s390/string: Convert memset(16|32|64)() to C

Convert memset(16|32|64)() 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.

Reviewed-by: Juergen Christ <jchrist@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>

arch/s390/boot/Makefile

@@ -31,7 +31,7 @@ CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
 CFLAGS_string.o = -ffreestanding
 
 obj-y	:= head.o als.o startup.o physmem_info.o ipl_parm.o ipl_report.o vmem.o
-obj-y	+= string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o
+obj-y	+= string.o ebcdic.o sclp_early_core.o ipl_vmparm.o cmdline.o
 obj-y	+= version.o pgm_check.o ctype.o ipl_data.o relocs.o alternative.o
 obj-y	+= uv.o printk.o trampoline.o
 obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o

arch/s390/boot/mem.S

@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include "../lib/mem.S"

arch/s390/boot/string.c

@@ -43,11 +43,7 @@ ssize_t sized_strscpy(char *dst, const char *src, size_t count)
 
 void *memset64(uint64_t *s, uint64_t v, size_t count)
 {
-	uint64_t *xs = s;
-
-	while (count--)
-		*xs++ = v;
-	return s;
+	return __memset64(s, v, count * sizeof(v));
 }
 
 char *skip_spaces(const char *str)

arch/s390/lib/Makefile

@@ -10,7 +10,6 @@ CFLAGS_string.o = -ffreestanding
 
 lib-y += delay.o string.o uaccess.o find.o spinlock.o tishift.o
 lib-y += csum-partial.o
-obj-y += mem.o
 lib-$(CONFIG_KPROBES) += probes.o
 lib-$(CONFIG_UPROBES) += probes.o
 obj-$(CONFIG_S390_KPROBES_SANITY_TEST) += test_kprobes_s390.o

arch/s390/lib/mem.S

@@ -1,57 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * String handling functions.
- *
- * Copyright IBM Corp. 2012
- */
-
-#include <linux/export.h>
-#include <linux/linkage.h>
-#include <asm/nospec-insn.h>
-
-	GEN_BR_THUNK %r14
-
-/*
- * __memset16/32/64
- *
- * 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)
- */
-.macro __MEMSET bits,bytes,insn
-SYM_FUNC_START(__memset\bits)
-	ltgr	%r4,%r4
-	jz	.L__memset_exit\bits
-	cghi	%r4,\bytes
-	je	.L__memset_store\bits
-	aghi	%r4,-(\bytes+1)
-	srlg	%r5,%r4,8
-	ltgr	%r5,%r5
-	lgr	%r1,%r2
-	jz	.L__memset_remainder\bits
-.L__memset_loop\bits:
-	\insn	%r3,0(%r1)
-	mvc	\bytes(256-\bytes,%r1),0(%r1)
-	la	%r1,256(%r1)
-	brctg	%r5,.L__memset_loop\bits
-.L__memset_remainder\bits:
-	\insn	%r3,0(%r1)
-	exrl	%r4,.L__memset_mvc\bits
-	BR_EX	%r14
-.L__memset_store\bits:
-	\insn	%r3,0(%r2)
-.L__memset_exit\bits:
-	BR_EX	%r14
-.L__memset_mvc\bits:
-	mvc	\bytes(1,%r1),0(%r1)
-SYM_FUNC_END(__memset\bits)
-.endm
-
-__MEMSET 16,2,sth
-EXPORT_SYMBOL(__memset16)
-
-__MEMSET 32,4,st
-EXPORT_SYMBOL(__memset32)
-
-__MEMSET 64,8,stg
-EXPORT_SYMBOL(__memset64)

arch/s390/lib/string.c

@@ -158,6 +158,53 @@ EXPORT_SYMBOL(__memcpy);
 EXPORT_SYMBOL(memcpy);
 #endif
 
+#define DEFINE_MEMSET(_bits, _bytes, _type)					\
+void *__memset##_bits(_type *s, _type v, size_t n)				\
+{										\
+	_type *xs = s;								\
+										\
+	if (!n)									\
+		return s;							\
+	while (n >= 256) {							\
+		*xs = v;							\
+		asm volatile(							\
+			"	mvc	%[_b](256-%[_b],%[xs]),0(%[xs])\n"	\
+			:							\
+			: [xs] "a" (xs), [_b] "i" (_bytes)			\
+			: "memory");						\
+		xs = (_type *)((char *)xs + 256);				\
+		n -= 256;							\
+	}									\
+	if (!n)									\
+		return s;							\
+	*xs = v;								\
+	if (n == _bytes)							\
+		return s;							\
+	n -= _bytes + 1;							\
+	asm volatile(								\
+		"	exrl	 %[n],1f\n"					\
+		"	j	 2f\n"						\
+		"1:	mvc	 %[_b](1,%[xs]),0(%[xs])\n"			\
+		"2:"								\
+		:								\
+		: [n] "a" (n), [xs] "a" (xs), [_b] "i" (_bytes)			\
+		: "memory");							\
+	return s;								\
+}										\
+EXPORT_SYMBOL(__memset##_bits)
+
+#ifdef __HAVE_ARCH_MEMSET16
+DEFINE_MEMSET(16, 2, uint16_t);
+#endif
+
+#ifdef __HAVE_ARCH_MEMSET32
+DEFINE_MEMSET(32, 4, uint32_t);
+#endif
+
+#ifdef __HAVE_ARCH_MEMSET64
+DEFINE_MEMSET(64, 8, uint64_t);
+#endif
+
 /*
  * Helper functions to find the end of a string
  */

arch/s390/purgatory/Makefile

@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
-purgatory-y := head.o purgatory.o string.o sha256.o mem.o
+purgatory-y := head.o purgatory.o string.o sha256.o
 
 targets += $(purgatory-y) purgatory.lds purgatory purgatory.chk purgatory.ro
 PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
@@ -10,9 +10,6 @@ $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE
 
 CFLAGS_sha256.o := -D__NO_FORTIFY
 
-$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
-	$(call if_changed_rule,as_o_S)
-
 CC_FLAGS_MARCH_MINIMUM := -march=z10
 
 KBUILD_CFLAGS := $(CC_FLAGS_DIALECT) -fno-strict-aliasing -Wall -Wstrict-prototypes