diff mbox series

[v5,2/2] x86: Add bounds `x86_non_temporal_threshold`

Message ID 20220615183240.623735-1-goldstein.w.n@gmail.com
State Superseded
Headers
Series None |

Commit Message

Noah Goldstein June 15, 2022, 6:32 p.m. UTC 
  The lower-bound (131072) and upper-bound (SIZE_MAX / 16) are assumed
by memmove-vec-unaligned-erms.

The lower-bound is needed because memmove-vec-unaligned-erms unrolls
the loop aggressively in the L(large_memset_4x) case.

The upper-bound is needed because memmove-vec-unaligned-erms
right-shifts the value of `x86_non_temporal_threshold` by
LOG_4X_MEMCPY_THRESH (4) which without a bound may overflow.

The lack of lower-bound can be a correctness issue. The lack of
upper-bound cannot.
---
 manual/tunables.texi       | 2 +-
 sysdeps/x86/dl-cacheinfo.h | 7 ++++++-
 2 files changed, 7 insertions(+), 2 deletions(-)

Comments

H.J. Lu June 15, 2022, 6:43 p.m. UTC | #1 
On Wed, Jun 15, 2022 at 11:32 AM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
>
> The lower-bound (131072) and upper-bound (SIZE_MAX / 16) are assumed
> by memmove-vec-unaligned-erms.
>
> The lower-bound is needed because memmove-vec-unaligned-erms unrolls
> the loop aggressively in the L(large_memset_4x) case.
>
> The upper-bound is needed because memmove-vec-unaligned-erms
> right-shifts the value of `x86_non_temporal_threshold` by
> LOG_4X_MEMCPY_THRESH (4) which without a bound may overflow.
>
> The lack of lower-bound can be a correctness issue. The lack of
> upper-bound cannot.
> ---
>  manual/tunables.texi       | 2 +-
>  sysdeps/x86/dl-cacheinfo.h | 7 ++++++-
>  2 files changed, 7 insertions(+), 2 deletions(-)
>
> diff --git a/manual/tunables.texi b/manual/tunables.texi
> index 1482412078..a420ed6206 100644
> --- a/manual/tunables.texi
> +++ b/manual/tunables.texi
> @@ -47,7 +47,7 @@ glibc.malloc.mxfast: 0x0 (min: 0x0, max: 0xffffffffffffffff)
>  glibc.elision.skip_lock_busy: 3 (min: -2147483648, max: 2147483647)
>  glibc.malloc.top_pad: 0x0 (min: 0x0, max: 0xffffffffffffffff)
>  glibc.cpu.x86_rep_stosb_threshold: 0x800 (min: 0x1, max: 0xffffffffffffffff)
> -glibc.cpu.x86_non_temporal_threshold: 0xc0000 (min: 0x0, max: 0xffffffffffffffff)
> +glibc.cpu.x86_non_temporal_threshold: 0xc0000 (min: 0x20000, max: 0x0fffffffffffffff)
>  glibc.cpu.x86_shstk:
>  glibc.cpu.hwcap_mask: 0x6 (min: 0x0, max: 0xffffffffffffffff)
>  glibc.malloc.mmap_max: 0 (min: -2147483648, max: 2147483647)
> diff --git a/sysdeps/x86/dl-cacheinfo.h b/sysdeps/x86/dl-cacheinfo.h
> index cc3b840f9c..b4ff385ae1 100644
> --- a/sysdeps/x86/dl-cacheinfo.h
> +++ b/sysdeps/x86/dl-cacheinfo.h
> @@ -931,8 +931,13 @@ dl_init_cacheinfo (struct cpu_features *cpu_features)
>
>    TUNABLE_SET_WITH_BOUNDS (x86_data_cache_size, data, 0, SIZE_MAX);
>    TUNABLE_SET_WITH_BOUNDS (x86_shared_cache_size, shared, 0, SIZE_MAX);
> +  /* SIZE_MAX >> 4 because memmove-vec-unaligned-erms right-shifts the value of
> +     'x86_non_temporal_threshold' by `LOG_4X_MEMCPY_THRESH` (4) and it is best
> +     if that operation cannot overflow. 0x20000 (131072) because the
> +     L(large_memset_4x) case aggressively unrolls the loop.  Both values are

How is 0x20000 computed?  Shouldn't it depend on vector size?

> +     reflected in the manual.  */
>    TUNABLE_SET_WITH_BOUNDS (x86_non_temporal_threshold, non_temporal_threshold,
> -                          0, SIZE_MAX);
> +                          0x20000, SIZE_MAX >> 4);
>    TUNABLE_SET_WITH_BOUNDS (x86_rep_movsb_threshold, rep_movsb_threshold,
>                            minimum_rep_movsb_threshold, SIZE_MAX);
>    TUNABLE_SET_WITH_BOUNDS (x86_rep_stosb_threshold, rep_stosb_threshold, 1,
> --
> 2.34.1
>
diff mbox series

Patch

diff --git a/manual/tunables.texi b/manual/tunables.texi
index 1482412078..a420ed6206 100644
--- a/manual/tunables.texi
+++ b/manual/tunables.texi
@@ -47,7 +47,7 @@  glibc.malloc.mxfast: 0x0 (min: 0x0, max: 0xffffffffffffffff)
 glibc.elision.skip_lock_busy: 3 (min: -2147483648, max: 2147483647)
 glibc.malloc.top_pad: 0x0 (min: 0x0, max: 0xffffffffffffffff)
 glibc.cpu.x86_rep_stosb_threshold: 0x800 (min: 0x1, max: 0xffffffffffffffff)
-glibc.cpu.x86_non_temporal_threshold: 0xc0000 (min: 0x0, max: 0xffffffffffffffff)
+glibc.cpu.x86_non_temporal_threshold: 0xc0000 (min: 0x20000, max: 0x0fffffffffffffff)
 glibc.cpu.x86_shstk:
 glibc.cpu.hwcap_mask: 0x6 (min: 0x0, max: 0xffffffffffffffff)
 glibc.malloc.mmap_max: 0 (min: -2147483648, max: 2147483647)
diff --git a/sysdeps/x86/dl-cacheinfo.h b/sysdeps/x86/dl-cacheinfo.h
index cc3b840f9c..b4ff385ae1 100644
--- a/sysdeps/x86/dl-cacheinfo.h
+++ b/sysdeps/x86/dl-cacheinfo.h
@@ -931,8 +931,13 @@  dl_init_cacheinfo (struct cpu_features *cpu_features)
 
   TUNABLE_SET_WITH_BOUNDS (x86_data_cache_size, data, 0, SIZE_MAX);
   TUNABLE_SET_WITH_BOUNDS (x86_shared_cache_size, shared, 0, SIZE_MAX);
+  /* SIZE_MAX >> 4 because memmove-vec-unaligned-erms right-shifts the value of
+     'x86_non_temporal_threshold' by `LOG_4X_MEMCPY_THRESH` (4) and it is best
+     if that operation cannot overflow. 0x20000 (131072) because the
+     L(large_memset_4x) case aggressively unrolls the loop.  Both values are
+     reflected in the manual.  */
   TUNABLE_SET_WITH_BOUNDS (x86_non_temporal_threshold, non_temporal_threshold,
-			   0, SIZE_MAX);
+			   0x20000, SIZE_MAX >> 4);
   TUNABLE_SET_WITH_BOUNDS (x86_rep_movsb_threshold, rep_movsb_threshold,
 			   minimum_rep_movsb_threshold, SIZE_MAX);
   TUNABLE_SET_WITH_BOUNDS (x86_rep_stosb_threshold, rep_stosb_threshold, 1,