string: split strnlen, optimize strlen in assembler (DONE)

This change provides an optimized hand-written strlen function for
SuperH targets. The original plan was to declare the C-based naive
version weak and just let the linker figure out the proper one to use,
but unfortunately static libraries don't work like that; ld
intentionally stops at the first version even if it's weak. Instead,
some #ifdef's are used in the C-based strlen to not compile it when
unneeded.

The optimized strlen uses 4-byte accesses and cmp/str.

CMakeLists.txt

@@ -137,7 +137,8 @@ set(SOURCES
   src/libc/string/memset.c
   src/libc/string/strcmp.c
   src/libc/string/strdup.c
-  src/libc/string/strlen.c)
+  src/libc/string/strlen.c
+  src/libc/string/strnlen.c)
 
 if(vhex-generic IN_LIST TARGET_FOLDERS)
   # TODO
@@ -169,6 +170,7 @@ if(sh-generic IN_LIST TARGET_FOLDERS)
     src/libc/setjmp/target/sh-generic/setjmp.S
     src/libc/setjmp/target/sh-generic/longjmp.S
     src/libc/string/target/sh-generic/memchr.S
+    src/libc/string/target/sh-generic/strlen.S
     src/target/sh-generic/cpucap.c)
 endif()
 

STATUS

@@ -130,7 +130,7 @@ DONE:       Function/symbol/macro is defined, builds, links, and is tested
 !    7.21.5.8  strtok: TODO
      7.21.6.1  memset: DONE
 !    7.21.6.2  strerror: TODO
-!    7.21.6.3  strlen: TODO
+     7.21.6.3  strlen: DONE
      Extensions:
      - strnlen: TODO
      - strchrnul: TODO

src/libc/string/strlen.c

@@ -1,37 +1,12 @@
 #include <string.h>
 
-/*
+#ifndef __SUPPORT_ARCH_SH
-** The  strlen() function calculates the length of the string pointed to by s,
-** excluding the termi‐nating null byte ('\0').
-**
-** TODO: use quad-word access !
-*/
-size_t strlen(char const *str)
-{
-	size_t i;
 
-	if (str == NULL)
+size_t strlen(char const *s)
-		return (0);
+{
-	i = -1;
+	size_t i = 0;
-	while (str[++i] != '\0') ;
+	while(s[i]) i++;
-	return (i);
+	return i;
 }
 
-/*
+#endif /*__SUPPORT_ARCH_SH*/
-** The strnlen() function returns the number of bytes in the string pointed to
-** by s, excluding the terminating null byte ('\0'), but at most maxlen.
-** In doing this, strnlen() looks  only  at  the first maxlen characters in the
-** string pointed to by s and never beyond s+maxlen.
-**
-** TODO: use quad-word access !
-*/
-size_t strnlen(char const *str, size_t maxlen)
-{
-	size_t i;
-
-	if (str == NULL)
-		return (0);
-	i = -1;
-	while (str[++i] != '\0' && (size_t)i < maxlen) ;
-	return (i);
-}

src/libc/string/strnlen.c

@@ -0,0 +1,8 @@
+#include <string.h>
+
+size_t strnlen(char const *s, size_t n)
+{
+	size_t i = 0;
+	while(s[i] && i < n) i++;
+	return i;
+}

src/libc/string/target/sh-generic/strlen.S

@@ -0,0 +1,36 @@
+.global _strlen
+.type _strlen, @function
+
+_strlen:
+	mov	r4, r0
+	mov	#0, r2
+
+	/* Check 3 bytes to make sure we don't skip any when aligning */
+	mov.b	@r0+, r1
+	tst	r1, r1
+	bt	.end
+	mov.b	@r0+, r1
+	tst	r1, r1
+	bt	.end
+	mov.b	@r0+, r1
+	tst	r1, r1
+	bt	.end
+
+	/* Align to a 4-byte boundary */
+	or	#3, r0
+	xor	#3, r0
+
+	/* Read bytes by groups of 4 */
+1:	mov.l	@r0+, r1
+	cmp/str	r1, r2
+	bf	1b
+
+	/* Go back to find out which of the last 4 bytes is the NUL */
+	add	#-4, r0
+2:	mov.b	@r0+, r1
+	tst	r1, r1
+	bf	2b
+
+.end:	add	#-1, r0
+	rts
+	sub	r4, r0