[PATCH v2 4/8] s390/string: Convert memset() to C

[Heiko Carstens <hca@linux.ibm.com>]

Convert memset() from assembler to C, which should make it easier to
read and change, if required. And it allows the compiler to optimize
the code, and use different instructions, except for the used inline
assemblies.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/lib/mem.S    | 63 ------------------------------------------
 arch/s390/lib/string.c | 61 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+), 63 deletions(-)

diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index 712b955ea9b4..a27b103d7450 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -11,69 +11,6 @@
 
 	GEN_BR_THUNK %r14
 
-/*
- * memset implementation
- *
- * This code corresponds to the C construct below. We do distinguish
- * between clearing (c == 0) and setting a memory array (c != 0) simply
- * because nearly all memset invocations in the kernel clear memory and
- * the xc instruction is preferred in such cases.
- *
- * void *memset(void *s, int c, size_t n)
- * {
- *	if (likely(c == 0))
- *		return __builtin_memset(s, 0, n);
- *	return __builtin_memset(s, c, n);
- * }
- */
-SYM_FUNC_START(__memset)
-	ltgr	%r4,%r4
-	jz	.Lmemset_exit
-	ltgr	%r3,%r3
-	jnz	.Lmemset_fill
-	aghi	%r4,-1
-	srlg	%r3,%r4,8
-	ltgr	%r3,%r3
-	lgr	%r1,%r2
-	jz	.Lmemset_clear_remainder
-.Lmemset_clear_loop:
-	xc	0(256,%r1),0(%r1)
-	la	%r1,256(%r1)
-	brctg	%r3,.Lmemset_clear_loop
-.Lmemset_clear_remainder:
-	exrl	%r4,.Lmemset_xc
-.Lmemset_exit:
-	BR_EX	%r14
-.Lmemset_fill:
-	cghi	%r4,1
-	lgr	%r1,%r2
-	je	.Lmemset_fill_exit
-	aghi	%r4,-2
-	srlg	%r5,%r4,8
-	ltgr	%r5,%r5
-	jz	.Lmemset_fill_remainder
-.Lmemset_fill_loop:
-	stc	%r3,0(%r1)
-	mvc	1(255,%r1),0(%r1)
-	la	%r1,256(%r1)
-	brctg	%r5,.Lmemset_fill_loop
-.Lmemset_fill_remainder:
-	stc	%r3,0(%r1)
-	exrl	%r4,.Lmemset_mvc
-	BR_EX	%r14
-.Lmemset_fill_exit:
-	stc	%r3,0(%r1)
-	BR_EX	%r14
-.Lmemset_xc:
-	xc	0(1,%r1),0(%r1)
-.Lmemset_mvc:
-	mvc	1(1,%r1),0(%r1)
-SYM_FUNC_END(__memset)
-EXPORT_SYMBOL(__memset)
-
-SYM_FUNC_ALIAS(memset, __memset)
-EXPORT_SYMBOL(memset)
-
 /*
  * memcpy implementation
  *
diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c
index 66286d486ef8..ff9c4b57b6f1 100644
--- a/arch/s390/lib/string.c
+++ b/arch/s390/lib/string.c
@@ -63,6 +63,67 @@ EXPORT_SYMBOL(__memmove);
 EXPORT_SYMBOL(memmove);
 #endif
 
+#ifdef __HAVE_ARCH_MEMSET
+noinstr void *__memset(void *s, int c, size_t n)
+{
+	char *xs = s;
+
+	if (!n)
+		return s;
+	if (!c) {
+		/* Clear memory */
+		while (n >= 256) {
+			asm volatile(
+				"	xc	 0(256,%[xs]),0(%[xs])"
+				:
+				: [xs] "a" (xs)
+				: "cc", "memory");
+			xs += 256;
+			n -= 256;
+		}
+		if (!n)
+			return s;
+		asm volatile(
+			"	exrl	%[n],0f\n"
+			"	j	1f\n"
+			"0:	xc	0(1,%[xs]),0(%[xs])\n"
+			"1:"
+			:
+			: [xs] "a" (xs), [n] "a" (n - 1)
+			: "cc", "memory");
+	} else {
+		/* Fill memory */
+		while (n >= 256) {
+			*xs = c;
+			asm volatile(
+				"	mvc	1(255,%[xs]),0(%[xs])"
+				:
+				: [xs] "a" (xs)
+				: "memory");
+			xs += 256;
+			n -= 256;
+		}
+		if (!n)
+			return s;
+		*xs = c;
+		if (n == 1)
+			return s;
+		asm volatile(
+			"	exrl	%[n],0f\n"
+			"	j	1f\n"
+			"0:	mvc	1(1,%[xs]),0(%[xs])\n"
+			"1:"
+			:
+			: [xs] "a" (xs), [n] "a" (n - 2)
+			: "memory");
+	}
+	return s;
+}
+SYMBOL_FUNCTION_ALIAS(memset, __memset);
+EXPORT_SYMBOL(__memset);
+EXPORT_SYMBOL(memset);
+#endif
+
 /*
  * Helper functions to find the end of a string
  */
-- 
2.53.0