Re: [PATCH v11 05/29] string: Improve generic strnlen with memchr

[Adhemerval Zanella Netto <adhemerval.zanella@linaro.org>]

On 01/02/23 16:39, Noah Goldstein wrote:
> On Wed, Feb 1, 2023 at 11:04 AM Adhemerval Zanella
> <adhemerval.zanella@linaro.org> wrote:
>>
>> It also cleanups the multiple inclusion by leaving the ifunc
>> implementation to undef the weak_alias and libc_hidden_def.
>>
>> Co-authored-by: Richard Henderson  <richard.henderson@linaro.org>
>> ---
>>  string/strnlen.c                              | 137 +-----------------
>>  sysdeps/i386/i686/multiarch/strnlen-c.c       |  14 +-
>>  .../power4/multiarch/strnlen-ppc32.c          |  14 +-
>>  sysdeps/s390/strnlen-c.c                      |  14 +-
>>  4 files changed, 27 insertions(+), 152 deletions(-)
>>
>> diff --git a/string/strnlen.c b/string/strnlen.c
>> index 6ff294eab1..dc23354ec8 100644
>> --- a/string/strnlen.c
>> +++ b/string/strnlen.c
>> @@ -1,10 +1,6 @@
>>  /* Find the length of STRING, but scan at most MAXLEN characters.
>>     Copyright (C) 1991-2023 Free Software Foundation, Inc.
>>
>> -   Based on strlen written by Torbjorn Granlund (tege@sics.se),
>> -   with help from Dan Sahlin (dan@sics.se);
>> -   commentary by Jim Blandy (jimb@ai.mit.edu).
>> -
>>     The GNU C Library is free software; you can redistribute it and/or
>>     modify it under the terms of the GNU Lesser General Public License as
>>     published by the Free Software Foundation; either version 2.1 of the
>> @@ -20,7 +16,6 @@
>>     not, see <https://www.gnu.org/licenses/>.  */
>>
>>  #include <string.h>
>> -#include <stdlib.h>
>>
>>  /* Find the length of S, but scan at most MAXLEN characters.  If no
>>     '\0' terminator is found in that many characters, return MAXLEN.  */
>> @@ -32,134 +27,12 @@
>>  size_t
>>  __strnlen (const char *str, size_t maxlen)
>>  {
>> -  const char *char_ptr, *end_ptr = str + maxlen;
>> -  const unsigned long int *longword_ptr;
>> -  unsigned long int longword, himagic, lomagic;
>> -
>> -  if (maxlen == 0)
>> -    return 0;
>> -
>> -  if (__glibc_unlikely (end_ptr < str))
>> -    end_ptr = (const char *) ~0UL;
>> -
>> -  /* 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')
>> -      {
>> -       if (char_ptr > end_ptr)
>> -         char_ptr = end_ptr;
>> -       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;
>> -
>> -  /* Bits 31, 24, 16, and 8 of this number are zero.  Call these bits
>> -     the "holes."  Note that there is a hole just to the left of
>> -     each byte, with an extra at the end:
>> -
>> -     bits:  01111110 11111110 11111110 11111111
>> -     bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD
>> -
>> -     The 1-bits make sure that carries propagate to the next 0-bit.
>> -     The 0-bits provide holes for carries to fall into.  */
>> -  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 ();
>> -
>> -  /* 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.  */
>> -  while (longword_ptr < (unsigned long int *) end_ptr)
>> -    {
>> -      /* We tentatively exit the loop if adding MAGIC_BITS to
>> -        LONGWORD fails to change any of the hole bits of LONGWORD.
>> -
>> -        1) Is this safe?  Will it catch all the zero bytes?
>> -        Suppose there is a byte with all zeros.  Any carry bits
>> -        propagating from its left will fall into the hole at its
>> -        least significant bit and stop.  Since there will be no
>> -        carry from its most significant bit, the LSB of the
>> -        byte to the left will be unchanged, and the zero will be
>> -        detected.
>> -
>> -        2) Is this worthwhile?  Will it ignore everything except
>> -        zero bytes?  Suppose every byte of LONGWORD has a bit set
>> -        somewhere.  There will be a carry into bit 8.  If bit 8
>> -        is set, this will carry into bit 16.  If bit 8 is clear,
>> -        one of bits 9-15 must be set, so there will be a carry
>> -        into bit 16.  Similarly, there will be a carry into bit
>> -        24.  If one of bits 24-30 is set, there will be a carry
>> -        into bit 31, so all of the hole bits will be changed.
>> -
>> -        The one misfire occurs when bits 24-30 are clear and bit
>> -        31 is set; in this case, the hole at bit 31 is not
>> -        changed.  If we had access to the processor carry flag,
>> -        we could close this loophole by putting the fourth hole
>> -        at bit 32!
>> -
>> -        So it ignores everything except 128's, when they're aligned
>> -        properly.  */
>> -
>> -      longword = *longword_ptr++;
>> -
>> -      if ((longword - lomagic) & himagic)
>> -       {
>> -         /* Which of the bytes was the zero?  If none of them were, it was
>> -            a misfire; continue the search.  */
>> -
>> -         const char *cp = (const char *) (longword_ptr - 1);
>> -
>> -         char_ptr = cp;
>> -         if (cp[0] == 0)
>> -           break;
>> -         char_ptr = cp + 1;
>> -         if (cp[1] == 0)
>> -           break;
>> -         char_ptr = cp + 2;
>> -         if (cp[2] == 0)
>> -           break;
>> -         char_ptr = cp + 3;
>> -         if (cp[3] == 0)
>> -           break;
>> -         if (sizeof (longword) > 4)
>> -           {
>> -             char_ptr = cp + 4;
>> -             if (cp[4] == 0)
>> -               break;
>> -             char_ptr = cp + 5;
>> -             if (cp[5] == 0)
>> -               break;
>> -             char_ptr = cp + 6;
>> -             if (cp[6] == 0)
>> -               break;
>> -             char_ptr = cp + 7;
>> -             if (cp[7] == 0)
>> -               break;
>> -           }
>> -       }
>> -      char_ptr = end_ptr;
>> -    }
>> -
>> -  if (char_ptr > end_ptr)
>> -    char_ptr = end_ptr;
>> -  return char_ptr - str;
>> +  const char *found = memchr (str, '\0', maxlen);
> Can be __memchr to skip PLT no?

The internal memchr alias is defined with libc_hidden_builtin_def (memchr), so
calling 'memchr' will issue the internal alias.  For instance, on loongarch 
(which uses generic strnlen):

$ objdump -t string/strnlen.os | grep memchr
0000000000000000         *UND*  0000000000000000 __GI_memchr