[PATCH v4 1/2] x86: Cleanup bounds checking in large memcpy case

[H.J. Lu]

On Wed, Jun 15, 2022 at 10:41 AM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
>
> 1. Fix incorrect lower-bound threshold in L(large_memcpy_2x).
>    Previously was using `__x86_rep_movsb_threshold` and should
>    have been using `__x86_shared_non_temporal_threshold`.
>
> 2. Avoid reloading __x86_shared_non_temporal_threshold before
>    the L(large_memcpy_4x) bounds check.
>
> 3. Document the second bounds check for L(large_memcpy_4x)
>    more clearly.
> ---
>  .../multiarch/memmove-vec-unaligned-erms.S    | 29 ++++++++++++++-----
>  1 file changed, 21 insertions(+), 8 deletions(-)
>
> diff --git a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
> index af51177d5d..d1518b8bab 100644
> --- a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
> +++ b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
> @@ -118,7 +118,13 @@
>  # define LARGE_LOAD_SIZE (VEC_SIZE * 4)
>  #endif
>
> -/* Amount to shift rdx by to compare for memcpy_large_4x.  */
> +/* Amount to shift __x86_shared_non_temporal_threshold by for
> +   bound for memcpy_large_4x. This is essentially use to to
> +   indicate that the copy is far beyond the scope of L3
> +   (assuming no user config x86_non_temporal_threshold) and to
> +   use a more aggressively unrolled loop.  NB: before
> +   increasing the value also update initialization of
> +   x86_non_temporal_threshold.  */
>  #ifndef LOG_4X_MEMCPY_THRESH
>  # define LOG_4X_MEMCPY_THRESH 4
>  #endif
> @@ -724,9 +730,14 @@ L(skip_short_movsb_check):
>         .p2align 4,, 10
>  #if (defined USE_MULTIARCH || VEC_SIZE == 16) && IS_IN (libc)
>  L(large_memcpy_2x_check):
> -       cmp     __x86_rep_movsb_threshold(%rip), %RDX_LP
> -       jb      L(more_8x_vec_check)
> +       /* Entry from L(large_memcpy_2x) has a redundant load of
> +          __x86_shared_non_temporal_threshold(%rip). L(large_memcpy_2x)
> +          is only use for the non-erms memmove which is generally less
> +          common.  */
>  L(large_memcpy_2x):
> +       mov     __x86_shared_non_temporal_threshold(%rip), %R11_LP
> +       cmp     %R11_LP, %RDX_LP
> +       jb      L(more_8x_vec_check)
>         /* To reach this point it is impossible for dst > src and
>            overlap. Remaining to check is src > dst and overlap. rcx
>            already contains dst - src. Negate rcx to get src - dst. If
> @@ -774,18 +785,21 @@ L(large_memcpy_2x):
>         /* ecx contains -(dst - src). not ecx will return dst - src - 1
>            which works for testing aliasing.  */
>         notl    %ecx
> +       movq    %rdx, %r10
>         testl   $(PAGE_SIZE - VEC_SIZE * 8), %ecx
>         jz      L(large_memcpy_4x)
>
> -       movq    %rdx, %r10
> -       shrq    $LOG_4X_MEMCPY_THRESH, %r10
> -       cmp     __x86_shared_non_temporal_threshold(%rip), %r10
> +       /* r11 has __x86_shared_non_temporal_threshold.  Shift it left
> +          by LOG_4X_MEMCPY_THRESH to get L(large_memcpy_4x) threshold.
> +        */
> +       shlq    $LOG_4X_MEMCPY_THRESH, %r11
> +       cmp     %r11, %rdx
>         jae     L(large_memcpy_4x)
>
>         /* edx will store remainder size for copying tail.  */
>         andl    $(PAGE_SIZE * 2 - 1), %edx
>         /* r10 stores outer loop counter.  */
> -       shrq    $((LOG_PAGE_SIZE + 1) - LOG_4X_MEMCPY_THRESH), %r10
> +       shrq    $(LOG_PAGE_SIZE + 1), %r10
>         /* Copy 4x VEC at a time from 2 pages.  */
>         .p2align 4
>  L(loop_large_memcpy_2x_outer):
> @@ -850,7 +864,6 @@ L(large_memcpy_2x_end):
>
>         .p2align 4
>  L(large_memcpy_4x):
> -       movq    %rdx, %r10
>         /* edx will store remainder size for copying tail.  */
>         andl    $(PAGE_SIZE * 4 - 1), %edx
>         /* r10 stores outer loop counter.  */
> --
> 2.34.1
>

LGTM.

Thanks.

-- 
H.J.