[PATCH v4] eal/x86: fix memcpy alignment mask definition

Konstantin Ananyev konstantin.ananyev at huawei.com
Mon Sep 7 16:10:27 CEST 2026



> An alignment mask (ALIGNMENT_MASK) is temporarily defined for internal
> purposes, but it is publicly exposed when including the header file,
> potentially colliding with existing definitions with the same name.
> Fixed this potential issue by adding the RTE_MEMCPY_ prefix to the
> definition.
> 
> Furthermore, the superfluous function declaration at the top of the file
> was removed, and its description was moved to the function definition,
> to improve search results with source code browsers.
> 
> Also, changed "!(addrs & MASK)" to "(addrs & MASK) == 0" to follow DPDK
> coding style.
> 
> None of these changes should have any practical effect.
> 
> Fixes: f5472703c0bd ("eal: optimize aligned memcpy on x86")
> 
> Signed-off-by: Morten Brørup <mb at smartsharesystems.com>
> Acked-by: Bruce Richardson <bruce.richardson at intel.com>
> ---
> v4:
> * Really, really changed it this time.
>   When editing patch files, remember to edit the code too.
> v3:
> * Actually changed "!(addrs & MASK)" to "(addrs & MASK) == 0".
>   In v2, it was changed in my editor, but not saved to disk.
> v2:
> * Changed "!(addrs & MASK)" to "(addrs & MASK) == 0". (AI)
> ---
>  lib/eal/x86/include/rte_memcpy.h | 37 +++++++++++++++-----------------
>  1 file changed, 17 insertions(+), 20 deletions(-)
> 
> diff --git a/lib/eal/x86/include/rte_memcpy.h
> b/lib/eal/x86/include/rte_memcpy.h
> index 8ed8c55010..41fb08ab95 100644
> --- a/lib/eal/x86/include/rte_memcpy.h
> +++ b/lib/eal/x86/include/rte_memcpy.h
> @@ -32,21 +32,6 @@ extern "C" {
>  #define RTE_MEMCPY_AVX
>  #endif
> 
> -/**
> - * Copy bytes from one location to another. The locations must not overlap.
> - *
> - * @param dst
> - *   Pointer to the destination of the data.
> - * @param src
> - *   Pointer to the source data.
> - * @param n
> - *   Number of bytes to copy.
> - * @return
> - *   Pointer to the destination data.
> - */
> -static __rte_always_inline void *
> -rte_memcpy(void *__rte_restrict dst, const void *__rte_restrict src, size_t n);
> -
>  /**
>   * Copy bytes from one location to another,
>   * locations must not overlap.
> @@ -187,7 +172,7 @@ rte_mov256(uint8_t *__rte_restrict dst, const uint8_t
> *__rte_restrict src)
>   * AVX512 implementation below
>   */
> 
> -#define ALIGNMENT_MASK 0x3F
> +#define RTE_MEMCPY_ALIGNMENT_MASK 0x3F
> 
>  /**
>   * Copy 128-byte blocks from one location to another,
> @@ -333,7 +318,7 @@ rte_memcpy_generic_more_than_64(void *__rte_restrict
> dst, const void *__rte_rest
>   * AVX implementation below
>   */
> 
> -#define ALIGNMENT_MASK 0x1F
> +#define RTE_MEMCPY_ALIGNMENT_MASK 0x1F
> 
>  /**
>   * Copy 128-byte blocks from one location to another,
> @@ -444,7 +429,7 @@ rte_memcpy_generic_more_than_64(void *__rte_restrict
> dst, const void *__rte_rest
>   * SSE implementation below
>   */
> 
> -#define ALIGNMENT_MASK 0x0F
> +#define RTE_MEMCPY_ALIGNMENT_MASK 0x0F
> 
>  /**
>   * Macro for copying unaligned block from one location to another with constant
> load offset,
> @@ -673,6 +658,18 @@ rte_memcpy_aligned_more_than_64(void
> *__rte_restrict dst, const void *__rte_rest
>  	return ret;
>  }
> 
> +/**
> + * Copy bytes from one location to another. The locations must not overlap.
> + *
> + * @param dst
> + *   Pointer to the destination of the data.
> + * @param src
> + *   Pointer to the source data.
> + * @param n
> + *   Number of bytes to copy.
> + * @return
> + *   Pointer to the destination data.
> + */
>  static __rte_always_inline void *
>  rte_memcpy(void *__rte_restrict dst, const void *__rte_restrict src, size_t n)
>  {
> @@ -709,13 +706,13 @@ rte_memcpy(void *__rte_restrict dst, const void
> *__rte_restrict src, size_t n)
>  	}
> 
>  	/* Implementation for size > 64 bytes depends on alignment with vector
> register size. */
> -	if (!(((uintptr_t)dst | (uintptr_t)src) & ALIGNMENT_MASK))
> +	if ((((uintptr_t)dst | (uintptr_t)src) & RTE_MEMCPY_ALIGNMENT_MASK)
> == 0)
>  		return rte_memcpy_aligned_more_than_64(dst, src, n);
>  	else
>  		return rte_memcpy_generic_more_than_64(dst, src, n);
>  }
> 
> -#undef ALIGNMENT_MASK
> +#undef RTE_MEMCPY_ALIGNMENT_MASK
> 
>  #ifdef __cplusplus
>  }
> --
Acked-by: Konstantin Ananyev <konstantin.ananyev at huawei.com>
> 2.43.0



More information about the dev mailing list