diff mbox

[3/*,v2] Generic string strlen and rawmemchr

Message ID 20150527091858.GC27814@domone
State New
Headers show

Commit Message

Ondřej Bílka May 27, 2015, 9:18 a.m. UTC
With strlen and rawmemchr I use same idea.

As one could get rawmemchr with strlen by first xoring input and
strlen from rawmemchr by letting gcc optimize rawmemchr(x,0) these
belong together. I keep them separate now but it could change if you
want it.

 	* string/strlen.c: Use skeleton.
 	* string/rawmemchr.c: Likewise.
diff mbox

Patch

diff --git a/string/rawmemchr.c b/string/rawmemchr.c
index 05b22be..4aeaf03 100644
--- a/string/rawmemchr.c
+++ b/string/rawmemchr.c
@@ -1,10 +1,5 @@ 
 /* Copyright (C) 1991-2015 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
-   commentary by Jim Blandy (jimb@ai.mit.edu);
-   adaptation to memchr 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
@@ -20,166 +15,23 @@ 
    License along with the GNU C Library; if not, see
    <http://www.gnu.org/licenses/>.  */
 
-#ifdef HAVE_CONFIG_H
-#include <config.h>
-#endif
+#include <string.h>
+#include <stdlib.h>
 
-#undef __ptr_t
-#define __ptr_t void *
+#undef rawmemchr
+#undef __rawmemchr
 
-#if defined (_LIBC)
-# include <string.h>
-# include <memcopy.h>
-# include <stdlib.h>
-#endif
 
-#if defined (HAVE_LIMITS_H) || defined (_LIBC)
-# include <limits.h>
-#endif
+#include "string/common.h"
+#define EXPRESSION(p, c) (contains_zero (p ^ c))
+#include "string/skeleton.h"
 
-#define LONG_MAX_32_BITS 2147483647
-
-#ifndef LONG_MAX
-#define LONG_MAX LONG_MAX_32_BITS
-#endif
-
-#include <sys/types.h>
-
-#undef memchr
-
-#ifndef RAWMEMCHR
-# define RAWMEMCHR __rawmemchr
-#endif
-
-/* Find the first occurrence of C in S.  */
-__ptr_t
-RAWMEMCHR (s, c_in)
-     const __ptr_t s;
-     int c_in;
+void *
+__rawmemchr (const void *s, int c)
 {
-  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)
-      return (__ptr_t) 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.  */
-
-  if (sizeof (longword) != 4 && sizeof (longword) != 8)
-    abort ();
-
-#if LONG_MAX <= LONG_MAX_32_BITS
-  magic_bits = 0x7efefeff;
-#else
-  magic_bits = ((unsigned long int) 0x7efefefe << 32) | 0xfefefeff;
-#endif
-
-  /* Set up a longword, each of whose bytes is C.  */
-  charmask = c | (c << 8);
-  charmask |= charmask << 16;
-#if LONG_MAX > LONG_MAX_32_BITS
-  charmask |= charmask << 32;
-#endif
-
-  /* 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 (1)
-    {
-      /* 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.
-
-	 3) But wait!  Aren't we looking for C, not 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.  */
-
-      longword = *longword_ptr++ ^ charmask;
-
-      /* 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)
-	{
-	  /* Which of the bytes was C?  If none of them were, it was
-	     a misfire; continue the search.  */
-
-	  const unsigned char *cp = (const unsigned char *) (longword_ptr - 1);
-
-	  if (cp[0] == c)
-	    return (__ptr_t) cp;
-	  if (cp[1] == c)
-	    return (__ptr_t) &cp[1];
-	  if (cp[2] == c)
-	    return (__ptr_t) &cp[2];
-	  if (cp[3] == c)
-	    return (__ptr_t) &cp[3];
-#if LONG_MAX > 2147483647
-	  if (cp[4] == c)
-	    return (__ptr_t) &cp[4];
-	  if (cp[5] == c)
-	    return (__ptr_t) &cp[5];
-	  if (cp[6] == c)
-	    return (__ptr_t) &cp[6];
-	  if (cp[7] == c)
-	    return (__ptr_t) &cp[7];
-#endif
-	}
-    }
+  return (void *) string_skeleton (s, c, NULL);
 }
+
 libc_hidden_def (__rawmemchr)
 weak_alias (__rawmemchr, rawmemchr)
+
diff --git a/string/strlen.c b/string/strlen.c
index d066bde..2cc0369 100644
--- a/string/strlen.c
+++ b/string/strlen.c
@@ -1,8 +1,5 @@ 
 /* Copyright (C) 1991-2015 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
-   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
@@ -25,81 +22,15 @@ 
 
 /* Return the length of the null-terminated string STR.  Scan for
    the null terminator quickly by testing four bytes at a time.  */
+
+#include "string/common.h"
+#define EXPRESSION(p, c) (contains_zero (p))
+#include "string/skeleton.h"
+
 size_t
 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;
-
-  /* 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.  */
-  for (;;)
-    {
-      longword = *longword_ptr++;
-
-      if (((longword - lomagic) & ~longword & himagic) != 0)
-	{
-	  /* 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);
-
-	  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 string_skeleton (str, 0, 0) - str;
 }
+
 libc_hidden_builtin_def (strlen)