[PATCH v5 07/17] string: Improve generic strchr

[Adhemerval Zanella <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} and string-extbyte function.

Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc-linux-gnu,
and powerpc64-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  <rth@twiddle.net>
---
 string/strchr.c         | 172 +++++++---------------------------------
 sysdeps/s390/strchr-c.c |  11 +--
 2 files changed, 34 insertions(+), 149 deletions(-)

diff --git a/string/strchr.c b/string/strchr.c
index bfd0c4e4bc..6bbee7f79d 100644
--- a/string/strchr.c
+++ b/string/strchr.c
@@ -22,164 +22,48 @@
 
 #include <string.h>
 #include <stdlib.h>
+#include <stdint.h>
+#include <string-fza.h>
+#include <string-fzb.h>
+#include <string-fzi.h>
+#include <string-extbyte.h>
+#include <string-maskoff.h>
 
 #undef strchr
+#undef index
 
-#ifndef STRCHR
-# define STRCHR strchr
+#ifdef STRCHR
+# define strchr STRCHR
 #endif
 
 /* Find the first occurrence of C in S.  */
 char *
-STRCHR (const char *s, int c_in)
+strchr (const char *s, 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)
-      return (void *) char_ptr;
-    else if (*char_ptr == '\0')
-      return NULL;
-
-  /* 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.
+  /* Set up a word, each of whose bytes is C.  */
+  unsigned char c = (unsigned char) c_in;
+  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.
+  /* Align the input address to op_t.  */
+  uintptr_t s_int = (uintptr_t) s;
+  const op_t *word_ptr = word_containing (s);
 
-	 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!
+  /* Read the first aligned word, but force bytes before the string to
+     match neither zero nor goal (we make sure the high bit of each byte
+     is 1, and the low 7 bits are all the opposite of the goal byte).  */
+  op_t bmask = create_mask (s_int);
+  op_t word = (*word_ptr | bmask) ^ (repeated_c & highbit_mask (bmask));
 
-	 So it ignores everything except 128's, when they're aligned
-	 properly.
+  while (! has_zero_eq (word, repeated_c))
+    word = *++word_ptr;
 
-	 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.  */
-
-      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)
-	    return (char *) cp;
-	  else if (*cp == '\0')
-	    return NULL;
-	  if (*++cp == c)
-	    return (char *) cp;
-	  else if (*cp == '\0')
-	    return NULL;
-	  if (*++cp == c)
-	    return (char *) cp;
-	  else if (*cp == '\0')
-	    return NULL;
-	  if (*++cp == c)
-	    return (char *) cp;
-	  else if (*cp == '\0')
-	    return NULL;
-	  if (sizeof (longword) > 4)
-	    {
-	      if (*++cp == c)
-		return (char *) cp;
-	      else if (*cp == '\0')
-		return NULL;
-	      if (*++cp == c)
-		return (char *) cp;
-	      else if (*cp == '\0')
-		return NULL;
-	      if (*++cp == c)
-		return (char *) cp;
-	      else if (*cp == '\0')
-		return NULL;
-	      if (*++cp == c)
-		return (char *) cp;
-	      else if (*cp == '\0')
-		return NULL;
-	    }
-	}
-    }
+  op_t found = index_first_zero_eq (word, repeated_c);
 
+  if (extractbyte (word, found) == c)
+    return (char *) (word_ptr) + found;
   return NULL;
 }
-
-#ifdef weak_alias
-# undef index
+#ifndef STRCHR
 weak_alias (strchr, index)
-#endif
 libc_hidden_builtin_def (strchr)
+#endif
diff --git a/sysdeps/s390/strchr-c.c b/sysdeps/s390/strchr-c.c
index 4ac3a62fba..a5a1781b1c 100644
--- a/sysdeps/s390/strchr-c.c
+++ b/sysdeps/s390/strchr-c.c
@@ -21,13 +21,14 @@
 #if HAVE_STRCHR_C
 # if HAVE_STRCHR_IFUNC
 #  define STRCHR STRCHR_C
-#  undef weak_alias
+# endif
+
+# include <string/strchr.c>
+
+# if HAVE_STRCHR_IFUNC
 #  if defined SHARED && IS_IN (libc)
-#   undef libc_hidden_builtin_def
-#   define libc_hidden_builtin_def(name)			\
-     __hidden_ver1 (__strchr_c, __GI_strchr, __strchr_c);
+__hidden_ver1 (__strchr_c, __GI_strchr, __strchr_c);
 #  endif
 # endif
 
-# include <string/strchr.c>
 #endif
-- 
2.34.1