s390: implement memset16, memset32 & memset64

Provide fast versions of the new memset variants. E.g. the generic
memset64 is ten times slower than the optimized version if used on a
whole page.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

1 files changed, 22 insertions, 0 deletions

diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h
index 8fb43319693d..aa9c3a0f59ff 100644
--- a/arch/s390/include/asm/string.h
+++ b/arch/s390/include/asm/string.h
@@ -17,6 +17,9 @@
 #define __HAVE_ARCH_MEMMOVE	/* gcc builtin & arch function */
 #define __HAVE_ARCH_MEMSCAN	/* inline & arch function */
 #define __HAVE_ARCH_MEMSET	/* gcc builtin & arch function */
+#define __HAVE_ARCH_MEMSET16	/* arch function */
+#define __HAVE_ARCH_MEMSET32	/* arch function */
+#define __HAVE_ARCH_MEMSET64	/* arch function */
 #define __HAVE_ARCH_STRCAT	/* inline & arch function */
 #define __HAVE_ARCH_STRCMP	/* arch function */
 #define __HAVE_ARCH_STRCPY	/* inline & arch function */
@@ -49,6 +52,25 @@ extern char *strstr(const char *, const char *);
 #undef __HAVE_ARCH_STRSEP
 #undef __HAVE_ARCH_STRSPN
 
+void *__memset16(uint16_t *s, uint16_t v, size_t count);
+void *__memset32(uint32_t *s, uint32_t v, size_t count);
+void *__memset64(uint64_t *s, uint64_t v, size_t count);
+
+static inline void *memset16(uint16_t *s, uint16_t v, size_t count)
+{
+	return __memset16(s, v, count * sizeof(v));
+}
+
+static inline void *memset32(uint32_t *s, uint32_t v, size_t count)
+{
+	return __memset32(s, v, count * sizeof(v));
+}
+
+static inline void *memset64(uint64_t *s, uint64_t v, size_t count)
+{
+	return __memset64(s, v, count * sizeof(v));
+}
+
 #if !defined(IN_ARCH_STRING_C) && (!defined(CONFIG_FORTIFY_SOURCE) || defined(__NO_FORTIFY))
 
 static inline void *memchr(const void * s, int c, size_t n)