Merge tag 'csky-for-linus-5.19-rc1' of https://github.com/c-sky/csky-linux

Pull arch/csky updates from Guo Ren:

 - Three atomic optimizations

 - memcpy/memcpy_io optimization

 - Some coding conventions for Kbuild, removing warnings

* tag 'csky-for-linus-5.19-rc1' of https://github.com/c-sky/csky-linux:
  csky: Move $(core-y) into arch/csky/Kbuild
  csky: Remove unused core-y for dts
  csky: Remove unused $(dtb-y) from boot/Makefile
  csky: atomic: Add conditional atomic operations' optimization
  csky: atomic: Add custom atomic.h implementation
  csky: atomic: Optimize cmpxchg with acquire & release
  csky: optimize memcpy_{from,to}io() and memset_io()
  csky: Add C based string functions
  csky: Fix versioncheck warnings
  csky: patch_text: Fixup last cpu should be master
  csky: fix typos in comments

22 files changed, 562 insertions, 375 deletions

diff --git a/arch/csky/Kbuild b/arch/csky/Kbuild
index 4e39f7abdeb6..0621eaea4196 100644
--- a/arch/csky/Kbuild
+++ b/arch/csky/Kbuild
@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
+obj-y += kernel/ mm/
+
 # for cleaning
 subdir- += boot
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 75ef86605d69..21d72b078eef 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -320,6 +320,14 @@ config HOTPLUG_CPU
 	  controlled through /sys/devices/system/cpu/cpu1/hotplug/target.
 
 	  Say N if you want to disable CPU hotplug.
+
+config HAVE_EFFICIENT_UNALIGNED_STRING_OPS
+	bool "Enable EFFICIENT_UNALIGNED_STRING_OPS for abiv2"
+	depends on CPU_CK807 || CPU_CK810 || CPU_CK860
+	help
+	  Say Y here to enable EFFICIENT_UNALIGNED_STRING_OPS. Some CPU models could
+	  deal with unaligned access by hardware.
+
 endmenu
 
 source "arch/csky/Kconfig.platforms"
diff --git a/arch/csky/Makefile b/arch/csky/Makefile
index 866805077636..4e1d619fd5c6 100644
--- a/arch/csky/Makefile
+++ b/arch/csky/Makefile
@@ -61,15 +61,12 @@ KBUILD_AFLAGS += $(KBUILD_CFLAGS)
 
 head-y := arch/csky/kernel/head.o
 
-core-y += arch/csky/kernel/
-core-y += arch/csky/mm/
 core-y += arch/csky/$(CSKYABI)/
 
 libs-y += arch/csky/lib/ \
 	$(shell $(CC) $(KBUILD_CFLAGS) $(KCFLAGS) -print-libgcc-file-name)
 
 boot := arch/csky/boot
-core-y += $(boot)/dts/
 
 all: zImage
 
diff --git a/arch/csky/abiv1/Makefile b/arch/csky/abiv1/Makefile
index 601ce3b2fb85..a4b2ade0fc67 100644
--- a/arch/csky/abiv1/Makefile
+++ b/arch/csky/abiv1/Makefile
@@ -4,5 +4,3 @@ obj-y					+= bswapdi.o
 obj-y					+= bswapsi.o
 obj-y					+= cacheflush.o
 obj-y					+= mmap.o
-obj-y					+= memcpy.o
-obj-y					+= strksyms.o
diff --git a/arch/csky/abiv1/memcpy.S b/arch/csky/abiv1/memcpy.S
deleted file mode 100644
index 5078eb5169fa..000000000000
--- a/arch/csky/abiv1/memcpy.S
+++ /dev/null
@@ -1,347 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
-
-#include <linux/linkage.h>
-
-.macro	GET_FRONT_BITS rx y
-#ifdef	__cskyLE__
-	lsri	\rx, \y
-#else
-	lsli	\rx, \y
-#endif
-.endm
-
-.macro	GET_AFTER_BITS rx y
-#ifdef	__cskyLE__
-	lsli	\rx, \y
-#else
-	lsri	\rx, \y
-#endif
-.endm
-
-/* void *memcpy(void *dest, const void *src, size_t n); */
-ENTRY(memcpy)
-	mov	r7, r2
-	cmplti	r4, 4
-	bt	.L_copy_by_byte
-	mov	r6, r2
-	andi	r6, 3
-	cmpnei	r6, 0
-	jbt	.L_dest_not_aligned
-	mov	r6, r3
-	andi	r6, 3
-	cmpnei	r6, 0
-	jbt	.L_dest_aligned_but_src_not_aligned
-.L0:
-	cmplti	r4, 16
-	jbt	.L_aligned_and_len_less_16bytes
-	subi	sp, 8
-	stw	r8, (sp, 0)
-.L_aligned_and_len_larger_16bytes:
-	ldw	r1, (r3, 0)
-	ldw	r5, (r3, 4)
-	ldw	r8, (r3, 8)
-	stw	r1, (r7, 0)
-	ldw	r1, (r3, 12)
-	stw	r5, (r7, 4)
-	stw	r8, (r7, 8)
-	stw	r1, (r7, 12)
-	subi	r4, 16
-	addi	r3, 16
-	addi	r7, 16
-	cmplti	r4, 16
-	jbf	.L_aligned_and_len_larger_16bytes
-	ldw	r8, (sp, 0)
-	addi	sp, 8
-	cmpnei	r4, 0
-	jbf	.L_return
-
-.L_aligned_and_len_less_16bytes:
-	cmplti	r4, 4
-	bt	.L_copy_by_byte
-.L1:
-	ldw	r1, (r3, 0)
-	stw	r1, (r7, 0)
-	subi	r4, 4
-	addi	r3, 4
-	addi	r7, 4
-	cmplti	r4, 4
-	jbf	.L1
-	br	.L_copy_by_byte
-
-.L_return:
-	rts
-
-.L_copy_by_byte:                      /* len less than 4 bytes */
-	cmpnei	r4, 0
-	jbf	.L_return
-.L4:
-	ldb	r1, (r3, 0)
-	stb	r1, (r7, 0)
-	addi	r3, 1
-	addi	r7, 1
-	decne	r4
-	jbt	.L4
-	rts
-
-/*
- * If dest is not aligned, just copying some bytes makes the dest align.
- * Afther that, we judge whether the src is aligned.
- */
-.L_dest_not_aligned:
-	mov	r5, r3
-	rsub	r5, r5, r7
-	abs	r5, r5
-	cmplt	r5, r4
-	bt	.L_copy_by_byte
-	mov	r5, r7
-	sub	r5, r3
-	cmphs	r5, r4
-	bf	.L_copy_by_byte
-	mov	r5, r6
-.L5:
-	ldb	r1, (r3, 0)              /* makes the dest align. */
-	stb	r1, (r7, 0)
-	addi	r5, 1
-	subi	r4, 1
-	addi	r3, 1
-	addi	r7, 1
-	cmpnei	r5, 4
-	jbt	.L5
-	cmplti	r4, 4
-	jbt	.L_copy_by_byte
-	mov	r6, r3                   /* judge whether the src is aligned. */
-	andi	r6, 3
-	cmpnei	r6, 0
-	jbf	.L0
-
-/* Judge the number of misaligned, 1, 2, 3? */
-.L_dest_aligned_but_src_not_aligned:
-	mov	r5, r3
-	rsub	r5, r5, r7
-	abs	r5, r5
-	cmplt	r5, r4
-	bt	.L_copy_by_byte
-	bclri	r3, 0
-	bclri	r3, 1
-	ldw	r1, (r3, 0)
-	addi	r3, 4
-	cmpnei	r6, 2
-	bf	.L_dest_aligned_but_src_not_aligned_2bytes
-	cmpnei	r6, 3
-	bf	.L_dest_aligned_but_src_not_aligned_3bytes
-
-.L_dest_aligned_but_src_not_aligned_1byte:
-	mov	r5, r7
-	sub	r5, r3
-	cmphs	r5, r4
-	bf	.L_copy_by_byte
-	cmplti	r4, 16
-	bf	.L11
-.L10:                                     /* If the len is less than 16 bytes */
-	GET_FRONT_BITS r1 8
-	mov	r5, r1
-	ldw	r6, (r3, 0)
-	mov	r1, r6
-	GET_AFTER_BITS r6 24
-	or	r5, r6
-	stw	r5, (r7, 0)
-	subi	r4, 4
-	addi	r3, 4
-	addi	r7, 4
-	cmplti	r4, 4
-	bf	.L10
-	subi	r3, 3
-	br	.L_copy_by_byte
-.L11:
-	subi	sp, 16
-	stw	r8, (sp, 0)
-	stw	r9, (sp, 4)
-	stw	r10, (sp, 8)
-	stw	r11, (sp, 12)
-.L12:
-	ldw	r5, (r3, 0)
-	ldw	r11, (r3, 4)
-	ldw	r8, (r3, 8)
-	ldw	r9, (r3, 12)
-
-	GET_FRONT_BITS r1 8               /* little or big endian? */
-	mov	r10, r5
-	GET_AFTER_BITS r5 24
-	or	r5, r1
-
-	GET_FRONT_BITS r10 8
-	mov	r1, r11
-	GET_AFTER_BITS r11 24
-	or	r11, r10
-
-	GET_FRONT_BITS r1 8
-	mov	r10, r8
-	GET_AFTER_BITS r8 24
-	or	r8, r1
-
-	GET_FRONT_BITS r10 8
-	mov	r1, r9
-	GET_AFTER_BITS r9 24
-	or	r9, r10
-
-	stw	r5, (r7, 0)
-	stw	r11, (r7, 4)
-	stw	r8, (r7, 8)
-	stw	r9, (r7, 12)
-	subi	r4, 16
-	addi	r3, 16
-	addi	r7, 16
-	cmplti	r4, 16
-	jbf	.L12
-	ldw	r8, (sp, 0)
-	ldw	r9, (sp, 4)
-	ldw	r10, (sp, 8)
-	ldw	r11, (sp, 12)
-	addi	sp , 16
-	cmplti	r4, 4
-	bf	.L10
-	subi	r3, 3
-	br	.L_copy_by_byte
-
-.L_dest_aligned_but_src_not_aligned_2bytes:
-	cmplti	r4, 16
-	bf	.L21
-.L20:
-	GET_FRONT_BITS r1 16
-	mov	r5, r1
-	ldw	r6, (r3, 0)
-	mov	r1, r6
-	GET_AFTER_BITS r6 16
-	or	r5, r6
-	stw	r5, (r7, 0)
-	subi	r4, 4
-	addi	r3, 4
-	addi	r7, 4
-	cmplti	r4, 4
-	bf	.L20
-	subi	r3, 2
-	br	.L_copy_by_byte
-	rts
-
-.L21:	/* n > 16 */
-	subi 	sp, 16
-	stw	r8, (sp, 0)
-	stw	r9, (sp, 4)
-	stw	r10, (sp, 8)
-	stw	r11, (sp, 12)
-
-.L22:
-	ldw	r5, (r3, 0)
-	ldw	r11, (r3, 4)
-	ldw	r8, (r3, 8)
-	ldw	r9, (r3, 12)
-
-	GET_FRONT_BITS r1 16
-	mov	r10, r5
-	GET_AFTER_BITS r5 16
-	or	r5, r1
-
-	GET_FRONT_BITS r10 16
-	mov	r1, r11
-	GET_AFTER_BITS r11 16
-	or	r11, r10
-
-	GET_FRONT_BITS r1 16
-	mov	r10, r8
-	GET_AFTER_BITS r8 16
-	or	r8, r1
-
-	GET_FRONT_BITS r10 16
-	mov	r1, r9
-	GET_AFTER_BITS r9 16
-	or	r9, r10
-
-	stw	r5, (r7, 0)
-	stw	r11, (r7, 4)
-	stw	r8, (r7, 8)
-	stw	r9, (r7, 12)
-	subi	r4, 16
-	addi	r3, 16
-	addi	r7, 16
-	cmplti	r4, 16
-	jbf	.L22
-	ldw	r8, (sp, 0)
-	ldw	r9, (sp, 4)
-	ldw	r10, (sp, 8)
-	ldw	r11, (sp, 12)
-	addi	sp, 16
-	cmplti	r4, 4
-	bf	.L20
-	subi	r3, 2
-	br	.L_copy_by_byte
-
-
-.L_dest_aligned_but_src_not_aligned_3bytes:
-	cmplti	r4, 16
-	bf	.L31
-.L30:
-	GET_FRONT_BITS r1 24
-	mov	r5, r1
-	ldw	r6, (r3, 0)
-	mov	r1, r6
-	GET_AFTER_BITS r6 8
-	or	r5, r6
-	stw	r5, (r7, 0)
-	subi	r4, 4
-	addi	r3, 4
-	addi	r7, 4
-	cmplti	r4, 4
-	bf	.L30
-	subi	r3, 1
-	br	.L_copy_by_byte
-.L31:
-	subi	sp, 16
-	stw	r8, (sp, 0)
-	stw	r9, (sp, 4)
-	stw	r10, (sp, 8)
-	stw	r11, (sp, 12)
-.L32:
-	ldw	r5, (r3, 0)
-	ldw	r11, (r3, 4)
-	ldw	r8, (r3, 8)
-	ldw	r9, (r3, 12)
-
-	GET_FRONT_BITS r1 24
-	mov	r10, r5
-	GET_AFTER_BITS r5 8
-	or	r5, r1
-
-	GET_FRONT_BITS r10 24
-	mov	r1, r11
-	GET_AFTER_BITS r11 8
-	or	r11, r10
-
-	GET_FRONT_BITS r1 24
-	mov	r10, r8
-	GET_AFTER_BITS r8 8
-	or	r8, r1
-
-	GET_FRONT_BITS r10 24
-	mov	r1, r9
-	GET_AFTER_BITS r9 8
-	or	r9, r10
-
-	stw	r5, (r7, 0)
-	stw	r11, (r7, 4)
-	stw	r8, (r7, 8)
-	stw	r9, (r7, 12)
-	subi	r4, 16
-	addi	r3, 16
-	addi	r7, 16
-	cmplti	r4, 16
-	jbf	.L32
-	ldw	r8, (sp, 0)
-	ldw	r9, (sp, 4)
-	ldw	r10, (sp, 8)
-	ldw	r11, (sp, 12)
-	addi	sp, 16
-	cmplti	r4, 4
-	bf	.L30
-	subi	r3, 1
-	br	.L_copy_by_byte
diff --git a/arch/csky/abiv1/strksyms.c b/arch/csky/abiv1/strksyms.c
deleted file mode 100644
index c7ccbb27e8d7..000000000000
--- a/arch/csky/abiv1/strksyms.c
+++ /dev/null
@@ -1,6 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
-
-#include <linux/module.h>
-
-EXPORT_SYMBOL(memcpy);
diff --git a/arch/csky/abiv2/Makefile b/arch/csky/abiv2/Makefile
index c561efa5533c..ea8005fe01a8 100644
--- a/arch/csky/abiv2/Makefile
+++ b/arch/csky/abiv2/Makefile
@@ -2,9 +2,11 @@
 obj-y				+= cacheflush.o
 obj-$(CONFIG_CPU_HAS_FPU)	+= fpu.o
 obj-y				+= memcmp.o
+ifeq ($(CONFIG_HAVE_EFFICIENT_UNALIGNED_STRING_OPS), y)
 obj-y				+= memcpy.o
 obj-y				+= memmove.o
 obj-y				+= memset.o
+endif
 obj-y				+= strcmp.o
 obj-y				+= strcpy.o
 obj-y				+= strlen.o
diff --git a/arch/csky/abiv2/strksyms.c b/arch/csky/abiv2/strksyms.c
index 06da723d8202..8d1fd28c6cf9 100644
--- a/arch/csky/abiv2/strksyms.c
+++ b/arch/csky/abiv2/strksyms.c
@@ -3,10 +3,12 @@
 
 #include <linux/module.h>
 
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_STRING_OPS
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memcmp);
 EXPORT_SYMBOL(memmove);
+#endif
+EXPORT_SYMBOL(memcmp);
 EXPORT_SYMBOL(strcmp);
 EXPORT_SYMBOL(strcpy);
 EXPORT_SYMBOL(strlen);
diff --git a/arch/csky/boot/Makefile b/arch/csky/boot/Makefile
index dbc9b1bd72f0..c3cfde28f8e6 100644
--- a/arch/csky/boot/Makefile
+++ b/arch/csky/boot/Makefile
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 targets := Image zImage uImage
-targets += $(dtb-y)
 
 $(obj)/Image: vmlinux FORCE
 	$(call if_changed,objcopy)
diff --git a/arch/csky/include/asm/atomic.h b/arch/csky/include/asm/atomic.h
new file mode 100644
index 000000000000..60406ef9c2bb
--- /dev/null
+++ b/arch/csky/include/asm/atomic.h
@@ -0,0 +1,237 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_ATOMIC_H
+#define __ASM_CSKY_ATOMIC_H
+
+#ifdef CONFIG_SMP
+#include <asm-generic/atomic64.h>
+
+#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
+
+#define __atomic_acquire_fence()	__bar_brarw()
+
+#define __atomic_release_fence()	__bar_brwaw()
+
+static __always_inline int arch_atomic_read(const atomic_t *v)
+{
+	return READ_ONCE(v->counter);
+}
+static __always_inline void arch_atomic_set(atomic_t *v, int i)
+{
+	WRITE_ONCE(v->counter, i);
+}
+
+#define ATOMIC_OP(op)							\
+static __always_inline							\
+void arch_atomic_##op(int i, atomic_t *v)				\
+{									\
+	unsigned long tmp;						\
+	__asm__ __volatile__ (						\
+	"1:	ldex.w		%0, (%2)	\n"			\
+	"	" #op "		%0, %1		\n"			\
+	"	stex.w		%0, (%2)	\n"			\
+	"	bez		%0, 1b		\n"			\
+	: "=&r" (tmp)							\
+	: "r" (i), "r" (&v->counter)					\
+	: "memory");							\
+}
+
+ATOMIC_OP(add)
+ATOMIC_OP(sub)
+ATOMIC_OP(and)
+ATOMIC_OP( or)
+ATOMIC_OP(xor)
+
+#undef ATOMIC_OP
+
+#define ATOMIC_FETCH_OP(op)						\
+static __always_inline							\
+int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v)		\
+{									\
+	register int ret, tmp;						\
+	__asm__ __volatile__ (						\
+	"1:	ldex.w		%0, (%3) \n"				\
+	"	mov		%1, %0   \n"				\
+	"	" #op "		%0, %2   \n"				\
+	"	stex.w		%0, (%3) \n"				\
+	"	bez		%0, 1b   \n"				\
+		: "=&r" (tmp), "=&r" (ret)				\
+		: "r" (i), "r"(&v->counter) 				\
+		: "memory");						\
+	return ret;							\
+}
+
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static __always_inline							\
+int arch_atomic_##op##_return_relaxed(int i, atomic_t *v)		\
+{									\
+	return arch_atomic_fetch_##op##_relaxed(i, v) c_op i;		\
+}
+
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_FETCH_OP(op)						\
+	ATOMIC_OP_RETURN(op, c_op)
+
+ATOMIC_OPS(add, +)
+ATOMIC_OPS(sub, -)
+
+#define arch_atomic_fetch_add_relaxed	arch_atomic_fetch_add_relaxed
+#define arch_atomic_fetch_sub_relaxed	arch_atomic_fetch_sub_relaxed
+
+#define arch_atomic_add_return_relaxed	arch_atomic_add_return_relaxed
+#define arch_atomic_sub_return_relaxed	arch_atomic_sub_return_relaxed
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+
+#define ATOMIC_OPS(op)							\
+	ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS( or)
+ATOMIC_OPS(xor)
+
+#define arch_atomic_fetch_and_relaxed	arch_atomic_fetch_and_relaxed
+#define arch_atomic_fetch_or_relaxed	arch_atomic_fetch_or_relaxed
+#define arch_atomic_fetch_xor_relaxed	arch_atomic_fetch_xor_relaxed
+
+#undef ATOMIC_OPS
+
+#undef ATOMIC_FETCH_OP
+
+static __always_inline int
+arch_atomic_fetch_add_unless(atomic_t *v, int a, int u)
+{
+	int prev, tmp;
+
+	__asm__ __volatile__ (
+		RELEASE_FENCE
+		"1:	ldex.w		%0, (%3)	\n"
+		"	cmpne		%0, %4		\n"
+		"	bf		2f		\n"
+		"	mov		%1, %0		\n"
+		"	add		%1, %2		\n"
+		"	stex.w		%1, (%3)	\n"
+		"	bez		%1, 1b		\n"
+		FULL_FENCE
+		"2:\n"
+		: "=&r" (prev), "=&r" (tmp)
+		: "r" (a), "r" (&v->counter), "r" (u)
+		: "memory");
+
+	return prev;
+}
+#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless
+
+static __always_inline bool
+arch_atomic_inc_unless_negative(atomic_t *v)
+{
+	int rc, tmp;
+
+	__asm__ __volatile__ (
+		RELEASE_FENCE
+		"1:	ldex.w		%0, (%2)	\n"
+		"	movi		%1, 0		\n"
+		"	blz		%0, 2f		\n"
+		"	movi		%1, 1		\n"
+		"	addi		%0, 1		\n"
+		"	stex.w		%0, (%2)	\n"
+		"	bez		%0, 1b		\n"
+		FULL_FENCE
+		"2:\n"
+		: "=&r" (tmp), "=&r" (rc)
+		: "r" (&v->counter)
+		: "memory");
+
+	return tmp ? true : false;
+
+}
+#define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative
+
+static __always_inline bool
+arch_atomic_dec_unless_positive(atomic_t *v)
+{
+	int rc, tmp;
+
+	__asm__ __volatile__ (
+		RELEASE_FENCE
+		"1:	ldex.w		%0, (%2)	\n"
+		"	movi		%1, 0		\n"
+		"	bhz		%0, 2f		\n"
+		"	movi		%1, 1		\n"
+		"	subi		%0, 1		\n"
+		"	stex.w		%0, (%2)	\n"
+		"	bez		%0, 1b		\n"
+		FULL_FENCE
+		"2:\n"
+		: "=&r" (tmp), "=&r" (rc)
+		: "r" (&v->counter)
+		: "memory");
+
+	return tmp ? true : false;
+}
+#define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive
+
+static __always_inline int
+arch_atomic_dec_if_positive(atomic_t *v)
+{
+	int dec, tmp;
+
+	__asm__ __volatile__ (
+		RELEASE_FENCE
+		"1:	ldex.w		%0, (%2)	\n"
+		"	subi		%1, %0, 1	\n"
+		"	blz		%1, 2f		\n"
+		"	stex.w		%1, (%2)	\n"
+		"	bez		%1, 1b		\n"
+		FULL_FENCE
+		"2:\n"
+		: "=&r" (dec), "=&r" (tmp)
+		: "r" (&v->counter)
+		: "memory");
+
+	return dec - 1;
+}
+#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive
+
+#define ATOMIC_OP()							\
+static __always_inline							\
+int arch_atomic_xchg_relaxed(atomic_t *v, int n)			\
+{									\
+	return __xchg_relaxed(n, &(v->counter), 4);			\
+}									\
+static __always_inline							\
+int arch_atomic_cmpxchg_relaxed(atomic_t *v, int o, int n)		\
+{									\
+	return __cmpxchg_relaxed(&(v->counter), o, n, 4);		\
+}									\
+static __always_inline							\
+int arch_atomic_cmpxchg_acquire(atomic_t *v, int o, int n)		\
+{									\
+	return __cmpxchg_acquire(&(v->counter), o, n, 4);		\
+}									\
+static __always_inline							\
+int arch_atomic_cmpxchg(atomic_t *v, int o, int n)			\
+{									\
+	return __cmpxchg(&(v->counter), o, n, 4);			\
+}
+
+#define ATOMIC_OPS()							\
+	ATOMIC_OP()
+
+ATOMIC_OPS()
+
+#define arch_atomic_xchg_relaxed	arch_atomic_xchg_relaxed
+#define arch_atomic_cmpxchg_relaxed	arch_atomic_cmpxchg_relaxed
+#define arch_atomic_cmpxchg_acquire	arch_atomic_cmpxchg_acquire
+#define arch_atomic_cmpxchg		arch_atomic_cmpxchg
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP
+
+#else
+#include <asm-generic/atomic.h>
+#endif
+
+#endif /* __ASM_CSKY_ATOMIC_H */
diff --git a/arch/csky/include/asm/barrier.h b/arch/csky/include/asm/barrier.h
index f4045dd53e17..15de58b10aec 100644
--- a/arch/csky/include/asm/barrier.h
+++ b/arch/csky/include/asm/barrier.h
@@ -37,17 +37,21 @@
  * bar.brar
  * bar.bwaw
  */
+#define FULL_FENCE		".long 0x842fc000\n"
+#define ACQUIRE_FENCE		".long 0x8427c000\n"
+#define RELEASE_FENCE		".long 0x842ec000\n"
+
 #define __bar_brw()	asm volatile (".long 0x842cc000\n":::"memory")
 #define __bar_br()	asm volatile (".long 0x8424c000\n":::"memory")
 #define __bar_bw()	asm volatile (".long 0x8428c000\n":::"memory")
 #define __bar_arw()	asm volatile (".long 0x8423c000\n":::"memory")
 #define __bar_ar()	asm volatile (".long 0x8421c000\n":::"memory")
 #define __bar_aw()	asm volatile (".long 0x8422c000\n":::"memory")
-#define __bar_brwarw()	asm volatile (".long 0x842fc000\n":::"memory")
-#define __bar_brarw()	asm volatile (".long 0x8427c000\n":::"memory")
+#define __bar_brwarw()	asm volatile (FULL_FENCE:::"memory")
+#define __bar_brarw()	asm volatile (ACQUIRE_FENCE:::"memory")
 #define __bar_bwarw()	asm volatile (".long 0x842bc000\n":::"memory")
 #define __bar_brwar()	asm volatile (".long 0x842dc000\n":::"memory")
-#define __bar_brwaw()	asm volatile (".long 0x842ec000\n":::"memory")
+#define __bar_brwaw()	asm volatile (RELEASE_FENCE:::"memory")
 #define __bar_brar()	asm volatile (".long 0x8425c000\n":::"memory")
 #define __bar_brar()	asm volatile (".long 0x8425c000\n":::"memory")
 #define __bar_bwaw()	asm volatile (".long 0x842ac000\n":::"memory")
@@ -56,7 +60,6 @@
 #define __smp_rmb()	__bar_brar()
 #define __smp_wmb()	__bar_bwaw()
 
-#define ACQUIRE_FENCE		".long 0x8427c000\n"
 #define __smp_acquire_fence()	__bar_brarw()
 #define __smp_release_fence()	__bar_brwaw()
 
diff --git a/arch/csky/include/asm/cmpxchg.h b/arch/csky/include/asm/cmpxchg.h
index d1bef11f8dc9..5b8faccd65e4 100644
--- a/arch/csky/include/asm/cmpxchg.h
+++ b/arch/csky/include/asm/cmpxchg.h
@@ -64,15 +64,71 @@ extern void __bad_xchg(void);
 #define arch_cmpxchg_relaxed(ptr, o, n) \
 	(__cmpxchg_relaxed((ptr), (o), (n), sizeof(*(ptr))))
 
-#define arch_cmpxchg(ptr, o, n) 				\
+#define __cmpxchg_acquire(ptr, old, new, size)			\
 ({								\
+	__typeof__(ptr) __ptr = (ptr);				\
+	__typeof__(new) __new = (new);				\
+	__typeof__(new) __tmp;					\
+	__typeof__(old) __old = (old);				\
+	__typeof__(*(ptr)) __ret;				\
+	switch (size) {						\
+	case 4:							\
+		asm volatile (					\
+		"1:	ldex.w		%0, (%3) \n"		\
+		"	cmpne		%0, %4   \n"		\
+		"	bt		2f       \n"		\
+		"	mov		%1, %2   \n"		\
+		"	stex.w		%1, (%3) \n"		\
+		"	bez		%1, 1b   \n"		\
+		ACQUIRE_FENCE					\
+		"2:				 \n"		\
+			: "=&r" (__ret), "=&r" (__tmp)		\
+			: "r" (__new), "r"(__ptr), "r"(__old)	\
+			:);					\
+		break;						\
+	default:						\
+		__bad_xchg();					\
+	}							\
+	__ret;							\
+})
+
+#define arch_cmpxchg_acquire(ptr, o, n) \
+	(__cmpxchg_acquire((ptr), (o), (n), sizeof(*(ptr))))
+
+#define __cmpxchg(ptr, old, new, size)				\
+({								\
+	__typeof__(ptr) __ptr = (ptr);				\
+	__typeof__(new) __new = (new);				\
+	__typeof__(new) __tmp;					\
+	__typeof__(old) __old = (old);				\
 	__typeof__(*(ptr)) __ret;				\
-	__smp_release_fence();					\
-	__ret = arch_cmpxchg_relaxed(ptr, o, n);		\
-	__smp_acquire_fence();					\
+	switch (size) {						\
+	case 4:							\
+		asm volatile (					\
+		RELEASE_FENCE					\
+		"1:	ldex.w		%0, (%3) \n"		\
+		"	cmpne		%0, %4   \n"		\
+		"	bt		2f       \n"		\
+		"	mov		%1, %2   \n"		\
+		"	stex.w		%1, (%3) \n"		\
+		"	bez		%1, 1b   \n"		\
+		FULL_FENCE					\
+		"2:				 \n"		\
+			: "=&r" (__ret), "=&r" (__tmp)		\
+			: "r" (__new), "r"(__ptr), "r"(__old)	\
+			:);					\
+		break;						\
+	default:						\
+		__bad_xchg();					\
+	}							\
 	__ret;							\
 })
 
+#define arch_cmpxchg(ptr, o, n)					\
+	(__cmpxchg((ptr), (o), (n), sizeof(*(ptr))))
+
+#define arch_cmpxchg_local(ptr, o, n)				\
+	(__cmpxchg_relaxed((ptr), (o), (n), sizeof(*(ptr))))
 #else
 #include <asm-generic/cmpxchg.h>
 #endif
diff --git a/arch/csky/include/asm/io.h b/arch/csky/include/asm/io.h
index f82654053dc0..4725bb977b0f 100644
--- a/arch/csky/include/asm/io.h
+++ b/arch/csky/include/asm/io.h
@@ -5,7 +5,6 @@
 
 #include <linux/pgtable.h>
 #include <linux/types.h>
-#include <linux/version.h>
 
 /*
  * I/O memory access primitives. Reads are ordered relative to any
@@ -33,6 +32,17 @@
 #endif
 
 /*
+ * String version of I/O memory access operations.
+ */
+extern void __memcpy_fromio(void *, const volatile void __iomem *, size_t);
+extern void __memcpy_toio(volatile void __iomem *, const void *, size_t);
+extern void __memset_io(volatile void __iomem *, int, size_t);
+
+#define memset_io(c,v,l)        __memset_io((c),(v),(l))
+#define memcpy_fromio(a,c,l)    __memcpy_fromio((a),(c),(l))
+#define memcpy_toio(c,a,l)      __memcpy_toio((c),(a),(l))
+
+/*
  * I/O memory mapping functions.
  */
 #define ioremap_wc(addr, size) \
diff --git a/arch/csky/kernel/Makefile b/arch/csky/kernel/Makefile
index 6c0f36010ed0..4eb41421ca5b 100644
--- a/arch/csky/kernel/Makefile
+++ b/arch/csky/kernel/Makefile
@@ -2,7 +2,7 @@
 extra-y := head.o vmlinux.lds
 
 obj-y += entry.o atomic.o signal.o traps.o irq.o time.o vdso.o vdso/
-obj-y += power.o syscall.o syscall_table.o setup.o
+obj-y += power.o syscall.o syscall_table.o setup.o io.o
 obj-y += process.o cpu-probe.o ptrace.o stacktrace.o
 obj-y += probes/
 
diff --git a/arch/csky/kernel/io.c b/arch/csky/kernel/io.c
new file mode 100644
index 000000000000..5883f13fa2b1
--- /dev/null
+++ b/arch/csky/kernel/io.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/io.h>
+
+/*
+ * Copy data from IO memory space to "real" memory space.
+ */
+void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count)
+{
+	while (count && !IS_ALIGNED((unsigned long)from, 4)) {
+		*(u8 *)to = __raw_readb(from);
+		from++;
+		to++;
+		count--;
+	}
+
+	while (count >= 4) {
+		*(u32 *)to = __raw_readl(from);
+		from += 4;
+		to += 4;
+		count -= 4;
+	}
+
+	while (count) {
+		*(u8 *)to = __raw_readb(from);
+		from++;
+		to++;
+		count--;
+	}
+}
+EXPORT_SYMBOL(__memcpy_fromio);
+
+/*
+ * Copy data from "real" memory space to IO memory space.
+ */
+void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count)
+{
+	while (count && !IS_ALIGNED((unsigned long)to, 4)) {
+		__raw_writeb(*(u8 *)from, to);
+		from++;
+		to++;
+		count--;
+	}
+
+	while (count >= 4) {
+		__raw_writel(*(u32 *)from, to);
+		from += 4;
+		to += 4;
+		count -= 4;
+	}
+
+	while (count) {
+		__raw_writeb(*(u8 *)from, to);
+		from++;
+		to++;
+		count--;
+	}
+}
+EXPORT_SYMBOL(__memcpy_toio);
+
+/*
+ * "memset" on IO memory space.
+ */
+void __memset_io(volatile void __iomem *dst, int c, size_t count)
+{
+	u32 qc = (u8)c;
+
+	qc |= qc << 8;
+	qc |= qc << 16;
+
+	while (count && !IS_ALIGNED((unsigned long)dst, 4)) {
+		__raw_writeb(c, dst);
+		dst++;
+		count--;
+	}
+
+	while (count >= 4) {
+		__raw_writel(qc, dst);
+		dst += 4;
+		count -= 4;
+	}
+
+	while (count) {
+		__raw_writeb(c, dst);
+		dst++;
+		count--;
+	}
+}
+EXPORT_SYMBOL(__memset_io);
diff --git a/arch/csky/kernel/module.c b/arch/csky/kernel/module.c
index 6cd82d69c655..f11b3e573344 100644
--- a/arch/csky/kernel/module.c
+++ b/arch/csky/kernel/module.c
@@ -68,7 +68,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab,
 			*location = rel[i].r_addend + sym->st_value;
 			break;
 		case R_CSKY_PC32:
-			/* Add the value, subtract its postition */
+			/* Add the value, subtract its position */
 			*location = rel[i].r_addend + sym->st_value
 							- (uint32_t)location;
 			break;
diff --git a/arch/csky/kernel/probes/kprobes.c b/arch/csky/kernel/probes/kprobes.c
index 42920f25e73c..34ba684d5962 100644
--- a/arch/csky/kernel/probes/kprobes.c
+++ b/arch/csky/kernel/probes/kprobes.c
@@ -30,7 +30,7 @@ static int __kprobes patch_text_cb(void *priv)
 	struct csky_insn_patch *param = priv;
 	unsigned int addr = (unsigned int)param->addr;
 
-	if (atomic_inc_return(&param->cpu_count) == 1) {
+	if (atomic_inc_return(&param->cpu_count) == num_online_cpus()) {
 		*(u16 *) addr = cpu_to_le16(param->opcode);
 		dcache_wb_range(addr, addr + 2);
 		atomic_inc(&param->cpu_count);
diff --git a/arch/csky/kernel/probes/uprobes.c b/arch/csky/kernel/probes/uprobes.c
index 1a9e0961b2b5..2d31a12e46cf 100644
--- a/arch/csky/kernel/probes/uprobes.c
+++ b/arch/csky/kernel/probes/uprobes.c
@@ -102,7 +102,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	struct uprobe_task *utask = current->utask;
 
 	/*
-	 * Task has received a fatal signal, so reset back to probbed
+	 * Task has received a fatal signal, so reset back to probed
 	 * address.
 	 */
 	instruction_pointer_set(regs, utask->vaddr);
diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c
index 3d0ca22cd0e2..5de04707aa07 100644
--- a/arch/csky/kernel/process.c
+++ b/arch/csky/kernel/process.c
@@ -2,7 +2,6 @@
 // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
 
 #include <linux/module.h>
-#include <linux/version.h>
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/debug.h>
diff --git a/arch/csky/lib/Makefile b/arch/csky/lib/Makefile
index 7fbdbb2c4d12..d0ce6e2d7ab2 100644
--- a/arch/csky/lib/Makefile
+++ b/arch/csky/lib/Makefile
@@ -1,3 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 lib-y  := usercopy.o delay.o
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
+ifneq ($(CONFIG_HAVE_EFFICIENT_UNALIGNED_STRING_OPS), y)
+lib-y  += string.o
+endif
diff --git a/arch/csky/lib/string.c b/arch/csky/lib/string.c
new file mode 100644
index 000000000000..d65626fcaeac
--- /dev/null
+++ b/arch/csky/lib/string.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * String functions optimized for hardware which doesn't
+ * handle unaligned memory accesses efficiently.
+ *
+ * Copyright (C) 2021 Matteo Croce
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+
+/* Minimum size for a word copy to be convenient */
+#define BYTES_LONG	sizeof(long)
+#define WORD_MASK	(BYTES_LONG - 1)
+#define MIN_THRESHOLD	(BYTES_LONG * 2)
+
+/* convenience union to avoid cast between different pointer types */
+union types {
+	u8 *as_u8;
+	unsigned long *as_ulong;
+	uintptr_t as_uptr;
+};
+
+union const_types {
+	const u8 *as_u8;
+	unsigned long *as_ulong;
+	uintptr_t as_uptr;
+};
+
+void *memcpy(void *dest, const void *src, size_t count)
+{
+	union const_types s = { .as_u8 = src };
+	union types d = { .as_u8 = dest };
+	int distance = 0;
+
+	if (count < MIN_THRESHOLD)
+		goto copy_remainder;
+
+	/* Copy a byte at time until destination is aligned. */
+	for (; d.as_uptr & WORD_MASK; count--)
+		*d.as_u8++ = *s.as_u8++;
+
+	distance = s.as_uptr & WORD_MASK;
+
+	if (distance) {
+		unsigned long last, next;
+
+		/*
+		 * s is distance bytes ahead of d, and d just reached
+		 * the alignment boundary. Move s backward to word align it
+		 * and shift data to compensate for distance, in order to do
+		 * word-by-word copy.
+		 */
+		s.as_u8 -= distance;
+
+		next = s.as_ulong[0];
+		for (; count >= BYTES_LONG; count -= BYTES_LONG) {
+			last = next;
+			next = s.as_ulong[1];
+
+			d.as_ulong[0] = last >> (distance * 8) |
+				next << ((BYTES_LONG - distance) * 8);
+
+			d.as_ulong++;
+			s.as_ulong++;
+		}
+
+		/* Restore s with the original offset. */
+		s.as_u8 += distance;
+	} else {
+		/*
+		 * If the source and dest lower bits are the same, do a simple
+		 * 32/64 bit wide copy.
+		 */
+		for (; count >= BYTES_LONG; count -= BYTES_LONG)
+			*d.as_ulong++ = *s.as_ulong++;
+	}
+
+copy_remainder:
+	while (count--)
+		*d.as_u8++ = *s.as_u8++;
+
+	return dest;
+}
+EXPORT_SYMBOL(memcpy);
+
+/*
+ * Simply check if the buffer overlaps an call memcpy() in case,
+ * otherwise do a simple one byte at time backward copy.
+ */
+void *memmove(void *dest, const void *src, size_t count)
+{
+	if (dest < src || src + count <= dest)
+		return memcpy(dest, src, count);
+
+	if (dest > src) {
+		const char *s = src + count;
+		char *tmp = dest + count;
+
+		while (count--)
+			*--tmp = *--s;
+	}
+	return dest;
+}
+EXPORT_SYMBOL(memmove);
+
+void *memset(void *s, int c, size_t count)
+{
+	union types dest = { .as_u8 = s };
+
+	if (count >= MIN_THRESHOLD) {
+		unsigned long cu = (unsigned long)c;
+
+		/* Compose an ulong with 'c' repeated 4/8 times */
+		cu |= cu << 8;
+		cu |= cu << 16;
+		/* Suppress warning on 32 bit machines */
+		cu |= (cu << 16) << 16;
+
+		for (; count && dest.as_uptr & WORD_MASK; count--)
+			*dest.as_u8++ = c;
+
+		/* Copy using the largest size allowed */
+		for (; count >= BYTES_LONG; count -= BYTES_LONG)
+			*dest.as_ulong++ = cu;
+	}
+
+	/* copy the remainder */
+	while (count--)
+		*dest.as_u8++ = c;
+
+	return s;
+}
+EXPORT_SYMBOL(memset);
diff --git a/arch/csky/mm/dma-mapping.c b/arch/csky/mm/dma-mapping.c
index c3a775a7e8f9..82447029feb4 100644
--- a/arch/csky/mm/dma-mapping.c
+++ b/arch/csky/mm/dma-mapping.c
@@ -9,7 +9,6 @@
 #include <linux/mm.h>
 #include <linux/scatterlist.h>
 #include <linux/types.h>
-#include <linux/version.h>
 #include <asm/cache.h>
 
 static inline void cache_op(phys_addr_t paddr, size_t size,