tunables: Add IFUNC selection and cache sizes

On Wed, Jun 21, 2017 at 9:42 AM, Siddhesh Poyarekar <siddhesh@gotplt.org> wrote:
> On Wednesday 21 June 2017 08:21 PM, H.J. Lu wrote:
>>> This block is no longer valid since the tunables are not read for setxid
>>> binaries.  If you want to make a case for hwcaps to be read in setxid
>>> binaries, then it should be made along with hwcap_mask since they're
>>> essentially the same feature for different machines.
>>>
>>
>> Here is the updated patch.  OK for master?
>>
>
> That looks like an outdated patch; attached by mistake?

Oops.  Here is the right one.

Sorry for that.

On Wednesday 21 June 2017 10:18 PM, H.J. Lu wrote:
> Oops.  Here is the right one.
> 
> Sorry for that.
> 
> 
> 0001-x86-Rename-glibc.tune.ifunc-to-glibc.tune.hwcaps.patch

Looks good.

Thanks,
Siddhesh

> From e5a2f128a7ce24daa377c6888b4940ae7cb7efd0 Mon Sep 17 00:00:00 2001
> From: "H.J. Lu" <hjl.tools@gmail.com>
> Date: Wed, 21 Jun 2017 05:38:03 -0700
> Subject: [PATCH] x86: Rename glibc.tune.ifunc to glibc.tune.hwcaps
> 
> Rename glibc.tune.ifunc to glibc.tune.hwcaps and move it to
> sysdeps/x86/dl-tunables.list since it is x86 specicifc.  Also
> change type of data_cache_size, data_cache_size and
> non_temporal_threshold to unsigned long int to match size_t.
> Remove usage DEFAULT_STRLEN from cpu-tunables.c.
> 
> 	* elf/dl-tunables.list (glibc.tune.ifunc): Removed.
> 	* sysdeps/x86/dl-tunables.list (glibc.tune.hwcaps): New.
> 	Remove security_level on all fields.
> 	* manual/tunables.texi: Replace ifunc with hwcaps.
> 	* sysdeps/x86/cpu-features.c (TUNABLE_CALLBACK (set_ifunc)):
> 	Renamed to ..
> 	(TUNABLE_CALLBACK (set_hwcaps)): This.
> 	(init_cpu_features): Updated.
> 	* sysdeps/x86/cpu-features.h (cpu_features): Change type of
> 	data_cache_size, data_cache_size and non_temporal_threshold to
> 	unsigned long int.
> 	* sysdeps/x86/cpu-tunables.c (DEFAULT_STRLEN): Removed.
> 	(TUNABLE_CALLBACK (set_ifunc)): Renamed to ...
> 	(TUNABLE_CALLBACK (set_hwcaps)): This.  Update comments.  Don't
> 	use DEFAULT_STRLEN.
> ---
>  elf/dl-tunables.list         |  4 ----
>  manual/tunables.texi         |  8 ++++----
>  sysdeps/x86/cpu-features.c   |  4 ++--
>  sysdeps/x86/cpu-features.h   |  6 +++---
>  sysdeps/x86/cpu-tunables.c   | 29 +++++++++++------------------
>  sysdeps/x86/dl-tunables.list |  6 +++---
>  6 files changed, 23 insertions(+), 34 deletions(-)
> 
> diff --git a/elf/dl-tunables.list b/elf/dl-tunables.list
> index b8b0ce5..df4f962 100644
> --- a/elf/dl-tunables.list
> +++ b/elf/dl-tunables.list
> @@ -83,9 +83,5 @@ glibc {
>        env_alias: LD_HWCAP_MASK
>        default: HWCAP_IMPORTANT
>        }
> -    ifunc {
> -      type: STRING
> -      security_level: SXID_IGNORE
> -    }
>    }
>  }
> diff --git a/manual/tunables.texi b/manual/tunables.texi
> index 3263f94..689e894 100644
> --- a/manual/tunables.texi
> +++ b/manual/tunables.texi
> @@ -198,8 +198,8 @@ is 8 times the number of cores online.
>  @cindex hardware capability tunables
>  @cindex hwcap tunables
>  @cindex tunables, hwcap
> -@cindex ifunc tunables
> -@cindex tunables, ifunc
> +@cindex hwcaps tunables
> +@cindex tunables, hwcaps
>  @cindex data_cache_size tunables
>  @cindex tunables, data_cache_size
>  @cindex shared_cache_size tunables
> @@ -222,8 +222,8 @@ extensions available in the processor at runtime for some architectures.  The
>  capabilities at runtime, thus disabling use of those extensions.
>  @end deftp
>  
> -@deftp Tunable glibc.tune.ifunc
> -The @code{glibc.tune.ifunc=-xxx,yyy,-zzz...} tunable allows the user to
> +@deftp Tunable glibc.tune.hwcaps
> +The @code{glibc.tune.hwcaps=-xxx,yyy,-zzz...} tunable allows the user to
>  enable CPU/ARCH feature @code{yyy}, disable CPU/ARCH feature @code{xxx}
>  and @code{zzz} where the feature name is case-sensitive and has to match
>  the ones in @code{sysdeps/x86/cpu-features.h}.
> diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c
> index 76f053a..1d087ea 100644
> --- a/sysdeps/x86/cpu-features.c
> +++ b/sysdeps/x86/cpu-features.c
> @@ -25,7 +25,7 @@
>  # include <unistd.h>		/* Get STDOUT_FILENO for _dl_printf.  */
>  # include <elf/dl-tunables.h>
>  
> -extern void TUNABLE_CALLBACK (set_ifunc) (tunable_val_t *)
> +extern void TUNABLE_CALLBACK (set_hwcaps) (tunable_val_t *)
>    attribute_hidden;
>  #endif
>  
> @@ -322,7 +322,7 @@ no_cpuid:
>    cpu_features->kind = kind;
>  
>  #if HAVE_TUNABLES
> -  TUNABLE_GET (ifunc, tunable_val_t *, TUNABLE_CALLBACK (set_ifunc));
> +  TUNABLE_GET (hwcaps, tunable_val_t *, TUNABLE_CALLBACK (set_hwcaps));
>    cpu_features->non_temporal_threshold
>      = TUNABLE_GET (x86_non_temporal_threshold, long int, NULL);
>    cpu_features->data_cache_size
> diff --git a/sysdeps/x86/cpu-features.h b/sysdeps/x86/cpu-features.h
> index fef5e18..3ed67f5 100644
> --- a/sysdeps/x86/cpu-features.h
> +++ b/sysdeps/x86/cpu-features.h
> @@ -217,12 +217,12 @@ struct cpu_features
>    unsigned int feature[FEATURE_INDEX_MAX];
>    /* Data cache size for use in memory and string routines, typically
>       L1 size.  */
> -  long int data_cache_size;
> +  unsigned long int data_cache_size;
>    /* Shared cache size for use in memory and string routines, typically
>       L2 or L3 size.  */
> -  long int shared_cache_size;
> +  unsigned long int shared_cache_size;
>    /* Threshold to use non temporal store.  */
> -  long int non_temporal_threshold;
> +  unsigned long int non_temporal_threshold;
>  };
>  
>  /* Used from outside of glibc to get access to the CPU features
> diff --git a/sysdeps/x86/cpu-tunables.c b/sysdeps/x86/cpu-tunables.c
> index 9258fb4..872dd12 100644
> --- a/sysdeps/x86/cpu-tunables.c
> +++ b/sysdeps/x86/cpu-tunables.c
> @@ -31,16 +31,12 @@
>  # if defined USE_MULTIARCH && !defined SHARED
>  #  ifdef __x86_64__
>  #   define DEFAULT_MEMCMP	__memcmp_sse2
> -#   define DEFAULT_STRLEN	__strlen_sse2
>  #  else
>  #   define DEFAULT_MEMCMP	__memcmp_ia32
> -#   define DEFAULT_STRLEN	strlen
>  #  endif
>  extern __typeof (memcmp) DEFAULT_MEMCMP;
> -extern __typeof (strlen) DEFAULT_STRLEN;
>  # else
>  #  define DEFAULT_MEMCMP	memcmp
> -#  define DEFAULT_STRLEN	strlen
>  # endif
>  
>  # define CHECK_GLIBC_IFUNC_CPU_OFF(f, cpu_features, name, len)		\
> @@ -112,30 +108,27 @@ extern __typeof (strlen) DEFAULT_STRLEN;
>  
>  attribute_hidden
>  void
> -TUNABLE_CALLBACK (set_ifunc) (tunable_val_t *valp)
> +TUNABLE_CALLBACK (set_hwcaps) (tunable_val_t *valp)
>  {
>    /* The current IFUNC selection is based on microbenchmarks in glibc.
>       It should give the best performance for most workloads.  But other
>       choices may have better performance for a particular workload or on
>       the hardware which wasn't available when the selection was made.
> -     The environment variable, GLIBC_IFUNC=-xxx,yyy,-zzz...., can be
> -     used to enable CPU/ARCH feature yyy, disable CPU/ARCH feature yyy
> -     and zzz, where the feature name is case-sensitive and has to match
> -     the ones in cpu-features.h.  It can be used by glibc developers to
> -     tune for a new processor or override the IFUNC selection to improve
> -     performance for a particular workload.
> +     The environment variable:
>  
> -     Since all CPU/ARCH features are hardware optimizations without
> -     security implication, except for Prefer_MAP_32BIT_EXEC, which can
> -     only be disabled, we check GLIBC_IFUNC for programs, including
> -     set*id ones.
> +     GLIBC_TUNABLES=glibc.tune.hwcaps=-xxx,yyy,-zzz,....
> +
> +     can be used to enable CPU/ARCH feature yyy, disable CPU/ARCH feature
> +     yyy and zzz, where the feature name is case-sensitive and has to
> +     match the ones in cpu-features.h.  It can be used by glibc developers
> +     to tune for a new processor or override the IFUNC selection to
> +     improve performance for a particular workload.
>  
>       NOTE: the IFUNC selection may change over time.  Please check all
>       multiarch implementations when experimenting.  */
>  
>    const char *p = valp->strval;
>    struct cpu_features *cpu_features = &GLRO(dl_x86_cpu_features);
> -  const char *end = p + DEFAULT_STRLEN (p);
>    size_t len;
>  
>    do
> @@ -145,7 +138,7 @@ TUNABLE_CALLBACK (set_ifunc) (tunable_val_t *valp)
>        size_t nl;
>  
>        for (c = p; *c != ','; c++)
> -	if (c >= end)
> +	if (*c == '\0')
>  	  break;
>  
>        len = c - p;
> @@ -325,6 +318,6 @@ TUNABLE_CALLBACK (set_ifunc) (tunable_val_t *valp)
>  	}
>        p += len + 1;
>      }
> -  while (p < end);
> +  while (*p != '\0');
>  }
>  #endif
> diff --git a/sysdeps/x86/dl-tunables.list b/sysdeps/x86/dl-tunables.list
> index 50c130a..99a9cc4 100644
> --- a/sysdeps/x86/dl-tunables.list
> +++ b/sysdeps/x86/dl-tunables.list
> @@ -18,17 +18,17 @@
>  
>  glibc {
>    tune {
> +    hwcaps {
> +      type: STRING
> +    }
>      x86_non_temporal_threshold {
>        type: SIZE_T
> -      security_level: SXID_IGNORE
>      }
>      x86_data_cache_size {
>        type: SIZE_T
> -      security_level: SXID_IGNORE
>      }
>      x86_shared_cache_size {
>        type: SIZE_T
> -      security_level: SXID_IGNORE
>      }
>    }
>  }
>