Re: [PATCH v1] x86: Fallback {str|wcs}cmp RTM in the ncmp overflow case [BZ #28896]

["H.J. Lu" <hjl.tools@gmail.com>]

On Tue, Feb 15, 2022 at 8:28 AM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
>
> In the overflow fallback strncmp-avx2-rtm and wcsncmp-avx2-rtm would
> call strcmp-avx2 and wcsncmp-avx2 respectively. This would have
> not checks around vzeroupper and would trigger spurious
> aborts. This commit fixes that.

Include a testcase?

> test-strcmp, test-strncmp, test-wcscmp, and test-wcsncmp all
> pass. Note not tested on a machine that supports RTM (non
> available).
> ---
>  sysdeps/x86_64/multiarch/strcmp-avx2.S      | 8 ++------
>  sysdeps/x86_64/multiarch/strncmp-avx2-rtm.S | 1 +
>  sysdeps/x86_64/multiarch/strncmp-avx2.S     | 1 +
>  sysdeps/x86_64/multiarch/wcsncmp-avx2-rtm.S | 2 +-
>  sysdeps/x86_64/multiarch/wcsncmp-avx2.S     | 2 +-
>  5 files changed, 6 insertions(+), 8 deletions(-)
>
> diff --git a/sysdeps/x86_64/multiarch/strcmp-avx2.S b/sysdeps/x86_64/multiarch/strcmp-avx2.S
> index 07a5a2c889..52ff5ad724 100644
> --- a/sysdeps/x86_64/multiarch/strcmp-avx2.S
> +++ b/sysdeps/x86_64/multiarch/strcmp-avx2.S
> @@ -193,10 +193,10 @@ L(ret_zero):
>         .p2align 4,, 5
>  L(one_or_less):
>         jb      L(ret_zero)
> -#  ifdef USE_AS_WCSCMP
>         /* 'nbe' covers the case where length is negative (large
>            unsigned).  */
> -       jnbe    __wcscmp_avx2
> +       jnbe    OVERFLOW_STRCMP
> +#  ifdef USE_AS_WCSCMP
>         movl    (%rdi), %edx
>         xorl    %eax, %eax
>         cmpl    (%rsi), %edx
> @@ -205,10 +205,6 @@ L(one_or_less):
>         negl    %eax
>         orl     $1, %eax
>  #  else
> -       /* 'nbe' covers the case where length is negative (large
> -          unsigned).  */
> -
> -       jnbe    __strcmp_avx2
>         movzbl  (%rdi), %eax
>         movzbl  (%rsi), %ecx
>         subl    %ecx, %eax
> diff --git a/sysdeps/x86_64/multiarch/strncmp-avx2-rtm.S b/sysdeps/x86_64/multiarch/strncmp-avx2-rtm.S
> index 37d1224bb9..68bad365ba 100644
> --- a/sysdeps/x86_64/multiarch/strncmp-avx2-rtm.S
> +++ b/sysdeps/x86_64/multiarch/strncmp-avx2-rtm.S
> @@ -1,3 +1,4 @@
>  #define STRCMP __strncmp_avx2_rtm
>  #define USE_AS_STRNCMP 1
> +#define OVERFLOW_STRCMP        __strcmp_avx2_rtm
>  #include "strcmp-avx2-rtm.S"
> diff --git a/sysdeps/x86_64/multiarch/strncmp-avx2.S b/sysdeps/x86_64/multiarch/strncmp-avx2.S
> index 1678bcc235..f138e9f1fd 100644
> --- a/sysdeps/x86_64/multiarch/strncmp-avx2.S
> +++ b/sysdeps/x86_64/multiarch/strncmp-avx2.S
> @@ -1,3 +1,4 @@
>  #define STRCMP __strncmp_avx2
>  #define USE_AS_STRNCMP 1
> +#define OVERFLOW_STRCMP __strcmp_avx2
>  #include "strcmp-avx2.S"
> diff --git a/sysdeps/x86_64/multiarch/wcsncmp-avx2-rtm.S b/sysdeps/x86_64/multiarch/wcsncmp-avx2-rtm.S
> index 4e88c70cc6..f467582cbe 100644
> --- a/sysdeps/x86_64/multiarch/wcsncmp-avx2-rtm.S
> +++ b/sysdeps/x86_64/multiarch/wcsncmp-avx2-rtm.S
> @@ -1,5 +1,5 @@
>  #define STRCMP __wcsncmp_avx2_rtm
>  #define USE_AS_STRNCMP 1
>  #define USE_AS_WCSCMP 1
> -
> +#define OVERFLOW_STRCMP        __wcscmp_avx2_rtm
>  #include "strcmp-avx2-rtm.S"
> diff --git a/sysdeps/x86_64/multiarch/wcsncmp-avx2.S b/sysdeps/x86_64/multiarch/wcsncmp-avx2.S
> index 4fa1de4d3f..e9ede522b8 100644
> --- a/sysdeps/x86_64/multiarch/wcsncmp-avx2.S
> +++ b/sysdeps/x86_64/multiarch/wcsncmp-avx2.S
> @@ -1,5 +1,5 @@
>  #define STRCMP __wcsncmp_avx2
>  #define USE_AS_STRNCMP 1
>  #define USE_AS_WCSCMP 1
> -
> +#define OVERFLOW_STRCMP        __wcscmp_avx2
>  #include "strcmp-avx2.S"
> --
> 2.25.1
>


-- 
H.J.