Improve strtok and strtok_r performance. Instead of calling strpbrk which

calls strcspn, call strcspn directly so we get the end of the token without
an extra call to rawmemchr.  Also avoid an unnecessary call to strcspn after
the last token by adding an early exit for an empty string.  Change strtok
to tailcall strtok_r to avoid unnecessary code duplication.

Remove the special header optimization for strtok_r of a 1-character
constant string - both strspn and strcspn contain optimizations for this
case.  Benchmarking this showed similar performance in the worst case,
but up to 5.5x better performance in the "found" case for large inputs.

	* benchtests/bench-strtok.c (oldstrtok): Add old implementation.
	* string/strtok.c (strtok): Change to tailcall __strtok_r.
	* string/strtok_r.c (__strtok_r): Optimize for performance.
	* string/string-inlines.c (__old_strtok_r_1c): New function.
	* string/bits/string2.h (__strtok_r): Move to string-inlines.c.

1 files changed, 16 insertions, 15 deletions

diff --git a/string/strtok_r.c b/string/strtok_r.c
index f351304766..2d251f90d7 100644
--- a/string/strtok_r.c
+++ b/string/strtok_r.c
@@ -22,14 +22,10 @@
 
 #include <string.h>
 
-#undef strtok_r
-#undef __strtok_r
-
 #ifndef _LIBC
 /* Get specification.  */
 # include "strtok_r.h"
 # define __strtok_r strtok_r
-# define __rawmemchr strchr
 #endif
 
 /* Parse S into tokens separated by characters in DELIM.
@@ -45,11 +41,17 @@
 char *
 __strtok_r (char *s, const char *delim, char **save_ptr)
 {
-  char *token;
+  char *end;
 
   if (s == NULL)
     s = *save_ptr;
 
+  if (*s == '\0')
+    {
+      *save_ptr = s;
+      return NULL;
+    }
+
   /* Scan leading delimiters.  */
   s += strspn (s, delim);
   if (*s == '\0')
@@ -59,18 +61,17 @@ __strtok_r (char *s, const char *delim, char **save_ptr)
     }
 
   /* Find the end of the token.  */
-  token = s;
-  s = strpbrk (token, delim);
-  if (s == NULL)
-    /* This token finishes the string.  */
-    *save_ptr = __rawmemchr (token, '\0');
-  else
+  end = s + strcspn (s, delim);
+  if (*end == '\0')
     {
-      /* Terminate the token and make *SAVE_PTR point past it.  */
-      *s = '\0';
-      *save_ptr = s + 1;
+      *save_ptr = end;
+      return s;
     }
-  return token;
+
+  /* Terminate the token and make *SAVE_PTR point past it.  */
+  *end = '\0';
+  *save_ptr = end + 1;
+  return s;
 }
 #ifdef weak_alias
 libc_hidden_def (__strtok_r)