[v12,04/31] string: Improve generic strlen

  New algorithm read the first aligned address and mask off the
unwanted bytes (this strategy is similar to arch-specific
implementations used on powerpc, sparc, and sh).

The loop now read word-aligned address and check using the has_zero
macro.

Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc-linux-gnu,
and powercp64-linux-gnu by removing the arch-specific assembly
implementation and disabling multi-arch (it covers both LE and BE
for 64 and 32 bits).

Co-authored-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
---
 string/strlen.c         | 92 ++++++++++-------------------------------
 sysdeps/s390/strlen-c.c | 10 +++--
 2 files changed, 28 insertions(+), 74 deletions(-)
  

On Thu, Feb 2, 2023 at 12:12 PM Adhemerval Zanella
<adhemerval.zanella@linaro.org> wrote:
>
> New algorithm read the first aligned address and mask off the
> unwanted bytes (this strategy is similar to arch-specific
> implementations used on powerpc, sparc, and sh).
>
> The loop now read word-aligned address and check using the has_zero
> macro.
>
> Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc-linux-gnu,
> and powercp64-linux-gnu by removing the arch-specific assembly
> implementation and disabling multi-arch (it covers both LE and BE
> for 64 and 32 bits).
>
> Co-authored-by: Richard Henderson <richard.henderson@linaro.org>
> Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
> ---
>  string/strlen.c         | 92 ++++++++++-------------------------------
>  sysdeps/s390/strlen-c.c | 10 +++--
>  2 files changed, 28 insertions(+), 74 deletions(-)
>
> diff --git a/string/strlen.c b/string/strlen.c
> index ee1aae0fff..5a4424f9a5 100644
> --- a/string/strlen.c
> +++ b/string/strlen.c
> @@ -15,86 +15,38 @@
>     License along with the GNU C Library; if not, see
>     <https://www.gnu.org/licenses/>.  */
>
> +#include <libc-pointer-arith.h>
> +#include <string-fzb.h>
> +#include <string-fzc.h>
> +#include <string-fzi.h>
> +#include <string-shift.h>
>  #include <string.h>
> -#include <stdlib.h>
>
> -#undef strlen
> -
> -#ifndef STRLEN
> -# define STRLEN strlen
> +#ifdef STRLEN
> +# define __strlen STRLEN
>  #endif
>
>  /* Return the length of the null-terminated string STR.  Scan for
>     the null terminator quickly by testing four bytes at a time.  */
>  size_t
> -STRLEN (const char *str)
> +__strlen (const char *str)
>  {
> -  const char *char_ptr;
> -  const unsigned long int *longword_ptr;
> -  unsigned long int longword, himagic, lomagic;
> -
> -  /* Handle the first few characters by reading one character at a time.
> -     Do this until CHAR_PTR is aligned on a longword boundary.  */
> -  for (char_ptr = str; ((unsigned long int) char_ptr
> -                       & (sizeof (longword) - 1)) != 0;
> -       ++char_ptr)
> -    if (*char_ptr == '\0')
> -      return char_ptr - str;
> -
> -  /* All these elucidatory comments refer to 4-byte longwords,
> -     but the theory applies equally well to 8-byte longwords.  */
> -
> -  longword_ptr = (unsigned long int *) char_ptr;
> +  /* Align pointer to sizeof op_t.  */
> +  const uintptr_t s_int = (uintptr_t) str;
> +  const op_t *word_ptr = (const op_t*) PTR_ALIGN_DOWN (str, sizeof (op_t));
>
> -  /* Computing (longword - lomagic) sets the high bit of any corresponding
> -     byte that is either zero or greater than 0x80.  The latter case can be
> -     filtered out by computing (~longword & himagic).  The final result
> -     will always be non-zero if one of the bytes of longword is zero.  */
> -  himagic = 0x80808080L;
> -  lomagic = 0x01010101L;
> -  if (sizeof (longword) > 4)
> -    {
> -      /* 64-bit version of the magic.  */
> -      /* Do the shift in two steps to avoid a warning if long has 32 bits.  */
> -      himagic = ((himagic << 16) << 16) | himagic;
> -      lomagic = ((lomagic << 16) << 16) | lomagic;
> -    }
> -  if (sizeof (longword) > 8)
> -    abort ();
> +  op_t word = *word_ptr;
> +  find_t mask = shift_find (find_zero_all (word), s_int);
> +  if (mask != 0)
> +    return index_first (mask);
>
> -  /* Instead of the traditional loop which tests each character,
> -     we will test a longword at a time.  The tricky part is testing
> -     if *any of the four* bytes in the longword in question are zero.  */
> -  for (;;)
> -    {
> -      longword = *longword_ptr++;
> +  do
> +    word = *++word_ptr;
> +  while (! has_zero (word));
>
> -      if (((longword - lomagic) & ~longword & himagic) != 0)
> -       {
> -         /* Which of the bytes was the zero?  */
> -
> -         const char *cp = (const char *) (longword_ptr - 1);
> -
> -         if (cp[0] == 0)
> -           return cp - str;
> -         if (cp[1] == 0)
> -           return cp - str + 1;
> -         if (cp[2] == 0)
> -           return cp - str + 2;
> -         if (cp[3] == 0)
> -           return cp - str + 3;
> -         if (sizeof (longword) > 4)
> -           {
> -             if (cp[4] == 0)
> -               return cp - str + 4;
> -             if (cp[5] == 0)
> -               return cp - str + 5;
> -             if (cp[6] == 0)
> -               return cp - str + 6;
> -             if (cp[7] == 0)
> -               return cp - str + 7;
> -           }
> -       }
> -    }
> +  return ((const char *) word_ptr) + index_first_zero (word) - str;
>  }
> +#ifndef STRLEN
> +weak_alias (__strlen, strlen)
>  libc_hidden_builtin_def (strlen)
> +#endif
> diff --git a/sysdeps/s390/strlen-c.c b/sysdeps/s390/strlen-c.c
> index b829ef2452..0a33a6f8e5 100644
> --- a/sysdeps/s390/strlen-c.c
> +++ b/sysdeps/s390/strlen-c.c
> @@ -21,12 +21,14 @@
>  #if HAVE_STRLEN_C
>  # if HAVE_STRLEN_IFUNC
>  #  define STRLEN STRLEN_C
> +# endif
> +
> +# include <string/strlen.c>
> +
> +# if HAVE_STRLEN_IFUNC
>  #  if defined SHARED && IS_IN (libc)
> -#   undef libc_hidden_builtin_def
> -#   define libc_hidden_builtin_def(name)               \
> -  __hidden_ver1 (__strlen_c, __GI_strlen, __strlen_c);
> +__hidden_ver1 (__strlen_c, __GI_strlen, __strlen_c);
>  #  endif
>  # endif
>
> -# include <string/strlen.c>
>  #endif
> --
> 2.34.1
>

LGTM.
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>