From e8a83681f458d95d197bd37208fed3c3900def03 Mon Sep 17 00:00:00 2001 From: Bruce Richardson Date: Mon, 12 Oct 2020 15:51:48 +0100 Subject: [PATCH] eal/x86: fix memcpy AVX-512 enablement When testing on some x86 platforms, code compiled with meson was observed running at a different power-license level to that compiled with make. This is due to the fact that meson auto-detects the instruction sets available on the system and enabled AVX512 rte_memcpy when AVX512 was available, while on make, a build time AVX-512 flag needed to be explicitly set to enable that AVX512 rte_memcpy code path. In the absence of runtime path selection for rte_memcpy - which is complicated by it being a static inline function in a header file - we can fix this behaviour regression by similarly having a build-time option which must be set to enable the AVX-512 memcpy path. Fixes: a25a650be5f0 ("build: add infrastructure for meson and ninja builds") Fixes: 3e1bb55fd6ef ("build/x86: add SSE flags") Cc: stable@dpdk.org Signed-off-by: Bruce Richardson Tested-by: Yingya Han --- lib/librte_eal/include/generic/rte_memcpy.h | 4 ++++ lib/librte_eal/x86/include/rte_memcpy.h | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/lib/librte_eal/include/generic/rte_memcpy.h b/lib/librte_eal/include/generic/rte_memcpy.h index 701e550c31..e7f0f8eaa9 100644 --- a/lib/librte_eal/include/generic/rte_memcpy.h +++ b/lib/librte_eal/include/generic/rte_memcpy.h @@ -95,6 +95,10 @@ rte_mov256(uint8_t *dst, const uint8_t *src); * @note This is implemented as a macro, so it's address should not be taken * and care is needed as parameter expressions may be evaluated multiple times. * + * @note For x86 platforms to enable the AVX-512 memcpy implementation, set + * -DRTE_MEMCPY_AVX512 macro in CFLAGS, or define the RTE_MEMCPY_AVX512 macro + * explicitly in the source file before including the rte_memcpy header file. + * * @param dst * Pointer to the destination of the data. * @param src diff --git a/lib/librte_eal/x86/include/rte_memcpy.h b/lib/librte_eal/x86/include/rte_memcpy.h index 008a3de67f..79f381dd9b 100644 --- a/lib/librte_eal/x86/include/rte_memcpy.h +++ b/lib/librte_eal/x86/include/rte_memcpy.h @@ -45,7 +45,7 @@ extern "C" { static __rte_always_inline void * rte_memcpy(void *dst, const void *src, size_t n); -#ifdef __AVX512F__ +#if defined __AVX512F__ && defined RTE_MEMCPY_AVX512 #define ALIGNMENT_MASK 0x3F -- 2.20.1