[PATCH 0/8] s390/string: Convert various functions to C

[PATCH 0/8] s390/string: Convert various functions to C

[Heiko Carstens]

While working on something else I stumbled again across the various mem*()
helper functions, which were implemented in assembler to avoid recursive
calls [1], when using the compiler's builtin functions.

Convert the functions back to C using inline assemblies, which makes them
hopefully a bit more readable and maintainable. Also improve the memmove()
implementation by using the mvcrl instruction for the backward copy case.

Thanks,
Heiko

[1] commit 535c611ddd3e ("s390/string: provide asm lib functions for memcpy and memcmp")

Heiko Carstens (8):
  s390/purgatory: Enforce z10 minimum architecture level
  s390: Add .noinstr.text to boot and purgatory linker scripts
  s390/string: Convert memmove() to C
  s390/string: Convert memset() to C
  s390/string: Convert memset() to C
  s390/string: Convert memset(16|32|64)() to C
  s390/memmove: Optimize backward copy case
  s390/tishift: Convert __ashlti3(), __ashrti3(), __lshrti3() to C

 arch/s390/boot/Makefile                |   2 +-
 arch/s390/boot/mem.S                   |   2 -
 arch/s390/boot/string.c                |   6 +-
 arch/s390/boot/vmlinux.lds.S           |   1 +
 arch/s390/include/asm/asm-prototypes.h |   4 -
 arch/s390/lib/Makefile                 |   1 -
 arch/s390/lib/mem.S                    | 192 ----------------------
 arch/s390/lib/string.c                 | 210 +++++++++++++++++++++++++
 arch/s390/lib/tishift.S                |  63 --------
 arch/s390/lib/tishift.c                |  64 ++++++++
 arch/s390/lib/tishift.h                |   8 +
 arch/s390/purgatory/Makefile           |   9 +-
 arch/s390/purgatory/purgatory.lds.S    |   1 +
 13 files changed, 290 insertions(+), 273 deletions(-)
 delete mode 100644 arch/s390/boot/mem.S
 delete mode 100644 arch/s390/lib/mem.S
 delete mode 100644 arch/s390/lib/tishift.S
 create mode 100644 arch/s390/lib/tishift.c
 create mode 100644 arch/s390/lib/tishift.h

-- 
2.53.0

[PATCH 1/8] s390/purgatory: Enforce z10 minimum architecture level

[Heiko Carstens]

The purgatory code is compiled without the -march option. This means the
default architecture level of the compiler is used. This can cause
problems, e.g. if instructions used in inline assemblies are for a higher
architecture level than the default architecture level of the compiler.

Use z10 as minimum architecture level, similar to the boot code, to enforce
a defined architecture level set.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/purgatory/Makefile | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index 95a8ac45b67e..f55764d0c49e 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -13,18 +13,20 @@ 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
 KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
 KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
 KBUILD_CFLAGS += -Os -m64 -msoft-float -fno-common
 KBUILD_CFLAGS += -fno-stack-protector
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
-KBUILD_CFLAGS += -D__DISABLE_EXPORTS
+KBUILD_CFLAGS += $(CC_FLAGS_MARCH_MINIMUM) -D__DISABLE_EXPORTS
 KBUILD_CFLAGS += $(CLANG_FLAGS)
 KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 KBUILD_CFLAGS += $(call cc-option, -Wno-default-const-init-unsafe)
 KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
-KBUILD_AFLAGS += -D__DISABLE_EXPORTS
+KBUILD_AFLAGS += $(CC_FLAGS_MARCH_MINIMUM) -D__DISABLE_EXPORTS
 
 # Since we link purgatory with -r unresolved symbols are not checked, so we
 # also link a purgatory.chk binary without -r to check for unresolved symbols.
-- 
2.53.0

[PATCH 2/8] s390: Add .noinstr.text to boot and purgatory linker scripts

[Heiko Carstens]

Upcoming changes will result in a .noinstr.text section within the
boot and purgatory string.o binary. Explicitly add the new section to
avoid orphaned warnings from the linker.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/boot/vmlinux.lds.S        | 1 +
 arch/s390/purgatory/purgatory.lds.S | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S
index 070bc18babd0..d44964592541 100644
--- a/arch/s390/boot/vmlinux.lds.S
+++ b/arch/s390/boot/vmlinux.lds.S
@@ -31,6 +31,7 @@ SECTIONS
 		_text = .;	/* Text */
 		*(.text)
 		*(.text.*)
+		*(.noinstr.text)
 		INIT_TEXT
 		_etext = . ;
 	}
diff --git a/arch/s390/purgatory/purgatory.lds.S b/arch/s390/purgatory/purgatory.lds.S
index 482eb4fbcef1..387d0db4085f 100644
--- a/arch/s390/purgatory/purgatory.lds.S
+++ b/arch/s390/purgatory/purgatory.lds.S
@@ -19,6 +19,7 @@ SECTIONS
 		_text = .;	/* Text */
 		*(.text)
 		*(.text.*)
+		*(.noinstr.text)
 		_etext = . ;
 	}
 	.rodata : {
-- 
2.53.0

[PATCH 3/8] s390/string: Convert memmove() to C

[Heiko Carstens]

Convert memmove() 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    | 41 -------------------------------------
 arch/s390/lib/string.c | 46 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+), 41 deletions(-)

diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index d026debf250c..712b955ea9b4 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -11,47 +11,6 @@
 
 	GEN_BR_THUNK %r14
 
-/*
- * void *memmove(void *dest, const void *src, size_t n)
- */
-SYM_FUNC_START(__memmove)
-	ltgr	%r4,%r4
-	lgr	%r1,%r2
-	jz	.Lmemmove_exit
-	aghi	%r4,-1
-	clgr	%r2,%r3
-	jnh	.Lmemmove_forward
-	la	%r5,1(%r4,%r3)
-	clgr	%r2,%r5
-	jl	.Lmemmove_reverse
-.Lmemmove_forward:
-	srlg	%r0,%r4,8
-	ltgr	%r0,%r0
-	jz	.Lmemmove_forward_remainder
-.Lmemmove_forward_loop:
-	mvc	0(256,%r1),0(%r3)
-	la	%r1,256(%r1)
-	la	%r3,256(%r3)
-	brctg	%r0,.Lmemmove_forward_loop
-.Lmemmove_forward_remainder:
-	exrl	%r4,.Lmemmove_mvc
-.Lmemmove_exit:
-	BR_EX	%r14
-.Lmemmove_reverse:
-	ic	%r0,0(%r4,%r3)
-	stc	%r0,0(%r4,%r1)
-	brctg	%r4,.Lmemmove_reverse
-	ic	%r0,0(%r4,%r3)
-	stc	%r0,0(%r4,%r1)
-	BR_EX	%r14
-.Lmemmove_mvc:
-	mvc	0(1,%r1),0(%r3)
-SYM_FUNC_END(__memmove)
-EXPORT_SYMBOL(__memmove)
-
-SYM_FUNC_ALIAS(memmove, __memmove)
-EXPORT_SYMBOL(memmove)
-
 /*
  * memset implementation
  *
diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c
index 757f58960198..c4fa71a341a7 100644
--- a/arch/s390/lib/string.c
+++ b/arch/s390/lib/string.c
@@ -17,6 +17,52 @@
 #include <linux/export.h>
 #include <asm/asm.h>
 
+#define SYMBOL_FUNCTION_ALIAS(alias, name)		\
+asm(".globl " __stringify(alias) "\n\t"			\
+    ".set   " __stringify(alias) "," __stringify(name))
+
+#ifdef __HAVE_ARCH_MEMMOVE
+noinstr void *__memmove(void *dest, const void *src, size_t n)
+{
+	const char *s = src;
+	char *d = dest;
+
+	if (!n)
+		return dest;
+	if ((d <= s || d > s + n)) {
+		/* Forward copy */
+		while (n >= 256) {
+			asm volatile(
+				"	mvc	0(256,%[d]),0(%[s])\n"
+				:
+				: [d] "a" (d), [s] "a" (s)
+				: "memory");
+			d += 256;
+			s += 256;
+			n -= 256;
+		}
+		if (n) {
+			asm volatile(
+				"	exrl	%[n],0f\n"
+				"	j	1f\n"
+				"0:	mvc	0(1,%[d]),0(%[s])\n"
+				"1:"
+				:
+				: [d] "a" (d), [s] "a" (s), [n] "a" (n - 1)
+				: "memory");
+		}
+	} else {
+		/* Backward copy */
+		while (n--)
+			d[n] = s[n];
+	}
+	return dest;
+}
+SYMBOL_FUNCTION_ALIAS(memmove, __memmove);
+EXPORT_SYMBOL(__memmove);
+EXPORT_SYMBOL(memmove);
+#endif
+
 /*
  * Helper functions to find the end of a string
  */
-- 
2.53.0

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

[Heiko Carstens]

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 c4fa71a341a7..557ef2e5a16f 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_MEMMOVE
+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

[PATCH 5/8] s390/string: Convert memset() to C

[Heiko Carstens]

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    | 31 -------------------------------
 arch/s390/lib/string.c | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+), 31 deletions(-)

diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index a27b103d7450..d2e1ca87a568 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -11,37 +11,6 @@
 
 	GEN_BR_THUNK %r14
 
-/*
- * memcpy implementation
- *
- * void *memcpy(void *dest, const void *src, size_t n)
- */
-SYM_FUNC_START(__memcpy)
-	ltgr	%r4,%r4
-	jz	.Lmemcpy_exit
-	aghi	%r4,-1
-	srlg	%r5,%r4,8
-	ltgr	%r5,%r5
-	lgr	%r1,%r2
-	jnz	.Lmemcpy_loop
-.Lmemcpy_remainder:
-	exrl	%r4,.Lmemcpy_mvc
-.Lmemcpy_exit:
-	BR_EX	%r14
-.Lmemcpy_loop:
-	mvc	0(256,%r1),0(%r3)
-	la	%r1,256(%r1)
-	la	%r3,256(%r3)
-	brctg	%r5,.Lmemcpy_loop
-	j	.Lmemcpy_remainder
-.Lmemcpy_mvc:
-	mvc	0(1,%r1),0(%r3)
-SYM_FUNC_END(__memcpy)
-EXPORT_SYMBOL(__memcpy)
-
-SYM_FUNC_ALIAS(memcpy, __memcpy)
-EXPORT_SYMBOL(memcpy)
-
 /*
  * __memset16/32/64
  *
diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c
index 557ef2e5a16f..957a27bc2aae 100644
--- a/arch/s390/lib/string.c
+++ b/arch/s390/lib/string.c
@@ -124,6 +124,40 @@ EXPORT_SYMBOL(__memset);
 EXPORT_SYMBOL(memset);
 #endif
 
+#ifdef __HAVE_ARCH_MEMCPY
+noinstr void *__memcpy(void *dest, const void *src, size_t n)
+{
+	void *d = dest;
+
+	if (!n)
+		return d;
+	while (n >= 256) {
+		asm volatile(
+			"	mvc	0(256,%[dest]),0(%[src])"
+			:
+			: [dest] "a" (dest), [src] "a" (src)
+			: "memory");
+		dest += 256;
+		src += 256;
+		n -= 256;
+	}
+	if (!n)
+		return d;
+	asm volatile(
+		"	exrl	%[n],1f\n"
+		"	j	2f\n"
+		"1:	mvc	0(1,%[dest]),0(%[src])\n"
+		"2:"
+		:
+		: [dest] "a" (dest), [src] "a" (src), [n] "a" (n - 1)
+		: "memory");
+	return d;
+}
+SYMBOL_FUNCTION_ALIAS(memcpy, __memcpy);
+EXPORT_SYMBOL(__memcpy);
+EXPORT_SYMBOL(memcpy);
+#endif
+
 /*
  * Helper functions to find the end of a string
  */
-- 
2.53.0

[PATCH 6/8] s390/string: Convert memset(16|32|64)() to C

[Heiko Carstens]

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.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/boot/Makefile      |  2 +-
 arch/s390/boot/mem.S         |  2 --
 arch/s390/boot/string.c      |  6 +---
 arch/s390/lib/Makefile       |  1 -
 arch/s390/lib/mem.S          | 57 ------------------------------------
 arch/s390/lib/string.c       | 47 +++++++++++++++++++++++++++++
 arch/s390/purgatory/Makefile |  5 +---
 7 files changed, 50 insertions(+), 70 deletions(-)
 delete mode 100644 arch/s390/boot/mem.S
 delete mode 100644 arch/s390/lib/mem.S

diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index a1e719a79d38..08bcee4025e6 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -26,7 +26,7 @@ KBUILD_CFLAGS += $(call cc-option, -Wno-default-const-init-unsafe)
 CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
 
 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
diff --git a/arch/s390/boot/mem.S b/arch/s390/boot/mem.S
deleted file mode 100644
index b33463633f03..000000000000
--- a/arch/s390/boot/mem.S
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include "../lib/mem.S"
diff --git a/arch/s390/boot/string.c b/arch/s390/boot/string.c
index bd68161434a6..e4ad196cb720 100644
--- a/arch/s390/boot/string.c
+++ b/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)
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index 2bf47204f6ab..81bfc746931c 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -5,7 +5,6 @@
 
 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
diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
deleted file mode 100644
index d2e1ca87a568..000000000000
--- a/arch/s390/lib/mem.S
+++ /dev/null
@@ -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)
diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c
index 957a27bc2aae..120dd2960fee 100644
--- a/arch/s390/lib/string.c
+++ b/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
  */
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index f55764d0c49e..e74410bb1b88 100644
--- a/arch/s390/purgatory/Makefile
+++ b/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
-- 
2.53.0

[PATCH 7/8] s390/memmove: Optimize backward copy case

[Heiko Carstens]

memmove() copies byte wise for the backward copy case, when the mvc
instruction cannot be used. This is quite slow, but can be optimized
with the mvcrl instruction, which is available since z15.

Some numbers (measured on a shared z16 LPAR) show that the new
implementation is nearly always faster, except for the non realistic
one and two byte cases:

size    old   new
   1    2ns   3ns
   2    4ns   5ns
   4    5ns   5ns
   8    8ns   5ns
  16   12ns   6ns
  32    8ns   7ns
  64   15ns   7ns
 128   31ns   9ns
 256   64ns  10ns
 512  129ns  18ns
1024  250ns  19ns
2048  498ns  38ns

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/lib/string.c | 24 +++++++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c
index 120dd2960fee..a188ad3f53b9 100644
--- a/arch/s390/lib/string.c
+++ b/arch/s390/lib/string.c
@@ -15,6 +15,7 @@
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/export.h>
+#include <asm/facility.h>
 #include <asm/asm.h>
 
 #define SYMBOL_FUNCTION_ALIAS(alias, name)		\
@@ -51,8 +52,29 @@ noinstr void *__memmove(void *dest, const void *src, size_t n)
 				: [d] "a" (d), [s] "a" (s), [n] "a" (n - 1)
 				: "memory");
 		}
+		return dest;
+	}
+	/* Backward copy */
+	if (test_facility(61)) {
+		/* Use mvcrl instruction if available */
+		while (n >= 256) {
+			asm volatile(
+				"	lghi	%%r0,255\n"
+				"	.insn	sse,0xe50a00000000,%[d],%[s]\n"
+				: [d] "=Q" (*(d + n - 256))
+				: [s] "Q" (*(s + n - 256))
+				: "0", "memory");
+			n -= 256;
+		}
+		if (n) {
+			asm volatile(
+				"	lgr	%%r0,%[n]\n"
+				"	.insn	sse,0xe50a00000000,%[d],%[s]\n"
+				: [d] "=Q" (*d)
+				: [s] "Q" (*s), [n] "d" (n - 1)
+				: "0", "memory");
+		}
 	} else {
-		/* Backward copy */
 		while (n--)
 			d[n] = s[n];
 	}
-- 
2.53.0

[PATCH 8/8] s390/tishift: Convert __ashlti3(), __ashrti3(), __lshrti3() to C

[Heiko Carstens]

There is no reason to have __ashlti3(), __ashrti3(), and __lshrti3()
implemented in C. Convert them all to C, which allows the compiler to
optimize the code if newer instructions allow that.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/include/asm/asm-prototypes.h |  4 --
 arch/s390/lib/tishift.S                | 63 -------------------------
 arch/s390/lib/tishift.c                | 64 ++++++++++++++++++++++++++
 arch/s390/lib/tishift.h                |  8 ++++
 4 files changed, 72 insertions(+), 67 deletions(-)
 delete mode 100644 arch/s390/lib/tishift.S
 create mode 100644 arch/s390/lib/tishift.c
 create mode 100644 arch/s390/lib/tishift.h

diff --git a/arch/s390/include/asm/asm-prototypes.h b/arch/s390/include/asm/asm-prototypes.h
index 7bd1801cf241..d4da4436d02b 100644
--- a/arch/s390/include/asm/asm-prototypes.h
+++ b/arch/s390/include/asm/asm-prototypes.h
@@ -8,8 +8,4 @@
 #include <asm/nospec-branch.h>
 #include <asm-generic/asm-prototypes.h>
 
-__int128_t __ashlti3(__int128_t a, int b);
-__int128_t __ashrti3(__int128_t a, int b);
-__int128_t __lshrti3(__int128_t a, int b);
-
 #endif /* _ASM_S390_PROTOTYPES_H */
diff --git a/arch/s390/lib/tishift.S b/arch/s390/lib/tishift.S
deleted file mode 100644
index 96214f51f49b..000000000000
--- a/arch/s390/lib/tishift.S
+++ /dev/null
@@ -1,63 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-#include <linux/export.h>
-#include <linux/linkage.h>
-#include <asm/nospec-insn.h>
-
-	.section .noinstr.text, "ax"
-
-	GEN_BR_THUNK %r14
-
-SYM_FUNC_START(__ashlti3)
-	lmg	%r0,%r1,0(%r3)
-	cije	%r4,0,1f
-	lhi	%r3,64
-	sr	%r3,%r4
-	jnh	0f
-	srlg	%r3,%r1,0(%r3)
-	sllg	%r0,%r0,0(%r4)
-	sllg	%r1,%r1,0(%r4)
-	ogr	%r0,%r3
-	j	1f
-0:	sllg	%r0,%r1,-64(%r4)
-	lghi	%r1,0
-1:	stmg	%r0,%r1,0(%r2)
-	BR_EX	%r14
-SYM_FUNC_END(__ashlti3)
-EXPORT_SYMBOL(__ashlti3)
-
-SYM_FUNC_START(__ashrti3)
-	lmg	%r0,%r1,0(%r3)
-	cije	%r4,0,1f
-	lhi	%r3,64
-	sr	%r3,%r4
-	jnh	0f
-	sllg	%r3,%r0,0(%r3)
-	srlg	%r1,%r1,0(%r4)
-	srag	%r0,%r0,0(%r4)
-	ogr	%r1,%r3
-	j	1f
-0:	srag	%r1,%r0,-64(%r4)
-	srag	%r0,%r0,63
-1:	stmg	%r0,%r1,0(%r2)
-	BR_EX	%r14
-SYM_FUNC_END(__ashrti3)
-EXPORT_SYMBOL(__ashrti3)
-
-SYM_FUNC_START(__lshrti3)
-	lmg	%r0,%r1,0(%r3)
-	cije	%r4,0,1f
-	lhi	%r3,64
-	sr	%r3,%r4
-	jnh	0f
-	sllg	%r3,%r0,0(%r3)
-	srlg	%r1,%r1,0(%r4)
-	srlg	%r0,%r0,0(%r4)
-	ogr	%r1,%r3
-	j	1f
-0:	srlg	%r1,%r0,-64(%r4)
-	lghi	%r0,0
-1:	stmg	%r0,%r1,0(%r2)
-	BR_EX	%r14
-SYM_FUNC_END(__lshrti3)
-EXPORT_SYMBOL(__lshrti3)
diff --git a/arch/s390/lib/tishift.c b/arch/s390/lib/tishift.c
new file mode 100644
index 000000000000..668819531459
--- /dev/null
+++ b/arch/s390/lib/tishift.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/export.h>
+#include <linux/types.h>
+#include "tishift.h"
+
+union ti {
+	__int128_t val;
+	struct {
+		u64 high;
+		u64 low;
+	};
+};
+
+__int128_t __ashlti3(__int128_t a, int shift)
+{
+	union ti ti = { .val = a };
+
+	if (!shift)
+		return ti.val;
+	if (shift < 64) {
+		ti.high = (ti.high << shift) | (ti.low >> (64 - shift));
+		ti.low = ti.low << shift;
+	} else {
+		ti.high = ti.low << (shift - 64);
+		ti.low = 0;
+	}
+	return ti.val;
+}
+EXPORT_SYMBOL(__ashlti3);
+
+__int128_t __ashrti3(__int128_t a, int shift)
+{
+	union ti ti = { .val = a };
+
+	if (!shift)
+		return ti.val;
+	if (shift < 64) {
+		ti.low = (ti.low >> shift) | (ti.high << (64 - shift));
+		ti.high = (int64_t)ti.high >> shift;
+	} else {
+		ti.low = (int64_t)ti.high >> (shift - 64);
+		ti.high = (int64_t)ti.high >> 63;
+	}
+	return ti.val;
+}
+EXPORT_SYMBOL(__ashrti3);
+
+__int128_t __lshrti3(__int128_t a, int shift)
+{
+	union ti ti = { .val = a };
+
+	if (!shift)
+		return ti.val;
+	if (shift < 64) {
+		ti.low = (ti.low >> shift) | (ti.high << (64 - shift));
+		ti.high = ti.high >> shift;
+	} else {
+		ti.low = ti.high >> (shift - 64);
+		ti.high = 0;
+	}
+	return ti.val;
+}
+EXPORT_SYMBOL(__lshrti3);
diff --git a/arch/s390/lib/tishift.h b/arch/s390/lib/tishift.h
new file mode 100644
index 000000000000..c93327bc74f6
--- /dev/null
+++ b/arch/s390/lib/tishift.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _S390_LIB_TISHIFT_H
+
+__int128_t __ashlti3(__int128_t a, int b);
+__int128_t __ashrti3(__int128_t a, int b);
+__int128_t __lshrti3(__int128_t a, int b);
+
+#endif /* _S390_LIB_TISHIFT_H */
-- 
2.53.0