[PATCH v6 08/17] string: Improve generic strchrnul

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

From: Adhemerval Zanella Netto <adhemerval.zanella@linaro.org>

New algorithm have the following key differences:

  - Reads first word unaligned and use string-maskoff function to
    remove unwanted data.  This strategy follow arch-specific
    optimization used on aarch64 and powerpc.

  - Use string-fz{b,i} functions.

Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc64-linux-gnu,
and powerpc-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>
---
 string/strchrnul.c                            | 153 +++---------------
 .../power4/multiarch/strchrnul-ppc32.c        |   4 -
 sysdeps/s390/strchrnul-c.c                    |   2 -
 3 files changed, 22 insertions(+), 137 deletions(-)

diff --git a/string/strchrnul.c b/string/strchrnul.c
index fa2db4b417..4a34a1be6e 100644
--- a/string/strchrnul.c
+++ b/string/strchrnul.c
@@ -1,10 +1,5 @@
 /* Copyright (C) 1991-2023 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
-   Based on strlen implementation by Torbjorn Granlund (tege@sics.se),
-   with help from Dan Sahlin (dan@sics.se) and
-   bug fix and commentary by Jim Blandy (jimb@ai.mit.edu);
-   adaptation to strchr suggested by Dick Karpinski (dick@cca.ucsf.edu),
-   and implemented by Roland McGrath (roland@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
@@ -21,146 +16,42 @@
    <https://www.gnu.org/licenses/>.  */
 
 #include <string.h>
-#include <memcopy.h>
 #include <stdlib.h>
+#include <stdint.h>
+#include <string-fza.h>
+#include <string-fzb.h>
+#include <string-fzi.h>
+#include <string-maskoff.h>
 
 #undef __strchrnul
 #undef strchrnul
 
-#ifndef STRCHRNUL
-# define STRCHRNUL __strchrnul
+#ifdef STRCHRNUL
+# define __strchrnul STRCHRNUL
 #endif
 
 /* Find the first occurrence of C in S or the final NUL byte.  */
 char *
-STRCHRNUL (const char *s, int c_in)
+__strchrnul (const char *str, int c_in)
 {
-  const unsigned char *char_ptr;
-  const unsigned long int *longword_ptr;
-  unsigned long int longword, magic_bits, charmask;
-  unsigned char c;
-
-  c = (unsigned char) c_in;
-
-  /* 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 = (const unsigned char *) s;
-       ((unsigned long int) char_ptr & (sizeof (longword) - 1)) != 0;
-       ++char_ptr)
-    if (*char_ptr == c || *char_ptr == '\0')
-      return (void *) char_ptr;
-
-  /* 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.  */
-  magic_bits = -1;
-  magic_bits = magic_bits / 0xff * 0xfe << 1 >> 1 | 1;
-
-  /* Set up a longword, each of whose bytes is C.  */
-  charmask = c | (c << 8);
-  charmask |= charmask << 16;
-  if (sizeof (longword) > 4)
-    /* Do the shift in two steps to avoid a warning if long has 32 bits.  */
-    charmask |= (charmask << 16) << 16;
-  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.  */
-  for (;;)
-    {
-      /* 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.
+  op_t repeated_c = repeat_bytes (c_in);
 
-	 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.
+  uintptr_t s_int = (uintptr_t) str;
+  const op_t *word_ptr = word_containing (str);
 
-	 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!
+  op_t word = *word_ptr;
 
-	 So it ignores everything except 128's, when they're aligned
-	 properly.
+  op_t mask = check_mask (find_zero_eq_all (word, repeated_c), s_int);
+  if (mask != 0)
+    return (char *) str + index_first (mask);
 
-	 3) But wait!  Aren't we looking for C as well as zero?
-	 Good point.  So what we do is XOR LONGWORD with a longword,
-	 each of whose bytes is C.  This turns each byte that is C
-	 into a zero.  */
+  do
+    word = *++word_ptr;
+  while (! has_zero_eq (word, repeated_c));
 
-      longword = *longword_ptr++;
-
-      /* Add MAGIC_BITS to LONGWORD.  */
-      if ((((longword + magic_bits)
-
-	    /* Set those bits that were unchanged by the addition.  */
-	    ^ ~longword)
-
-	   /* Look at only the hole bits.  If any of the hole bits
-	      are unchanged, most likely one of the bytes was a
-	      zero.  */
-	   & ~magic_bits) != 0
-
-	  /* That caught zeroes.  Now test for C.  */
-	  || ((((longword ^ charmask) + magic_bits) ^ ~(longword ^ charmask))
-	      & ~magic_bits) != 0)
-	{
-	  /* Which of the bytes was C or zero?
-	     If none of them were, it was a misfire; continue the search.  */
-
-	  const unsigned char *cp = (const unsigned char *) (longword_ptr - 1);
-
-	  if (*cp == c || *cp == '\0')
-	    return (char *) cp;
-	  if (*++cp == c || *cp == '\0')
-	    return (char *) cp;
-	  if (*++cp == c || *cp == '\0')
-	    return (char *) cp;
-	  if (*++cp == c || *cp == '\0')
-	    return (char *) cp;
-	  if (sizeof (longword) > 4)
-	    {
-	      if (*++cp == c || *cp == '\0')
-		return (char *) cp;
-	      if (*++cp == c || *cp == '\0')
-		return (char *) cp;
-	      if (*++cp == c || *cp == '\0')
-		return (char *) cp;
-	      if (*++cp == c || *cp == '\0')
-		return (char *) cp;
-	    }
-	}
-    }
-
-  /* This should never happen.  */
-  return NULL;
+  op_t found = index_first_zero_eq (word, repeated_c);
+  return (char *) word_ptr + found;
 }
-
+#ifndef STRCHRNUL
 weak_alias (__strchrnul, strchrnul)
+#endif
diff --git a/sysdeps/powerpc/powerpc32/power4/multiarch/strchrnul-ppc32.c b/sysdeps/powerpc/powerpc32/power4/multiarch/strchrnul-ppc32.c
index 88ce5dfffa..da03ac7c04 100644
--- a/sysdeps/powerpc/powerpc32/power4/multiarch/strchrnul-ppc32.c
+++ b/sysdeps/powerpc/powerpc32/power4/multiarch/strchrnul-ppc32.c
@@ -19,10 +19,6 @@
 #include <string.h>
 
 #define STRCHRNUL  __strchrnul_ppc
-
-#undef weak_alias
-#define weak_alias(a,b )
-
 extern __typeof (strchrnul) __strchrnul_ppc attribute_hidden;
 
 #include <string/strchrnul.c>
diff --git a/sysdeps/s390/strchrnul-c.c b/sysdeps/s390/strchrnul-c.c
index e1248d1dbf..ff6aa38d4f 100644
--- a/sysdeps/s390/strchrnul-c.c
+++ b/sysdeps/s390/strchrnul-c.c
@@ -22,8 +22,6 @@
 # if HAVE_STRCHRNUL_IFUNC
 #  define STRCHRNUL STRCHRNUL_C
 #  define __strchrnul STRCHRNUL
-#  undef weak_alias
-#  define weak_alias(name, alias)
 # endif
 
 # include <string/strchrnul.c>
-- 
2.34.1