64_NEON_PMULL -static rte_net_crc_handler handlers_neon[]
> = {
> +#endif
> +#ifdef CC_ARM64_NEON_PMULL_SUPPORT
> +static const rte_net_crc_handler handlers_neon[] = {
> [RTE_NET_CRC16_CCITT] = rte_crc16_ccitt_neon_handler,
> [RTE_NET_CRC32_ETH] = rte_crc32_eth_neon_handler, }; #endif
>
> +/* Scalar handling */
> +
> /**
> * Reflect the bits about the middle
> *
> @@ -142,29 +134,82 @@ rte_crc32_eth_handler(const uint8_t *data,
> uint32_t data_len)
> crc32_eth_lut);
> }
>
> +/* SSE4.2/PCLMULQDQ handling */
> +
> +#define SSE42_PCLMULQDQ_CPU_SUPPORTED \
> + rte_cpu_get_flag_enabled(RTE_CPUFLAG_PCLMULQDQ)
> +
> +static const rte_net_crc_handler *
> +sse42_pclmulqdq_get_handlers(void)
> +{
> +#ifdef CC_X86_64_SSE42_PCLMULQDQ_SUPPORT
> + if (SSE42_PCLMULQDQ_CPU_SUPPORTED)
> + return handlers_sse42;
> +#endif
> + return NULL;
> +}
> +
> +static uint8_t
> +sse42_pclmulqdq_init(void)
> +{
> +#ifdef CC_X86_64_SSE42_PCLMULQDQ_SUPPORT
> + if (SSE42_PCLMULQDQ_CPU_SUPPORTED) {
> + rte_net_crc_sse42_init();
> + return 1;
> + }
> +#endif
> + return 0;
> +}
> +
> +/* NEON/PMULL handling */
> +
> +#define NEON_PMULL_CPU_SUPPORTED \
> + rte_cpu_get_flag_enabled(RTE_CPUFLAG_PMULL)
> +
> +static const rte_net_crc_handler *
> +neon_pmull_get_handlers(void)
> +{
> +#ifdef CC_ARM64_NEON_PMULL_SUPPORT
> + if (NEON_PMULL_CPU_SUPPORTED)
> + return handlers_neon;
> +#endif
> + return NULL;
> +}
> +
> +static uint8_t
> +neon_pmull_init(void)
> +{
> +#ifdef CC_ARM64_NEON_PMULL_SUPPORT
> + if (NEON_PMULL_CPU_SUPPORTED) {
> + rte_net_crc_neon_init();
> + return 1;
> + }
> +#endif
> + return 0;
> +}
> +
> +/* Public API */
> +
> void
> rte_net_crc_set_alg(enum rte_net_crc_alg alg) {
> + handlers = NULL;
> +
> switch (alg) {
> -#ifdef X86_64_SSE42_PCLMULQDQ
> case RTE_NET_CRC_SSE42:
> - handlers = handlers_sse42;
> - break;
> -#elif defined ARM64_NEON_PMULL
> - /* fall-through */
> + handlers = sse42_pclmulqdq_get_handlers();
> + break; /* for x86, always break here */
> case RTE_NET_CRC_NEON:
> - if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_PMULL)) {
> - handlers = handlers_neon;
> - break;
> - }
> -#endif
> + handlers = neon_pmull_get_handlers();
> /* fall-through */
> case RTE_NET_CRC_SCALAR:
> /* fall-through */
> default:
> - handlers = handlers_scalar;
> break;
> }
> +
> + if (handlers == NULL)
> + handlers = handlers_scalar;
> }
>
> uint32_t
> @@ -188,15 +233,10 @@ RTE_INIT(rte_net_crc_init)
>
> rte_net_crc_scalar_init();
>
> -#ifdef X86_64_SSE42_PCLMULQDQ
> - alg = RTE_NET_CRC_SSE42;
> - rte_net_crc_sse42_init();
> -#elif defined ARM64_NEON_PMULL
> - if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_PMULL)) {
> + if (sse42_pclmulqdq_init())
> + alg = RTE_NET_CRC_SSE42;
> + if (neon_pmull_init())
> alg = RTE_NET_CRC_NEON;
> - rte_net_crc_neon_init();
> - }
> -#endif
>
> rte_net_crc_set_alg(alg);
> }
> --
> 2.12.3
The change looks good to me.
Reviewed-by: Ruifeng Wang <ruifeng.w...@arm.com>
