[PATCH 4/*] Generic string memchr and strnlen

[OndÅej BÃlka <neleai at seznam dot cz>]

Here we first deal with functions that use size bound.
Main technical complication is pointer wraparound for large n so it
needs to be handled accordingly. Otherwise its almost same as rawmemchr.

As I wrote before that we could optimize  memchr(x,0,n) to strnlen
opposite is also true. Here strnlen uses memchr and lets gcc simply
that.

Comments?

	* string/memchr.c: Use skeleton.
	* string/strnlen.c: Likewise.

diff --git a/string/memchr.c b/string/memchr.c
index 6896465..fede01a 100644
--- a/string/memchr.c
+++ b/string/memchr.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
@@ -20,143 +15,41 @@
    License along with the GNU C Library; if not, see
    <http://www.gnu.org/licenses/>.  */
 
-#ifndef _LIBC
-# include <config.h>
-#endif
-
 #include <string.h>
-
-#include <stddef.h>
-
-#include <limits.h>
+#include <stdlib.h>
 
 #undef __memchr
-#ifdef _LIBC
-# undef memchr
-#endif
+#undef memchr
 
-#ifndef weak_alias
-# define __memchr memchr
-#endif
+/* 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 ^ c))
+#define BOUND(p) ((uintptr_t) p >= (uintptr_t) end)
+#include "string/skeleton.h"
 
 #ifndef MEMCHR
 # define MEMCHR __memchr
 #endif
 
-/* Search no more than N bytes of S for C.  */
+#ifdef STATIC
+static __always_inline
+#endif
 void *
-MEMCHR (void const *s, int c_in, size_t n)
+MEMCHR (const void *_str, int c, size_t n)
 {
-  /* On 32-bit hardware, choosing longword to be a 32-bit unsigned
-     long instead of a 64-bit uintmax_t tends to give better
-     performance.  On 64-bit hardware, unsigned long is generally 64
-     bits already.  Change this typedef to experiment with
-     performance.  */
-  typedef unsigned long int longword;
-
-  const unsigned char *char_ptr;
-  const longword *longword_ptr;
-  longword repeated_one;
-  longword repeated_c;
-  unsigned char c;
-
-  c = (unsigned char) c_in;
-
-  /* Handle the first few bytes by reading one byte at a time.
-     Do this until CHAR_PTR is aligned on a longword boundary.  */
-  for (char_ptr = (const unsigned char *) s;
-       n > 0 && (size_t) char_ptr % sizeof (longword) != 0;
-       --n, ++char_ptr)
-    if (*char_ptr == c)
-      return (void *) char_ptr;
-
-  longword_ptr = (const longword *) char_ptr;
-
-  /* All these elucidatory comments refer to 4-byte longwords,
-     but the theory applies equally well to any size longwords.  */
-
-  /* Compute auxiliary longword values:
-     repeated_one is a value which has a 1 in every byte.
-     repeated_c has c in every byte.  */
-  repeated_one = 0x01010101;
-  repeated_c = c | (c << 8);
-  repeated_c |= repeated_c << 16;
-  if (0xffffffffU < (longword) -1)
-    {
-      repeated_one |= repeated_one << 31 << 1;
-      repeated_c |= repeated_c << 31 << 1;
-      if (8 < sizeof (longword))
-	{
-	  size_t i;
-
-	  for (i = 64; i < sizeof (longword) * 8; i *= 2)
-	    {
-	      repeated_one |= repeated_one << i;
-	      repeated_c |= repeated_c << i;
-	    }
-	}
-    }
-
-  /* Instead of the traditional loop which tests each byte, 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 equal to c.  We first use an xor
-     with repeated_c.  This reduces the task to testing whether *any of the
-     four* bytes in longword1 is zero.
-
-     We compute tmp =
-       ((longword1 - repeated_one) & ~longword1) & (repeated_one << 7).
-     That is, we perform the following operations:
-       1. Subtract repeated_one.
-       2. & ~longword1.
-       3. & a mask consisting of 0x80 in every byte.
-     Consider what happens in each byte:
-       - If a byte of longword1 is zero, step 1 and 2 transform it into 0xff,
-	 and step 3 transforms it into 0x80.  A carry can also be propagated
-	 to more significant bytes.
-       - If a byte of longword1 is nonzero, let its lowest 1 bit be at
-	 position k (0 <= k <= 7); so the lowest k bits are 0.  After step 1,
-	 the byte ends in a single bit of value 0 and k bits of value 1.
-	 After step 2, the result is just k bits of value 1: 2^k - 1.  After
-	 step 3, the result is 0.  And no carry is produced.
-     So, if longword1 has only non-zero bytes, tmp is zero.
-     Whereas if longword1 has a zero byte, call j the position of the least
-     significant zero byte.  Then the result has a zero at positions 0, ...,
-     j-1 and a 0x80 at position j.  We cannot predict the result at the more
-     significant bytes (positions j+1..3), but it does not matter since we
-     already have a non-zero bit at position 8*j+7.
-
-     So, the test whether any byte in longword1 is zero is equivalent to
-     testing whether tmp is nonzero.  */
-
-  while (n >= sizeof (longword))
-    {
-      longword longword1 = *longword_ptr ^ repeated_c;
-
-      if ((((longword1 - repeated_one) & ~longword1)
-	   & (repeated_one << 7)) != 0)
-	break;
-      longword_ptr++;
-      n -= sizeof (longword);
-    }
-
-  char_ptr = (const unsigned char *) longword_ptr;
-
-  /* At this point, we know that either n < sizeof (longword), or one of the
-     sizeof (longword) bytes starting at char_ptr is == c.  On little-endian
-     machines, we could determine the first such byte without any further
-     memory accesses, just by looking at the tmp result from the last loop
-     iteration.  But this does not work on big-endian machines.  Choose code
-     that works in both cases.  */
-
-  for (; n > 0; --n, ++char_ptr)
-    {
-      if (*char_ptr == c)
-	return (void *) char_ptr;
-    }
-
-  return NULL;
+  if (n == 0)
+    return NULL;
+  char *str = (char *) _str;
+  char *end = (char *) (((uintptr_t) str) + n);
+  if ((uintptr_t) end < (uintptr_t) str)
+    end = (char *) UINTPTR_MAX;
+  char *ret = string_skeleton (str, c, end);
+  return (void *)((uintptr_t) ret < (uintptr_t) end ? ret : NULL);
 }
-#ifdef weak_alias
+
+#ifndef STATIC
 weak_alias (__memchr, memchr)
-#endif
 libc_hidden_builtin_def (memchr)
+#endif
diff --git a/string/strnlen.c b/string/strnlen.c
index 803d78b..a5917de 100644
--- a/string/strnlen.c
+++ b/string/strnlen.c
@@ -1,15 +1,10 @@
-/* Find the length of STRING, but scan at most MAXLEN characters.
-   Copyright (C) 1991-2015 Free Software Foundation, Inc.
-   Contributed by Jakub Jelinek <jakub@redhat.com>.
-
-   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).
+/* Copyright (C) 1991-2015 Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
 
    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
-   License, or (at your option) any later version.
+   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 License, or (at your option) any later version.
 
    The GNU C Library is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
@@ -17,149 +12,28 @@
    Lesser General Public License for more details.
 
    You should have received a copy of the GNU Lesser General Public
-   License along with the GNU C Library; see the file COPYING.LIB.  If
-   not, see <http://www.gnu.org/licenses/>.  */
+   License along with the GNU C Library; if not, see
+   <http://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.  */
+#undef strlen
+
+/* Return the length of the null-terminated string STR.  Scan for
+   the null terminator quickly by testing four bytes at a time.  */
 
-#ifdef STRNLEN
-# define __strnlen STRNLEN
-#endif
+#define STATIC
+#define MEMCHR memchr_static
+#include "string/memchr.c"
 
 size_t
-__strnlen (const char *str, size_t maxlen)
+__strnlen (const char *str, size_t n)
 {
-  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;
+  char *ret = MEMCHR (str, 0, n); 
+  return ret ? ret - str : n;
 }
-#ifndef STRNLEN
+
 weak_alias (__strnlen, strnlen)
-#endif
 libc_hidden_def (strnlen)
+