x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

174 files changed, 14597 insertions, 0 deletions

diff --git a/arch/csky/Kbuild b/arch/csky/Kbuild
new file mode 100644
index 000000000..0621eaea4
--- /dev/null
+++ b/arch/csky/Kbuild
@@ -0,0 +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
new file mode 100644
index 000000000..4331313a4
--- /dev/null
+++ b/arch/csky/Kconfig
@@ -0,0 +1,355 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config CSKY
+	def_bool y
+	select ARCH_32BIT_OFF_T
+	select ARCH_HAS_CPU_CACHE_ALIASING
+	select ARCH_HAS_DMA_PREP_COHERENT
+	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select ARCH_USE_BUILTIN_BSWAP
+	select ARCH_USE_QUEUED_RWLOCKS
+	select ARCH_USE_QUEUED_SPINLOCKS
+	select ARCH_HAS_CURRENT_STACK_POINTER
+	select ARCH_INLINE_READ_LOCK if !PREEMPTION
+	select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION
+	select ARCH_INLINE_READ_LOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_READ_LOCK_IRQSAVE if !PREEMPTION
+	select ARCH_INLINE_READ_UNLOCK if !PREEMPTION
+	select ARCH_INLINE_READ_UNLOCK_BH if !PREEMPTION
+	select ARCH_INLINE_READ_UNLOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_READ_UNLOCK_IRQRESTORE if !PREEMPTION
+	select ARCH_INLINE_WRITE_LOCK if !PREEMPTION
+	select ARCH_INLINE_WRITE_LOCK_BH if !PREEMPTION
+	select ARCH_INLINE_WRITE_LOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_WRITE_LOCK_IRQSAVE if !PREEMPTION
+	select ARCH_INLINE_WRITE_UNLOCK if !PREEMPTION
+	select ARCH_INLINE_WRITE_UNLOCK_BH if !PREEMPTION
+	select ARCH_INLINE_WRITE_UNLOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE if !PREEMPTION
+	select ARCH_INLINE_SPIN_TRYLOCK if !PREEMPTION
+	select ARCH_INLINE_SPIN_TRYLOCK_BH if !PREEMPTION
+	select ARCH_INLINE_SPIN_LOCK if !PREEMPTION
+	select ARCH_INLINE_SPIN_LOCK_BH if !PREEMPTION
+	select ARCH_INLINE_SPIN_LOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_SPIN_LOCK_IRQSAVE if !PREEMPTION
+	select ARCH_INLINE_SPIN_UNLOCK if !PREEMPTION
+	select ARCH_INLINE_SPIN_UNLOCK_BH if !PREEMPTION
+	select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION
+	select ARCH_NEED_CMPXCHG_1_EMU
+	select ARCH_WANT_FRAME_POINTERS if !CPU_CK610 && $(cc-option,-mbacktrace)
+	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
+	select COMMON_CLK
+	select CLKSRC_MMIO
+	select CSKY_MPINTC if CPU_CK860
+	select CSKY_MP_TIMER if CPU_CK860
+	select CSKY_APB_INTC
+	select DMA_DIRECT_REMAP
+	select IRQ_DOMAIN
+	select DW_APB_TIMER_OF
+	select GENERIC_IOREMAP
+	select GENERIC_LIB_ASHLDI3
+	select GENERIC_LIB_ASHRDI3
+	select GENERIC_LIB_LSHRDI3
+	select GENERIC_LIB_MULDI3
+	select GENERIC_LIB_CMPDI2
+	select GENERIC_LIB_UCMPDI2
+	select GENERIC_ALLOCATOR
+	select GENERIC_ATOMIC64
+	select GENERIC_CPU_DEVICES
+	select GENERIC_IRQ_CHIP
+	select GENERIC_IRQ_PROBE
+	select GENERIC_IRQ_SHOW
+	select GENERIC_IRQ_MULTI_HANDLER
+	select GENERIC_SCHED_CLOCK
+	select GENERIC_SMP_IDLE_THREAD
+	select GX6605S_TIMER if CPU_CK610
+	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_JUMP_LABEL if !CPU_CK610
+	select HAVE_ARCH_JUMP_LABEL_RELATIVE
+	select HAVE_ARCH_MMAP_RND_BITS
+	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_CONTEXT_TRACKING_USER
+	select HAVE_VIRT_CPU_ACCOUNTING_GEN
+	select HAVE_DEBUG_BUGVERBOSE
+	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS
+	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_ERROR_INJECTION
+	select HAVE_KERNEL_GZIP
+	select HAVE_KERNEL_LZO
+	select HAVE_KERNEL_LZMA
+	select HAVE_KPROBES if !CPU_CK610
+	select HAVE_KPROBES_ON_FTRACE if !CPU_CK610
+	select HAVE_KRETPROBES if !CPU_CK610
+	select HAVE_PAGE_SIZE_4KB
+	select HAVE_PERF_EVENTS
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_DMA_CONTIGUOUS
+	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_STACKPROTECTOR
+	select HAVE_SYSCALL_TRACEPOINTS
+	select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU
+	select LOCK_MM_AND_FIND_VMA
+	select MAY_HAVE_SPARSE_IRQ
+	select MODULES_USE_ELF_RELA if MODULES
+	select OF
+	select OF_EARLY_FLATTREE
+	select PERF_USE_VMALLOC if CPU_CK610
+	select RTC_LIB
+	select TIMER_OF
+	select GENERIC_PCI_IOMAP
+	select HAVE_PCI
+	select PCI_DOMAINS_GENERIC if PCI
+	select PCI_SYSCALL if PCI
+	select PCI_MSI if PCI
+	select TRACE_IRQFLAGS_SUPPORT
+
+config LOCKDEP_SUPPORT
+	def_bool y
+
+config ARCH_SUPPORTS_UPROBES
+	def_bool y if !CPU_CK610
+
+config CPU_HAS_CACHEV2
+	bool
+
+config CPU_HAS_FPUV2
+	bool
+
+config CPU_HAS_HILO
+	bool
+
+config CPU_HAS_TLBI
+	bool
+
+config CPU_HAS_LDSTEX
+	bool
+	help
+	  For SMP, CPU needs "ldex&stex" instructions for atomic operations.
+
+config CPU_NEED_TLBSYNC
+	bool
+
+config CPU_NEED_SOFTALIGN
+	bool
+
+config CPU_NO_USER_BKPT
+	bool
+	help
+	  For abiv2 we couldn't use "trap 1" as user space bkpt in gdbserver, because
+	  abiv2 is 16/32bit instruction set and "trap 1" is 32bit.
+	  So we need a 16bit instruction as user space bkpt, and it will cause an illegal
+	  instruction exception.
+	  In kernel we parse the *regs->pc to determine whether to send SIGTRAP or not.
+
+config GENERIC_CALIBRATE_DELAY
+	def_bool y
+
+config GENERIC_CSUM
+	def_bool y
+
+config GENERIC_HWEIGHT
+	def_bool y
+
+config MMU
+	def_bool y
+
+config STACKTRACE_SUPPORT
+	def_bool y
+
+config TIME_LOW_RES
+	def_bool y
+
+config CPU_ASID_BITS
+	int
+	default "8"	if (CPU_CK610 || CPU_CK807 || CPU_CK810)
+	default "12"	if (CPU_CK860)
+
+config L1_CACHE_SHIFT
+	int
+	default "4"	if (CPU_CK610)
+	default "5"	if (CPU_CK807 || CPU_CK810)
+	default "6"	if (CPU_CK860)
+
+config ARCH_MMAP_RND_BITS_MIN
+	default 8
+
+# max bits determined by the following formula:
+#  VA_BITS - PAGE_SHIFT - 3
+config ARCH_MMAP_RND_BITS_MAX
+	default 17
+
+menu "Processor type and features"
+
+choice
+	prompt "CPU MODEL"
+	default CPU_CK807
+
+config CPU_CK610
+	bool "CSKY CPU ck610"
+	select CPU_NEED_TLBSYNC
+	select CPU_NEED_SOFTALIGN
+	select CPU_NO_USER_BKPT
+
+config CPU_CK810
+	bool "CSKY CPU ck810"
+	select CPU_HAS_HILO
+	select CPU_NEED_TLBSYNC
+
+config CPU_CK807
+	bool "CSKY CPU ck807"
+	select CPU_HAS_HILO
+
+config CPU_CK860
+	bool "CSKY CPU ck860"
+	select CPU_HAS_TLBI
+	select CPU_HAS_CACHEV2
+	select CPU_HAS_LDSTEX
+	select CPU_HAS_FPUV2
+endchoice
+
+choice
+	prompt "PAGE OFFSET"
+	default PAGE_OFFSET_80000000
+
+config PAGE_OFFSET_80000000
+	bool "PAGE OFFSET 2G (user:kernel = 2:2)"
+
+config PAGE_OFFSET_A0000000
+	bool "PAGE OFFSET 2.5G (user:kernel = 2.5:1.5)"
+endchoice
+
+config PAGE_OFFSET
+	hex
+	default 0x80000000 if PAGE_OFFSET_80000000
+	default 0xa0000000 if PAGE_OFFSET_A0000000
+choice
+
+	prompt "C-SKY PMU type"
+	depends on PERF_EVENTS
+	depends on CPU_CK807 || CPU_CK810 || CPU_CK860
+
+config CPU_PMU_NONE
+	bool "None"
+
+config CSKY_PMU_V1
+	bool "Performance Monitoring Unit Ver.1"
+
+endchoice
+
+choice
+	prompt "Power Manager Instruction (wait/doze/stop)"
+	default CPU_PM_NONE
+
+config CPU_PM_NONE
+	bool "None"
+
+config CPU_PM_WAIT
+	bool "wait"
+
+config CPU_PM_DOZE
+	bool "doze"
+
+config CPU_PM_STOP
+	bool "stop"
+endchoice
+
+menuconfig HAVE_TCM
+	bool "Tightly-Coupled/Sram Memory"
+	depends on !COMPILE_TEST
+	help
+	  The implementation are not only used by TCM (Tightly-Coupled Memory)
+	  but also used by sram on SOC bus. It follow existed linux tcm
+	  software interface, so that old tcm application codes could be
+	  re-used directly.
+
+if HAVE_TCM
+config ITCM_RAM_BASE
+	hex "ITCM ram base"
+	default 0xffffffff
+
+config ITCM_NR_PAGES
+	int "Page count of ITCM size: NR*4KB"
+	range 1 256
+	default 32
+
+config HAVE_DTCM
+	bool "DTCM Support"
+
+config DTCM_RAM_BASE
+	hex "DTCM ram base"
+	depends on HAVE_DTCM
+	default 0xffffffff
+
+config DTCM_NR_PAGES
+	int "Page count of DTCM size: NR*4KB"
+	depends on HAVE_DTCM
+	range 1 256
+	default 32
+endif
+
+config CPU_HAS_VDSP
+	bool "CPU has VDSP coprocessor"
+	depends on CPU_HAS_FPU && CPU_HAS_FPUV2
+
+config CPU_HAS_FPU
+	bool "CPU has FPU coprocessor"
+	depends on CPU_CK807 || CPU_CK810 || CPU_CK860
+
+config CPU_HAS_ICACHE_INS
+	bool "CPU has Icache invalidate instructions"
+	depends on CPU_HAS_CACHEV2
+
+config CPU_HAS_TEE
+	bool "CPU has Trusted Execution Environment"
+	depends on CPU_CK810
+
+config SMP
+	bool "Symmetric Multi-Processing (SMP) support for C-SKY"
+	depends on CPU_CK860
+	default n
+
+config NR_CPUS
+	int "Maximum number of CPUs (2-32)"
+	range 2 32
+	depends on SMP
+	default "4"
+
+config HIGHMEM
+	bool "High Memory Support"
+	depends on !CPU_CK610
+	select KMAP_LOCAL
+	default y
+
+config DRAM_BASE
+	hex "DRAM start addr (the same with memory-section in dts)"
+	default 0x0
+
+config HOTPLUG_CPU
+	bool "Support for hot-pluggable CPUs"
+	select GENERIC_IRQ_MIGRATION
+	depends on SMP
+	help
+	  Say Y here to allow turning CPUs off and on. CPUs can be
+	  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"
+
+source "kernel/Kconfig.hz"
diff --git a/arch/csky/Kconfig.debug b/arch/csky/Kconfig.debug
new file mode 100644
index 000000000..295942fe3
--- /dev/null
+++ b/arch/csky/Kconfig.debug
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# dummy file, do not delete
diff --git a/arch/csky/Kconfig.platforms b/arch/csky/Kconfig.platforms
new file mode 100644
index 000000000..639e17f4e
--- /dev/null
+++ b/arch/csky/Kconfig.platforms
@@ -0,0 +1,9 @@
+menu "Platform drivers selection"
+
+config ARCH_CSKY_DW_APB_ICTL
+	bool "Select dw-apb interrupt controller"
+	select DW_APB_ICTL
+	default y
+	help
+	  This enables support for snps dw-apb-ictl
+endmenu
diff --git a/arch/csky/Makefile b/arch/csky/Makefile
new file mode 100644
index 000000000..0e4237e55
--- /dev/null
+++ b/arch/csky/Makefile
@@ -0,0 +1,78 @@
+# SPDX-License-Identifier: GPL-2.0-only
+OBJCOPYFLAGS		:=-O binary
+GZFLAGS			:=-9
+
+ifdef CONFIG_CPU_HAS_FPU
+FPUEXT = f
+endif
+
+ifdef CONFIG_CPU_HAS_VDSP
+VDSPEXT = v
+endif
+
+ifdef CONFIG_CPU_HAS_TEE
+TEEEXT = t
+endif
+
+ifdef CONFIG_CPU_CK610
+CPUTYPE	= ck610
+CSKYABI	= abiv1
+endif
+
+ifdef CONFIG_CPU_CK810
+CPUTYPE = ck810
+CSKYABI	= abiv2
+endif
+
+ifdef CONFIG_CPU_CK807
+CPUTYPE = ck807
+CSKYABI	= abiv2
+endif
+
+ifdef CONFIG_CPU_CK860
+CPUTYPE = ck860
+CSKYABI	= abiv2
+endif
+
+ifneq ($(CSKYABI),)
+MCPU_STR = $(CPUTYPE)$(FPUEXT)$(VDSPEXT)$(TEEEXT)
+KBUILD_CFLAGS += -mcpu=$(CPUTYPE) -Wa,-mcpu=$(MCPU_STR)
+KBUILD_CFLAGS += -DCSKYCPU_DEF_NAME=\"$(MCPU_STR)\"
+KBUILD_CFLAGS += -msoft-float -mdiv
+KBUILD_CFLAGS += -fno-tree-vectorize
+endif
+
+KBUILD_CFLAGS += -pipe
+ifeq ($(CSKYABI),abiv2)
+KBUILD_CFLAGS += -mno-stack-size
+endif
+
+ifdef CONFIG_FRAME_POINTER
+KBUILD_CFLAGS += -mbacktrace
+endif
+
+abidirs := $(patsubst %,arch/csky/%/,$(CSKYABI))
+KBUILD_CFLAGS += $(patsubst %,-I$(srctree)/%inc,$(abidirs))
+
+KBUILD_CPPFLAGS += -mlittle-endian
+LDFLAGS += -EL
+
+KBUILD_AFLAGS += $(KBUILD_CFLAGS)
+
+core-y += arch/csky/$(CSKYABI)/
+
+libs-y += arch/csky/lib/ \
+	$(shell $(CC) $(KBUILD_CFLAGS) $(KCFLAGS) -print-libgcc-file-name)
+
+boot := arch/csky/boot
+
+all: zImage
+
+zImage Image uImage: vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+
+define archhelp
+  echo  '* zImage       - Compressed kernel image (arch/$(ARCH)/boot/zImage)'
+  echo  '  Image        - Uncompressed kernel image (arch/$(ARCH)/boot/Image)'
+  echo  '  uImage       - U-Boot wrapped zImage'
+endef
diff --git a/arch/csky/abiv1/Makefile b/arch/csky/abiv1/Makefile
new file mode 100644
index 000000000..a4b2ade0f
--- /dev/null
+++ b/arch/csky/abiv1/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_CPU_NEED_SOFTALIGN)	+= alignment.o
+obj-y					+= bswapdi.o
+obj-y					+= bswapsi.o
+obj-y					+= cacheflush.o
+obj-y					+= mmap.o
diff --git a/arch/csky/abiv1/alignment.c b/arch/csky/abiv1/alignment.c
new file mode 100644
index 000000000..aee904833
--- /dev/null
+++ b/arch/csky/abiv1/alignment.c
@@ -0,0 +1,340 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/kernel.h>
+#include <linux/uaccess.h>
+#include <linux/ptrace.h>
+
+static int align_kern_enable = 1;
+static int align_usr_enable = 1;
+static int align_kern_count = 0;
+static int align_usr_count = 0;
+
+static inline uint32_t get_ptreg(struct pt_regs *regs, uint32_t rx)
+{
+	return rx == 15 ? regs->lr : *((uint32_t *)&(regs->a0) - 2 + rx);
+}
+
+static inline void put_ptreg(struct pt_regs *regs, uint32_t rx, uint32_t val)
+{
+	if (rx == 15)
+		regs->lr = val;
+	else
+		*((uint32_t *)&(regs->a0) - 2 + rx) = val;
+}
+
+/*
+ * Get byte-value from addr and set it to *valp.
+ *
+ * Success: return 0
+ * Failure: return 1
+ */
+static int ldb_asm(uint32_t addr, uint32_t *valp)
+{
+	uint32_t val;
+	int err;
+
+	asm volatile (
+		"movi	%0, 0\n"
+		"1:\n"
+		"ldb	%1, (%2)\n"
+		"br	3f\n"
+		"2:\n"
+		"movi	%0, 1\n"
+		"br	3f\n"
+		".section __ex_table,\"a\"\n"
+		".align 2\n"
+		".long	1b, 2b\n"
+		".previous\n"
+		"3:\n"
+		: "=&r"(err), "=r"(val)
+		: "r" (addr)
+	);
+
+	*valp = val;
+
+	return err;
+}
+
+/*
+ * Put byte-value to addr.
+ *
+ * Success: return 0
+ * Failure: return 1
+ */
+static int stb_asm(uint32_t addr, uint32_t val)
+{
+	int err;
+
+	asm volatile (
+		"movi	%0, 0\n"
+		"1:\n"
+		"stb	%1, (%2)\n"
+		"br	3f\n"
+		"2:\n"
+		"movi	%0, 1\n"
+		"br	3f\n"
+		".section __ex_table,\"a\"\n"
+		".align 2\n"
+		".long	1b, 2b\n"
+		".previous\n"
+		"3:\n"
+		: "=&r"(err)
+		: "r"(val), "r" (addr)
+	);
+
+	return err;
+}
+
+/*
+ * Get half-word from [rx + imm]
+ *
+ * Success: return 0
+ * Failure: return 1
+ */
+static int ldh_c(struct pt_regs *regs, uint32_t rz, uint32_t addr)
+{
+	uint32_t byte0, byte1;
+
+	if (ldb_asm(addr, &byte0))
+		return 1;
+	addr += 1;
+	if (ldb_asm(addr, &byte1))
+		return 1;
+
+	byte0 |= byte1 << 8;
+	put_ptreg(regs, rz, byte0);
+
+	return 0;
+}
+
+/*
+ * Store half-word to [rx + imm]
+ *
+ * Success: return 0
+ * Failure: return 1
+ */
+static int sth_c(struct pt_regs *regs, uint32_t rz, uint32_t addr)
+{
+	uint32_t byte0, byte1;
+
+	byte0 = byte1 = get_ptreg(regs, rz);
+
+	byte0 &= 0xff;
+
+	if (stb_asm(addr, byte0))
+		return 1;
+
+	addr += 1;
+	byte1 = (byte1 >> 8) & 0xff;
+	if (stb_asm(addr, byte1))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * Get word from [rx + imm]
+ *
+ * Success: return 0
+ * Failure: return 1
+ */
+static int ldw_c(struct pt_regs *regs, uint32_t rz, uint32_t addr)
+{
+	uint32_t byte0, byte1, byte2, byte3;
+
+	if (ldb_asm(addr, &byte0))
+		return 1;
+
+	addr += 1;
+	if (ldb_asm(addr, &byte1))
+		return 1;
+
+	addr += 1;
+	if (ldb_asm(addr, &byte2))
+		return 1;
+
+	addr += 1;
+	if (ldb_asm(addr, &byte3))
+		return 1;
+
+	byte0 |= byte1 << 8;
+	byte0 |= byte2 << 16;
+	byte0 |= byte3 << 24;
+
+	put_ptreg(regs, rz, byte0);
+
+	return 0;
+}
+
+/*
+ * Store word to [rx + imm]
+ *
+ * Success: return 0
+ * Failure: return 1
+ */
+static int stw_c(struct pt_regs *regs, uint32_t rz, uint32_t addr)
+{
+	uint32_t byte0, byte1, byte2, byte3;
+
+	byte0 = byte1 = byte2 = byte3 = get_ptreg(regs, rz);
+
+	byte0 &= 0xff;
+
+	if (stb_asm(addr, byte0))
+		return 1;
+
+	addr += 1;
+	byte1 = (byte1 >> 8) & 0xff;
+	if (stb_asm(addr, byte1))
+		return 1;
+
+	addr += 1;
+	byte2 = (byte2 >> 16) & 0xff;
+	if (stb_asm(addr, byte2))
+		return 1;
+
+	addr += 1;
+	byte3 = (byte3 >> 24) & 0xff;
+	if (stb_asm(addr, byte3))
+		return 1;
+
+	return 0;
+}
+
+extern int fixup_exception(struct pt_regs *regs);
+
+#define OP_LDH 0xc000
+#define OP_STH 0xd000
+#define OP_LDW 0x8000
+#define OP_STW 0x9000
+
+void csky_alignment(struct pt_regs *regs)
+{
+	int ret;
+	uint16_t tmp;
+	uint32_t opcode = 0;
+	uint32_t rx     = 0;
+	uint32_t rz     = 0;
+	uint32_t imm    = 0;
+	uint32_t addr   = 0;
+
+	if (!user_mode(regs))
+		goto kernel_area;
+
+	if (!align_usr_enable) {
+		pr_err("%s user disabled.\n", __func__);
+		goto bad_area;
+	}
+
+	align_usr_count++;
+
+	ret = get_user(tmp, (uint16_t *)instruction_pointer(regs));
+	if (ret) {
+		pr_err("%s get_user failed.\n", __func__);
+		goto bad_area;
+	}
+
+	goto good_area;
+
+kernel_area:
+	if (!align_kern_enable) {
+		pr_err("%s kernel disabled.\n", __func__);
+		goto bad_area;
+	}
+
+	align_kern_count++;
+
+	tmp = *(uint16_t *)instruction_pointer(regs);
+
+good_area:
+	opcode = (uint32_t)tmp;
+
+	rx  = opcode & 0xf;
+	imm = (opcode >> 4) & 0xf;
+	rz  = (opcode >> 8) & 0xf;
+	opcode &= 0xf000;
+
+	if (rx == 0 || rx == 1 || rz == 0 || rz == 1)
+		goto bad_area;
+
+	switch (opcode) {
+	case OP_LDH:
+		addr = get_ptreg(regs, rx) + (imm << 1);
+		ret = ldh_c(regs, rz, addr);
+		break;
+	case OP_LDW:
+		addr = get_ptreg(regs, rx) + (imm << 2);
+		ret = ldw_c(regs, rz, addr);
+		break;
+	case OP_STH:
+		addr = get_ptreg(regs, rx) + (imm << 1);
+		ret = sth_c(regs, rz, addr);
+		break;
+	case OP_STW:
+		addr = get_ptreg(regs, rx) + (imm << 2);
+		ret = stw_c(regs, rz, addr);
+		break;
+	}
+
+	if (ret)
+		goto bad_area;
+
+	regs->pc += 2;
+
+	return;
+
+bad_area:
+	if (!user_mode(regs)) {
+		if (fixup_exception(regs))
+			return;
+
+		bust_spinlocks(1);
+		pr_alert("%s opcode: %x, rz: %d, rx: %d, imm: %d, addr: %x.\n",
+				__func__, opcode, rz, rx, imm, addr);
+		show_regs(regs);
+		bust_spinlocks(0);
+		make_task_dead(SIGKILL);
+	}
+
+	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)addr);
+}
+
+static const struct ctl_table alignment_tbl[] = {
+	{
+		.procname = "kernel_enable",
+		.data = &align_kern_enable,
+		.maxlen = sizeof(align_kern_enable),
+		.mode = 0666,
+		.proc_handler = &proc_dointvec
+	},
+	{
+		.procname = "user_enable",
+		.data = &align_usr_enable,
+		.maxlen = sizeof(align_usr_enable),
+		.mode = 0666,
+		.proc_handler = &proc_dointvec
+	},
+	{
+		.procname = "kernel_count",
+		.data = &align_kern_count,
+		.maxlen = sizeof(align_kern_count),
+		.mode = 0666,
+		.proc_handler = &proc_dointvec
+	},
+	{
+		.procname = "user_count",
+		.data = &align_usr_count,
+		.maxlen = sizeof(align_usr_count),
+		.mode = 0666,
+		.proc_handler = &proc_dointvec
+	},
+};
+
+static int __init csky_alignment_init(void)
+{
+	register_sysctl_init("csky/csky_alignment", alignment_tbl);
+	return 0;
+}
+
+arch_initcall(csky_alignment_init);
diff --git a/arch/csky/abiv1/bswapdi.c b/arch/csky/abiv1/bswapdi.c
new file mode 100644
index 000000000..f50a1d6e3
--- /dev/null
+++ b/arch/csky/abiv1/bswapdi.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/export.h>
+#include <linux/compiler.h>
+#include <uapi/linux/swab.h>
+
+unsigned long long notrace __bswapdi2(unsigned long long u)
+{
+	return ___constant_swab64(u);
+}
+EXPORT_SYMBOL(__bswapdi2);
diff --git a/arch/csky/abiv1/bswapsi.c b/arch/csky/abiv1/bswapsi.c
new file mode 100644
index 000000000..0f79182e8
--- /dev/null
+++ b/arch/csky/abiv1/bswapsi.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/export.h>
+#include <linux/compiler.h>
+#include <uapi/linux/swab.h>
+
+unsigned int notrace __bswapsi2(unsigned int u)
+{
+	return ___constant_swab32(u);
+}
+EXPORT_SYMBOL(__bswapsi2);
diff --git a/arch/csky/abiv1/cacheflush.c b/arch/csky/abiv1/cacheflush.c
new file mode 100644
index 000000000..4bc0aad3c
--- /dev/null
+++ b/arch/csky/abiv1/cacheflush.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/syscalls.h>
+#include <linux/spinlock.h>
+#include <asm/page.h>
+#include <asm/cache.h>
+#include <asm/cacheflush.h>
+#include <asm/cachectl.h>
+#include <asm/tlbflush.h>
+
+#define PG_dcache_clean		PG_arch_1
+
+void flush_dcache_folio(struct folio *folio)
+{
+	struct address_space *mapping;
+
+	if (is_zero_pfn(folio_pfn(folio)))
+		return;
+
+	mapping = folio_flush_mapping(folio);
+
+	if (mapping && !folio_mapped(folio))
+		clear_bit(PG_dcache_clean, &folio->flags.f);
+	else {
+		dcache_wbinv_all();
+		if (mapping)
+			icache_inv_all();
+		set_bit(PG_dcache_clean, &folio->flags.f);
+	}
+}
+EXPORT_SYMBOL(flush_dcache_folio);
+
+void flush_dcache_page(struct page *page)
+{
+	flush_dcache_folio(page_folio(page));
+}
+EXPORT_SYMBOL(flush_dcache_page);
+
+void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
+		unsigned long addr, pte_t *ptep, unsigned int nr)
+{
+	unsigned long pfn = pte_pfn(*ptep);
+	struct folio *folio;
+
+	flush_tlb_page(vma, addr);
+
+	if (!pfn_valid(pfn))
+		return;
+
+	if (is_zero_pfn(pfn))
+		return;
+
+	folio = page_folio(pfn_to_page(pfn));
+	if (!test_and_set_bit(PG_dcache_clean, &folio->flags.f))
+		dcache_wbinv_all();
+
+	if (folio_flush_mapping(folio)) {
+		if (vma->vm_flags & VM_EXEC)
+			icache_inv_all();
+	}
+}
+
+void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
+	unsigned long end)
+{
+	dcache_wbinv_all();
+
+	if (vma->vm_flags & VM_EXEC)
+		icache_inv_all();
+}
diff --git a/arch/csky/abiv1/inc/abi/cacheflush.h b/arch/csky/abiv1/inc/abi/cacheflush.h
new file mode 100644
index 000000000..21cc7965c
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/cacheflush.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_CACHEFLUSH_H
+#define __ABI_CSKY_CACHEFLUSH_H
+
+#include <linux/mm.h>
+#include <asm/string.h>
+#include <asm/cache.h>
+
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
+extern void flush_dcache_page(struct page *);
+void flush_dcache_folio(struct folio *);
+#define flush_dcache_folio flush_dcache_folio
+
+#define flush_cache_mm(mm)			dcache_wbinv_all()
+#define flush_cache_page(vma, page, pfn)	cache_wbinv_all()
+#define flush_cache_dup_mm(mm)			cache_wbinv_all()
+
+#define flush_dcache_mmap_lock(mapping)		xa_lock_irq(&mapping->i_pages)
+#define flush_dcache_mmap_unlock(mapping)	xa_unlock_irq(&mapping->i_pages)
+
+#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1
+static inline void flush_kernel_vmap_range(void *addr, int size)
+{
+	dcache_wbinv_all();
+}
+static inline void invalidate_kernel_vmap_range(void *addr, int size)
+{
+	dcache_wbinv_all();
+}
+
+#define ARCH_HAS_FLUSH_ANON_PAGE
+static inline void flush_anon_page(struct vm_area_struct *vma,
+			 struct page *page, unsigned long vmaddr)
+{
+	if (PageAnon(page))
+		cache_wbinv_all();
+}
+
+/*
+ * if (current_mm != vma->mm) cache_wbinv_range(start, end) will be broken.
+ * Use cache_wbinv_all() here and need to be improved in future.
+ */
+extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
+
+static inline void flush_cache_vmap(unsigned long start, unsigned long end)
+{
+	cache_wbinv_all();
+}
+
+#define flush_cache_vmap_early(start, end)	do { } while (0)
+#define flush_cache_vunmap(start, end)		cache_wbinv_all()
+
+#define flush_icache_range(start, end)		cache_wbinv_range(start, end)
+#define flush_icache_mm_range(mm, start, end)	cache_wbinv_range(start, end)
+#define flush_icache_deferred(mm)		do {} while (0);
+
+#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
+do { \
+	memcpy(dst, src, len); \
+} while (0)
+
+#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
+do { \
+	memcpy(dst, src, len); \
+	cache_wbinv_all(); \
+} while (0)
+
+#endif /* __ABI_CSKY_CACHEFLUSH_H */
diff --git a/arch/csky/abiv1/inc/abi/ckmmu.h b/arch/csky/abiv1/inc/abi/ckmmu.h
new file mode 100644
index 000000000..416b30c57
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/ckmmu.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_CKMMUV1_H
+#define __ASM_CSKY_CKMMUV1_H
+#include <abi/reg_ops.h>
+
+static inline int read_mmu_index(void)
+{
+	return cprcr("cpcr0");
+}
+
+static inline void write_mmu_index(int value)
+{
+	cpwcr("cpcr0", value);
+}
+
+static inline int read_mmu_entrylo0(void)
+{
+	return cprcr("cpcr2") << 6;
+}
+
+static inline int read_mmu_entrylo1(void)
+{
+	return cprcr("cpcr3") << 6;
+}
+
+static inline void write_mmu_pagemask(int value)
+{
+	cpwcr("cpcr6", value);
+}
+
+static inline int read_mmu_entryhi(void)
+{
+	return cprcr("cpcr4");
+}
+
+static inline void write_mmu_entryhi(int value)
+{
+	cpwcr("cpcr4", value);
+}
+
+static inline unsigned long read_mmu_msa0(void)
+{
+	return cprcr("cpcr30");
+}
+
+static inline void write_mmu_msa0(unsigned long value)
+{
+	cpwcr("cpcr30", value);
+}
+
+static inline unsigned long read_mmu_msa1(void)
+{
+	return cprcr("cpcr31");
+}
+
+static inline void write_mmu_msa1(unsigned long value)
+{
+	cpwcr("cpcr31", value);
+}
+
+/*
+ * TLB operations.
+ */
+static inline void tlb_probe(void)
+{
+	cpwcr("cpcr8", 0x80000000);
+}
+
+static inline void tlb_read(void)
+{
+	cpwcr("cpcr8", 0x40000000);
+}
+
+static inline void tlb_invalid_all(void)
+{
+	cpwcr("cpcr8", 0x04000000);
+}
+
+
+static inline void local_tlb_invalid_all(void)
+{
+	tlb_invalid_all();
+}
+
+static inline void tlb_invalid_indexed(void)
+{
+	cpwcr("cpcr8", 0x02000000);
+}
+
+static inline void setup_pgd(pgd_t *pgd, int asid)
+{
+	cpwcr("cpcr29", __pa(pgd) | BIT(0));
+	write_mmu_entryhi(asid);
+}
+
+static inline pgd_t *get_pgd(void)
+{
+	return __va(cprcr("cpcr29") & ~BIT(0));
+}
+#endif /* __ASM_CSKY_CKMMUV1_H */
diff --git a/arch/csky/abiv1/inc/abi/elf.h b/arch/csky/abiv1/inc/abi/elf.h
new file mode 100644
index 000000000..3058cc06b
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/elf.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_ELF_H
+#define __ABI_CSKY_ELF_H
+
+#define ELF_CORE_COPY_REGS(pr_reg, regs) do {	\
+	pr_reg[0] = regs->pc;			\
+	pr_reg[1] = regs->regs[9];		\
+	pr_reg[2] = regs->usp;			\
+	pr_reg[3] = regs->sr;			\
+	pr_reg[4] = regs->a0;			\
+	pr_reg[5] = regs->a1;			\
+	pr_reg[6] = regs->a2;			\
+	pr_reg[7] = regs->a3;			\
+	pr_reg[8] = regs->regs[0];		\
+	pr_reg[9] = regs->regs[1];		\
+	pr_reg[10] = regs->regs[2];		\
+	pr_reg[11] = regs->regs[3];		\
+	pr_reg[12] = regs->regs[4];		\
+	pr_reg[13] = regs->regs[5];		\
+	pr_reg[14] = regs->regs[6];		\
+	pr_reg[15] = regs->regs[7];		\
+	pr_reg[16] = regs->regs[8];		\
+	pr_reg[17] = regs->lr;			\
+} while (0);
+#endif /* __ABI_CSKY_ELF_H */
diff --git a/arch/csky/abiv1/inc/abi/entry.h b/arch/csky/abiv1/inc/abi/entry.h
new file mode 100644
index 000000000..b6a2109b8
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/entry.h
@@ -0,0 +1,176 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_ENTRY_H
+#define __ASM_CSKY_ENTRY_H
+
+#include <asm/setup.h>
+#include <abi/regdef.h>
+
+#define LSAVE_PC	8
+#define LSAVE_PSR	12
+#define LSAVE_A0	24
+#define LSAVE_A1	28
+#define LSAVE_A2	32
+#define LSAVE_A3	36
+#define LSAVE_A4	40
+#define LSAVE_A5	44
+
+#define usp ss1
+
+.macro USPTOKSP
+	mtcr	sp, usp
+	mfcr	sp, ss0
+.endm
+
+.macro KSPTOUSP
+	mtcr	sp, ss0
+	mfcr	sp, usp
+.endm
+
+.macro	SAVE_ALL epc_inc
+	mtcr    r13, ss2
+	mfcr    r13, epsr
+	btsti   r13, 31
+	bt      1f
+	USPTOKSP
+1:
+	subi    sp, 32
+	subi    sp, 32
+	subi    sp, 16
+	stw     r13, (sp, 12)
+
+	stw     lr, (sp, 4)
+
+	mfcr	lr, epc
+	movi	r13, \epc_inc
+	add	lr, r13
+	stw     lr, (sp, 8)
+
+	mov	lr, sp
+	addi	lr, 32
+	addi	lr, 32
+	addi	lr, 16
+	bt	2f
+	mfcr	lr, ss1
+2:
+	stw     lr, (sp, 16)
+
+	stw     a0, (sp, 20)
+	stw     a0, (sp, 24)
+	stw     a1, (sp, 28)
+	stw     a2, (sp, 32)
+	stw     a3, (sp, 36)
+
+	addi	sp, 32
+	addi	sp, 8
+	mfcr    r13, ss2
+	stw	r6, (sp)
+	stw	r7, (sp, 4)
+	stw	r8, (sp, 8)
+	stw	r9, (sp, 12)
+	stw	r10, (sp, 16)
+	stw	r11, (sp, 20)
+	stw	r12, (sp, 24)
+	stw	r13, (sp, 28)
+	stw	r14, (sp, 32)
+	stw	r1, (sp, 36)
+	subi	sp, 32
+	subi	sp, 8
+.endm
+
+.macro	RESTORE_ALL
+	ldw	lr, (sp, 4)
+	ldw     a0, (sp, 8)
+	mtcr    a0, epc
+	ldw     a0, (sp, 12)
+	mtcr    a0, epsr
+	btsti   a0, 31
+	bt      1f
+	ldw     a0, (sp, 16)
+	mtcr	a0, ss1
+1:
+	ldw     a0, (sp, 24)
+	ldw     a1, (sp, 28)
+	ldw     a2, (sp, 32)
+	ldw     a3, (sp, 36)
+
+	addi	sp, 32
+	addi	sp, 8
+	ldw	r6, (sp)
+	ldw	r7, (sp, 4)
+	ldw	r8, (sp, 8)
+	ldw	r9, (sp, 12)
+	ldw	r10, (sp, 16)
+	ldw	r11, (sp, 20)
+	ldw	r12, (sp, 24)
+	ldw	r13, (sp, 28)
+	ldw	r14, (sp, 32)
+	ldw	r1, (sp, 36)
+	addi	sp, 32
+	addi	sp, 8
+
+	bt      2f
+	KSPTOUSP
+2:
+	rte
+.endm
+
+.macro SAVE_SWITCH_STACK
+	subi    sp, 32
+	stm     r8-r15, (sp)
+.endm
+
+.macro RESTORE_SWITCH_STACK
+	ldm     r8-r15, (sp)
+	addi    sp, 32
+.endm
+
+/* MMU registers operators. */
+.macro RD_MIR	rx
+	cprcr   \rx, cpcr0
+.endm
+
+.macro RD_MEH	rx
+	cprcr   \rx, cpcr4
+.endm
+
+.macro RD_MCIR	rx
+	cprcr   \rx, cpcr8
+.endm
+
+.macro RD_PGDR  rx
+	cprcr   \rx, cpcr29
+.endm
+
+.macro WR_MEH	rx
+	cpwcr   \rx, cpcr4
+.endm
+
+.macro WR_MCIR	rx
+	cpwcr   \rx, cpcr8
+.endm
+
+.macro SETUP_MMU
+	/* Init psr and enable ee */
+	lrw	r6, DEFAULT_PSR_VALUE
+	mtcr    r6, psr
+	psrset  ee
+
+	/* Select MMU as co-processor */
+	cpseti	cp15
+
+	/*
+	 * cpcr30 format:
+	 * 31 - 29 | 28 - 4 | 3 | 2 | 1 | 0
+	 *   BA     Reserved  C   D   V
+	 */
+	cprcr	r6, cpcr30
+	lsri	r6, 29
+	lsli	r6, 29
+	addi	r6, 0xe
+	cpwcr	r6, cpcr30
+
+	movi	r6, 0
+	cpwcr	r6, cpcr31
+.endm
+#endif /* __ASM_CSKY_ENTRY_H */
diff --git a/arch/csky/abiv1/inc/abi/page.h b/arch/csky/abiv1/inc/abi/page.h
new file mode 100644
index 000000000..58307254e
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/page.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <asm/shmparam.h>
+
+extern void flush_dcache_page(struct page *page);
+
+static inline unsigned long pages_do_alias(unsigned long addr1,
+					   unsigned long addr2)
+{
+	return (addr1 ^ addr2) & (SHMLBA-1);
+}
+
+#define clear_user_page clear_user_page
+static inline void clear_user_page(void *addr, unsigned long vaddr,
+				   struct page *page)
+{
+	clear_page(addr);
+	if (pages_do_alias((unsigned long) addr, vaddr & PAGE_MASK))
+		flush_dcache_page(page);
+}
+
+static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
+				  struct page *page)
+{
+	copy_page(to, from);
+	if (pages_do_alias((unsigned long) to, vaddr & PAGE_MASK))
+		flush_dcache_page(page);
+}
diff --git a/arch/csky/abiv1/inc/abi/pgtable-bits.h b/arch/csky/abiv1/inc/abi/pgtable-bits.h
new file mode 100644
index 000000000..ae7a2f76d
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/pgtable-bits.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_PGTABLE_BITS_H
+#define __ASM_CSKY_PGTABLE_BITS_H
+
+/* implemented in software */
+#define _PAGE_PRESENT		(1<<0)
+#define _PAGE_READ		(1<<1)
+#define _PAGE_WRITE		(1<<2)
+#define _PAGE_ACCESSED		(1<<3)
+#define _PAGE_MODIFIED		(1<<4)
+
+/* We borrow bit 9 to store the exclusive marker in swap PTEs. */
+#define _PAGE_SWP_EXCLUSIVE	(1<<9)
+
+/* implemented in hardware */
+#define _PAGE_GLOBAL		(1<<6)
+#define _PAGE_VALID		(1<<7)
+#define _PAGE_DIRTY		(1<<8)
+
+#define _PAGE_CACHE		(3<<9)
+#define _PAGE_UNCACHE		(2<<9)
+#define _PAGE_SO		_PAGE_UNCACHE
+#define _CACHE_MASK		(7<<9)
+
+#define _CACHE_CACHED		_PAGE_CACHE
+#define _CACHE_UNCACHED		_PAGE_UNCACHE
+
+#define _PAGE_PROT_NONE		_PAGE_READ
+
+/*
+ * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
+ * are !pte_none() && !pte_present().
+ *
+ * Format of swap PTE:
+ *     bit          0:    _PAGE_PRESENT (zero)
+ *     bit          1:    _PAGE_READ (zero)
+ *     bit      2 - 5:    swap type[0 - 3]
+ *     bit          6:    _PAGE_GLOBAL (zero)
+ *     bit          7:    _PAGE_VALID (zero)
+ *     bit          8:    swap type[4]
+ *     bit          9:    exclusive marker
+ *     bit    10 - 31:    swap offset
+ */
+#define __swp_type(x)			((((x).val >> 2) & 0xf) | \
+					(((x).val >> 4) & 0x10))
+#define __swp_offset(x)			((x).val >> 10)
+#define __swp_entry(type, offset)	((swp_entry_t) { \
+					((type & 0xf) << 2) | \
+					((type & 0x10) << 4) | \
+					((offset) << 10)})
+
+#define HAVE_ARCH_UNMAPPED_AREA
+
+#endif /* __ASM_CSKY_PGTABLE_BITS_H */
diff --git a/arch/csky/abiv1/inc/abi/reg_ops.h b/arch/csky/abiv1/inc/abi/reg_ops.h
new file mode 100644
index 000000000..abd01a243
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/reg_ops.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_REG_OPS_H
+#define __ABI_REG_OPS_H
+#include <asm/reg_ops.h>
+
+#define cprcr(reg)					\
+({							\
+	unsigned int tmp;				\
+	asm volatile("cprcr %0, "reg"\n":"=b"(tmp));	\
+	tmp;						\
+})
+
+#define cpwcr(reg, val)					\
+({							\
+	asm volatile("cpwcr %0, "reg"\n"::"b"(val));	\
+})
+
+static inline unsigned int mfcr_hint(void)
+{
+	return mfcr("cr30");
+}
+
+static inline unsigned int mfcr_ccr2(void) { return 0; }
+
+#endif /* __ABI_REG_OPS_H */
diff --git a/arch/csky/abiv1/inc/abi/regdef.h b/arch/csky/abiv1/inc/abi/regdef.h
new file mode 100644
index 000000000..c75ecf2ca
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/regdef.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_REGDEF_H
+#define __ASM_CSKY_REGDEF_H
+
+#ifdef __ASSEMBLER__
+#define syscallid	r1
+#else
+#define syscallid	"r1"
+#endif
+
+#define regs_syscallid(regs) regs->regs[9]
+#define regs_fp(regs) regs->regs[2]
+
+/*
+ * PSR format:
+ * | 31 | 30-24 | 23-16 | 15 14 | 13-0 |
+ *   S     CPID     VEC     TM
+ *
+ *    S: Super Mode
+ * CPID: Coprocessor id, only 15 for MMU
+ *  VEC: Exception Number
+ *   TM: Trace Mode
+ */
+#define DEFAULT_PSR_VALUE	0x8f000000
+
+#define SYSTRACE_SAVENUM	2
+
+#define TRAP0_SIZE		2
+
+#endif /* __ASM_CSKY_REGDEF_H */
diff --git a/arch/csky/abiv1/inc/abi/string.h b/arch/csky/abiv1/inc/abi/string.h
new file mode 100644
index 000000000..de50117b9
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/string.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_STRING_H
+#define __ABI_CSKY_STRING_H
+
+#define __HAVE_ARCH_MEMCPY
+extern void *memcpy(void *, const void *, __kernel_size_t);
+
+#define __HAVE_ARCH_MEMMOVE
+extern void *memmove(void *, const void *, __kernel_size_t);
+
+#define __HAVE_ARCH_MEMSET
+extern void *memset(void *, int,  __kernel_size_t);
+
+#endif /* __ABI_CSKY_STRING_H */
diff --git a/arch/csky/abiv1/inc/abi/switch_context.h b/arch/csky/abiv1/inc/abi/switch_context.h
new file mode 100644
index 000000000..ec73fd7c9
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/switch_context.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_PTRACE_H
+#define __ABI_CSKY_PTRACE_H
+
+struct switch_stack {
+	unsigned long r8;
+	unsigned long r9;
+	unsigned long r10;
+	unsigned long r11;
+	unsigned long r12;
+	unsigned long r13;
+	unsigned long r14;
+	unsigned long r15;
+};
+#endif /* __ABI_CSKY_PTRACE_H */
diff --git a/arch/csky/abiv1/inc/abi/vdso.h b/arch/csky/abiv1/inc/abi/vdso.h
new file mode 100644
index 000000000..9e6d0a2fd
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/vdso.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_VDSO_H
+#define __ABI_CSKY_VDSO_H
+
+/* movi r1, 127; addi r1, (139 - 127) */
+#define SET_SYSCALL_ID	.long 0x20b167f1
+
+#endif /* __ABI_CSKY_VDSO_H */
diff --git a/arch/csky/abiv1/mmap.c b/arch/csky/abiv1/mmap.c
new file mode 100644
index 000000000..1047865e8
--- /dev/null
+++ b/arch/csky/abiv1/mmap.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/shm.h>
+#include <linux/sched.h>
+#include <linux/random.h>
+#include <linux/io.h>
+
+#define COLOUR_ALIGN(addr,pgoff)		\
+	((((addr)+SHMLBA-1)&~(SHMLBA-1)) +	\
+	 (((pgoff)<<PAGE_SHIFT) & (SHMLBA-1)))
+
+/*
+ * We need to ensure that shared mappings are correctly aligned to
+ * avoid aliasing issues with VIPT caches.  We need to ensure that
+ * a specific page of an object is always mapped at a multiple of
+ * SHMLBA bytes.
+ *
+ * We unconditionally provide this function for all cases.
+ */
+unsigned long
+arch_get_unmapped_area(struct file *filp, unsigned long addr,
+		unsigned long len, unsigned long pgoff,
+		unsigned long flags, vm_flags_t vm_flags)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int do_align = 0;
+	struct vm_unmapped_area_info info = {
+		.length = len,
+		.low_limit = mm->mmap_base,
+		.high_limit = TASK_SIZE,
+		.align_offset = pgoff << PAGE_SHIFT
+	};
+
+	/*
+	 * We only need to do colour alignment if either the I or D
+	 * caches alias.
+	 */
+	do_align = filp || (flags & MAP_SHARED);
+
+	/*
+	 * We enforce the MAP_FIXED case.
+	 */
+	if (flags & MAP_FIXED) {
+		if (flags & MAP_SHARED &&
+		    (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
+			return -EINVAL;
+		return addr;
+	}
+
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
+	if (addr) {
+		if (do_align)
+			addr = COLOUR_ALIGN(addr, pgoff);
+		else
+			addr = PAGE_ALIGN(addr);
+
+		vma = find_vma(mm, addr);
+		if (TASK_SIZE - len >= addr &&
+		    (!vma || addr + len <= vm_start_gap(vma)))
+			return addr;
+	}
+
+	info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
+	return vm_unmapped_area(&info);
+}
diff --git a/arch/csky/abiv2/Makefile b/arch/csky/abiv2/Makefile
new file mode 100644
index 000000000..ea8005fe0
--- /dev/null
+++ b/arch/csky/abiv2/Makefile
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-y				+= cacheflush.o
+obj-$(CONFIG_CPU_HAS_FPU)	+= fpu.o
+obj-y				+= memcmp.o
+ifeq ($(CONFIG_HAVE_EFFICIENT_UNALIGNED_STRING_OPS), y)
+obj-y				+= memcpy.o
+obj-y				+= memmove.o
+obj-y				+= memset.o
+endif
+obj-y				+= strcmp.o
+obj-y				+= strcpy.o
+obj-y				+= strlen.o
+obj-y				+= strksyms.o
+obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o
diff --git a/arch/csky/abiv2/cacheflush.c b/arch/csky/abiv2/cacheflush.c
new file mode 100644
index 000000000..064b0f0f9
--- /dev/null
+++ b/arch/csky/abiv2/cacheflush.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/cache.h>
+#include <linux/highmem.h>
+#include <linux/mm.h>
+#include <asm/cache.h>
+#include <asm/tlbflush.h>
+
+void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
+		unsigned long address, pte_t *pte, unsigned int nr)
+{
+	unsigned long pfn = pte_pfn(*pte);
+	struct folio *folio;
+	unsigned int i;
+
+	flush_tlb_page(vma, address);
+
+	if (!pfn_valid(pfn))
+		return;
+
+	folio = page_folio(pfn_to_page(pfn));
+
+	if (test_and_set_bit(PG_dcache_clean, &folio->flags.f))
+		return;
+
+	icache_inv_range(address, address + nr*PAGE_SIZE);
+	for (i = 0; i < folio_nr_pages(folio); i++) {
+		unsigned long addr = (unsigned long) kmap_local_folio(folio,
+								i * PAGE_SIZE);
+
+		dcache_wb_range(addr, addr + PAGE_SIZE);
+		if (vma->vm_flags & VM_EXEC)
+			icache_inv_range(addr, addr + PAGE_SIZE);
+		kunmap_local((void *) addr);
+	}
+}
+
+void flush_icache_deferred(struct mm_struct *mm)
+{
+	unsigned int cpu = smp_processor_id();
+	cpumask_t *mask = &mm->context.icache_stale_mask;
+
+	if (cpumask_test_cpu(cpu, mask)) {
+		cpumask_clear_cpu(cpu, mask);
+		/*
+		 * Ensure the remote hart's writes are visible to this hart.
+		 * This pairs with a barrier in flush_icache_mm.
+		 */
+		smp_mb();
+		local_icache_inv_all(NULL);
+	}
+}
+
+void flush_icache_mm_range(struct mm_struct *mm,
+		unsigned long start, unsigned long end)
+{
+	unsigned int cpu;
+	cpumask_t others, *mask;
+
+	preempt_disable();
+
+#ifdef CONFIG_CPU_HAS_ICACHE_INS
+	if (mm == current->mm) {
+		icache_inv_range(start, end);
+		preempt_enable();
+		return;
+	}
+#endif
+
+	/* Mark every hart's icache as needing a flush for this MM. */
+	mask = &mm->context.icache_stale_mask;
+	cpumask_setall(mask);
+
+	/* Flush this hart's I$ now, and mark it as flushed. */
+	cpu = smp_processor_id();
+	cpumask_clear_cpu(cpu, mask);
+	local_icache_inv_all(NULL);
+
+	/*
+	 * Flush the I$ of other harts concurrently executing, and mark them as
+	 * flushed.
+	 */
+	cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu));
+
+	if (mm != current->active_mm || !cpumask_empty(&others)) {
+		on_each_cpu_mask(&others, local_icache_inv_all, NULL, 1);
+		cpumask_clear(mask);
+	}
+
+	preempt_enable();
+}
diff --git a/arch/csky/abiv2/fpu.c b/arch/csky/abiv2/fpu.c
new file mode 100644
index 000000000..5acc5c2e5
--- /dev/null
+++ b/arch/csky/abiv2/fpu.c
@@ -0,0 +1,270 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/ptrace.h>
+#include <linux/uaccess.h>
+#include <abi/reg_ops.h>
+
+#define MTCR_MASK	0xFC00FFE0
+#define MFCR_MASK	0xFC00FFE0
+#define MTCR_DIST	0xC0006420
+#define MFCR_DIST	0xC0006020
+
+/*
+ * fpu_libc_helper() is to help libc to excute:
+ *  - mfcr %a, cr<1, 2>
+ *  - mfcr %a, cr<2, 2>
+ *  - mtcr %a, cr<1, 2>
+ *  - mtcr %a, cr<2, 2>
+ */
+int fpu_libc_helper(struct pt_regs *regs)
+{
+	int fault;
+	unsigned long instrptr, regx = 0;
+	unsigned long index = 0, tmp = 0;
+	unsigned long tinstr = 0;
+	u16 instr_hi, instr_low;
+
+	instrptr = instruction_pointer(regs);
+	if (instrptr & 1)
+		return 0;
+
+	fault = __get_user(instr_low, (u16 *)instrptr);
+	if (fault)
+		return 0;
+
+	fault = __get_user(instr_hi, (u16 *)(instrptr + 2));
+	if (fault)
+		return 0;
+
+	tinstr = instr_hi | ((unsigned long)instr_low << 16);
+
+	if (((tinstr >> 21) & 0x1F) != 2)
+		return 0;
+
+	if ((tinstr & MTCR_MASK) == MTCR_DIST) {
+		index = (tinstr >> 16) & 0x1F;
+		if (index > 13)
+			return 0;
+
+		tmp = tinstr & 0x1F;
+		if (tmp > 2)
+			return 0;
+
+		regx =  *(&regs->a0 + index);
+
+		if (tmp == 1)
+			mtcr("cr<1, 2>", regx);
+		else if (tmp == 2)
+			mtcr("cr<2, 2>", regx);
+		else
+			return 0;
+
+		regs->pc += 4;
+		return 1;
+	}
+
+	if ((tinstr & MFCR_MASK) == MFCR_DIST) {
+		index = tinstr & 0x1F;
+		if (index > 13)
+			return 0;
+
+		tmp = ((tinstr >> 16) & 0x1F);
+		if (tmp > 2)
+			return 0;
+
+		if (tmp == 1)
+			regx = mfcr("cr<1, 2>");
+		else if (tmp == 2)
+			regx = mfcr("cr<2, 2>");
+		else
+			return 0;
+
+		*(&regs->a0 + index) = regx;
+
+		regs->pc += 4;
+		return 1;
+	}
+
+	return 0;
+}
+
+void fpu_fpe(struct pt_regs *regs)
+{
+	int sig, code;
+	unsigned int fesr;
+
+	fesr = mfcr("cr<2, 2>");
+
+	sig = SIGFPE;
+	code = FPE_FLTUNK;
+
+	if (fesr & FPE_ILLE) {
+		sig = SIGILL;
+		code = ILL_ILLOPC;
+	} else if (fesr & FPE_IDC) {
+		sig = SIGILL;
+		code = ILL_ILLOPN;
+	} else if (fesr & FPE_FEC) {
+		sig = SIGFPE;
+		if (fesr & FPE_IOC)
+			code = FPE_FLTINV;
+		else if (fesr & FPE_DZC)
+			code = FPE_FLTDIV;
+		else if (fesr & FPE_UFC)
+			code = FPE_FLTUND;
+		else if (fesr & FPE_OFC)
+			code = FPE_FLTOVF;
+		else if (fesr & FPE_IXC)
+			code = FPE_FLTRES;
+	}
+
+	force_sig_fault(sig, code, (void __user *)regs->pc);
+}
+
+#define FMFVR_FPU_REGS(vrx, vry)	\
+	"fmfvrl %0, "#vrx"\n"		\
+	"fmfvrh %1, "#vrx"\n"		\
+	"fmfvrl %2, "#vry"\n"		\
+	"fmfvrh %3, "#vry"\n"
+
+#define FMTVR_FPU_REGS(vrx, vry)	\
+	"fmtvrl "#vrx", %0\n"		\
+	"fmtvrh "#vrx", %1\n"		\
+	"fmtvrl "#vry", %2\n"		\
+	"fmtvrh "#vry", %3\n"
+
+#define STW_FPU_REGS(a, b, c, d)	\
+	"stw    %0, (%4, "#a")\n"	\
+	"stw    %1, (%4, "#b")\n"	\
+	"stw    %2, (%4, "#c")\n"	\
+	"stw    %3, (%4, "#d")\n"
+
+#define LDW_FPU_REGS(a, b, c, d)	\
+	"ldw    %0, (%4, "#a")\n"	\
+	"ldw    %1, (%4, "#b")\n"	\
+	"ldw    %2, (%4, "#c")\n"	\
+	"ldw    %3, (%4, "#d")\n"
+
+void save_to_user_fp(struct user_fp *user_fp)
+{
+	unsigned long flg;
+	unsigned long tmp1, tmp2;
+	unsigned long *fpregs;
+
+	local_irq_save(flg);
+
+	tmp1 = mfcr("cr<1, 2>");
+	tmp2 = mfcr("cr<2, 2>");
+
+	user_fp->fcr = tmp1;
+	user_fp->fesr = tmp2;
+
+	fpregs = &user_fp->vr[0];
+#ifdef CONFIG_CPU_HAS_FPUV2
+#ifdef CONFIG_CPU_HAS_VDSP
+	asm volatile(
+		"vstmu.32    vr0-vr3,   (%0)\n"
+		"vstmu.32    vr4-vr7,   (%0)\n"
+		"vstmu.32    vr8-vr11,  (%0)\n"
+		"vstmu.32    vr12-vr15, (%0)\n"
+		"fstmu.64    vr16-vr31, (%0)\n"
+		: "+a"(fpregs)
+		::"memory");
+#else
+	asm volatile(
+		"fstmu.64    vr0-vr31,  (%0)\n"
+		: "+a"(fpregs)
+		::"memory");
+#endif
+#else
+	{
+	unsigned long tmp3, tmp4;
+
+	asm volatile(
+		FMFVR_FPU_REGS(vr0, vr1)
+		STW_FPU_REGS(0, 4, 16, 20)
+		FMFVR_FPU_REGS(vr2, vr3)
+		STW_FPU_REGS(32, 36, 48, 52)
+		FMFVR_FPU_REGS(vr4, vr5)
+		STW_FPU_REGS(64, 68, 80, 84)
+		FMFVR_FPU_REGS(vr6, vr7)
+		STW_FPU_REGS(96, 100, 112, 116)
+		"addi	%4, 128\n"
+		FMFVR_FPU_REGS(vr8, vr9)
+		STW_FPU_REGS(0, 4, 16, 20)
+		FMFVR_FPU_REGS(vr10, vr11)
+		STW_FPU_REGS(32, 36, 48, 52)
+		FMFVR_FPU_REGS(vr12, vr13)
+		STW_FPU_REGS(64, 68, 80, 84)
+		FMFVR_FPU_REGS(vr14, vr15)
+		STW_FPU_REGS(96, 100, 112, 116)
+		: "=a"(tmp1), "=a"(tmp2), "=a"(tmp3),
+		  "=a"(tmp4), "+a"(fpregs)
+		::"memory");
+	}
+#endif
+
+	local_irq_restore(flg);
+}
+
+void restore_from_user_fp(struct user_fp *user_fp)
+{
+	unsigned long flg;
+	unsigned long tmp1, tmp2;
+	unsigned long *fpregs;
+
+	local_irq_save(flg);
+
+	tmp1 = user_fp->fcr;
+	tmp2 = user_fp->fesr;
+
+	mtcr("cr<1, 2>", tmp1);
+	mtcr("cr<2, 2>", tmp2);
+
+	fpregs = &user_fp->vr[0];
+#ifdef CONFIG_CPU_HAS_FPUV2
+#ifdef CONFIG_CPU_HAS_VDSP
+	asm volatile(
+		"vldmu.32    vr0-vr3,   (%0)\n"
+		"vldmu.32    vr4-vr7,   (%0)\n"
+		"vldmu.32    vr8-vr11,  (%0)\n"
+		"vldmu.32    vr12-vr15, (%0)\n"
+		"fldmu.64    vr16-vr31, (%0)\n"
+		: "+a"(fpregs)
+		::"memory");
+#else
+	asm volatile(
+		"fldmu.64    vr0-vr31,  (%0)\n"
+		: "+a"(fpregs)
+		::"memory");
+#endif
+#else
+	{
+	unsigned long tmp3, tmp4;
+
+	asm volatile(
+		LDW_FPU_REGS(0, 4, 16, 20)
+		FMTVR_FPU_REGS(vr0, vr1)
+		LDW_FPU_REGS(32, 36, 48, 52)
+		FMTVR_FPU_REGS(vr2, vr3)
+		LDW_FPU_REGS(64, 68, 80, 84)
+		FMTVR_FPU_REGS(vr4, vr5)
+		LDW_FPU_REGS(96, 100, 112, 116)
+		FMTVR_FPU_REGS(vr6, vr7)
+		"addi	%4, 128\n"
+		LDW_FPU_REGS(0, 4, 16, 20)
+		FMTVR_FPU_REGS(vr8, vr9)
+		LDW_FPU_REGS(32, 36, 48, 52)
+		FMTVR_FPU_REGS(vr10, vr11)
+		LDW_FPU_REGS(64, 68, 80, 84)
+		FMTVR_FPU_REGS(vr12, vr13)
+		LDW_FPU_REGS(96, 100, 112, 116)
+		FMTVR_FPU_REGS(vr14, vr15)
+		: "=a"(tmp1), "=a"(tmp2), "=a"(tmp3),
+		  "=a"(tmp4), "+a"(fpregs)
+		::"memory");
+	}
+#endif
+	local_irq_restore(flg);
+}
diff --git a/arch/csky/abiv2/inc/abi/cacheflush.h b/arch/csky/abiv2/inc/abi/cacheflush.h
new file mode 100644
index 000000000..da51a0f02
--- /dev/null
+++ b/arch/csky/abiv2/inc/abi/cacheflush.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_CACHEFLUSH_H
+#define __ABI_CSKY_CACHEFLUSH_H
+
+/* Keep includes the same across arches.  */
+#include <linux/mm.h>
+
+/*
+ * The cache doesn't need to be flushed when TLB entries change when
+ * the cache is mapped to physical memory, not virtual memory
+ */
+#define flush_cache_all()			do { } while (0)
+#define flush_cache_mm(mm)			do { } while (0)
+#define flush_cache_dup_mm(mm)			do { } while (0)
+#define flush_cache_range(vma, start, end)	do { } while (0)
+#define flush_cache_page(vma, vmaddr, pfn)	do { } while (0)
+
+#define PG_dcache_clean		PG_arch_1
+
+static inline void flush_dcache_folio(struct folio *folio)
+{
+	if (test_bit(PG_dcache_clean, &folio->flags.f))
+		clear_bit(PG_dcache_clean, &folio->flags.f);
+}
+#define flush_dcache_folio flush_dcache_folio
+
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
+static inline void flush_dcache_page(struct page *page)
+{
+	flush_dcache_folio(page_folio(page));
+}
+
+#define flush_dcache_mmap_lock(mapping)		do { } while (0)
+#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
+
+#define flush_icache_range(start, end)		cache_wbinv_range(start, end)
+
+void flush_icache_mm_range(struct mm_struct *mm,
+			unsigned long start, unsigned long end);
+void flush_icache_deferred(struct mm_struct *mm);
+
+#define flush_cache_vmap(start, end)		do { } while (0)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
+#define flush_cache_vunmap(start, end)		do { } while (0)
+
+#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
+do { \
+	memcpy(dst, src, len); \
+	if (vma->vm_flags & VM_EXEC) { \
+		dcache_wb_range((unsigned long)dst, \
+				(unsigned long)dst + len); \
+		flush_icache_mm_range(current->mm, \
+				(unsigned long)dst, \
+				(unsigned long)dst + len); \
+		} \
+} while (0)
+#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
+	memcpy(dst, src, len)
+
+#endif /* __ABI_CSKY_CACHEFLUSH_H */
diff --git a/arch/csky/abiv2/inc/abi/ckmmu.h b/arch/csky/abiv2/inc/abi/ckmmu.h
new file mode 100644
index 000000000..64215f238
--- /dev/null
+++ b/arch/csky/abiv2/inc/abi/ckmmu.h
@@ -0,0 +1,139 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_CKMMUV2_H
+#define __ASM_CSKY_CKMMUV2_H
+
+#include <abi/reg_ops.h>
+#include <asm/barrier.h>
+
+static inline int read_mmu_index(void)
+{
+	return mfcr("cr<0, 15>");
+}
+
+static inline void write_mmu_index(int value)
+{
+	mtcr("cr<0, 15>", value);
+}
+
+static inline int read_mmu_entrylo0(void)
+{
+	return mfcr("cr<2, 15>");
+}
+
+static inline int read_mmu_entrylo1(void)
+{
+	return mfcr("cr<3, 15>");
+}
+
+static inline void write_mmu_pagemask(int value)
+{
+	mtcr("cr<6, 15>", value);
+}
+
+static inline int read_mmu_entryhi(void)
+{
+	return mfcr("cr<4, 15>");
+}
+
+static inline void write_mmu_entryhi(int value)
+{
+	mtcr("cr<4, 15>", value);
+}
+
+static inline unsigned long read_mmu_msa0(void)
+{
+	return mfcr("cr<30, 15>");
+}
+
+static inline void write_mmu_msa0(unsigned long value)
+{
+	mtcr("cr<30, 15>", value);
+}
+
+static inline unsigned long read_mmu_msa1(void)
+{
+	return mfcr("cr<31, 15>");
+}
+
+static inline void write_mmu_msa1(unsigned long value)
+{
+	mtcr("cr<31, 15>", value);
+}
+
+/*
+ * TLB operations.
+ */
+static inline void tlb_probe(void)
+{
+	mtcr("cr<8, 15>", 0x80000000);
+}
+
+static inline void tlb_read(void)
+{
+	mtcr("cr<8, 15>", 0x40000000);
+}
+
+static inline void tlb_invalid_all(void)
+{
+#ifdef CONFIG_CPU_HAS_TLBI
+	sync_is();
+	asm volatile(
+		"tlbi.alls	\n"
+		"sync.i		\n"
+		:
+		:
+		: "memory");
+#else
+	mtcr("cr<8, 15>", 0x04000000);
+#endif
+}
+
+static inline void local_tlb_invalid_all(void)
+{
+#ifdef CONFIG_CPU_HAS_TLBI
+	sync_is();
+	asm volatile(
+		"tlbi.all	\n"
+		"sync.i		\n"
+		:
+		:
+		: "memory");
+#else
+	tlb_invalid_all();
+#endif
+}
+
+static inline void tlb_invalid_indexed(void)
+{
+	mtcr("cr<8, 15>", 0x02000000);
+}
+
+#define NOP32 ".long 0x4820c400\n"
+
+static inline void setup_pgd(pgd_t *pgd, int asid)
+{
+#ifdef CONFIG_CPU_HAS_TLBI
+	sync_is();
+#else
+	mb();
+#endif
+	asm volatile(
+#ifdef CONFIG_CPU_HAS_TLBI
+		"mtcr %1, cr<28, 15>	\n"
+#endif
+		"mtcr %1, cr<29, 15>	\n"
+		"mtcr %0, cr< 4, 15>	\n"
+		".rept 64		\n"
+		NOP32
+		".endr			\n"
+		:
+		:"r"(asid), "r"(__pa(pgd) | BIT(0))
+		:"memory");
+}
+
+static inline pgd_t *get_pgd(void)
+{
+	return __va(mfcr("cr<29, 15>") & ~BIT(0));
+}
+#endif /* __ASM_CSKY_CKMMUV2_H */
diff --git a/arch/csky/abiv2/inc/abi/elf.h b/arch/csky/abiv2/inc/abi/elf.h
new file mode 100644
index 000000000..290f49ef4
--- /dev/null
+++ b/arch/csky/abiv2/inc/abi/elf.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_ELF_H
+#define __ABI_CSKY_ELF_H
+
+/* The member sort in array pr_reg[x] is defined by GDB. */
+#define ELF_CORE_COPY_REGS(pr_reg, regs) do {	\
+	pr_reg[0] = regs->pc;			\
+	pr_reg[1] = regs->a1;			\
+	pr_reg[2] = regs->a0;			\
+	pr_reg[3] = regs->sr;			\
+	pr_reg[4] = regs->a2;			\
+	pr_reg[5] = regs->a3;			\
+	pr_reg[6] = regs->regs[0];		\
+	pr_reg[7] = regs->regs[1];		\
+	pr_reg[8] = regs->regs[2];		\
+	pr_reg[9] = regs->regs[3];		\
+	pr_reg[10] = regs->regs[4];		\
+	pr_reg[11] = regs->regs[5];		\
+	pr_reg[12] = regs->regs[6];		\
+	pr_reg[13] = regs->regs[7];		\
+	pr_reg[14] = regs->regs[8];		\
+	pr_reg[15] = regs->regs[9];		\
+	pr_reg[16] = regs->usp;			\
+	pr_reg[17] = regs->lr;			\
+	pr_reg[18] = regs->exregs[0];		\
+	pr_reg[19] = regs->exregs[1];		\
+	pr_reg[20] = regs->exregs[2];		\
+	pr_reg[21] = regs->exregs[3];		\
+	pr_reg[22] = regs->exregs[4];		\
+	pr_reg[23] = regs->exregs[5];		\
+	pr_reg[24] = regs->exregs[6];		\
+	pr_reg[25] = regs->exregs[7];		\
+	pr_reg[26] = regs->exregs[8];		\
+	pr_reg[27] = regs->exregs[9];		\
+	pr_reg[28] = regs->exregs[10];		\
+	pr_reg[29] = regs->exregs[11];		\
+	pr_reg[30] = regs->exregs[12];		\
+	pr_reg[31] = regs->exregs[13];		\
+	pr_reg[32] = regs->exregs[14];		\
+	pr_reg[33] = regs->tls;			\
+} while (0);
+#endif /* __ABI_CSKY_ELF_H */
diff --git a/arch/csky/abiv2/inc/abi/entry.h b/arch/csky/abiv2/inc/abi/entry.h
new file mode 100644
index 000000000..cca63e699
--- /dev/null
+++ b/arch/csky/abiv2/inc/abi/entry.h
@@ -0,0 +1,314 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_ENTRY_H
+#define __ASM_CSKY_ENTRY_H
+
+#include <asm/setup.h>
+#include <abi/regdef.h>
+
+#define LSAVE_PC	8
+#define LSAVE_PSR	12
+#define LSAVE_A0	24
+#define LSAVE_A1	28
+#define LSAVE_A2	32
+#define LSAVE_A3	36
+#define LSAVE_A4	40
+#define LSAVE_A5	44
+
+#define KSPTOUSP
+#define USPTOKSP
+
+#define usp cr<14, 1>
+
+.macro SAVE_ALL epc_inc
+	subi    sp, 152
+	stw	tls, (sp, 0)
+	stw	lr, (sp, 4)
+
+	RD_MEH	lr
+	WR_MEH	lr
+
+	mfcr	lr, epc
+	movi	tls, \epc_inc
+	add	lr, tls
+	stw	lr, (sp, 8)
+
+	mfcr	lr, epsr
+	stw	lr, (sp, 12)
+	btsti   lr, 31
+	bf      1f
+	addi    lr, sp, 152
+	br	2f
+1:
+	mfcr	lr, usp
+2:
+	stw	lr, (sp, 16)
+
+	stw     a0, (sp, 20)
+	stw     a0, (sp, 24)
+	stw     a1, (sp, 28)
+	stw     a2, (sp, 32)
+	stw     a3, (sp, 36)
+
+	addi	sp, 40
+	stm	r4-r13, (sp)
+
+	addi    sp, 40
+	stm     r16-r30, (sp)
+#ifdef CONFIG_CPU_HAS_HILO
+	mfhi	lr
+	stw	lr, (sp, 60)
+	mflo	lr
+	stw	lr, (sp, 64)
+	mfcr	lr, cr14
+	stw	lr, (sp, 68)
+#endif
+	subi	sp, 80
+.endm
+
+.macro	RESTORE_ALL
+	ldw	tls, (sp, 0)
+	ldw	lr, (sp, 4)
+	ldw	a0, (sp, 8)
+	mtcr	a0, epc
+	ldw	a0, (sp, 12)
+	mtcr	a0, epsr
+	btsti   a0, 31
+	ldw	a0, (sp, 16)
+	mtcr	a0, usp
+	mtcr	a0, ss0
+
+#ifdef CONFIG_CPU_HAS_HILO
+	ldw	a0, (sp, 140)
+	mthi	a0
+	ldw	a0, (sp, 144)
+	mtlo	a0
+	ldw	a0, (sp, 148)
+	mtcr	a0, cr14
+#endif
+
+	ldw     a0, (sp, 24)
+	ldw     a1, (sp, 28)
+	ldw     a2, (sp, 32)
+	ldw     a3, (sp, 36)
+
+	addi	sp, 40
+	ldm	r4-r13, (sp)
+	addi    sp, 40
+	ldm     r16-r30, (sp)
+	addi    sp, 72
+	bf	1f
+	mfcr	sp, ss0
+1:
+	rte
+.endm
+
+.macro SAVE_REGS_FTRACE
+	subi    sp, 152
+	stw	tls, (sp, 0)
+	stw	lr, (sp, 4)
+
+	mfcr	lr, psr
+	stw	lr, (sp, 12)
+
+	addi    lr, sp, 152
+	stw	lr, (sp, 16)
+
+	stw     a0, (sp, 20)
+	stw     a0, (sp, 24)
+	stw     a1, (sp, 28)
+	stw     a2, (sp, 32)
+	stw     a3, (sp, 36)
+
+	addi	sp, 40
+	stm	r4-r13, (sp)
+
+	addi    sp, 40
+	stm     r16-r30, (sp)
+#ifdef CONFIG_CPU_HAS_HILO
+	mfhi	lr
+	stw	lr, (sp, 60)
+	mflo	lr
+	stw	lr, (sp, 64)
+	mfcr	lr, cr14
+	stw	lr, (sp, 68)
+#endif
+	subi	sp, 80
+.endm
+
+.macro	RESTORE_REGS_FTRACE
+	ldw	tls, (sp, 0)
+
+#ifdef CONFIG_CPU_HAS_HILO
+	ldw	a0, (sp, 140)
+	mthi	a0
+	ldw	a0, (sp, 144)
+	mtlo	a0
+	ldw	a0, (sp, 148)
+	mtcr	a0, cr14
+#endif
+
+	ldw     a0, (sp, 24)
+	ldw     a1, (sp, 28)
+	ldw     a2, (sp, 32)
+	ldw     a3, (sp, 36)
+
+	addi	sp, 40
+	ldm	r4-r13, (sp)
+	addi    sp, 40
+	ldm     r16-r30, (sp)
+	addi    sp, 72
+.endm
+
+.macro SAVE_SWITCH_STACK
+	subi    sp, 64
+	stm	r4-r11, (sp)
+	stw	lr,  (sp, 32)
+	stw	r16, (sp, 36)
+	stw	r17, (sp, 40)
+	stw	r26, (sp, 44)
+	stw	r27, (sp, 48)
+	stw	r28, (sp, 52)
+	stw	r29, (sp, 56)
+	stw	r30, (sp, 60)
+#ifdef CONFIG_CPU_HAS_HILO
+	subi	sp, 16
+	mfhi	lr
+	stw	lr, (sp, 0)
+	mflo	lr
+	stw	lr, (sp, 4)
+	mfcr	lr, cr14
+	stw	lr, (sp, 8)
+#endif
+.endm
+
+.macro RESTORE_SWITCH_STACK
+#ifdef CONFIG_CPU_HAS_HILO
+	ldw	lr, (sp, 0)
+	mthi	lr
+	ldw	lr, (sp, 4)
+	mtlo	lr
+	ldw	lr, (sp, 8)
+	mtcr	lr, cr14
+	addi	sp, 16
+#endif
+	ldm	r4-r11, (sp)
+	ldw	lr,  (sp, 32)
+	ldw	r16, (sp, 36)
+	ldw	r17, (sp, 40)
+	ldw	r26, (sp, 44)
+	ldw	r27, (sp, 48)
+	ldw	r28, (sp, 52)
+	ldw	r29, (sp, 56)
+	ldw	r30, (sp, 60)
+	addi	sp, 64
+.endm
+
+/* MMU registers operators. */
+.macro RD_MIR rx
+	mfcr	\rx, cr<0, 15>
+.endm
+
+.macro RD_MEH rx
+	mfcr	\rx, cr<4, 15>
+.endm
+
+.macro RD_MCIR rx
+	mfcr	\rx, cr<8, 15>
+.endm
+
+.macro RD_PGDR rx
+	mfcr	\rx, cr<29, 15>
+.endm
+
+.macro RD_PGDR_K rx
+	mfcr	\rx, cr<28, 15>
+.endm
+
+.macro WR_MEH rx
+	mtcr	\rx, cr<4, 15>
+.endm
+
+.macro WR_MCIR rx
+	mtcr	\rx, cr<8, 15>
+.endm
+
+#ifdef CONFIG_PAGE_OFFSET_80000000
+#define MSA_SET cr<30, 15>
+#define MSA_CLR cr<31, 15>
+#endif
+
+#ifdef CONFIG_PAGE_OFFSET_A0000000
+#define MSA_SET cr<31, 15>
+#define MSA_CLR cr<30, 15>
+#endif
+
+.macro SETUP_MMU
+	/* Init psr and enable ee */
+	lrw	r6, DEFAULT_PSR_VALUE
+	mtcr    r6, psr
+	psrset  ee
+
+	/* Invalid I/Dcache BTB BHT */
+	movi	r6, 7
+	lsli	r6, 16
+	addi	r6, (1<<4) | 3
+	mtcr	r6, cr17
+
+	/* Invalid all TLB */
+	bgeni   r6, 26
+	mtcr	r6, cr<8, 15> /* Set MCIR */
+
+	/* Check MMU on/off */
+	mfcr	r6, cr18
+	btsti	r6, 0
+	bt	1f
+
+	/* MMU off: setup mapping tlb entry */
+	movi	r6, 0
+	mtcr	r6, cr<6, 15> /* Set MPR with 4K page size */
+
+	grs	r6, 1f /* Get current pa by PC */
+	bmaski  r7, (PAGE_SHIFT + 1) /* r7 = 0x1fff */
+	andn    r6, r7
+	mtcr	r6, cr<4, 15> /* Set MEH */
+
+	mov	r8, r6
+	movi    r7, 0x00000006
+	or      r8, r7
+	mtcr	r8, cr<2, 15> /* Set MEL0 */
+	movi    r7, 0x00001006
+	or      r8, r7
+	mtcr	r8, cr<3, 15> /* Set MEL1 */
+
+	bgeni   r8, 28
+	mtcr	r8, cr<8, 15> /* Set MCIR to write TLB */
+
+	br	2f
+1:
+	/*
+	 * MMU on: use origin MSA value from bootloader
+	 *
+	 * cr<30/31, 15> MSA register format:
+	 * 31 - 29 | 28 - 9 | 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0
+	 *   BA     Reserved  SH  WA  B   SO SEC  C   D   V
+	 */
+	mfcr	r6, MSA_SET /* Get MSA */
+2:
+	lsri	r6, 29
+	lsli	r6, 29
+	addi	r6, 0x1ce
+	mtcr	r6, MSA_SET /* Set MSA */
+
+	movi    r6, 0
+	mtcr	r6, MSA_CLR /* Clr MSA */
+
+	/* enable MMU */
+	mfcr    r6, cr18
+	bseti	r6, 0
+	mtcr    r6, cr18
+
+	jmpi	3f /* jump to va */
+3:
+.endm
+#endif /* __ASM_CSKY_ENTRY_H */
diff --git a/arch/csky/abiv2/inc/abi/fpu.h b/arch/csky/abiv2/inc/abi/fpu.h
new file mode 100644
index 000000000..aabb79355
--- /dev/null
+++ b/arch/csky/abiv2/inc/abi/fpu.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_FPU_H
+#define __ASM_CSKY_FPU_H
+
+#include <asm/sigcontext.h>
+#include <asm/ptrace.h>
+
+int fpu_libc_helper(struct pt_regs *regs);
+void fpu_fpe(struct pt_regs *regs);
+
+static inline void init_fpu(void) { mtcr("cr<1, 2>", 0); }
+
+void save_to_user_fp(struct user_fp *user_fp);
+void restore_from_user_fp(struct user_fp *user_fp);
+
+/*
+ * Define the fesr bit for fpe handle.
+ */
+#define  FPE_ILLE  (1 << 16)    /* Illegal instruction  */
+#define  FPE_FEC   (1 << 7)     /* Input float-point arithmetic exception */
+#define  FPE_IDC   (1 << 5)     /* Input denormalized exception */
+#define  FPE_IXC   (1 << 4)     /* Inexact exception */
+#define  FPE_UFC   (1 << 3)     /* Underflow exception */
+#define  FPE_OFC   (1 << 2)     /* Overflow exception */
+#define  FPE_DZC   (1 << 1)     /* Divide by zero exception */
+#define  FPE_IOC   (1 << 0)     /* Invalid operation exception */
+#define  FPE_REGULAR_EXCEPTION (FPE_IXC | FPE_UFC | FPE_OFC | FPE_DZC | FPE_IOC)
+
+#ifdef CONFIG_OPEN_FPU_IDE
+#define IDE_STAT   (1 << 5)
+#else
+#define IDE_STAT   0
+#endif
+
+#ifdef CONFIG_OPEN_FPU_IXE
+#define IXE_STAT   (1 << 4)
+#else
+#define IXE_STAT   0
+#endif
+
+#ifdef CONFIG_OPEN_FPU_UFE
+#define UFE_STAT   (1 << 3)
+#else
+#define UFE_STAT   0
+#endif
+
+#ifdef CONFIG_OPEN_FPU_OFE
+#define OFE_STAT   (1 << 2)
+#else
+#define OFE_STAT   0
+#endif
+
+#ifdef CONFIG_OPEN_FPU_DZE
+#define DZE_STAT   (1 << 1)
+#else
+#define DZE_STAT   0
+#endif
+
+#ifdef CONFIG_OPEN_FPU_IOE
+#define IOE_STAT   (1 << 0)
+#else
+#define IOE_STAT   0
+#endif
+
+#endif /* __ASM_CSKY_FPU_H */
diff --git a/arch/csky/abiv2/inc/abi/page.h b/arch/csky/abiv2/inc/abi/page.h
new file mode 100644
index 000000000..a5a255013
--- /dev/null
+++ b/arch/csky/abiv2/inc/abi/page.h
@@ -0,0 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
+				  struct page *page)
+{
+	copy_page(to, from);
+}
diff --git a/arch/csky/abiv2/inc/abi/pgtable-bits.h b/arch/csky/abiv2/inc/abi/pgtable-bits.h
new file mode 100644
index 000000000..526152bd2
--- /dev/null
+++ b/arch/csky/abiv2/inc/abi/pgtable-bits.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_PGTABLE_BITS_H
+#define __ASM_CSKY_PGTABLE_BITS_H
+
+/* implemented in software */
+#define _PAGE_ACCESSED		(1<<7)
+#define _PAGE_READ		(1<<8)
+#define _PAGE_WRITE		(1<<9)
+#define _PAGE_PRESENT		(1<<10)
+#define _PAGE_MODIFIED		(1<<11)
+
+/* We borrow bit 7 to store the exclusive marker in swap PTEs. */
+#define _PAGE_SWP_EXCLUSIVE	(1<<7)
+
+/* implemented in hardware */
+#define _PAGE_GLOBAL		(1<<0)
+#define _PAGE_VALID		(1<<1)
+#define _PAGE_DIRTY		(1<<2)
+
+#define _PAGE_SO		(1<<5)
+#define _PAGE_BUF		(1<<6)
+#define _PAGE_CACHE		(1<<3)
+#define _CACHE_MASK		_PAGE_CACHE
+
+#define _CACHE_CACHED		(_PAGE_CACHE | _PAGE_BUF)
+#define _CACHE_UNCACHED		(0)
+
+#define _PAGE_PROT_NONE		_PAGE_WRITE
+
+/*
+ * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
+ * are !pte_none() && !pte_present().
+ *
+ * Format of swap PTE:
+ *     bit          0:    _PAGE_GLOBAL (zero)
+ *     bit          1:    _PAGE_VALID (zero)
+ *     bit      2 - 6:    swap type
+ *     bit          7:    exclusive marker
+ *     bit          8:    swap offset[0]
+ *     bit          9:    _PAGE_WRITE (zero)
+ *     bit         10:    _PAGE_PRESENT (zero)
+ *     bit    11 - 31:    swap offset[1 - 21]
+ */
+#define __swp_type(x)			(((x).val >> 2) & 0x1f)
+#define __swp_offset(x)			((((x).val >> 8) & 0x1) | \
+					(((x).val >> 10) & 0x3ffffe))
+#define __swp_entry(type, offset)	((swp_entry_t) { \
+					((type & 0x1f) << 2) | \
+					((offset & 0x1) << 8) | \
+					((offset & 0x3ffffe) << 10)})
+
+#endif /* __ASM_CSKY_PGTABLE_BITS_H */
diff --git a/arch/csky/abiv2/inc/abi/reg_ops.h b/arch/csky/abiv2/inc/abi/reg_ops.h
new file mode 100644
index 000000000..49ba18a64
--- /dev/null
+++ b/arch/csky/abiv2/inc/abi/reg_ops.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_REG_OPS_H
+#define __ABI_REG_OPS_H
+#include <asm/reg_ops.h>
+
+static inline unsigned int mfcr_hint(void)
+{
+	return mfcr("cr31");
+}
+
+static inline unsigned int mfcr_ccr2(void)
+{
+	return mfcr("cr23");
+}
+#endif /* __ABI_REG_OPS_H */
diff --git a/arch/csky/abiv2/inc/abi/regdef.h b/arch/csky/abiv2/inc/abi/regdef.h
new file mode 100644
index 000000000..fc08d56cc
--- /dev/null
+++ b/arch/csky/abiv2/inc/abi/regdef.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_REGDEF_H
+#define __ASM_CSKY_REGDEF_H
+
+#ifdef __ASSEMBLER__
+#define syscallid	r7
+#else
+#define syscallid	"r7"
+#endif
+
+#define regs_syscallid(regs) regs->regs[3]
+#define regs_fp(regs) regs->regs[4]
+
+/*
+ * PSR format:
+ * | 31 | 30-24 | 23-16 | 15 14 | 13-10 | 9 | 8-0 |
+ *   S              VEC     TM            MM
+ *
+ *   S: Super Mode
+ * VEC: Exception Number
+ *  TM: Trace Mode
+ *  MM: Memory unaligned addr access
+ */
+#define DEFAULT_PSR_VALUE	0x80000200
+
+#define SYSTRACE_SAVENUM	5
+
+#define TRAP0_SIZE		4
+
+#endif /* __ASM_CSKY_REGDEF_H */
diff --git a/arch/csky/abiv2/inc/abi/string.h b/arch/csky/abiv2/inc/abi/string.h
new file mode 100644
index 000000000..f01bad2ac
--- /dev/null
+++ b/arch/csky/abiv2/inc/abi/string.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_STRING_H
+#define __ABI_CSKY_STRING_H
+
+#define __HAVE_ARCH_MEMCMP
+extern int memcmp(const void *, const void *, __kernel_size_t);
+
+#define __HAVE_ARCH_MEMCPY
+extern void *memcpy(void *, const void *, __kernel_size_t);
+
+#define __HAVE_ARCH_MEMMOVE
+extern void *memmove(void *, const void *, __kernel_size_t);
+
+#define __HAVE_ARCH_MEMSET
+extern void *memset(void *, int,  __kernel_size_t);
+
+#define __HAVE_ARCH_STRCMP
+extern int strcmp(const char *, const char *);
+
+#define __HAVE_ARCH_STRCPY
+extern char *strcpy(char *, const char *);
+
+#define __HAVE_ARCH_STRLEN
+extern __kernel_size_t strlen(const char *);
+
+#endif /* __ABI_CSKY_STRING_H */
diff --git a/arch/csky/abiv2/inc/abi/switch_context.h b/arch/csky/abiv2/inc/abi/switch_context.h
new file mode 100644
index 000000000..5dd5c3f4e
--- /dev/null
+++ b/arch/csky/abiv2/inc/abi/switch_context.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_PTRACE_H
+#define __ABI_CSKY_PTRACE_H
+
+struct switch_stack {
+#ifdef CONFIG_CPU_HAS_HILO
+	unsigned long rhi;
+	unsigned long rlo;
+	unsigned long cr14;
+	unsigned long pad;
+#endif
+	unsigned long r4;
+	unsigned long r5;
+	unsigned long r6;
+	unsigned long r7;
+	unsigned long r8;
+	unsigned long r9;
+	unsigned long r10;
+	unsigned long r11;
+
+	unsigned long r15;
+	unsigned long r16;
+	unsigned long r17;
+	unsigned long r26;
+	unsigned long r27;
+	unsigned long r28;
+	unsigned long r29;
+	unsigned long r30;
+};
+#endif /* __ABI_CSKY_PTRACE_H */
diff --git a/arch/csky/abiv2/inc/abi/vdso.h b/arch/csky/abiv2/inc/abi/vdso.h
new file mode 100644
index 000000000..40fd10d89
--- /dev/null
+++ b/arch/csky/abiv2/inc/abi/vdso.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_VDSO_H
+#define __ABI_CSKY_VDSO_H
+
+/* movi r7, 173 */
+#define SET_SYSCALL_ID	.long 0x008bea07
+
+#endif /* __ABI_CSKY_VDSO_H */
diff --git a/arch/csky/abiv2/mcount.S b/arch/csky/abiv2/mcount.S
new file mode 100644
index 000000000..d745e10c1
--- /dev/null
+++ b/arch/csky/abiv2/mcount.S
@@ -0,0 +1,211 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/linkage.h>
+#include <asm/ftrace.h>
+#include <abi/entry.h>
+#include <asm/asm-offsets.h>
+
+/*
+ * csky-gcc with -pg will put the following asm after prologue:
+ *      push	r15
+ *      jsri	_mcount
+ *
+ * stack layout after mcount_enter in _mcount():
+ *
+ * current sp => 0:+-------+
+ *                 | a0-a3 | -> must save all argument regs
+ *             +16:+-------+
+ *                 | lr    | -> _mcount lr (instrumente function's pc)
+ *             +20:+-------+
+ *                 | fp=r8 | -> instrumented function fp
+ *             +24:+-------+
+ *                 | plr   | -> instrumented function lr (parent's pc)
+ *                 +-------+
+ */
+
+.macro mcount_enter
+	subi	sp, 24
+	stw	a0, (sp, 0)
+	stw	a1, (sp, 4)
+	stw	a2, (sp, 8)
+	stw	a3, (sp, 12)
+	stw	lr, (sp, 16)
+	stw	r8, (sp, 20)
+.endm
+
+.macro mcount_exit
+	ldw	a0, (sp, 0)
+	ldw	a1, (sp, 4)
+	ldw	a2, (sp, 8)
+	ldw	a3, (sp, 12)
+	ldw	t1, (sp, 16)
+	ldw	r8, (sp, 20)
+	ldw	lr, (sp, 24)
+	addi	sp, 28
+	jmp	t1
+.endm
+
+.macro mcount_enter_regs
+	subi	sp, 8
+	stw	lr, (sp, 0)
+	stw	r8, (sp, 4)
+	SAVE_REGS_FTRACE
+.endm
+
+.macro mcount_exit_regs
+	RESTORE_REGS_FTRACE
+	subi	sp, 152
+	ldw	t1, (sp, 4)
+	addi	sp, 152
+	ldw	r8, (sp, 4)
+	ldw	lr, (sp, 8)
+	addi	sp, 12
+	jmp	t1
+.endm
+
+.macro save_return_regs
+	subi	sp, 16
+	stw	a0, (sp, 0)
+	stw	a1, (sp, 4)
+	stw	a2, (sp, 8)
+	stw	a3, (sp, 12)
+.endm
+
+.macro restore_return_regs
+	mov	lr, a0
+	ldw	a0, (sp, 0)
+	ldw	a1, (sp, 4)
+	ldw	a2, (sp, 8)
+	ldw	a3, (sp, 12)
+	addi	sp, 16
+.endm
+
+.macro nop32_stub
+	nop32
+	nop32
+	nop32
+.endm
+
+ENTRY(ftrace_stub)
+	jmp	lr
+END(ftrace_stub)
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+ENTRY(_mcount)
+	mcount_enter
+
+	/* r26 is link register, only used with jsri translation */
+	lrw	r26, ftrace_trace_function
+	ldw	r26, (r26, 0)
+	lrw	a1, ftrace_stub
+	cmpne	r26, a1
+	bf	skip_ftrace
+
+	mov	a0, lr
+	subi	a0, 4
+	ldw	a1, (sp, 24)
+	lrw	a2, function_trace_op
+	ldw	a2, (a2, 0)
+
+	jsr	r26
+
+#ifndef CONFIG_FUNCTION_GRAPH_TRACER
+skip_ftrace:
+	mcount_exit
+#else
+skip_ftrace:
+	lrw	a0, ftrace_graph_return
+	ldw	a0, (a0, 0)
+	lrw	a1, ftrace_stub
+	cmpne	a0, a1
+	bt	ftrace_graph_caller
+
+	lrw	a0, ftrace_graph_entry
+	ldw	a0, (a0, 0)
+	lrw	a1, ftrace_graph_entry_stub
+	cmpne	a0, a1
+	bt	ftrace_graph_caller
+
+	mcount_exit
+#endif
+END(_mcount)
+#else /* CONFIG_DYNAMIC_FTRACE */
+ENTRY(_mcount)
+	mov	t1, lr
+	ldw	lr, (sp, 0)
+	addi	sp, 4
+	jmp	t1
+ENDPROC(_mcount)
+
+ENTRY(ftrace_caller)
+	mcount_enter
+
+	ldw	a0, (sp, 16)
+	subi	a0, 4
+	ldw	a1, (sp, 24)
+	lrw	a2, function_trace_op
+	ldw	a2, (a2, 0)
+
+	nop
+GLOBAL(ftrace_call)
+	nop32_stub
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	nop
+GLOBAL(ftrace_graph_call)
+	nop32_stub
+#endif
+
+	mcount_exit
+ENDPROC(ftrace_caller)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+	mov	a0, sp
+	addi	a0, 24
+	ldw	a1, (sp, 16)
+	subi	a1, 4
+	mov	a2, r8
+	lrw	r26, prepare_ftrace_return
+	jsr	r26
+	mcount_exit
+END(ftrace_graph_caller)
+
+ENTRY(return_to_handler)
+	save_return_regs
+	mov	a0, r8
+	jsri	ftrace_return_to_handler
+	restore_return_regs
+	jmp	lr
+END(return_to_handler)
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+ENTRY(ftrace_regs_caller)
+	mcount_enter_regs
+
+	lrw	t1, PT_FRAME_SIZE
+	add	t1, sp
+
+	ldw	a0, (t1, 0)
+	subi	a0, 4
+	ldw	a1, (t1, 8)
+	lrw	a2, function_trace_op
+	ldw	a2, (a2, 0)
+	mov	a3, sp
+
+	nop
+GLOBAL(ftrace_regs_call)
+	nop32_stub
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	nop
+GLOBAL(ftrace_graph_regs_call)
+	nop32_stub
+#endif
+
+	mcount_exit_regs
+ENDPROC(ftrace_regs_caller)
+#endif /* CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/csky/abiv2/memcmp.S b/arch/csky/abiv2/memcmp.S
new file mode 100644
index 000000000..bf0d809f0
--- /dev/null
+++ b/arch/csky/abiv2/memcmp.S
@@ -0,0 +1,152 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/linkage.h>
+#include "sysdep.h"
+
+ENTRY(memcmp)
+	/* Test if len less than 4 bytes.  */
+	mov	r3, r0
+	movi	r0, 0
+	mov	r12, r4
+	cmplti	r2, 4
+	bt	.L_compare_by_byte
+
+	andi	r13, r0, 3
+	movi	r19, 4
+
+	/* Test if s1 is not 4 bytes aligned.  */
+	bnez	r13, .L_s1_not_aligned
+
+	LABLE_ALIGN
+.L_s1_aligned:
+	/* If dest is aligned, then copy.  */
+	zext	r18, r2, 31, 4
+	/* Test if len less than 16 bytes.  */
+	bez	r18, .L_compare_by_word
+
+.L_compare_by_4word:
+	/* If aligned, load word each time.  */
+	ldw	r20, (r3, 0)
+	ldw	r21, (r1, 0)
+	/* If s1[i] != s2[i], goto .L_byte_check.  */
+	cmpne	r20, r21
+	bt	.L_byte_check
+
+	ldw	r20, (r3, 4)
+	ldw	r21, (r1, 4)
+	cmpne	r20, r21
+	bt	.L_byte_check
+
+	ldw	r20, (r3, 8)
+	ldw	r21, (r1, 8)
+	cmpne	r20, r21
+	bt	.L_byte_check
+
+	ldw	r20, (r3, 12)
+	ldw	r21, (r1, 12)
+	cmpne	r20, r21
+	bt	.L_byte_check
+
+	PRE_BNEZAD (r18)
+	addi	a3, 16
+	addi	a1, 16
+
+	BNEZAD (r18, .L_compare_by_4word)
+
+.L_compare_by_word:
+	zext	r18, r2, 3, 2
+	bez	r18, .L_compare_by_byte
+.L_compare_by_word_loop:
+	ldw	r20, (r3, 0)
+	ldw	r21, (r1, 0)
+	addi	r3, 4
+	PRE_BNEZAD (r18)
+	cmpne	r20, r21
+	addi    r1, 4
+	bt	.L_byte_check
+	BNEZAD (r18, .L_compare_by_word_loop)
+
+.L_compare_by_byte:
+        zext    r18, r2, 1, 0
+        bez     r18, .L_return
+.L_compare_by_byte_loop:
+        ldb     r0, (r3, 0)
+        ldb     r4, (r1, 0)
+        addi    r3, 1
+        subu    r0, r4
+        PRE_BNEZAD (r18)
+        addi    r1, 1
+        bnez    r0, .L_return
+        BNEZAD (r18, .L_compare_by_byte_loop)
+
+.L_return:
+        mov     r4, r12
+        rts
+
+# ifdef __CSKYBE__
+/* d[i] != s[i] in word, so we check byte 0.  */
+.L_byte_check:
+        xtrb0   r0, r20
+        xtrb0   r2, r21
+        subu    r0, r2
+        bnez    r0, .L_return
+
+        /* check byte 1 */
+        xtrb1   r0, r20
+        xtrb1   r2, r21
+        subu    r0, r2
+        bnez    r0, .L_return
+
+        /* check byte 2 */
+        xtrb2   r0, r20
+        xtrb2   r2, r21
+        subu    r0, r2
+        bnez    r0, .L_return
+
+        /* check byte 3 */
+        xtrb3   r0, r20
+        xtrb3   r2, r21
+        subu    r0, r2
+# else
+/* s1[i] != s2[i] in word, so we check byte 3.  */
+.L_byte_check:
+	xtrb3	r0, r20
+	xtrb3	r2, r21
+        subu    r0, r2
+        bnez    r0, .L_return
+
+	/* check byte 2 */
+	xtrb2	r0, r20
+	xtrb2	r2, r21
+        subu    r0, r2
+        bnez    r0, .L_return
+
+	/* check byte 1 */
+	xtrb1	r0, r20
+	xtrb1	r2, r21
+	subu	r0, r2
+	bnez    r0, .L_return
+
+	/* check byte 0 */
+	xtrb0	r0, r20
+	xtrb0	r2, r21
+	subu	r0, r2
+	br	.L_return
+# endif /* !__CSKYBE__ */
+
+/* Compare when s1 is not aligned.  */
+.L_s1_not_aligned:
+	sub	r13, r19, r13
+	sub	r2, r13
+.L_s1_not_aligned_loop:
+	ldb	r0, (r3, 0)
+	ldb	r4, (r1, 0)
+	addi	r3, 1
+	subu	r0, r4
+	PRE_BNEZAD (r13)
+	addi	r1, 1
+	bnez	r0, .L_return
+	BNEZAD (r13, .L_s1_not_aligned_loop)
+	br	.L_s1_aligned
+ENDPROC(memcmp)
diff --git a/arch/csky/abiv2/memcpy.S b/arch/csky/abiv2/memcpy.S
new file mode 100644
index 000000000..145bf3a93
--- /dev/null
+++ b/arch/csky/abiv2/memcpy.S
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/linkage.h>
+#include "sysdep.h"
+
+ENTRY(__memcpy)
+ENTRY(memcpy)
+	/* Test if len less than 4 bytes.  */
+	mov	r12, r0
+	cmplti	r2, 4
+	bt	.L_copy_by_byte
+
+	andi	r13, r0, 3
+	movi	r19, 4
+	/* Test if dest is not 4 bytes aligned.  */
+	bnez	r13, .L_dest_not_aligned
+
+/* Hardware can handle unaligned access directly.  */
+.L_dest_aligned:
+	/* If dest is aligned, then copy.  */
+	zext	r18, r2, 31, 4
+
+	/* Test if len less than 16 bytes.  */
+	bez	r18, .L_len_less_16bytes
+	movi	r19, 0
+
+	LABLE_ALIGN
+.L_len_larger_16bytes:
+#if defined(__CK860__)
+	ldw	r3, (r1, 0)
+	stw	r3, (r0, 0)
+	ldw	r3, (r1, 4)
+	stw	r3, (r0, 4)
+	ldw	r3, (r1, 8)
+	stw	r3, (r0, 8)
+	ldw	r3, (r1, 12)
+	addi	r1, 16
+	stw	r3, (r0, 12)
+	addi	r0, 16
+#else
+	ldw	r20, (r1, 0)
+	ldw	r21, (r1, 4)
+	ldw	r22, (r1, 8)
+	ldw	r23, (r1, 12)
+	stw	r20, (r0, 0)
+	stw	r21, (r0, 4)
+	stw	r22, (r0, 8)
+	stw	r23, (r0, 12)
+	PRE_BNEZAD (r18)
+	addi	r1, 16
+	addi	r0, 16
+#endif
+	BNEZAD (r18, .L_len_larger_16bytes)
+
+.L_len_less_16bytes:
+	zext	r18, r2, 3, 2
+	bez	r18, .L_copy_by_byte
+.L_len_less_16bytes_loop:
+	ldw	r3, (r1, 0)
+	PRE_BNEZAD (r18)
+	addi	r1, 4
+	stw	r3, (r0, 0)
+	addi	r0, 4
+	BNEZAD (r18, .L_len_less_16bytes_loop)
+
+/* Test if len less than 4 bytes.  */
+.L_copy_by_byte:
+	zext	r18, r2, 1, 0
+	bez	r18, .L_return
+.L_copy_by_byte_loop:
+	ldb	r3, (r1, 0)
+	PRE_BNEZAD (r18)
+	addi	r1, 1
+	stb	r3, (r0, 0)
+	addi	r0, 1
+	BNEZAD (r18, .L_copy_by_byte_loop)
+
+.L_return:
+	mov	r0, r12
+	rts
+
+/*
+ * If dest is not aligned, just copying some bytes makes the
+ * dest align.
+ */
+.L_dest_not_aligned:
+	sub	r13, r19, r13
+	sub	r2, r13
+
+/* Makes the dest align.  */
+.L_dest_not_aligned_loop:
+	ldb	r3, (r1, 0)
+	PRE_BNEZAD (r13)
+	addi	r1, 1
+	stb	r3, (r0, 0)
+	addi	r0, 1
+	BNEZAD (r13, .L_dest_not_aligned_loop)
+	cmplti	r2, 4
+	bt	.L_copy_by_byte
+
+	/* Check whether the src is aligned.  */
+	jbr	.L_dest_aligned
+ENDPROC(__memcpy)
diff --git a/arch/csky/abiv2/memmove.S b/arch/csky/abiv2/memmove.S
new file mode 100644
index 000000000..5721e73ad
--- /dev/null
+++ b/arch/csky/abiv2/memmove.S
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/linkage.h>
+#include "sysdep.h"
+
+	.weak memmove
+ENTRY(__memmove)
+ENTRY(memmove)
+	subu	r3, r0, r1
+	cmphs	r3, r2
+	bt	memcpy
+
+	mov	r12, r0
+	addu	r0, r0, r2
+	addu	r1, r1, r2
+
+	/* Test if len less than 4 bytes.  */
+	cmplti	r2, 4
+	bt	.L_copy_by_byte
+
+	andi	r13, r0, 3
+	/* Test if dest is not 4 bytes aligned.  */
+	bnez	r13, .L_dest_not_aligned
+	/* Hardware can handle unaligned access directly.  */
+.L_dest_aligned:
+	/* If dest is aligned, then copy.  */
+	zext	r18, r2, 31, 4
+	/* Test if len less than 16 bytes.  */
+	bez	r18, .L_len_less_16bytes
+	movi	r19, 0
+
+	/* len > 16 bytes */
+	LABLE_ALIGN
+.L_len_larger_16bytes:
+	subi	r1, 16
+	subi	r0, 16
+#if defined(__CK860__)
+	ldw	r3, (r1, 12)
+	stw	r3, (r0, 12)
+	ldw	r3, (r1, 8)
+	stw	r3, (r0, 8)
+	ldw	r3, (r1, 4)
+	stw	r3, (r0, 4)
+	ldw	r3, (r1, 0)
+	stw	r3, (r0, 0)
+#else
+	ldw	r20, (r1, 0)
+	ldw	r21, (r1, 4)
+	ldw	r22, (r1, 8)
+	ldw	r23, (r1, 12)
+	stw	r20, (r0, 0)
+	stw	r21, (r0, 4)
+	stw	r22, (r0, 8)
+	stw	r23, (r0, 12)
+	PRE_BNEZAD (r18)
+#endif
+	BNEZAD (r18, .L_len_larger_16bytes)
+
+.L_len_less_16bytes:
+	zext	r18, r2, 3, 2
+	bez	r18, .L_copy_by_byte
+.L_len_less_16bytes_loop:
+	subi	r1, 4
+	subi	r0, 4
+	ldw	r3, (r1, 0)
+	PRE_BNEZAD (r18)
+	stw	r3, (r0, 0)
+	BNEZAD (r18, .L_len_less_16bytes_loop)
+
+	/* Test if len less than 4 bytes.  */
+.L_copy_by_byte:
+	zext	r18, r2, 1, 0
+	bez	r18, .L_return
+.L_copy_by_byte_loop:
+	subi	r1, 1
+	subi	r0, 1
+	ldb	r3, (r1, 0)
+	PRE_BNEZAD (r18)
+	stb	r3, (r0, 0)
+	BNEZAD (r18, .L_copy_by_byte_loop)
+
+.L_return:
+	mov	r0, r12
+	rts
+
+	/* If dest is not aligned, just copy some bytes makes the dest
+	   align.  */
+.L_dest_not_aligned:
+	sub	r2, r13
+.L_dest_not_aligned_loop:
+	subi	r1, 1
+	subi	r0, 1
+	/* Makes the dest align.  */
+	ldb	r3, (r1, 0)
+	PRE_BNEZAD (r13)
+	stb	r3, (r0, 0)
+	BNEZAD (r13, .L_dest_not_aligned_loop)
+	cmplti	r2, 4
+	bt	.L_copy_by_byte
+	/* Check whether the src is aligned.  */
+	jbr	.L_dest_aligned
+ENDPROC(memmove)
+ENDPROC(__memmove)
diff --git a/arch/csky/abiv2/memset.S b/arch/csky/abiv2/memset.S
new file mode 100644
index 000000000..a7e7d994b
--- /dev/null
+++ b/arch/csky/abiv2/memset.S
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/linkage.h>
+#include "sysdep.h"
+
+	.weak memset
+ENTRY(__memset)
+ENTRY(memset)
+	/* Test if len less than 4 bytes.  */
+	mov	r12, r0
+	cmplti	r2, 8
+	bt	.L_set_by_byte
+
+	andi	r13, r0, 3
+	movi	r19, 4
+	/* Test if dest is not 4 bytes aligned.  */
+	bnez	r13, .L_dest_not_aligned
+	/* Hardware can handle unaligned access directly.  */
+.L_dest_aligned:
+        zextb   r3, r1
+        lsli    r1, 8
+        or      r1, r3
+        lsli    r3, r1, 16
+        or      r3, r1
+
+	/* If dest is aligned, then copy.  */
+	zext	r18, r2, 31, 4
+	/* Test if len less than 16 bytes.  */
+	bez	r18, .L_len_less_16bytes
+
+	LABLE_ALIGN
+.L_len_larger_16bytes:
+	stw	r3, (r0, 0)
+	stw	r3, (r0, 4)
+	stw	r3, (r0, 8)
+	stw	r3, (r0, 12)
+	PRE_BNEZAD (r18)
+	addi	r0, 16
+	BNEZAD (r18, .L_len_larger_16bytes)
+
+.L_len_less_16bytes:
+	zext	r18, r2, 3, 2
+	andi	r2, 3
+	bez	r18, .L_set_by_byte
+.L_len_less_16bytes_loop:
+	stw	r3, (r0, 0)
+	PRE_BNEZAD (r18)
+	addi	r0, 4
+	BNEZAD (r18, .L_len_less_16bytes_loop)
+
+	/* Test if len less than 4 bytes.  */
+.L_set_by_byte:
+	zext	r18, r2, 2, 0
+	bez	r18, .L_return
+.L_set_by_byte_loop:
+	stb	r1, (r0, 0)
+	PRE_BNEZAD (r18)
+	addi	r0, 1
+	BNEZAD (r18, .L_set_by_byte_loop)
+
+.L_return:
+	mov	r0, r12
+	rts
+
+	/* If dest is not aligned, just set some bytes makes the dest
+	   align.  */
+
+.L_dest_not_aligned:
+	sub	r13, r19, r13
+	sub	r2, r13
+.L_dest_not_aligned_loop:
+	/* Makes the dest align.  */
+	stb	r1, (r0, 0)
+	PRE_BNEZAD (r13)
+	addi	r0, 1
+	BNEZAD (r13, .L_dest_not_aligned_loop)
+	cmplti	r2, 8
+	bt	.L_set_by_byte
+	/* Check whether the src is aligned.  */
+	jbr	.L_dest_aligned
+ENDPROC(memset)
+ENDPROC(__memset)
diff --git a/arch/csky/abiv2/strcmp.S b/arch/csky/abiv2/strcmp.S
new file mode 100644
index 000000000..f8403f4d8
--- /dev/null
+++ b/arch/csky/abiv2/strcmp.S
@@ -0,0 +1,168 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/linkage.h>
+#include "sysdep.h"
+
+ENTRY(strcmp)
+	mov	a3, a0
+	/* Check if the s1 addr is aligned.  */
+	xor	a2, a3, a1
+	andi	a2, 0x3
+	bnez	a2, 7f
+	andi	t1, a0, 0x3
+	bnez	t1, 5f
+
+1:
+	/* If aligned, load word each time.  */
+	ldw	t0, (a3, 0)
+	ldw	t1, (a1, 0)
+	/* If s1[i] != s2[i], goto 2f.  */
+	cmpne   t0, t1
+	bt      2f
+	/* If s1[i] == s2[i], check if s1 or s2 is at the end.  */
+	tstnbz	t0
+	/* If at the end, goto 3f (finish comparing).  */
+	bf	3f
+
+	ldw	t0, (a3, 4)
+	ldw	t1, (a1, 4)
+	cmpne	t0, t1
+	bt	2f
+	tstnbz	t0
+	bf	3f
+
+	ldw	t0, (a3, 8)
+	ldw	t1, (a1, 8)
+	cmpne	t0, t1
+	bt	2f
+	tstnbz	t0
+	bf	3f
+
+	ldw	t0, (a3, 12)
+	ldw	t1, (a1, 12)
+	cmpne	t0, t1
+	bt	2f
+	tstnbz	t0
+	bf	3f
+
+	ldw	t0, (a3, 16)
+	ldw	t1, (a1, 16)
+	cmpne	t0, t1
+	bt	2f
+	tstnbz	t0
+	bf	3f
+
+	ldw	t0, (a3, 20)
+	ldw	t1, (a1, 20)
+	cmpne	t0, t1
+	bt	2f
+	tstnbz	t0
+	bf	3f
+
+	ldw	t0, (a3, 24)
+	ldw	t1, (a1, 24)
+	cmpne	t0, t1
+	bt	2f
+	tstnbz	t0
+	bf	3f
+
+	ldw	t0, (a3, 28)
+	ldw	t1, (a1, 28)
+	cmpne	t0, t1
+	bt	2f
+	tstnbz	t0
+	bf	3f
+
+	addi	a3, 32
+	addi	a1, 32
+
+	br	1b
+
+# ifdef __CSKYBE__
+	/* d[i] != s[i] in word, so we check byte 0.  */
+2:
+	xtrb0   a0, t0
+	xtrb0   a2, t1
+	subu    a0, a2
+	bez     a2, 4f
+	bnez    a0, 4f
+
+	/* check byte 1 */
+	xtrb1   a0, t0
+	xtrb1   a2, t1
+	subu    a0, a2
+	bez     a2, 4f
+	bnez    a0, 4f
+
+	/* check byte 2 */
+	xtrb2   a0, t0
+	xtrb2   a2, t1
+	subu    a0, a2
+	bez     a2, 4f
+	bnez    a0, 4f
+
+	/* check byte 3 */
+	xtrb3   a0, t0
+	xtrb3   a2, t1
+	subu    a0, a2
+# else
+	/* s1[i] != s2[i] in word, so we check byte 3.  */
+2:
+	xtrb3	a0, t0
+	xtrb3	a2, t1
+	subu    a0, a2
+	bez     a2, 4f
+	bnez    a0, 4f
+
+	/* check byte 2 */
+	xtrb2	a0, t0
+	xtrb2	a2, t1
+	subu    a0, a2
+	bez     a2, 4f
+	bnez    a0, 4f
+
+	/* check byte 1 */
+	xtrb1	a0, t0
+	xtrb1	a2, t1
+	subu	a0, a2
+	bez	a2, 4f
+	bnez    a0, 4f
+
+	/* check byte 0 */
+	xtrb0	a0, t0
+	xtrb0	a2, t1
+	subu	a0, a2
+
+# endif /* !__CSKYBE__ */
+	jmp     lr
+3:
+	movi	a0, 0
+4:
+	jmp     lr
+
+	/* Compare when s1 or s2 is not aligned.  */
+5:
+	subi    t1, 4
+6:
+	ldb	a0, (a3, 0)
+	ldb	a2, (a1, 0)
+	subu	a0, a2
+	bez	a2, 4b
+	bnez	a0, 4b
+	addi    t1, 1
+	addi	a1, 1
+	addi	a3, 1
+	bnez	t1, 6b
+	br	1b
+
+7:
+	ldb	a0, (a3, 0)
+	addi	a3, 1
+	ldb	a2, (a1, 0)
+	addi	a1, 1
+	subu    a0, a2
+	bnez    a0, 4b
+	bnez	a2, 7b
+	jmp	r15
+ENDPROC(strcmp)
diff --git a/arch/csky/abiv2/strcpy.S b/arch/csky/abiv2/strcpy.S
new file mode 100644
index 000000000..3c6d3f6a5
--- /dev/null
+++ b/arch/csky/abiv2/strcpy.S
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/linkage.h>
+#include "sysdep.h"
+
+ENTRY(strcpy)
+	mov	a3, a0
+	/* Check if the src addr is aligned.  */
+        andi    t0, a1, 3
+        bnez	t0, 11f
+1:
+	/* Check if all the bytes in the word are not zero.  */
+	ldw	a2, (a1)
+	tstnbz	a2
+	bf	9f
+	stw	a2, (a3)
+
+	ldw	a2, (a1, 4)
+	tstnbz	a2
+	bf	2f
+	stw	a2, (a3, 4)
+
+	ldw	a2, (a1, 8)
+	tstnbz	a2
+	bf	3f
+	stw	a2, (a3, 8)
+
+	ldw	a2, (a1, 12)
+	tstnbz	a2
+	bf	4f
+	stw	a2, (a3, 12)
+
+	ldw	a2, (a1, 16)
+	tstnbz	a2
+	bf	5f
+	stw	a2, (a3, 16)
+
+	ldw	a2, (a1, 20)
+	tstnbz	a2
+	bf	6f
+	stw	a2, (a3, 20)
+
+	ldw	a2, (a1, 24)
+	tstnbz	a2
+	bf	7f
+	stw	a2, (a3, 24)
+
+	ldw	a2, (a1, 28)
+	tstnbz	a2
+	bf	8f
+	stw	a2, (a3, 28)
+
+	addi	a3, 32
+	addi	a1, 32
+	br	1b
+
+
+2:
+	addi	a3, 4
+	br	9f
+
+3:
+	addi	a3, 8
+	br	9f
+
+4:
+	addi	a3, 12
+	br	9f
+
+5:
+	addi	a3, 16
+	br	9f
+
+6:
+	addi	a3, 20
+	br	9f
+
+7:
+	addi	a3, 24
+	br	9f
+
+8:
+	addi	a3, 28
+9:
+# ifdef __CSKYBE__
+	xtrb0	t0, a2
+	st.b	t0, (a3)
+	bez	t0, 10f
+	xtrb1	t0, a2
+	st.b	t0, (a3, 1)
+	bez	t0, 10f
+	xtrb2	t0, a2
+	st.b	t0, (a3, 2)
+	bez	t0, 10f
+	stw	a2, (a3)
+# else
+	xtrb3	t0, a2
+	st.b	t0, (a3)
+	bez	t0, 10f
+	xtrb2	t0, a2
+	st.b	t0, (a3, 1)
+	bez	t0, 10f
+	xtrb1	t0, a2
+	st.b	t0, (a3, 2)
+	bez	t0, 10f
+	stw	a2, (a3)
+# endif	/* !__CSKYBE__ */
+10:
+	jmp	lr
+
+11:
+	subi    t0, 4
+12:
+        ld.b    a2, (a1)
+        st.b	a2, (a3)
+        bez	a2, 10b
+	addi    t0, 1
+        addi    a1, a1, 1
+        addi    a3, a3, 1
+	bnez	t0, 12b
+	jbr	1b
+ENDPROC(strcpy)
diff --git a/arch/csky/abiv2/strksyms.c b/arch/csky/abiv2/strksyms.c
new file mode 100644
index 000000000..8d1fd28c6
--- /dev/null
+++ b/arch/csky/abiv2/strksyms.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/module.h>
+
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_STRING_OPS
+EXPORT_SYMBOL(memcpy);
+EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(memmove);
+#endif
+EXPORT_SYMBOL(memcmp);
+EXPORT_SYMBOL(strcmp);
+EXPORT_SYMBOL(strcpy);
+EXPORT_SYMBOL(strlen);
diff --git a/arch/csky/abiv2/strlen.S b/arch/csky/abiv2/strlen.S
new file mode 100644
index 000000000..bcdd70764
--- /dev/null
+++ b/arch/csky/abiv2/strlen.S
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/linkage.h>
+#include "sysdep.h"
+
+ENTRY(strlen)
+	/* Check if the start addr is aligned.  */
+	mov	r3, r0
+	andi	r1, r0, 3
+	movi	r2, 4
+	movi	r0, 0
+	bnez	r1, .L_start_not_aligned
+
+	LABLE_ALIGN
+.L_start_addr_aligned:
+	/* Check if all the bytes in the word are not zero.  */
+	ldw	r1, (r3)
+	tstnbz	r1
+	bf	.L_string_tail
+
+	ldw	r1, (r3, 4)
+	addi	r0, 4
+	tstnbz	r1
+	bf	.L_string_tail
+
+	ldw	r1, (r3, 8)
+	addi	r0, 4
+	tstnbz	r1
+	bf	.L_string_tail
+
+	ldw	r1, (r3, 12)
+	addi	r0, 4
+	tstnbz	r1
+	bf	.L_string_tail
+
+	ldw	r1, (r3, 16)
+	addi	r0, 4
+	tstnbz	r1
+	bf	.L_string_tail
+
+	ldw	r1, (r3, 20)
+	addi	r0, 4
+	tstnbz	r1
+	bf	.L_string_tail
+
+	ldw	r1, (r3, 24)
+	addi	r0, 4
+	tstnbz	r1
+	bf	.L_string_tail
+
+	ldw	r1, (r3, 28)
+	addi	r0, 4
+	tstnbz	r1
+	bf	.L_string_tail
+
+	addi	r0, 4
+	addi	r3, 32
+	br	.L_start_addr_aligned
+
+.L_string_tail:
+# ifdef __CSKYBE__
+	xtrb0	r3, r1
+	bez	r3, .L_return
+	addi	r0, 1
+	xtrb1	r3, r1
+	bez	r3, .L_return
+	addi	r0, 1
+	xtrb2	r3, r1
+	bez	r3, .L_return
+	addi	r0, 1
+# else
+	xtrb3	r3, r1
+	bez	r3, .L_return
+	addi	r0, 1
+	xtrb2	r3, r1
+	bez	r3, .L_return
+	addi	r0, 1
+	xtrb1	r3, r1
+	bez	r3, .L_return
+	addi	r0, 1
+# endif	/* !__CSKYBE__ */
+
+.L_return:
+	rts
+
+.L_start_not_aligned:
+	sub	r2, r2, r1
+.L_start_not_aligned_loop:
+	ldb	r1, (r3)
+	PRE_BNEZAD (r2)
+	addi	r3, 1
+	bez	r1, .L_return
+	addi	r0, 1
+	BNEZAD (r2, .L_start_not_aligned_loop)
+	br	.L_start_addr_aligned
+ENDPROC(strlen)
diff --git a/arch/csky/abiv2/sysdep.h b/arch/csky/abiv2/sysdep.h
new file mode 100644
index 000000000..61abe9201
--- /dev/null
+++ b/arch/csky/abiv2/sysdep.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __SYSDEP_H
+#define __SYSDEP_H
+
+#ifdef __ASSEMBLER__
+
+#if defined(__CK860__)
+#define LABLE_ALIGN	\
+	.balignw 16, 0x6c03
+
+#define PRE_BNEZAD(R)
+
+#define BNEZAD(R, L)	\
+	bnezad	R, L
+#else
+#define LABLE_ALIGN	\
+	.balignw 8, 0x6c03
+
+#define PRE_BNEZAD(R)	\
+	subi	R, 1
+
+#define BNEZAD(R, L)	\
+	bnez	R, L
+#endif
+
+#endif
+
+#endif
diff --git a/arch/csky/boot/Makefile b/arch/csky/boot/Makefile
new file mode 100644
index 000000000..c3cfde28f
--- /dev/null
+++ b/arch/csky/boot/Makefile
@@ -0,0 +1,24 @@
+# SPDX-License-Identifier: GPL-2.0-only
+targets := Image zImage uImage
+
+$(obj)/Image: vmlinux FORCE
+	$(call if_changed,objcopy)
+	@echo '  Kernel: $@ is ready'
+
+compress-$(CONFIG_KERNEL_GZIP) = gzip
+compress-$(CONFIG_KERNEL_LZO)  = lzo
+compress-$(CONFIG_KERNEL_LZMA) = lzma
+compress-$(CONFIG_KERNEL_XZ)   = xzkern
+compress-$(CONFIG_KERNEL_LZ4)  = lz4
+
+$(obj)/zImage:  $(obj)/Image FORCE
+	$(call if_changed,$(compress-y))
+	@echo '  Kernel: $@ is ready'
+
+UIMAGE_ARCH		= sandbox
+UIMAGE_COMPRESSION	= $(compress-y)
+UIMAGE_LOADADDR		= $(shell $(NM) vmlinux | awk '$$NF == "_start" {print $$1}')
+
+$(obj)/uImage: $(obj)/zImage
+	$(call if_changed,uimage)
+	@echo 'Image: $@ is ready'
diff --git a/arch/csky/boot/dts/Makefile b/arch/csky/boot/dts/Makefile
new file mode 100644
index 000000000..aabffc191
--- /dev/null
+++ b/arch/csky/boot/dts/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+dtb-y := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts))
diff --git a/arch/csky/configs/defconfig b/arch/csky/configs/defconfig
new file mode 100644
index 000000000..ff559e516
--- /dev/null
+++ b/arch/csky/configs/defconfig
@@ -0,0 +1,54 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_DEFAULT_HOSTNAME="csky"
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_AUDIT=y
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_BSD_PROCESS_ACCT_V3=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=65536
+CONFIG_VT_HW_CONSOLE_BINDING=y
+CONFIG_SERIAL_NONSTANDARD=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_PM_DEVFREQ=y
+CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y
+CONFIG_DEVFREQ_GOV_PERFORMANCE=y
+CONFIG_DEVFREQ_GOV_POWERSAVE=y
+CONFIG_DEVFREQ_GOV_USERSPACE=y
+CONFIG_GENERIC_PHY=y
+CONFIG_EXT4_FS=y
+CONFIG_FANOTIFY=y
+CONFIG_QUOTA=y
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
+CONFIG_FSCACHE_STATS=y
+CONFIG_CACHEFILES=m
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_FAT_DEFAULT_UTF8=y
+CONFIG_NTFS_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_PROC_CHILDREN=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_CONFIGFS_FS=y
+CONFIG_CRAMFS=y
+CONFIG_ROMFS_FS=y
+CONFIG_NFS_FS=y
+CONFIG_PRINTK_TIME=y
+CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild
new file mode 100644
index 000000000..7dca0c6cd
--- /dev/null
+++ b/arch/csky/include/asm/Kbuild
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0
+syscall-y := syscall_table_32.h
+
+generic-y += asm-offsets.h
+generic-y += extable.h
+generic-y += kvm_para.h
+generic-y += mcs_spinlock.h
+generic-y += qrwlock.h
+generic-y += qrwlock_types.h
+generic-y += qspinlock.h
+generic-y += parport.h
+generic-y += ring_buffer.h
+generic-y += user.h
+generic-y += vmlinux.lds.h
+generic-y += text-patching.h
diff --git a/arch/csky/include/asm/addrspace.h b/arch/csky/include/asm/addrspace.h
new file mode 100644
index 000000000..6fc05d445
--- /dev/null
+++ b/arch/csky/include/asm/addrspace.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_ADDRSPACE_H
+#define __ASM_CSKY_ADDRSPACE_H
+
+#define KSEG0		0x80000000ul
+#define KSEG0ADDR(a)	(((unsigned long)a & 0x1fffffff) | KSEG0)
+
+#endif /* __ASM_CSKY_ADDRSPACE_H */
diff --git a/arch/csky/include/asm/asid.h b/arch/csky/include/asm/asid.h
new file mode 100644
index 000000000..6ff205a97
--- /dev/null
+++ b/arch/csky/include/asm/asid.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_ASM_ASID_H
+#define __ASM_ASM_ASID_H
+
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <linux/cpumask.h>
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
+
+struct asid_info
+{
+	atomic64_t	generation;
+	unsigned long	*map;
+	atomic64_t __percpu	*active;
+	u64 __percpu		*reserved;
+	u32			bits;
+	/* Lock protecting the structure */
+	raw_spinlock_t		lock;
+	/* Which CPU requires context flush on next call */
+	cpumask_t		flush_pending;
+	/* Number of ASID allocated by context (shift value) */
+	unsigned int		ctxt_shift;
+	/* Callback to locally flush the context. */
+	void			(*flush_cpu_ctxt_cb)(void);
+};
+
+#define NUM_ASIDS(info)			(1UL << ((info)->bits))
+#define NUM_CTXT_ASIDS(info)		(NUM_ASIDS(info) >> (info)->ctxt_shift)
+
+#define active_asid(info, cpu)	*per_cpu_ptr((info)->active, cpu)
+
+void asid_new_context(struct asid_info *info, atomic64_t *pasid,
+		      unsigned int cpu, struct mm_struct *mm);
+
+/*
+ * Check the ASID is still valid for the context. If not generate a new ASID.
+ *
+ * @pasid: Pointer to the current ASID batch
+ * @cpu: current CPU ID. Must have been acquired through get_cpu()
+ */
+static inline void asid_check_context(struct asid_info *info,
+				      atomic64_t *pasid, unsigned int cpu,
+				      struct mm_struct *mm)
+{
+	u64 asid, old_active_asid;
+
+	asid = atomic64_read(pasid);
+
+	/*
+	 * The memory ordering here is subtle.
+	 * If our active_asid is non-zero and the ASID matches the current
+	 * generation, then we update the active_asid entry with a relaxed
+	 * cmpxchg. Racing with a concurrent rollover means that either:
+	 *
+	 * - We get a zero back from the cmpxchg and end up waiting on the
+	 *   lock. Taking the lock synchronises with the rollover and so
+	 *   we are forced to see the updated generation.
+	 *
+	 * - We get a valid ASID back from the cmpxchg, which means the
+	 *   relaxed xchg in flush_context will treat us as reserved
+	 *   because atomic RmWs are totally ordered for a given location.
+	 */
+	old_active_asid = atomic64_read(&active_asid(info, cpu));
+	if (old_active_asid &&
+	    !((asid ^ atomic64_read(&info->generation)) >> info->bits) &&
+	    atomic64_cmpxchg_relaxed(&active_asid(info, cpu),
+				     old_active_asid, asid))
+		return;
+
+	asid_new_context(info, pasid, cpu, mm);
+}
+
+int asid_allocator_init(struct asid_info *info,
+			u32 bits, unsigned int asid_per_ctxt,
+			void (*flush_cpu_ctxt_cb)(void));
+
+#endif
diff --git a/arch/csky/include/asm/atomic.h b/arch/csky/include/asm/atomic.h
new file mode 100644
index 000000000..4dab44f61
--- /dev/null
+++ b/arch/csky/include/asm/atomic.h
@@ -0,0 +1,202 @@
+/* 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
+
+#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
new file mode 100644
index 000000000..c33fdcfe3
--- /dev/null
+++ b/arch/csky/include/asm/barrier.h
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_BARRIER_H
+#define __ASM_CSKY_BARRIER_H
+
+#ifndef __ASSEMBLER__
+
+#define nop()	asm volatile ("nop\n":::"memory")
+
+#ifdef CONFIG_SMP
+
+/*
+ * bar.brwarws: ordering barrier for all load/store instructions
+ *              before/after
+ *
+ * |31|30 26|25 21|20 16|15  10|9   5|4           0|
+ *  1  10000 00000 00000 100001	00001 0 bw br aw ar
+ *
+ * b: before
+ * a: after
+ * r: read
+ * w: write
+ *
+ * Here are all combinations:
+ *
+ * bar.brw
+ * bar.br
+ * bar.bw
+ * bar.arw
+ * bar.ar
+ * bar.aw
+ * bar.brwarw
+ * bar.brarw
+ * bar.bwarw
+ * bar.brwar
+ * bar.brwaw
+ * 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 (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 (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")
+
+#define __smp_mb()	__bar_brwarw()
+#define __smp_rmb()	__bar_brar()
+#define __smp_wmb()	__bar_bwaw()
+
+#define __smp_acquire_fence()	__bar_brarw()
+#define __smp_release_fence()	__bar_brwaw()
+
+#endif /* CONFIG_SMP */
+
+/*
+ * sync:        completion barrier, all sync.xx instructions
+ *              guarantee the last response received by bus transaction
+ *              made by ld/st instructions before sync.s
+ * sync.s:      inherit from sync, but also shareable to other cores
+ * sync.i:      inherit from sync, but also flush cpu pipeline
+ * sync.is:     the same with sync.i + sync.s
+ */
+#define mb()		asm volatile ("sync\n":::"memory")
+
+#ifdef CONFIG_CPU_HAS_CACHEV2
+/*
+ * Using three sync.is to prevent speculative PTW
+ */
+#define sync_is()	asm volatile ("sync.is\nsync.is\nsync.is\n":::"memory")
+#endif
+
+#include <asm-generic/barrier.h>
+
+#endif /* __ASSEMBLER__ */
+#endif /* __ASM_CSKY_BARRIER_H */
diff --git a/arch/csky/include/asm/bitops.h b/arch/csky/include/asm/bitops.h
new file mode 100644
index 000000000..80d67eee6
--- /dev/null
+++ b/arch/csky/include/asm/bitops.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_BITOPS_H
+#define __ASM_CSKY_BITOPS_H
+
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
+/*
+ * asm-generic/bitops/ffs.h
+ */
+static inline __attribute_const__ int ffs(int x)
+{
+	if (!x)
+		return 0;
+
+	asm volatile (
+		"brev %0\n"
+		"ff1  %0\n"
+		"addi %0, 1\n"
+		: "=&r"(x)
+		: "0"(x));
+	return x;
+}
+
+/*
+ * asm-generic/bitops/__ffs.h
+ */
+static __always_inline __attribute_const__ unsigned long __ffs(unsigned long x)
+{
+	asm volatile (
+		"brev %0\n"
+		"ff1  %0\n"
+		: "=&r"(x)
+		: "0"(x));
+	return x;
+}
+
+/*
+ * asm-generic/bitops/fls.h
+ */
+static __always_inline __attribute_const__ int fls(unsigned int x)
+{
+	asm volatile(
+		"ff1 %0\n"
+		: "=&r"(x)
+		: "0"(x));
+
+	return (32 - x);
+}
+
+/*
+ * asm-generic/bitops/__fls.h
+ */
+static __always_inline __attribute_const__ unsigned long __fls(unsigned long x)
+{
+	return fls(x) - 1;
+}
+
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/fls64.h>
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/lock.h>
+#include <asm-generic/bitops/atomic.h>
+
+/*
+ * bug fix, why only could use atomic!!!!
+ */
+#include <asm-generic/bitops/non-atomic.h>
+
+#include <asm-generic/bitops/le.h>
+#include <asm-generic/bitops/ext2-atomic.h>
+#endif /* __ASM_CSKY_BITOPS_H */
diff --git a/arch/csky/include/asm/bug.h b/arch/csky/include/asm/bug.h
new file mode 100644
index 000000000..03f1a5f91
--- /dev/null
+++ b/arch/csky/include/asm/bug.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_BUG_H
+#define __ASM_CSKY_BUG_H
+
+#include <linux/compiler.h>
+#include <linux/const.h>
+#include <linux/types.h>
+
+#define BUG()				\
+do {					\
+	asm volatile ("bkpt\n");	\
+	unreachable();			\
+} while (0)
+
+#define HAVE_ARCH_BUG
+
+#include <asm-generic/bug.h>
+
+struct pt_regs;
+
+void die(struct pt_regs *regs, const char *str);
+void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr);
+
+void show_regs(struct pt_regs *regs);
+void show_code(struct pt_regs *regs);
+
+#endif /* __ASM_CSKY_BUG_H */
diff --git a/arch/csky/include/asm/cache.h b/arch/csky/include/asm/cache.h
new file mode 100644
index 000000000..d575482e0
--- /dev/null
+++ b/arch/csky/include/asm/cache.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_CACHE_H
+#define __ASM_CSKY_CACHE_H
+
+/* bytes per L1 cache line */
+#define L1_CACHE_SHIFT	CONFIG_L1_CACHE_SHIFT
+
+#define L1_CACHE_BYTES	(1 << L1_CACHE_SHIFT)
+
+#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
+
+#ifndef __ASSEMBLER__
+
+void dcache_wb_line(unsigned long start);
+
+void icache_inv_range(unsigned long start, unsigned long end);
+void icache_inv_all(void);
+void local_icache_inv_all(void *priv);
+
+void dcache_wb_range(unsigned long start, unsigned long end);
+void dcache_wbinv_all(void);
+
+void cache_wbinv_range(unsigned long start, unsigned long end);
+void cache_wbinv_all(void);
+
+void dma_wbinv_range(unsigned long start, unsigned long end);
+void dma_inv_range(unsigned long start, unsigned long end);
+void dma_wb_range(unsigned long start, unsigned long end);
+
+#endif
+#endif  /* __ASM_CSKY_CACHE_H */
diff --git a/arch/csky/include/asm/cacheflush.h b/arch/csky/include/asm/cacheflush.h
new file mode 100644
index 000000000..d0f9eafe8
--- /dev/null
+++ b/arch/csky/include/asm/cacheflush.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_CACHEFLUSH_H
+#define __ASM_CSKY_CACHEFLUSH_H
+
+#include <linux/mm.h>
+#include <abi/cacheflush.h>
+
+#endif /* __ASM_CSKY_CACHEFLUSH_H */
diff --git a/arch/csky/include/asm/cachetype.h b/arch/csky/include/asm/cachetype.h
new file mode 100644
index 000000000..98cbe3af6
--- /dev/null
+++ b/arch/csky/include/asm/cachetype.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_CSKY_CACHETYPE_H
+#define __ASM_CSKY_CACHETYPE_H
+
+#include <linux/types.h>
+
+#define cpu_dcache_is_aliasing()	true
+
+#endif
diff --git a/arch/csky/include/asm/checksum.h b/arch/csky/include/asm/checksum.h
new file mode 100644
index 000000000..aa12ef4b9
--- /dev/null
+++ b/arch/csky/include/asm/checksum.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_CHECKSUM_H
+#define __ASM_CSKY_CHECKSUM_H
+
+#include <linux/in6.h>
+#include <asm/byteorder.h>
+
+static inline __sum16 csum_fold(__wsum csum)
+{
+	u32 tmp;
+
+	asm volatile(
+	"mov	%1, %0\n"
+	"rori	%0, 16\n"
+	"addu	%0, %1\n"
+	"lsri	%0, 16\n"
+	: "=r"(csum), "=r"(tmp)
+	: "0"(csum));
+
+	return (__force __sum16) ~csum;
+}
+#define csum_fold csum_fold
+
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+		unsigned short len, unsigned short proto, __wsum sum)
+{
+	asm volatile(
+	"clrc\n"
+	"addc    %0, %1\n"
+	"addc    %0, %2\n"
+	"addc    %0, %3\n"
+	"inct    %0\n"
+	: "=r"(sum)
+	: "r"((__force u32)saddr), "r"((__force u32)daddr),
+#ifdef __BIG_ENDIAN
+	"r"(proto + len),
+#else
+	"r"((proto + len) << 8),
+#endif
+	"0" ((__force unsigned long)sum)
+	: "cc");
+	return sum;
+}
+#define csum_tcpudp_nofold csum_tcpudp_nofold
+
+#include <asm-generic/checksum.h>
+
+#endif /* __ASM_CSKY_CHECKSUM_H */
diff --git a/arch/csky/include/asm/clocksource.h b/arch/csky/include/asm/clocksource.h
new file mode 100644
index 000000000..54da0e49e
--- /dev/null
+++ b/arch/csky/include/asm/clocksource.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_VDSO_CSKY_CLOCKSOURCE_H
+#define __ASM_VDSO_CSKY_CLOCKSOURCE_H
+
+#include <asm/vdso/clocksource.h>
+
+#endif
diff --git a/arch/csky/include/asm/cmpxchg.h b/arch/csky/include/asm/cmpxchg.h
new file mode 100644
index 000000000..db6dda471
--- /dev/null
+++ b/arch/csky/include/asm/cmpxchg.h
@@ -0,0 +1,165 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_CMPXCHG_H
+#define __ASM_CSKY_CMPXCHG_H
+
+#ifdef CONFIG_SMP
+#include <linux/bug.h>
+#include <asm/barrier.h>
+#include <linux/cmpxchg-emu.h>
+
+#define __xchg_relaxed(new, ptr, size)				\
+({								\
+	__typeof__(ptr) __ptr = (ptr);				\
+	__typeof__(new) __new = (new);				\
+	__typeof__(*(ptr)) __ret;				\
+	unsigned long tmp;					\
+	switch (size) {						\
+	case 2: {						\
+		u32 ret;					\
+		u32 shif = ((ulong)__ptr & 2) ? 16 : 0;		\
+		u32 mask = 0xffff << shif;			\
+		__ptr = (__typeof__(ptr))((ulong)__ptr & ~2);	\
+		__asm__ __volatile__ (				\
+			"1:	ldex.w %0, (%4)\n"		\
+			"	and    %1, %0, %2\n"		\
+			"	or     %1, %1, %3\n"		\
+			"	stex.w %1, (%4)\n"		\
+			"	bez    %1, 1b\n"		\
+			: "=&r" (ret), "=&r" (tmp)		\
+			: "r" (~mask),				\
+			  "r" ((u32)__new << shif),		\
+			  "r" (__ptr)				\
+			: "memory");				\
+		__ret = (__typeof__(*(ptr)))			\
+			((ret & mask) >> shif);			\
+		break;						\
+	}							\
+	case 4:							\
+		asm volatile (					\
+		"1:	ldex.w		%0, (%3) \n"		\
+		"	mov		%1, %2   \n"		\
+		"	stex.w		%1, (%3) \n"		\
+		"	bez		%1, 1b   \n"		\
+			: "=&r" (__ret), "=&r" (tmp)		\
+			: "r" (__new), "r"(__ptr)		\
+			:);					\
+		break;						\
+	default:						\
+		BUILD_BUG();					\
+	}							\
+	__ret;							\
+})
+
+#define arch_xchg_relaxed(ptr, x) \
+		(__xchg_relaxed((x), (ptr), sizeof(*(ptr))))
+
+#define __cmpxchg_relaxed(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 1:							\
+		__ret = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *)__ptr, (uintptr_t)__old, (uintptr_t)__new); \
+		break;						\
+	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"		\
+		"2:				 \n"		\
+			: "=&r" (__ret), "=&r" (__tmp)		\
+			: "r" (__new), "r"(__ptr), "r"(__old)	\
+			:);					\
+		break;						\
+	default:						\
+		BUILD_BUG();					\
+	}							\
+	__ret;							\
+})
+
+#define arch_cmpxchg_relaxed(ptr, o, n) \
+	(__cmpxchg_relaxed((ptr), (o), (n), sizeof(*(ptr))))
+
+#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 1:							\
+		__ret = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *)__ptr, (uintptr_t)__old, (uintptr_t)__new); \
+		break;						\
+	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:						\
+		BUILD_BUG();					\
+	}							\
+	__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;				\
+	switch (size) {						\
+	case 1:							\
+		__ret = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *)__ptr, (uintptr_t)__old, (uintptr_t)__new); \
+		break;						\
+	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:						\
+		BUILD_BUG();					\
+	}							\
+	__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
+
+#endif /* __ASM_CSKY_CMPXCHG_H */
diff --git a/arch/csky/include/asm/elf.h b/arch/csky/include/asm/elf.h
new file mode 100644
index 000000000..48b83e283
--- /dev/null
+++ b/arch/csky/include/asm/elf.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_ELF_H
+#define __ASM_CSKY_ELF_H
+
+#include <asm/ptrace.h>
+#include <abi/regdef.h>
+
+#define ELF_ARCH EM_CSKY
+#define EM_CSKY_OLD 39
+
+/* CSKY Relocations */
+#define R_CSKY_NONE               0
+#define R_CSKY_32                 1
+#define R_CSKY_PCIMM8BY4          2
+#define R_CSKY_PCIMM11BY2         3
+#define R_CSKY_PCIMM4BY2          4
+#define R_CSKY_PC32               5
+#define R_CSKY_PCRELJSR_IMM11BY2  6
+#define R_CSKY_GNU_VTINHERIT      7
+#define R_CSKY_GNU_VTENTRY        8
+#define R_CSKY_RELATIVE           9
+#define R_CSKY_COPY               10
+#define R_CSKY_GLOB_DAT           11
+#define R_CSKY_JUMP_SLOT          12
+#define R_CSKY_ADDR_HI16          24
+#define R_CSKY_ADDR_LO16          25
+#define R_CSKY_PCRELJSR_IMM26BY2  40
+
+typedef unsigned long elf_greg_t;
+
+typedef struct user_fp elf_fpregset_t;
+
+/*
+ * In gdb/bfd elf32-csky.c, csky_elf_grok_prstatus() use fixed size of
+ * elf_prstatus. It's 148 for abiv1 and 220 for abiv2, the size is enough
+ * for coredump and no need full sizeof(struct pt_regs).
+ */
+#define ELF_NGREG ((sizeof(struct pt_regs) / sizeof(elf_greg_t)) - 2)
+
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) (((x)->e_machine == ELF_ARCH) || \
+			   ((x)->e_machine == EM_CSKY_OLD))
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_EXEC_PAGESIZE		4096
+#define ELF_CLASS			ELFCLASS32
+#define ELF_PLAT_INIT(_r, load_addr)	{ _r->a0 = 0; }
+
+#ifdef __cskyBE__
+#define ELF_DATA	ELFDATA2MSB
+#else
+#define ELF_DATA	ELFDATA2LSB
+#endif
+
+/*
+ * This is the location that an ET_DYN program is loaded if exec'ed. Typical
+ * use of this is to invoke "./ld.so someprog" to test out a new version of
+ * the loader.  We need to make sure that it is out of the way of the program
+ * that it will "exec", and that there is sufficient room for the brk.
+ */
+#define ELF_ET_DYN_BASE	0x0UL
+#include <abi/elf.h>
+
+/* Similar, but for a thread other than current. */
+struct task_struct;
+extern int dump_task_regs(struct task_struct *tsk, elf_gregset_t *elf_regs);
+#define ELF_CORE_COPY_TASK_REGS(tsk, elf_regs) dump_task_regs(tsk, elf_regs)
+
+#define ELF_HWCAP	(0)
+
+/*
+ * This yields a string that ld.so will use to load implementation specific
+ * libraries for optimization. This is more specific in intent than poking
+ * at uname or /proc/cpuinfo.
+ */
+#define ELF_PLATFORM		(NULL)
+#define SET_PERSONALITY(ex)	set_personality(PER_LINUX)
+
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+struct linux_binprm;
+extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+				       int uses_interp);
+#endif /* __ASM_CSKY_ELF_H */
diff --git a/arch/csky/include/asm/fixmap.h b/arch/csky/include/asm/fixmap.h
new file mode 100644
index 000000000..49a77cbbe
--- /dev/null
+++ b/arch/csky/include/asm/fixmap.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_FIXMAP_H
+#define __ASM_CSKY_FIXMAP_H
+
+#include <asm/page.h>
+#include <asm/memory.h>
+#ifdef CONFIG_HIGHMEM
+#include <linux/threads.h>
+#include <asm/kmap_size.h>
+#endif
+
+enum fixed_addresses {
+#ifdef CONFIG_HAVE_TCM
+	FIX_TCM = TCM_NR_PAGES,
+#endif
+#ifdef CONFIG_HIGHMEM
+	FIX_KMAP_BEGIN,
+	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_MAX_IDX * NR_CPUS) - 1,
+#endif
+	__end_of_fixed_addresses
+};
+
+#define FIXADDR_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
+
+#include <asm-generic/fixmap.h>
+
+extern void fixrange_init(unsigned long start, unsigned long end,
+	pgd_t *pgd_base);
+extern void __init fixaddr_init(void);
+
+#endif /* __ASM_CSKY_FIXMAP_H */
diff --git a/arch/csky/include/asm/ftrace.h b/arch/csky/include/asm/ftrace.h
new file mode 100644
index 000000000..21532f218
--- /dev/null
+++ b/arch/csky/include/asm/ftrace.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_FTRACE_H
+#define __ASM_CSKY_FTRACE_H
+
+#define MCOUNT_INSN_SIZE	14
+
+#define HAVE_FUNCTION_GRAPH_FP_TEST
+
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+
+#define MCOUNT_ADDR	((unsigned long)_mcount)
+
+#ifndef __ASSEMBLER__
+
+extern void _mcount(unsigned long);
+
+extern void ftrace_graph_call(void);
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	return addr;
+}
+
+struct dyn_arch_ftrace {
+};
+
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer);
+
+#endif /* !__ASSEMBLER__ */
+#endif /* __ASM_CSKY_FTRACE_H */
diff --git a/arch/csky/include/asm/futex.h b/arch/csky/include/asm/futex.h
new file mode 100644
index 000000000..6cfd31272
--- /dev/null
+++ b/arch/csky/include/asm/futex.h
@@ -0,0 +1,121 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_FUTEX_H
+#define __ASM_CSKY_FUTEX_H
+
+#ifndef CONFIG_SMP
+#include <asm-generic/futex.h>
+#else
+#include <linux/atomic.h>
+#include <linux/futex.h>
+#include <linux/uaccess.h>
+#include <linux/errno.h>
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)		\
+{									\
+	u32 tmp;							\
+									\
+	__atomic_pre_full_fence();					\
+									\
+	__asm__ __volatile__ (						\
+	"1:	ldex.w	%[ov], %[u]			\n"		\
+	"	"insn"					\n"		\
+	"2:	stex.w	%[t], %[u]			\n"		\
+	"	bez	%[t], 1b			\n"		\
+	"	br	4f				\n"		\
+	"3:	mov	%[r], %[e]			\n"		\
+	"4:						\n"		\
+	"	.section __ex_table,\"a\"		\n"		\
+	"	.balign 4				\n"		\
+	"	.long	1b, 3b				\n"		\
+	"	.long	2b, 3b				\n"		\
+	"	.previous				\n"		\
+	: [r] "+r" (ret), [ov] "=&r" (oldval),				\
+	  [u] "+m" (*uaddr), [t] "=&r" (tmp)				\
+	: [op] "Jr" (oparg), [e] "jr" (-EFAULT)				\
+	: "memory");							\
+									\
+	__atomic_post_full_fence();					\
+}
+
+static inline int
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
+{
+	int oldval = 0, ret = 0;
+
+	if (!access_ok(uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		__futex_atomic_op("mov %[t], %[ov]",
+				  ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ADD:
+		__futex_atomic_op("add %[t], %[ov], %[op]",
+				  ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_OR:
+		__futex_atomic_op("or %[t], %[ov], %[op]",
+				  ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ANDN:
+		__futex_atomic_op("and %[t], %[ov], %[op]",
+				  ret, oldval, uaddr, ~oparg);
+		break;
+	case FUTEX_OP_XOR:
+		__futex_atomic_op("xor %[t], %[ov], %[op]",
+				  ret, oldval, uaddr, oparg);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	if (!ret)
+		*oval = oldval;
+
+	return ret;
+}
+
+
+
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	int ret = 0;
+	u32 val, tmp;
+
+	if (!access_ok(uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	__atomic_pre_full_fence();
+
+	__asm__ __volatile__ (
+	"1:	ldex.w	%[v], %[u]			\n"
+	"	cmpne	%[v], %[ov]			\n"
+	"	bt	4f				\n"
+	"	mov	%[t], %[nv]			\n"
+	"2:	stex.w	%[t], %[u]			\n"
+	"	bez	%[t], 1b			\n"
+	"	br	4f				\n"
+	"3:	mov	%[r], %[e]			\n"
+	"4:						\n"
+	"	.section __ex_table,\"a\"		\n"
+	"	.balign 4				\n"
+	"	.long	1b, 3b				\n"
+	"	.long	2b, 3b				\n"
+	"	.previous				\n"
+	: [r] "+r" (ret), [v] "=&r" (val), [u] "+m" (*uaddr),
+	  [t] "=&r" (tmp)
+	: [ov] "Jr" (oldval), [nv] "Jr" (newval), [e] "Jr" (-EFAULT)
+	: "memory");
+
+	__atomic_post_full_fence();
+
+	*uval = val;
+	return ret;
+}
+
+#endif /* CONFIG_SMP */
+#endif /* __ASM_CSKY_FUTEX_H */
diff --git a/arch/csky/include/asm/highmem.h b/arch/csky/include/asm/highmem.h
new file mode 100644
index 000000000..1ed810eff
--- /dev/null
+++ b/arch/csky/include/asm/highmem.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_HIGHMEM_H
+#define __ASM_CSKY_HIGHMEM_H
+
+#ifdef __KERNEL__
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/uaccess.h>
+#include <asm/kmap_size.h>
+#include <asm/cache.h>
+
+/* undef for production */
+#define HIGHMEM_DEBUG 1
+
+/* declarations for highmem.c */
+extern unsigned long highstart_pfn, highend_pfn;
+
+extern pte_t *pkmap_page_table;
+
+/*
+ * Right now we initialize only a single pte table. It can be extended
+ * easily, subsequent pte tables have to be allocated in one physical
+ * chunk of RAM.
+ */
+#define LAST_PKMAP 1024
+#define LAST_PKMAP_MASK (LAST_PKMAP-1)
+#define PKMAP_NR(virt)  ((virt-PKMAP_BASE) >> PAGE_SHIFT)
+#define PKMAP_ADDR(nr)  (PKMAP_BASE + ((nr) << PAGE_SHIFT))
+
+#define ARCH_HAS_KMAP_FLUSH_TLB
+extern void kmap_flush_tlb(unsigned long addr);
+
+#define flush_cache_kmaps() do {} while (0)
+
+#define arch_kmap_local_post_map(vaddr, pteval)	kmap_flush_tlb(vaddr)
+#define arch_kmap_local_post_unmap(vaddr)	kmap_flush_tlb(vaddr)
+
+extern void kmap_init(void);
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASM_CSKY_HIGHMEM_H */
diff --git a/arch/csky/include/asm/io.h b/arch/csky/include/asm/io.h
new file mode 100644
index 000000000..536d3bf32
--- /dev/null
+++ b/arch/csky/include/asm/io.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_IO_H
+#define __ASM_CSKY_IO_H
+
+#include <linux/pgtable.h>
+#include <linux/types.h>
+
+/*
+ * I/O memory access primitives. Reads are ordered relative to any
+ * following Normal memory access. Writes are ordered relative to any prior
+ * Normal memory access.
+ *
+ * For CACHEV1 (807, 810), store instruction could fast retire, so we need
+ * another mb() to prevent st fast retire.
+ *
+ * For CACHEV2 (860), store instruction with PAGE_ATTR_NO_BUFFERABLE won't
+ * fast retire.
+ */
+#define readb(c)		({ u8  __v = readb_relaxed(c); rmb(); __v; })
+#define readw(c)		({ u16 __v = readw_relaxed(c); rmb(); __v; })
+#define readl(c)		({ u32 __v = readl_relaxed(c); rmb(); __v; })
+
+#ifdef CONFIG_CPU_HAS_CACHEV2
+#define writeb(v,c)		({ wmb(); writeb_relaxed((v),(c)); })
+#define writew(v,c)		({ wmb(); writew_relaxed((v),(c)); })
+#define writel(v,c)		({ wmb(); writel_relaxed((v),(c)); })
+#else
+#define writeb(v,c)		({ wmb(); writeb_relaxed((v),(c)); mb(); })
+#define writew(v,c)		({ wmb(); writew_relaxed((v),(c)); mb(); })
+#define writel(v,c)		({ wmb(); writel_relaxed((v),(c)); mb(); })
+#endif
+
+/*
+ * I/O memory mapping functions.
+ */
+#define ioremap_wc(addr, size) \
+	ioremap_prot((addr), (size), \
+		__pgprot((_PAGE_IOREMAP & ~_CACHE_MASK) | _CACHE_UNCACHED))
+
+#include <asm-generic/io.h>
+
+#endif /* __ASM_CSKY_IO_H */
diff --git a/arch/csky/include/asm/irq_work.h b/arch/csky/include/asm/irq_work.h
new file mode 100644
index 000000000..d39fcc1f5
--- /dev/null
+++ b/arch/csky/include/asm/irq_work.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_IRQ_WORK_H
+#define __ASM_CSKY_IRQ_WORK_H
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return true;
+}
+
+#endif /* __ASM_CSKY_IRQ_WORK_H */
diff --git a/arch/csky/include/asm/irqflags.h b/arch/csky/include/asm/irqflags.h
new file mode 100644
index 000000000..9e3a569a5
--- /dev/null
+++ b/arch/csky/include/asm/irqflags.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_IRQFLAGS_H
+#define __ASM_CSKY_IRQFLAGS_H
+#include <abi/reg_ops.h>
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags;
+
+	flags = mfcr("psr");
+	asm volatile("psrclr ie\n":::"memory");
+	return flags;
+}
+#define arch_local_irq_save arch_local_irq_save
+
+static inline void arch_local_irq_enable(void)
+{
+	asm volatile("psrset ee, ie\n":::"memory");
+}
+#define arch_local_irq_enable arch_local_irq_enable
+
+static inline void arch_local_irq_disable(void)
+{
+	asm volatile("psrclr ie\n":::"memory");
+}
+#define arch_local_irq_disable arch_local_irq_disable
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	return mfcr("psr");
+}
+#define arch_local_save_flags arch_local_save_flags
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	mtcr("psr", flags);
+}
+#define arch_local_irq_restore arch_local_irq_restore
+
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return !(flags & (1<<6));
+}
+#define arch_irqs_disabled_flags arch_irqs_disabled_flags
+
+#include <asm-generic/irqflags.h>
+
+#endif /* __ASM_CSKY_IRQFLAGS_H */
diff --git a/arch/csky/include/asm/jump_label.h b/arch/csky/include/asm/jump_label.h
new file mode 100644
index 000000000..603b0caa8
--- /dev/null
+++ b/arch/csky/include/asm/jump_label.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_CSKY_JUMP_LABEL_H
+#define __ASM_CSKY_JUMP_LABEL_H
+
+#ifndef __ASSEMBLER__
+
+#include <linux/types.h>
+
+#define JUMP_LABEL_NOP_SIZE 4
+
+static __always_inline bool arch_static_branch(struct static_key *key,
+					       bool branch)
+{
+	asm goto(
+		"1:	nop32					\n"
+		"	.pushsection	__jump_table, \"aw\"	\n"
+		"	.align		2			\n"
+		"	.long		1b - ., %l[label] - .	\n"
+		"	.long		%0 - .			\n"
+		"	.popsection				\n"
+		:  :  "i"(&((char *)key)[branch]) :  : label);
+
+	return false;
+label:
+	return true;
+}
+
+static __always_inline bool arch_static_branch_jump(struct static_key *key,
+						    bool branch)
+{
+	asm goto(
+		"1:	bsr32		%l[label]		\n"
+		"	.pushsection	__jump_table, \"aw\"	\n"
+		"	.align		2			\n"
+		"	.long		1b - ., %l[label] - .	\n"
+		"	.long		%0 - .			\n"
+		"	.popsection				\n"
+		:  :  "i"(&((char *)key)[branch]) :  : label);
+
+	return false;
+label:
+	return true;
+}
+
+enum jump_label_type;
+void arch_jump_label_transform_static(struct jump_entry *entry,
+				      enum jump_label_type type);
+#define arch_jump_label_transform_static arch_jump_label_transform_static
+
+#endif  /* __ASSEMBLER__ */
+#endif	/* __ASM_CSKY_JUMP_LABEL_H */
diff --git a/arch/csky/include/asm/kprobes.h b/arch/csky/include/asm/kprobes.h
new file mode 100644
index 000000000..55267cbf5
--- /dev/null
+++ b/arch/csky/include/asm/kprobes.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_CSKY_KPROBES_H
+#define __ASM_CSKY_KPROBES_H
+
+#include <asm-generic/kprobes.h>
+
+#ifdef CONFIG_KPROBES
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+
+#define __ARCH_WANT_KPROBES_INSN_SLOT
+#define MAX_INSN_SIZE			1
+
+#define flush_insn_slot(p)		do { } while (0)
+#define kretprobe_blacklist_size	0
+
+#include <asm/probes.h>
+
+struct prev_kprobe {
+	struct kprobe *kp;
+	unsigned int status;
+};
+
+/* Single step context for kprobe */
+struct kprobe_step_ctx {
+	unsigned long ss_pending;
+	unsigned long match_addr;
+};
+
+/* per-cpu kprobe control block */
+struct kprobe_ctlblk {
+	unsigned int kprobe_status;
+	unsigned long saved_sr;
+	struct prev_kprobe prev_kprobe;
+	struct kprobe_step_ctx ss_ctx;
+};
+
+void arch_remove_kprobe(struct kprobe *p);
+int kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr);
+int kprobe_breakpoint_handler(struct pt_regs *regs);
+int kprobe_single_step_handler(struct pt_regs *regs);
+void __kretprobe_trampoline(void);
+void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
+
+#endif /* CONFIG_KPROBES */
+#endif /* __ASM_CSKY_KPROBES_H */
diff --git a/arch/csky/include/asm/memory.h b/arch/csky/include/asm/memory.h
new file mode 100644
index 000000000..d12179801
--- /dev/null
+++ b/arch/csky/include/asm/memory.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_MEMORY_H
+#define __ASM_CSKY_MEMORY_H
+
+#include <linux/compiler.h>
+#include <linux/const.h>
+#include <linux/types.h>
+#include <linux/sizes.h>
+
+#define FIXADDR_TOP	_AC(0xffffc000, UL)
+#define PKMAP_BASE	_AC(0xff800000, UL)
+#define VMALLOC_START	(PAGE_OFFSET + LOWMEM_LIMIT + (PAGE_SIZE * 8))
+#define VMALLOC_END	(PKMAP_BASE - (PAGE_SIZE * 2))
+
+#ifdef CONFIG_HAVE_TCM
+#ifdef CONFIG_HAVE_DTCM
+#define TCM_NR_PAGES	(CONFIG_ITCM_NR_PAGES + CONFIG_DTCM_NR_PAGES)
+#else
+#define TCM_NR_PAGES	(CONFIG_ITCM_NR_PAGES)
+#endif
+#define FIXADDR_TCM	_AC(FIXADDR_TOP - (TCM_NR_PAGES * PAGE_SIZE), UL)
+#endif
+
+#endif
diff --git a/arch/csky/include/asm/mmu.h b/arch/csky/include/asm/mmu.h
new file mode 100644
index 000000000..d78321901
--- /dev/null
+++ b/arch/csky/include/asm/mmu.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_MMU_H
+#define __ASM_CSKY_MMU_H
+
+typedef struct {
+	atomic64_t	asid;
+	void *vdso;
+	cpumask_t	icache_stale_mask;
+} mm_context_t;
+
+#endif /* __ASM_CSKY_MMU_H */
diff --git a/arch/csky/include/asm/mmu_context.h b/arch/csky/include/asm/mmu_context.h
new file mode 100644
index 000000000..95d99b307
--- /dev/null
+++ b/arch/csky/include/asm/mmu_context.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_MMU_CONTEXT_H
+#define __ASM_CSKY_MMU_CONTEXT_H
+
+#include <asm-generic/mm_hooks.h>
+#include <asm/setup.h>
+#include <asm/page.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <abi/ckmmu.h>
+
+#define ASID_MASK		((1 << CONFIG_CPU_ASID_BITS) - 1)
+#define cpu_asid(mm)		(atomic64_read(&mm->context.asid) & ASID_MASK)
+
+#define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.asid, 0); 0; })
+
+void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
+
+static inline void
+switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	  struct task_struct *tsk)
+{
+	unsigned int cpu = smp_processor_id();
+
+	if (prev != next)
+		check_and_switch_context(next, cpu);
+
+	setup_pgd(next->pgd, next->context.asid.counter);
+
+	flush_icache_deferred(next);
+}
+
+#include <asm-generic/mmu_context.h>
+
+#endif /* __ASM_CSKY_MMU_CONTEXT_H */
diff --git a/arch/csky/include/asm/page.h b/arch/csky/include/asm/page.h
new file mode 100644
index 000000000..76774dbce
--- /dev/null
+++ b/arch/csky/include/asm/page.h
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_PAGE_H
+#define __ASM_CSKY_PAGE_H
+
+#include <asm/setup.h>
+#include <asm/cache.h>
+#include <linux/const.h>
+
+#include <vdso/page.h>
+
+#define THREAD_SIZE	(PAGE_SIZE * 2)
+#define THREAD_MASK	(~(THREAD_SIZE - 1))
+#define THREAD_SHIFT	(PAGE_SHIFT + 1)
+
+
+/*
+ * For C-SKY "User-space:Kernel-space" is "2GB:2GB" fixed by hardware and there
+ * are two segment registers (MSA0 + MSA1) to mapping 512MB + 512MB physical
+ * address region. We use them mapping kernel 1GB direct-map address area and
+ * for more than 1GB of memory we use highmem.
+ */
+#define PAGE_OFFSET	CONFIG_PAGE_OFFSET
+#define SSEG_SIZE	0x20000000
+#define LOWMEM_LIMIT	(SSEG_SIZE * 2)
+
+#define PHYS_OFFSET_OFFSET (CONFIG_DRAM_BASE & (SSEG_SIZE - 1))
+
+#ifndef __ASSEMBLER__
+
+#include <linux/pfn.h>
+
+#define virt_addr_valid(kaddr)  ((void *)(kaddr) >= (void *)PAGE_OFFSET && \
+			(void *)(kaddr) < high_memory)
+
+extern void *memset(void *dest, int c, size_t l);
+extern void *memcpy(void *to, const void *from, size_t l);
+
+#define clear_page(page)	memset((page), 0, PAGE_SIZE)
+#define copy_page(to, from)	memcpy((to), (from), PAGE_SIZE)
+
+struct page;
+
+#include <abi/page.h>
+
+struct vm_area_struct;
+
+typedef struct { unsigned long pte_low; } pte_t;
+#define pte_val(x)	((x).pte_low)
+
+typedef struct { unsigned long pgd; } pgd_t;
+typedef struct { unsigned long pgprot; } pgprot_t;
+typedef struct page *pgtable_t;
+
+#define pgd_val(x)	((x).pgd)
+#define pgprot_val(x)	((x).pgprot)
+
+#define ptep_buddy(x)	((pte_t *)((unsigned long)(x) ^ sizeof(pte_t)))
+
+#define __pte(x)	((pte_t) { (x) })
+#define __pgd(x)	((pgd_t) { (x) })
+#define __pgprot(x)	((pgprot_t) { (x) })
+
+extern unsigned long va_pa_offset;
+
+#define ARCH_PFN_OFFSET	PFN_DOWN(va_pa_offset + PHYS_OFFSET_OFFSET)
+
+#define __pa(x)		 ((unsigned long)(x) - PAGE_OFFSET + va_pa_offset)
+#define __va(x) ((void *)((unsigned long)(x) + PAGE_OFFSET - va_pa_offset))
+
+#define __pa_symbol(x)	__pa(RELOC_HIDE((unsigned long)(x), 0))
+
+static inline unsigned long virt_to_pfn(const void *kaddr)
+{
+	return __pa(kaddr) >> PAGE_SHIFT;
+}
+
+#define MAP_NR(x)	PFN_DOWN((unsigned long)(x) - PAGE_OFFSET - \
+				 PHYS_OFFSET_OFFSET)
+#define virt_to_page(x)	(mem_map + MAP_NR(x))
+
+#define pfn_to_kaddr(x)	__va(PFN_PHYS(x))
+
+#include <asm-generic/memory_model.h>
+#include <asm-generic/getorder.h>
+
+#endif /* !__ASSEMBLER__ */
+#endif /* __ASM_CSKY_PAGE_H */
diff --git a/arch/csky/include/asm/pci.h b/arch/csky/include/asm/pci.h
new file mode 100644
index 000000000..42724c630
--- /dev/null
+++ b/arch/csky/include/asm/pci.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_CSKY_PCI_H
+#define __ASM_CSKY_PCI_H
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+
+#include <asm/io.h>
+
+/* Generic PCI */
+#include <asm-generic/pci.h>
+
+#endif  /* __ASM_CSKY_PCI_H */
diff --git a/arch/csky/include/asm/perf_event.h b/arch/csky/include/asm/perf_event.h
new file mode 100644
index 000000000..249905d8a
--- /dev/null
+++ b/arch/csky/include/asm/perf_event.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_PERF_EVENT_H
+#define __ASM_CSKY_PERF_EVENT_H
+
+#include <abi/regdef.h>
+
+#define perf_arch_fetch_caller_regs(regs, __ip) { \
+	(regs)->pc = (__ip); \
+	regs_fp(regs) = (unsigned long) __builtin_frame_address(0); \
+	asm volatile("mov %0, sp\n":"=r"((regs)->usp)); \
+}
+
+#endif /* __ASM_PERF_EVENT_ELF_H */
diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h
new file mode 100644
index 000000000..9ed2b15ff
--- /dev/null
+++ b/arch/csky/include/asm/pgalloc.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_PGALLOC_H
+#define __ASM_CSKY_PGALLOC_H
+
+#include <linux/highmem.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+
+#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
+#include <asm-generic/pgalloc.h>
+
+static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
+					pte_t *pte)
+{
+	set_pmd(pmd, __pmd(__pa(pte)));
+}
+
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
+					pgtable_t pte)
+{
+	set_pmd(pmd, __pmd(__pa(page_address(pte))));
+}
+
+extern void pgd_init(unsigned long *p);
+
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
+{
+	pte_t *pte;
+	unsigned long i;
+
+	pte = __pte_alloc_one_kernel(mm);
+	if (!pte)
+		return NULL;
+
+	for (i = 0; i < PAGE_SIZE/sizeof(pte_t); i++)
+		(pte + i)->pte_low = _PAGE_GLOBAL;
+
+	return pte;
+}
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	pgd_t *ret;
+	pgd_t *init;
+
+	ret = __pgd_alloc(mm, 0);
+	if (ret) {
+		init = pgd_offset(&init_mm, 0UL);
+		pgd_init((unsigned long *)ret);
+		memcpy(ret + USER_PTRS_PER_PGD, init + USER_PTRS_PER_PGD,
+			(PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+		/* prevent out of order excute */
+		smp_mb();
+#ifdef CONFIG_CPU_NEED_TLBSYNC
+		dcache_wb_range((unsigned int)ret,
+				(unsigned int)(ret + PTRS_PER_PGD));
+#endif
+	}
+
+	return ret;
+}
+
+#define __pte_free_tlb(tlb, pte, address)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
+
+extern void pagetable_init(void);
+extern void mmu_init(unsigned long min_pfn, unsigned long max_pfn);
+extern void pre_trap_init(void);
+
+#endif /* __ASM_CSKY_PGALLOC_H */
diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h
new file mode 100644
index 000000000..bafcd5823
--- /dev/null
+++ b/arch/csky/include/asm/pgtable.h
@@ -0,0 +1,263 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_PGTABLE_H
+#define __ASM_CSKY_PGTABLE_H
+
+#include <asm/fixmap.h>
+#include <asm/memory.h>
+#include <asm/addrspace.h>
+#include <abi/pgtable-bits.h>
+#include <asm-generic/pgtable-nopmd.h>
+
+#define PGDIR_SHIFT		22
+#define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK		(~(PGDIR_SIZE-1))
+
+#define USER_PTRS_PER_PGD	(PAGE_OFFSET/PGDIR_SIZE)
+
+/*
+ * C-SKY is two-level paging structure:
+ */
+
+#define PTRS_PER_PGD	(PAGE_SIZE / sizeof(pgd_t))
+#define PTRS_PER_PMD	1
+#define PTRS_PER_PTE	(PAGE_SIZE / sizeof(pte_t))
+
+#define pte_ERROR(e) \
+	pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low)
+#define pgd_ERROR(e) \
+	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+#define PFN_PTE_SHIFT	PAGE_SHIFT
+#define pmd_pfn(pmd)	(pmd_phys(pmd) >> PAGE_SHIFT)
+#define pmd_page(pmd)	(pfn_to_page(pmd_phys(pmd) >> PAGE_SHIFT))
+#define pte_clear(mm, addr, ptep)	set_pte((ptep), \
+	(((unsigned int) addr >= PAGE_OFFSET) ? __pte(_PAGE_GLOBAL) : __pte(0)))
+#define pte_none(pte)		(!(pte_val(pte) & ~_PAGE_GLOBAL))
+#define pte_present(pte)	(pte_val(pte) & _PAGE_PRESENT)
+#define pte_pfn(x)	((unsigned long)((x).pte_low >> PAGE_SHIFT))
+#define pfn_pte(pfn, prot) __pte(((unsigned long long)(pfn) << PAGE_SHIFT) \
+				| pgprot_val(prot))
+
+#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x)		((pte_t) { (x).val })
+
+#define pte_page(x)			pfn_to_page(pte_pfn(x))
+#define __mk_pte(page_nr, pgprot)	__pte(((page_nr) << PAGE_SHIFT) | \
+					pgprot_val(pgprot))
+
+/*
+ * C-SKY only has VALID and DIRTY bit in hardware. So we need to use the
+ * two bits emulate PRESENT, READ, WRITE, EXEC, MODIFIED, ACCESSED.
+ */
+#define _PAGE_BASE	(_PAGE_PRESENT | _PAGE_ACCESSED)
+
+#define PAGE_NONE	__pgprot(_PAGE_PROT_NONE)
+#define PAGE_READ	__pgprot(_PAGE_BASE | _PAGE_READ | \
+				_CACHE_CACHED)
+#define PAGE_WRITE	__pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_WRITE | \
+				_CACHE_CACHED)
+#define PAGE_SHARED PAGE_WRITE
+
+#define PAGE_KERNEL	__pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_VALID | \
+				_PAGE_WRITE | _PAGE_DIRTY | _PAGE_MODIFIED | \
+				_PAGE_GLOBAL | \
+				_CACHE_CACHED)
+
+#define _PAGE_IOREMAP		(_PAGE_BASE | _PAGE_READ | _PAGE_VALID | \
+				_PAGE_WRITE | _PAGE_DIRTY | _PAGE_MODIFIED | \
+				_PAGE_GLOBAL | \
+				_CACHE_UNCACHED | _PAGE_SO)
+
+#define _PAGE_CHG_MASK	(~(unsigned long) \
+				(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+				_CACHE_MASK | _PAGE_GLOBAL))
+
+#define MAX_SWAPFILES_CHECK() \
+		BUILD_BUG_ON(MAX_SWAPFILES_SHIFT != 5)
+
+extern void load_pgd(unsigned long pg_dir);
+extern pte_t invalid_pte_table[PTRS_PER_PTE];
+
+static inline void set_pte(pte_t *p, pte_t pte)
+{
+	*p = pte;
+#if defined(CONFIG_CPU_NEED_TLBSYNC)
+	dcache_wb_line((u32)p);
+#endif
+	/* prevent out of order excution */
+	smp_mb();
+}
+
+static inline pte_t *pmd_page_vaddr(pmd_t pmd)
+{
+	unsigned long ptr;
+
+	ptr = pmd_val(pmd);
+
+	return __va(ptr);
+}
+
+#define pmd_phys(pmd) pmd_val(pmd)
+
+static inline void set_pmd(pmd_t *p, pmd_t pmd)
+{
+	*p = pmd;
+#if defined(CONFIG_CPU_NEED_TLBSYNC)
+	dcache_wb_line((u32)p);
+#endif
+	/* prevent specul excute */
+	smp_mb();
+}
+
+
+static inline int pmd_none(pmd_t pmd)
+{
+	return pmd_val(pmd) == __pa(invalid_pte_table);
+}
+
+#define pmd_bad(pmd)	(pmd_val(pmd) & ~PAGE_MASK)
+
+static inline int pmd_present(pmd_t pmd)
+{
+	return (pmd_val(pmd) != __pa(invalid_pte_table));
+}
+
+static inline void pmd_clear(pmd_t *p)
+{
+	pmd_val(*p) = (__pa(invalid_pte_table));
+#if defined(CONFIG_CPU_NEED_TLBSYNC)
+	dcache_wb_line((u32)p);
+#endif
+}
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+static inline int pte_read(pte_t pte)
+{
+	return pte.pte_low & _PAGE_READ;
+}
+
+static inline int pte_write(pte_t pte)
+{
+	return (pte).pte_low & _PAGE_WRITE;
+}
+
+static inline int pte_dirty(pte_t pte)
+{
+	return (pte).pte_low & _PAGE_MODIFIED;
+}
+
+static inline int pte_young(pte_t pte)
+{
+	return (pte).pte_low & _PAGE_ACCESSED;
+}
+
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	pte_val(pte) &= ~(_PAGE_WRITE | _PAGE_DIRTY);
+	return pte;
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+	pte_val(pte) &= ~(_PAGE_MODIFIED|_PAGE_DIRTY);
+	return pte;
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+	pte_val(pte) &= ~(_PAGE_ACCESSED|_PAGE_VALID);
+	return pte;
+}
+
+static inline pte_t pte_mkwrite_novma(pte_t pte)
+{
+	pte_val(pte) |= _PAGE_WRITE;
+	if (pte_val(pte) & _PAGE_MODIFIED)
+		pte_val(pte) |= _PAGE_DIRTY;
+	return pte;
+}
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+	pte_val(pte) |= _PAGE_MODIFIED;
+	if (pte_val(pte) & _PAGE_WRITE)
+		pte_val(pte) |= _PAGE_DIRTY;
+	return pte;
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+	pte_val(pte) |= _PAGE_ACCESSED;
+	if (pte_val(pte) & _PAGE_READ)
+		pte_val(pte) |= _PAGE_VALID;
+	return pte;
+}
+
+static inline bool pte_swp_exclusive(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
+}
+
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+	pte_val(pte) |= _PAGE_SWP_EXCLUSIVE;
+	return pte;
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+	pte_val(pte) &= ~_PAGE_SWP_EXCLUSIVE;
+	return pte;
+}
+
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
+
+/*
+ * Macro to make mark a page protection value as "uncacheable".  Note
+ * that "protection" is really a misnomer here as the protection value
+ * contains the memory attribute bits, dirty bits, and various other
+ * bits as well.
+ */
+#define pgprot_noncached pgprot_noncached
+
+static inline pgprot_t pgprot_noncached(pgprot_t _prot)
+{
+	unsigned long prot = pgprot_val(_prot);
+
+	prot = (prot & ~_CACHE_MASK) | _CACHE_UNCACHED | _PAGE_SO;
+
+	return __pgprot(prot);
+}
+
+#define pgprot_writecombine pgprot_writecombine
+static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
+{
+	unsigned long prot = pgprot_val(_prot);
+
+	prot = (prot & ~_CACHE_MASK) | _CACHE_UNCACHED;
+
+	return __pgprot(prot);
+}
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	return __pte((pte_val(pte) & _PAGE_CHG_MASK) |
+		     (pgprot_val(newprot)));
+}
+
+extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+extern void paging_init(void);
+
+void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
+		unsigned long address, pte_t *pte, unsigned int nr);
+#define update_mmu_cache(vma, addr, ptep) \
+	update_mmu_cache_range(NULL, vma, addr, ptep, 1)
+
+#endif /* __ASM_CSKY_PGTABLE_H */
diff --git a/arch/csky/include/asm/probes.h b/arch/csky/include/asm/probes.h
new file mode 100644
index 000000000..5e526334e
--- /dev/null
+++ b/arch/csky/include/asm/probes.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_PROBES_H
+#define __ASM_CSKY_PROBES_H
+
+typedef u32 probe_opcode_t;
+typedef void (probes_handler_t) (u32 opcode, long addr, struct pt_regs *);
+
+/* architecture specific copy of original instruction */
+struct arch_probe_insn {
+	probe_opcode_t *insn;
+	probes_handler_t *handler;
+	/* restore address after simulation */
+	unsigned long restore;
+};
+
+#ifdef CONFIG_KPROBES
+typedef u32 kprobe_opcode_t;
+struct arch_specific_insn {
+	struct arch_probe_insn api;
+};
+#endif
+
+#endif /* __ASM_CSKY_PROBES_H */
diff --git a/arch/csky/include/asm/processor.h b/arch/csky/include/asm/processor.h
new file mode 100644
index 000000000..e487a46d1
--- /dev/null
+++ b/arch/csky/include/asm/processor.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_PROCESSOR_H
+#define __ASM_CSKY_PROCESSOR_H
+
+#include <linux/bitops.h>
+#include <linux/cache.h>
+#include <asm/ptrace.h>
+#include <asm/current.h>
+#include <abi/reg_ops.h>
+#include <abi/regdef.h>
+#include <abi/switch_context.h>
+#ifdef CONFIG_CPU_HAS_FPU
+#include <abi/fpu.h>
+#endif
+
+struct cpuinfo_csky {
+	unsigned long asid_cache;
+} __aligned(SMP_CACHE_BYTES);
+
+extern struct cpuinfo_csky cpu_data[];
+
+/*
+ * User space process size: 2GB. This is hardcoded into a few places,
+ * so don't change it unless you know what you are doing.  TASK_SIZE
+ * for a 64 bit kernel expandable to 8192EB, of which the current CSKY
+ * implementations will "only" be able to use 1TB ...
+ */
+#define TASK_SIZE	(PAGE_OFFSET - (PAGE_SIZE * 8))
+
+#ifdef __KERNEL__
+#define STACK_TOP       TASK_SIZE
+#define STACK_TOP_MAX   STACK_TOP
+#endif
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE      (TASK_SIZE / 3)
+
+struct thread_struct {
+	unsigned long  sp;        /* kernel stack pointer */
+	unsigned long  trap_no;   /* saved status register */
+
+	/* FPU regs */
+	struct user_fp __aligned(16) user_fp;
+};
+
+#define INIT_THREAD  { \
+	.sp = sizeof(init_stack) + (unsigned long) &init_stack, \
+}
+
+/*
+ * Do necessary setup to start up a newly executed thread.
+ *
+ * pass the data segment into user programs if it exists,
+ * it can't hurt anything as far as I can tell
+ */
+#define start_thread(_regs, _pc, _usp)					\
+do {									\
+	(_regs)->pc = (_pc);						\
+	(_regs)->regs[1] = 0; /* ABIV1 is R7, uClibc_main rtdl arg */	\
+	(_regs)->regs[2] = 0;						\
+	(_regs)->regs[3] = 0; /* ABIV2 is R7, use it? */		\
+	(_regs)->sr &= ~PS_S;						\
+	(_regs)->usp = (_usp);						\
+} while (0)
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+
+/* Prepare to copy thread state - unlazy all lazy status */
+#define prepare_to_copy(tsk)    do { } while (0)
+
+unsigned long __get_wchan(struct task_struct *p);
+
+#define KSTK_EIP(tsk)		(task_pt_regs(tsk)->pc)
+#define KSTK_ESP(tsk)		(task_pt_regs(tsk)->usp)
+
+#define task_pt_regs(p) \
+	((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1)
+
+#define cpu_relax() barrier()
+
+register unsigned long current_stack_pointer __asm__("sp");
+
+#endif /* __ASM_CSKY_PROCESSOR_H */
diff --git a/arch/csky/include/asm/ptrace.h b/arch/csky/include/asm/ptrace.h
new file mode 100644
index 000000000..5f01839e1
--- /dev/null
+++ b/arch/csky/include/asm/ptrace.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_PTRACE_H
+#define __ASM_CSKY_PTRACE_H
+
+#include <uapi/asm/ptrace.h>
+#include <asm/traps.h>
+#include <linux/types.h>
+#include <linux/compiler.h>
+
+#ifndef __ASSEMBLER__
+
+#define PS_S	0x80000000 /* Supervisor Mode */
+
+#define USR_BKPT	0x1464
+
+#define arch_has_single_step() (1)
+#define current_pt_regs() \
+({ (struct pt_regs *)((char *)current_thread_info() + THREAD_SIZE) - 1; })
+
+#define user_stack_pointer(regs) ((regs)->usp)
+
+#define user_mode(regs) (!((regs)->sr & PS_S))
+#define instruction_pointer(regs) ((regs)->pc)
+#define profile_pc(regs) instruction_pointer(regs)
+#define trap_no(regs) ((regs->sr >> 16) & 0xff)
+
+static inline void instruction_pointer_set(struct pt_regs *regs,
+					   unsigned long val)
+{
+	regs->pc = val;
+}
+
+#if defined(__CSKYABIV2__)
+#define MAX_REG_OFFSET offsetof(struct pt_regs, dcsr)
+#else
+#define MAX_REG_OFFSET offsetof(struct pt_regs, regs[9])
+#endif
+
+static inline bool in_syscall(struct pt_regs const *regs)
+{
+	return ((regs->sr >> 16) & 0xff) == VEC_TRAP0;
+}
+
+static inline void forget_syscall(struct pt_regs *regs)
+{
+	regs->sr &= ~(0xff << 16);
+}
+
+static inline unsigned long regs_return_value(struct pt_regs *regs)
+{
+	return regs->a0;
+}
+
+static inline void regs_set_return_value(struct pt_regs *regs,
+					 unsigned long val)
+{
+	regs->a0 = val;
+}
+
+/* Valid only for Kernel mode traps. */
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	return regs->usp;
+}
+
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+	return regs->regs[4];
+}
+static inline void frame_pointer_set(struct pt_regs *regs,
+				     unsigned long val)
+{
+	regs->regs[4] = val;
+}
+
+extern int regs_query_register_offset(const char *name);
+extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+						unsigned int n);
+
+/*
+ * regs_get_register() - get register value from its offset
+ * @regs:      pt_regs from which register value is gotten
+ * @offset:    offset of the register.
+ *
+ * regs_get_register returns the value of a register whose offset from @regs.
+ * The @offset is the offset of the register in struct pt_regs.
+ * If @offset is bigger than MAX_REG_OFFSET, this returns 0.
+ */
+static inline unsigned long regs_get_register(struct pt_regs *regs,
+						unsigned int offset)
+{
+	if (unlikely(offset > MAX_REG_OFFSET))
+		return 0;
+
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
+asmlinkage int syscall_trace_enter(struct pt_regs *regs);
+asmlinkage void syscall_trace_exit(struct pt_regs *regs);
+#endif /* __ASSEMBLER__ */
+#endif /* __ASM_CSKY_PTRACE_H */
diff --git a/arch/csky/include/asm/reg_ops.h b/arch/csky/include/asm/reg_ops.h
new file mode 100644
index 000000000..cccf7d525
--- /dev/null
+++ b/arch/csky/include/asm/reg_ops.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_REGS_OPS_H
+#define __ASM_REGS_OPS_H
+
+#define mfcr(reg)		\
+({				\
+	unsigned int tmp;	\
+	asm volatile(		\
+	"mfcr %0, "reg"\n"	\
+	: "=r"(tmp)		\
+	:			\
+	: "memory");		\
+	tmp;			\
+})
+
+#define mtcr(reg, val)		\
+({				\
+	asm volatile(		\
+	"mtcr %0, "reg"\n"	\
+	:			\
+	: "r"(val)		\
+	: "memory");		\
+})
+
+#endif /* __ASM_REGS_OPS_H */
diff --git a/arch/csky/include/asm/seccomp.h b/arch/csky/include/asm/seccomp.h
new file mode 100644
index 000000000..d33e75812
--- /dev/null
+++ b/arch/csky/include/asm/seccomp.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
+
+#include <asm-generic/seccomp.h>
+
+#define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_CSKY
+#define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+#define SECCOMP_ARCH_NATIVE_NAME	"csky"
+
+#endif /* _ASM_SECCOMP_H */
diff --git a/arch/csky/include/asm/sections.h b/arch/csky/include/asm/sections.h
new file mode 100644
index 000000000..ee5cdf226
--- /dev/null
+++ b/arch/csky/include/asm/sections.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_SECTIONS_H
+#define __ASM_SECTIONS_H
+
+#include <asm-generic/sections.h>
+
+extern char _start[];
+
+asmlinkage void csky_start(unsigned int unused, void *dtb_start);
+asmlinkage void csky_start_secondary(void);
+
+#endif /* __ASM_SECTIONS_H */
diff --git a/arch/csky/include/asm/shmparam.h b/arch/csky/include/asm/shmparam.h
new file mode 100644
index 000000000..2fe6cea0d
--- /dev/null
+++ b/arch/csky/include/asm/shmparam.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_SHMPARAM_H
+#define __ASM_CSKY_SHMPARAM_H
+
+#define SHMLBA	(4 * PAGE_SIZE)
+
+#define __ARCH_FORCE_SHMLBA
+
+#endif /* __ASM_CSKY_SHMPARAM_H */
diff --git a/arch/csky/include/asm/smp.h b/arch/csky/include/asm/smp.h
new file mode 100644
index 000000000..d3db334f3
--- /dev/null
+++ b/arch/csky/include/asm/smp.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_SMP_H
+#define __ASM_CSKY_SMP_H
+
+#include <linux/cpumask.h>
+#include <linux/irqreturn.h>
+#include <linux/threads.h>
+
+#ifdef CONFIG_SMP
+
+void __init setup_smp(void);
+
+void __init setup_smp_ipi(void);
+
+void arch_send_call_function_ipi_mask(struct cpumask *mask);
+
+void arch_send_call_function_single_ipi(int cpu);
+
+void __init set_send_ipi(void (*func)(const struct cpumask *mask), int irq);
+
+#define raw_smp_processor_id()	(current_thread_info()->cpu)
+
+int __cpu_disable(void);
+
+static inline void __cpu_die(unsigned int cpu) { }
+
+#endif /* CONFIG_SMP */
+
+#endif /* __ASM_CSKY_SMP_H */
diff --git a/arch/csky/include/asm/spinlock.h b/arch/csky/include/asm/spinlock.h
new file mode 100644
index 000000000..83a200534
--- /dev/null
+++ b/arch/csky/include/asm/spinlock.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_SPINLOCK_H
+#define __ASM_CSKY_SPINLOCK_H
+
+#include <asm/qspinlock.h>
+#include <asm/qrwlock.h>
+
+/* See include/linux/spinlock.h */
+#define smp_mb__after_spinlock()	smp_mb()
+
+#endif /* __ASM_CSKY_SPINLOCK_H */
diff --git a/arch/csky/include/asm/spinlock_types.h b/arch/csky/include/asm/spinlock_types.h
new file mode 100644
index 000000000..75bdf3af8
--- /dev/null
+++ b/arch/csky/include/asm/spinlock_types.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_SPINLOCK_TYPES_H
+#define __ASM_CSKY_SPINLOCK_TYPES_H
+
+#include <asm-generic/qspinlock_types.h>
+#include <asm-generic/qrwlock_types.h>
+
+#endif /* __ASM_CSKY_SPINLOCK_TYPES_H */
diff --git a/arch/csky/include/asm/stackprotector.h b/arch/csky/include/asm/stackprotector.h
new file mode 100644
index 000000000..d23747447
--- /dev/null
+++ b/arch/csky/include/asm/stackprotector.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_STACKPROTECTOR_H
+#define _ASM_STACKPROTECTOR_H 1
+
+extern unsigned long __stack_chk_guard;
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+	unsigned long canary = get_random_canary();
+
+	current->stack_canary = canary;
+	__stack_chk_guard = current->stack_canary;
+}
+
+#endif /* __ASM_SH_STACKPROTECTOR_H */
diff --git a/arch/csky/include/asm/string.h b/arch/csky/include/asm/string.h
new file mode 100644
index 000000000..82e99f52b
--- /dev/null
+++ b/arch/csky/include/asm/string.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _CSKY_STRING_MM_H_
+#define _CSKY_STRING_MM_H_
+
+#ifndef __ASSEMBLER__
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <abi/string.h>
+#endif
+
+#endif /* _CSKY_STRING_MM_H_ */
diff --git a/arch/csky/include/asm/switch_to.h b/arch/csky/include/asm/switch_to.h
new file mode 100644
index 000000000..731e46641
--- /dev/null
+++ b/arch/csky/include/asm/switch_to.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_SWITCH_TO_H
+#define __ASM_CSKY_SWITCH_TO_H
+
+#include <linux/thread_info.h>
+#ifdef CONFIG_CPU_HAS_FPU
+#include <abi/fpu.h>
+static inline void __switch_to_fpu(struct task_struct *prev,
+				   struct task_struct *next)
+{
+	save_to_user_fp(&prev->thread.user_fp);
+	restore_from_user_fp(&next->thread.user_fp);
+}
+#else
+static inline void __switch_to_fpu(struct task_struct *prev,
+				   struct task_struct *next)
+{}
+#endif
+
+/*
+ * Context switching is now performed out-of-line in switch_to.S
+ */
+extern struct task_struct *__switch_to(struct task_struct *,
+				       struct task_struct *);
+
+#define switch_to(prev, next, last)					\
+	do {								\
+		struct task_struct *__prev = (prev);			\
+		struct task_struct *__next = (next);			\
+		__switch_to_fpu(__prev, __next);			\
+		((last) = __switch_to((prev), (next)));			\
+	} while (0)
+
+#endif /* __ASM_CSKY_SWITCH_TO_H */
diff --git a/arch/csky/include/asm/syscall.h b/arch/csky/include/asm/syscall.h
new file mode 100644
index 000000000..717f44b4d
--- /dev/null
+++ b/arch/csky/include/asm/syscall.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_SYSCALL_H
+#define __ASM_SYSCALL_H
+
+#include <linux/sched.h>
+#include <linux/err.h>
+#include <abi/regdef.h>
+#include <uapi/linux/audit.h>
+
+extern void *sys_call_table[];
+
+static inline int
+syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
+{
+	return regs_syscallid(regs);
+}
+
+static inline void
+syscall_set_nr(struct task_struct *task, struct pt_regs *regs,
+	       int sysno)
+{
+	regs_syscallid(regs) = sysno;
+}
+
+static inline void
+syscall_rollback(struct task_struct *task, struct pt_regs *regs)
+{
+	regs->a0 = regs->orig_a0;
+}
+
+static inline long
+syscall_get_error(struct task_struct *task, struct pt_regs *regs)
+{
+	unsigned long error = regs->a0;
+
+	return IS_ERR_VALUE(error) ? error : 0;
+}
+
+static inline long
+syscall_get_return_value(struct task_struct *task, struct pt_regs *regs)
+{
+	return regs->a0;
+}
+
+static inline void
+syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
+		int error, long val)
+{
+	regs->a0 = (long) error ?: val;
+}
+
+static inline void
+syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
+		      unsigned long *args)
+{
+	args[0] = regs->orig_a0;
+	args++;
+	memcpy(args, &regs->a1, 5 * sizeof(args[0]));
+}
+
+static inline void
+syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
+		      const unsigned long *args)
+{
+	memcpy(&regs->a0, args, 6 * sizeof(regs->a0));
+	/*
+	 * Also copy the first argument into orig_a0
+	 * so that syscall_get_arguments() would return it
+	 * instead of the previous value.
+	 */
+	regs->orig_a0 = regs->a0;
+}
+
+static inline int
+syscall_get_arch(struct task_struct *task)
+{
+	return AUDIT_ARCH_CSKY;
+}
+
+#endif	/* __ASM_SYSCALL_H */
diff --git a/arch/csky/include/asm/syscalls.h b/arch/csky/include/asm/syscalls.h
new file mode 100644
index 000000000..ea9ce6138
--- /dev/null
+++ b/arch/csky/include/asm/syscalls.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_SYSCALLS_H
+#define __ASM_CSKY_SYSCALLS_H
+
+#include <asm-generic/syscalls.h>
+
+long sys_cacheflush(void __user *, unsigned long, int);
+
+long sys_set_thread_area(unsigned long addr);
+
+long sys_csky_fadvise64_64(int fd, int advice, loff_t offset, loff_t len);
+
+#endif /* __ASM_CSKY_SYSCALLS_H */
diff --git a/arch/csky/include/asm/tcm.h b/arch/csky/include/asm/tcm.h
new file mode 100644
index 000000000..bd1e662ec
--- /dev/null
+++ b/arch/csky/include/asm/tcm.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_TCM_H
+#define __ASM_CSKY_TCM_H
+
+#ifndef CONFIG_HAVE_TCM
+#error "You should not be including tcm.h unless you have a TCM!"
+#endif
+
+#include <linux/compiler.h>
+
+/* Tag variables with this */
+#define __tcmdata __section(".tcm.data")
+/* Tag constants with this */
+#define __tcmconst __section(".tcm.rodata")
+/* Tag functions inside TCM called from outside TCM with this */
+#define __tcmfunc __section(".tcm.text") noinline
+/* Tag function inside TCM called from inside TCM  with this */
+#define __tcmlocalfunc __section(".tcm.text")
+
+void *tcm_alloc(size_t len);
+void tcm_free(void *addr, size_t len);
+
+#endif
diff --git a/arch/csky/include/asm/thread_info.h b/arch/csky/include/asm/thread_info.h
new file mode 100644
index 000000000..fdd4f8ad4
--- /dev/null
+++ b/arch/csky/include/asm/thread_info.h
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_CSKY_THREAD_INFO_H
+#define _ASM_CSKY_THREAD_INFO_H
+
+#ifndef __ASSEMBLER__
+
+#include <asm/types.h>
+#include <asm/page.h>
+#include <asm/processor.h>
+#include <abi/switch_context.h>
+
+struct thread_info {
+	struct task_struct	*task;
+	void			*dump_exec_domain;
+	unsigned long		flags;
+	int			preempt_count;
+	unsigned long		tp_value;
+	struct restart_block	restart_block;
+	struct pt_regs		*regs;
+	unsigned int		cpu;
+};
+
+#define INIT_THREAD_INFO(tsk)			\
+{						\
+	.task		= &tsk,			\
+	.preempt_count  = INIT_PREEMPT_COUNT,	\
+	.cpu		= 0,			\
+	.restart_block = {			\
+		.fn = do_no_restart_syscall,	\
+	},					\
+}
+
+#define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT)
+
+#define thread_saved_fp(tsk) \
+	((unsigned long)(((struct switch_stack *)(tsk->thread.sp))->r8))
+
+#define thread_saved_sp(tsk) \
+	((unsigned long)(tsk->thread.sp))
+
+#define thread_saved_lr(tsk) \
+	((unsigned long)(((struct switch_stack *)(tsk->thread.sp))->r15))
+
+static inline struct thread_info *current_thread_info(void)
+{
+	unsigned long sp;
+
+	asm volatile("mov %0, sp\n":"=r"(sp));
+
+	return (struct thread_info *)(sp & ~(THREAD_SIZE - 1));
+}
+
+#endif /* !__ASSEMBLER__ */
+
+#define TIF_SIGPENDING		0	/* signal pending */
+#define TIF_NOTIFY_RESUME	1       /* callback before returning to user */
+#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
+#define TIF_UPROBE		3	/* uprobe breakpoint or singlestep */
+#define TIF_SYSCALL_TRACE	4	/* syscall trace active */
+#define TIF_SYSCALL_TRACEPOINT	5       /* syscall tracepoint instrumentation */
+#define TIF_SYSCALL_AUDIT	6	/* syscall auditing */
+#define TIF_NOTIFY_SIGNAL	7	/* signal notifications exist */
+#define TIF_POLLING_NRFLAG	16	/* poll_idle() is TIF_NEED_RESCHED */
+#define TIF_MEMDIE		18      /* is terminating due to OOM killer */
+#define TIF_RESTORE_SIGMASK	20	/* restore signal mask in do_signal() */
+#define TIF_SECCOMP		21	/* secure computing */
+
+#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
+#define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
+#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
+#define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_NOTIFY_SIGNAL	(1 << TIF_NOTIFY_SIGNAL)
+#define _TIF_UPROBE		(1 << TIF_UPROBE)
+#define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
+#define _TIF_MEMDIE		(1 << TIF_MEMDIE)
+#define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
+#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+
+#define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
+				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
+				 _TIF_NOTIFY_SIGNAL)
+
+#define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
+				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP)
+
+#endif	/* _ASM_CSKY_THREAD_INFO_H */
diff --git a/arch/csky/include/asm/tlb.h b/arch/csky/include/asm/tlb.h
new file mode 100644
index 000000000..702861c68
--- /dev/null
+++ b/arch/csky/include/asm/tlb.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_TLB_H
+#define __ASM_CSKY_TLB_H
+
+#include <asm/cacheflush.h>
+#include <asm-generic/tlb.h>
+
+#endif /* __ASM_CSKY_TLB_H */
diff --git a/arch/csky/include/asm/tlbflush.h b/arch/csky/include/asm/tlbflush.h
new file mode 100644
index 000000000..407160b4f
--- /dev/null
+++ b/arch/csky/include/asm/tlbflush.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_TLBFLUSH_H
+#define __ASM_TLBFLUSH_H
+
+/*
+ * TLB flushing:
+ *
+ *  - flush_tlb_all() flushes all processes TLB entries
+ *  - flush_tlb_mm(mm) flushes the specified mm context TLB entries
+ *  - flush_tlb_page(vma, vmaddr) flushes one page
+ *  - flush_tlb_range(vma, start, end) flushes a range of pages
+ *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
+ */
+extern void flush_tlb_all(void);
+extern void flush_tlb_mm(struct mm_struct *mm);
+extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long page);
+extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			    unsigned long end);
+extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+
+extern void flush_tlb_one(unsigned long vaddr);
+
+#endif
diff --git a/arch/csky/include/asm/traps.h b/arch/csky/include/asm/traps.h
new file mode 100644
index 000000000..6bbbbe431
--- /dev/null
+++ b/arch/csky/include/asm/traps.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_TRAPS_H
+#define __ASM_CSKY_TRAPS_H
+
+#include <linux/linkage.h>
+
+#define VEC_RESET	0
+#define VEC_ALIGN	1
+#define VEC_ACCESS	2
+#define VEC_ZERODIV	3
+#define VEC_ILLEGAL	4
+#define VEC_PRIV	5
+#define VEC_TRACE	6
+#define VEC_BREAKPOINT	7
+#define VEC_UNRECOVER	8
+#define VEC_SOFTRESET	9
+#define VEC_AUTOVEC	10
+#define VEC_FAUTOVEC	11
+#define VEC_HWACCEL	12
+
+#define	VEC_TLBMISS	14
+#define	VEC_TLBMODIFIED	15
+
+#define VEC_TRAP0	16
+#define VEC_TRAP1	17
+#define VEC_TRAP2	18
+#define VEC_TRAP3	19
+
+#define	VEC_TLBINVALIDL	20
+#define	VEC_TLBINVALIDS	21
+
+#define VEC_PRFL	29
+#define VEC_FPE		30
+
+extern void *vec_base[];
+
+#define VEC_INIT(i, func) \
+do { \
+	vec_base[i] = (void *)func; \
+} while (0)
+
+void csky_alignment(struct pt_regs *regs);
+
+asmlinkage void do_trap_unknown(struct pt_regs *regs);
+asmlinkage void do_trap_zdiv(struct pt_regs *regs);
+asmlinkage void do_trap_buserr(struct pt_regs *regs);
+asmlinkage void do_trap_misaligned(struct pt_regs *regs);
+asmlinkage void do_trap_bkpt(struct pt_regs *regs);
+asmlinkage void do_trap_illinsn(struct pt_regs *regs);
+asmlinkage void do_trap_fpe(struct pt_regs *regs);
+asmlinkage void do_trap_priv(struct pt_regs *regs);
+asmlinkage void trap_c(struct pt_regs *regs);
+
+asmlinkage void do_notify_resume(struct pt_regs *regs,
+			unsigned long thread_info_flags);
+
+asmlinkage void do_page_fault(struct pt_regs *regs);
+
+#endif /* __ASM_CSKY_TRAPS_H */
diff --git a/arch/csky/include/asm/uaccess.h b/arch/csky/include/asm/uaccess.h
new file mode 100644
index 000000000..2e927c21d
--- /dev/null
+++ b/arch/csky/include/asm/uaccess.h
@@ -0,0 +1,203 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_UACCESS_H
+#define __ASM_CSKY_UACCESS_H
+
+/*
+ * __put_user_fn
+ */
+extern int __put_user_bad(void);
+
+#define __put_user_asm_b(x, ptr, err)			\
+do {							\
+	int errcode;					\
+	__asm__ __volatile__(				\
+	"1:     stb   %1, (%2,0)	\n"		\
+	"       br    3f		\n"		\
+	"2:     mov   %0, %3		\n"		\
+	"       br    3f		\n"		\
+	".section __ex_table, \"a\"	\n"		\
+	".align   2			\n"		\
+	".long    1b,2b			\n"		\
+	".previous			\n"		\
+	"3:				\n"		\
+	: "=r"(err), "=r"(x), "=r"(ptr), "=r"(errcode)	\
+	: "0"(err), "1"(x), "2"(ptr), "3"(-EFAULT)	\
+	: "memory");					\
+} while (0)
+
+#define __put_user_asm_h(x, ptr, err)			\
+do {							\
+	int errcode;					\
+	__asm__ __volatile__(				\
+	"1:     sth   %1, (%2,0)	\n"		\
+	"       br    3f		\n"		\
+	"2:     mov   %0, %3		\n"		\
+	"       br    3f		\n"		\
+	".section __ex_table, \"a\"	\n"		\
+	".align   2			\n"		\
+	".long    1b,2b			\n"		\
+	".previous			\n"		\
+	"3:				\n"		\
+	: "=r"(err), "=r"(x), "=r"(ptr), "=r"(errcode)	\
+	: "0"(err), "1"(x), "2"(ptr), "3"(-EFAULT)	\
+	: "memory");					\
+} while (0)
+
+#define __put_user_asm_w(x, ptr, err)			\
+do {							\
+	int errcode;					\
+	__asm__ __volatile__(				\
+	"1:     stw   %1, (%2,0)	\n"		\
+	"       br    3f		\n"		\
+	"2:     mov   %0, %3		\n"		\
+	"       br    3f		\n"		\
+	".section __ex_table,\"a\"	\n"		\
+	".align   2			\n"		\
+	".long    1b, 2b		\n"		\
+	".previous			\n"		\
+	"3:				\n"		\
+	: "=r"(err), "=r"(x), "=r"(ptr), "=r"(errcode)	\
+	: "0"(err), "1"(x), "2"(ptr), "3"(-EFAULT)	\
+	: "memory");					\
+} while (0)
+
+#define __put_user_asm_64(x, ptr, err)			\
+do {							\
+	int tmp;					\
+	int errcode;					\
+							\
+	__asm__ __volatile__(				\
+	"     ldw     %3, (%1, 0)     \n"		\
+	"1:   stw     %3, (%2, 0)     \n"		\
+	"     ldw     %3, (%1, 4)     \n"		\
+	"2:   stw     %3, (%2, 4)     \n"		\
+	"     br      4f              \n"		\
+	"3:   mov     %0, %4          \n"		\
+	"     br      4f              \n"		\
+	".section __ex_table, \"a\"   \n"		\
+	".align   2                   \n"		\
+	".long    1b, 3b              \n"		\
+	".long    2b, 3b              \n"		\
+	".previous                    \n"		\
+	"4:                           \n"		\
+	: "=r"(err), "=r"(x), "=r"(ptr),		\
+	  "=r"(tmp), "=r"(errcode)			\
+	: "0"(err), "1"(x), "2"(ptr), "3"(0),		\
+	  "4"(-EFAULT)					\
+	: "memory");					\
+} while (0)
+
+static inline int __put_user_fn(size_t size, void __user *ptr, void *x)
+{
+	int retval = 0;
+	u32 tmp;
+
+	switch (size) {
+	case 1:
+		tmp = *(u8 *)x;
+		__put_user_asm_b(tmp, ptr, retval);
+		break;
+	case 2:
+		tmp = *(u16 *)x;
+		__put_user_asm_h(tmp, ptr, retval);
+		break;
+	case 4:
+		tmp = *(u32 *)x;
+		__put_user_asm_w(tmp, ptr, retval);
+		break;
+	case 8:
+		__put_user_asm_64(x, (u64 *)ptr, retval);
+		break;
+	}
+
+	return retval;
+}
+#define __put_user_fn __put_user_fn
+
+/*
+ * __get_user_fn
+ */
+extern int __get_user_bad(void);
+
+#define __get_user_asm_common(x, ptr, ins, err)		\
+do {							\
+	int errcode;					\
+	__asm__ __volatile__(				\
+	"1:   " ins " %1, (%4, 0)	\n"		\
+	"       br    3f		\n"		\
+	"2:     mov   %0, %2		\n"		\
+	"       movi  %1, 0		\n"		\
+	"       br    3f		\n"		\
+	".section __ex_table,\"a\"      \n"		\
+	".align   2			\n"		\
+	".long    1b, 2b		\n"		\
+	".previous			\n"		\
+	"3:				\n" 		\
+	: "=r"(err), "=r"(x), "=r"(errcode)		\
+	: "0"(0), "r"(ptr), "2"(-EFAULT)		\
+	: "memory");					\
+} while (0)
+
+#define __get_user_asm_64(x, ptr, err)			\
+do {							\
+	int tmp;					\
+	int errcode;					\
+							\
+	__asm__ __volatile__(				\
+	"1:   ldw     %3, (%2, 0)     \n"		\
+	"     stw     %3, (%1, 0)     \n"		\
+	"2:   ldw     %3, (%2, 4)     \n"		\
+	"     stw     %3, (%1, 4)     \n"		\
+	"     br      4f              \n"		\
+	"3:   mov     %0, %4          \n"		\
+	"     br      4f              \n"		\
+	".section __ex_table, \"a\"   \n"		\
+	".align   2                   \n"		\
+	".long    1b, 3b              \n"		\
+	".long    2b, 3b              \n"		\
+	".previous                    \n"		\
+	"4:                           \n"		\
+	: "=r"(err), "=r"(x), "=r"(ptr),		\
+	  "=r"(tmp), "=r"(errcode)			\
+	: "0"(err), "1"(x), "2"(ptr), "3"(0),		\
+	  "4"(-EFAULT)					\
+	: "memory");					\
+} while (0)
+
+static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
+{
+	int retval;
+	u32 tmp;
+
+	switch (size) {
+	case 1:
+		__get_user_asm_common(tmp, ptr, "ldb", retval);
+		*(u8 *)x = (u8)tmp;
+		break;
+	case 2:
+		__get_user_asm_common(tmp, ptr, "ldh", retval);
+		*(u16 *)x = (u16)tmp;
+		break;
+	case 4:
+		__get_user_asm_common(tmp, ptr, "ldw", retval);
+		*(u32 *)x = (u32)tmp;
+		break;
+	case 8:
+		__get_user_asm_64(x, ptr, retval);
+		break;
+	}
+
+	return retval;
+}
+#define __get_user_fn __get_user_fn
+
+unsigned long raw_copy_from_user(void *to, const void *from, unsigned long n);
+unsigned long raw_copy_to_user(void *to, const void *from, unsigned long n);
+
+unsigned long __clear_user(void __user *to, unsigned long n);
+#define __clear_user __clear_user
+
+#include <asm-generic/uaccess.h>
+
+#endif /* __ASM_CSKY_UACCESS_H */
diff --git a/arch/csky/include/asm/unistd.h b/arch/csky/include/asm/unistd.h
new file mode 100644
index 000000000..2c2c24de9
--- /dev/null
+++ b/arch/csky/include/asm/unistd.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <uapi/asm/unistd.h>
+
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SYS_CLONE
+
+#define NR_syscalls (__NR_syscalls)
diff --git a/arch/csky/include/asm/uprobes.h b/arch/csky/include/asm/uprobes.h
new file mode 100644
index 000000000..600388eb9
--- /dev/null
+++ b/arch/csky/include/asm/uprobes.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_CSKY_UPROBES_H
+#define __ASM_CSKY_UPROBES_H
+
+#include <asm/probes.h>
+
+#define MAX_UINSN_BYTES		4
+
+#define UPROBE_SWBP_INSN	USR_BKPT
+#define UPROBE_SWBP_INSN_SIZE	2
+#define UPROBE_XOL_SLOT_BYTES	MAX_UINSN_BYTES
+
+typedef u32 uprobe_opcode_t;
+
+struct arch_uprobe_task {
+	unsigned long   saved_trap_no;
+};
+
+struct arch_uprobe {
+	union {
+		u8 insn[MAX_UINSN_BYTES];
+		u8 ixol[MAX_UINSN_BYTES];
+	};
+	struct arch_probe_insn api;
+	unsigned long insn_size;
+	bool simulate;
+};
+
+int uprobe_breakpoint_handler(struct pt_regs *regs);
+int uprobe_single_step_handler(struct pt_regs *regs);
+
+#endif /* __ASM_CSKY_UPROBES_H */
diff --git a/arch/csky/include/asm/vdso.h b/arch/csky/include/asm/vdso.h
new file mode 100644
index 000000000..181a15eda
--- /dev/null
+++ b/arch/csky/include/asm/vdso.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_VDSO_H
+#define __ASM_CSKY_VDSO_H
+
+#include <linux/types.h>
+
+/*
+ * The VDSO symbols are mapped into Linux so we can just use regular symbol
+ * addressing to get their offsets in userspace.  The symbols are mapped at an
+ * offset of 0, but since the linker must support setting weak undefined
+ * symbols to the absolute address 0 it also happens to support other low
+ * addresses even when the code model suggests those low addresses would not
+ * otherwise be available.
+ */
+#define VDSO_SYMBOL(base, name)							\
+({										\
+	extern const char __vdso_##name[];					\
+	(void __user *)((unsigned long)(base) + __vdso_##name);			\
+})
+
+#endif /* __ASM_CSKY_VDSO_H */
diff --git a/arch/csky/include/asm/vmalloc.h b/arch/csky/include/asm/vmalloc.h
new file mode 100644
index 000000000..43dca6336
--- /dev/null
+++ b/arch/csky/include/asm/vmalloc.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_CSKY_VMALLOC_H
+#define _ASM_CSKY_VMALLOC_H
+
+#endif /* _ASM_CSKY_VMALLOC_H */
diff --git a/arch/csky/include/uapi/asm/Kbuild b/arch/csky/include/uapi/asm/Kbuild
new file mode 100644
index 000000000..2501e82a1
--- /dev/null
+++ b/arch/csky/include/uapi/asm/Kbuild
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+syscall-y += unistd_32.h
+
+generic-y += ucontext.h
diff --git a/arch/csky/include/uapi/asm/byteorder.h b/arch/csky/include/uapi/asm/byteorder.h
new file mode 100644
index 000000000..1aedd513b
--- /dev/null
+++ b/arch/csky/include/uapi/asm/byteorder.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef __ASM_CSKY_BYTEORDER_H
+#define __ASM_CSKY_BYTEORDER_H
+
+#include <linux/byteorder/little_endian.h>
+
+#endif /* __ASM_CSKY_BYTEORDER_H */
diff --git a/arch/csky/include/uapi/asm/cachectl.h b/arch/csky/include/uapi/asm/cachectl.h
new file mode 100644
index 000000000..ed7fad1ea
--- /dev/null
+++ b/arch/csky/include/uapi/asm/cachectl.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef __ASM_CSKY_CACHECTL_H
+#define __ASM_CSKY_CACHECTL_H
+
+/*
+ * See "man cacheflush"
+ */
+#define ICACHE  (1<<0)
+#define DCACHE  (1<<1)
+#define BCACHE  (ICACHE|DCACHE)
+
+#endif /* __ASM_CSKY_CACHECTL_H */
diff --git a/arch/csky/include/uapi/asm/perf_regs.h b/arch/csky/include/uapi/asm/perf_regs.h
new file mode 100644
index 000000000..d0a8ac6a1
--- /dev/null
+++ b/arch/csky/include/uapi/asm/perf_regs.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _ASM_CSKY_PERF_REGS_H
+#define _ASM_CSKY_PERF_REGS_H
+
+/* Index of struct pt_regs */
+enum perf_event_csky_regs {
+	PERF_REG_CSKY_TLS,
+	PERF_REG_CSKY_LR,
+	PERF_REG_CSKY_PC,
+	PERF_REG_CSKY_SR,
+	PERF_REG_CSKY_SP,
+	PERF_REG_CSKY_ORIG_A0,
+	PERF_REG_CSKY_A0,
+	PERF_REG_CSKY_A1,
+	PERF_REG_CSKY_A2,
+	PERF_REG_CSKY_A3,
+	PERF_REG_CSKY_REGS0,
+	PERF_REG_CSKY_REGS1,
+	PERF_REG_CSKY_REGS2,
+	PERF_REG_CSKY_REGS3,
+	PERF_REG_CSKY_REGS4,
+	PERF_REG_CSKY_REGS5,
+	PERF_REG_CSKY_REGS6,
+	PERF_REG_CSKY_REGS7,
+	PERF_REG_CSKY_REGS8,
+	PERF_REG_CSKY_REGS9,
+#if defined(__CSKYABIV2__)
+	PERF_REG_CSKY_EXREGS0,
+	PERF_REG_CSKY_EXREGS1,
+	PERF_REG_CSKY_EXREGS2,
+	PERF_REG_CSKY_EXREGS3,
+	PERF_REG_CSKY_EXREGS4,
+	PERF_REG_CSKY_EXREGS5,
+	PERF_REG_CSKY_EXREGS6,
+	PERF_REG_CSKY_EXREGS7,
+	PERF_REG_CSKY_EXREGS8,
+	PERF_REG_CSKY_EXREGS9,
+	PERF_REG_CSKY_EXREGS10,
+	PERF_REG_CSKY_EXREGS11,
+	PERF_REG_CSKY_EXREGS12,
+	PERF_REG_CSKY_EXREGS13,
+	PERF_REG_CSKY_EXREGS14,
+	PERF_REG_CSKY_HI,
+	PERF_REG_CSKY_LO,
+	PERF_REG_CSKY_DCSR,
+#endif
+	PERF_REG_CSKY_MAX,
+};
+#endif /* _ASM_CSKY_PERF_REGS_H */
diff --git a/arch/csky/include/uapi/asm/ptrace.h b/arch/csky/include/uapi/asm/ptrace.h
new file mode 100644
index 000000000..90a5c36e4
--- /dev/null
+++ b/arch/csky/include/uapi/asm/ptrace.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _CSKY_PTRACE_H
+#define _CSKY_PTRACE_H
+
+#ifndef __ASSEMBLER__
+
+struct pt_regs {
+	unsigned long	tls;
+	unsigned long	lr;
+	unsigned long	pc;
+	unsigned long	sr;
+	unsigned long	usp;
+
+	/*
+	 * a0, a1, a2, a3:
+	 * abiv1: r2, r3, r4, r5
+	 * abiv2: r0, r1, r2, r3
+	 */
+	unsigned long	orig_a0;
+	unsigned long	a0;
+	unsigned long	a1;
+	unsigned long	a2;
+	unsigned long	a3;
+
+	/*
+	 * ABIV2: r4 ~ r13
+	 * ABIV1: r6 ~ r14, r1
+	 */
+	unsigned long	regs[10];
+
+#if defined(__CSKYABIV2__)
+	/* r16 ~ r30 */
+	unsigned long	exregs[15];
+
+	unsigned long	rhi;
+	unsigned long	rlo;
+	unsigned long	dcsr;
+#endif
+};
+
+struct user_fp {
+	unsigned long	vr[96];
+	unsigned long	fcr;
+	unsigned long	fesr;
+	unsigned long	fid;
+	unsigned long	reserved;
+};
+
+#endif /* __ASSEMBLER__ */
+#endif /* _CSKY_PTRACE_H */
diff --git a/arch/csky/include/uapi/asm/sigcontext.h b/arch/csky/include/uapi/asm/sigcontext.h
new file mode 100644
index 000000000..859afb602
--- /dev/null
+++ b/arch/csky/include/uapi/asm/sigcontext.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef __ASM_CSKY_SIGCONTEXT_H
+#define __ASM_CSKY_SIGCONTEXT_H
+
+#include <asm/ptrace.h>
+
+struct sigcontext {
+	struct pt_regs	sc_pt_regs;
+	struct user_fp	sc_user_fp;
+};
+
+#endif /* __ASM_CSKY_SIGCONTEXT_H */
diff --git a/arch/csky/include/uapi/asm/unistd.h b/arch/csky/include/uapi/asm/unistd.h
new file mode 100644
index 000000000..44882179a
--- /dev/null
+++ b/arch/csky/include/uapi/asm/unistd.h
@@ -0,0 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#include <asm/unistd_32.h>
+
+#define __NR_sync_file_range2 84
+#undef __NR_sync_file_range
diff --git a/arch/csky/kernel/Makefile b/arch/csky/kernel/Makefile
new file mode 100644
index 000000000..a406a4ac2
--- /dev/null
+++ b/arch/csky/kernel/Makefile
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0-only
+always-$(KBUILD_BUILTIN) := vmlinux.lds
+
+obj-y += head.o 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 += process.o cpu-probe.o ptrace.o stacktrace.o
+obj-y += probes/
+
+obj-$(CONFIG_MODULES)			+= module.o
+obj-$(CONFIG_SMP)			+= smp.o
+obj-$(CONFIG_FUNCTION_TRACER)		+= ftrace.o
+obj-$(CONFIG_STACKTRACE)		+= stacktrace.o
+obj-$(CONFIG_CSKY_PMU_V1)		+= perf_event.o
+obj-$(CONFIG_PERF_EVENTS)		+= perf_callchain.o
+obj-$(CONFIG_HAVE_PERF_REGS)            += perf_regs.o
+obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
+endif
diff --git a/arch/csky/kernel/Makefile.syscalls b/arch/csky/kernel/Makefile.syscalls
new file mode 100644
index 000000000..3df3b5822
--- /dev/null
+++ b/arch/csky/kernel/Makefile.syscalls
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+
+syscall_abis_32 += csky time32 stat64 rlimit
+
diff --git a/arch/csky/kernel/asm-offsets.c b/arch/csky/kernel/asm-offsets.c
new file mode 100644
index 000000000..5525c8e7e
--- /dev/null
+++ b/arch/csky/kernel/asm-offsets.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+#define COMPILE_OFFSETS
+
+#include <linux/sched.h>
+#include <linux/kernel_stat.h>
+#include <linux/kbuild.h>
+#include <abi/regdef.h>
+
+int main(void)
+{
+	/* offsets into the task struct */
+	DEFINE(TASK_THREAD_INFO,  offsetof(struct task_struct, stack));
+	DEFINE(TASK_FLAGS,        offsetof(struct task_struct, flags));
+	DEFINE(TASK_PTRACE,       offsetof(struct task_struct, ptrace));
+	DEFINE(TASK_THREAD,       offsetof(struct task_struct, thread));
+	DEFINE(TASK_MM,           offsetof(struct task_struct, mm));
+	DEFINE(TASK_ACTIVE_MM,    offsetof(struct task_struct, active_mm));
+
+	/* offsets into the thread struct */
+	DEFINE(THREAD_KSP,        offsetof(struct thread_struct, sp));
+	DEFINE(THREAD_FESR,       offsetof(struct thread_struct, user_fp.fesr));
+	DEFINE(THREAD_FCR,        offsetof(struct thread_struct, user_fp.fcr));
+	DEFINE(THREAD_FPREG,      offsetof(struct thread_struct, user_fp.vr));
+
+	/* offsets into the thread_info struct */
+	DEFINE(TINFO_FLAGS,       offsetof(struct thread_info, flags));
+	DEFINE(TINFO_PREEMPT,     offsetof(struct thread_info, preempt_count));
+	DEFINE(TINFO_TP_VALUE,   offsetof(struct thread_info, tp_value));
+	DEFINE(TINFO_TASK,        offsetof(struct thread_info, task));
+
+	/* offsets into the pt_regs */
+	DEFINE(PT_PC,             offsetof(struct pt_regs, pc));
+	DEFINE(PT_ORIG_AO,        offsetof(struct pt_regs, orig_a0));
+	DEFINE(PT_SR,             offsetof(struct pt_regs, sr));
+
+	DEFINE(PT_A0,             offsetof(struct pt_regs, a0));
+	DEFINE(PT_A1,             offsetof(struct pt_regs, a1));
+	DEFINE(PT_A2,             offsetof(struct pt_regs, a2));
+	DEFINE(PT_A3,             offsetof(struct pt_regs, a3));
+	DEFINE(PT_REGS0,          offsetof(struct pt_regs, regs[0]));
+	DEFINE(PT_REGS1,          offsetof(struct pt_regs, regs[1]));
+	DEFINE(PT_REGS2,          offsetof(struct pt_regs, regs[2]));
+	DEFINE(PT_REGS3,          offsetof(struct pt_regs, regs[3]));
+	DEFINE(PT_REGS4,          offsetof(struct pt_regs, regs[4]));
+	DEFINE(PT_REGS5,          offsetof(struct pt_regs, regs[5]));
+	DEFINE(PT_REGS6,          offsetof(struct pt_regs, regs[6]));
+	DEFINE(PT_REGS7,          offsetof(struct pt_regs, regs[7]));
+	DEFINE(PT_REGS8,          offsetof(struct pt_regs, regs[8]));
+	DEFINE(PT_REGS9,          offsetof(struct pt_regs, regs[9]));
+	DEFINE(PT_R15,            offsetof(struct pt_regs, lr));
+#if defined(__CSKYABIV2__)
+	DEFINE(PT_R16,            offsetof(struct pt_regs, exregs[0]));
+	DEFINE(PT_R17,            offsetof(struct pt_regs, exregs[1]));
+	DEFINE(PT_R18,            offsetof(struct pt_regs, exregs[2]));
+	DEFINE(PT_R19,            offsetof(struct pt_regs, exregs[3]));
+	DEFINE(PT_R20,            offsetof(struct pt_regs, exregs[4]));
+	DEFINE(PT_R21,            offsetof(struct pt_regs, exregs[5]));
+	DEFINE(PT_R22,            offsetof(struct pt_regs, exregs[6]));
+	DEFINE(PT_R23,            offsetof(struct pt_regs, exregs[7]));
+	DEFINE(PT_R24,            offsetof(struct pt_regs, exregs[8]));
+	DEFINE(PT_R25,            offsetof(struct pt_regs, exregs[9]));
+	DEFINE(PT_R26,            offsetof(struct pt_regs, exregs[10]));
+	DEFINE(PT_R27,            offsetof(struct pt_regs, exregs[11]));
+	DEFINE(PT_R28,            offsetof(struct pt_regs, exregs[12]));
+	DEFINE(PT_R29,            offsetof(struct pt_regs, exregs[13]));
+	DEFINE(PT_R30,            offsetof(struct pt_regs, exregs[14]));
+	DEFINE(PT_R31,            offsetof(struct pt_regs, exregs[15]));
+	DEFINE(PT_RHI,            offsetof(struct pt_regs, rhi));
+	DEFINE(PT_RLO,            offsetof(struct pt_regs, rlo));
+#endif
+	DEFINE(PT_USP,            offsetof(struct pt_regs, usp));
+	DEFINE(PT_FRAME_SIZE,     sizeof(struct pt_regs));
+
+	/* offsets into the irq_cpustat_t struct */
+	DEFINE(CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t,
+						__softirq_pending));
+
+	/* signal defines */
+	DEFINE(SIGSEGV, SIGSEGV);
+	DEFINE(SIGTRAP, SIGTRAP);
+
+	return 0;
+}
diff --git a/arch/csky/kernel/atomic.S b/arch/csky/kernel/atomic.S
new file mode 100644
index 000000000..e73e548f7
--- /dev/null
+++ b/arch/csky/kernel/atomic.S
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/linkage.h>
+#include <abi/entry.h>
+
+.text
+
+/*
+ * int csky_cmpxchg(int oldval, int newval, int *ptr)
+ *
+ * If *ptr != oldval && return 1,
+ * else *ptr = newval return 0.
+ */
+ENTRY(csky_cmpxchg)
+	USPTOKSP
+
+	RD_MEH	a3
+	WR_MEH	a3
+
+	mfcr	a3, epc
+	addi	a3, TRAP0_SIZE
+
+	subi    sp, 16
+	stw     a3, (sp, 0)
+	mfcr    a3, epsr
+	stw     a3, (sp, 4)
+	mfcr	a3, usp
+	stw     a3, (sp, 8)
+
+	psrset	ee
+#ifdef CONFIG_CPU_HAS_LDSTEX
+1:
+	ldex	a3, (a2)
+	cmpne	a0, a3
+	bt16	2f
+	mov	a3, a1
+	stex	a3, (a2)
+	bez	a3, 1b
+2:
+	sync.is
+#else
+GLOBAL(csky_cmpxchg_ldw)
+	ldw	a3, (a2)
+	cmpne	a0, a3
+	bt16	3f
+GLOBAL(csky_cmpxchg_stw)
+	stw	a1, (a2)
+3:
+#endif
+	mvc	a0
+	ldw	a3, (sp, 0)
+	mtcr	a3, epc
+	ldw     a3, (sp, 4)
+	mtcr	a3, epsr
+	ldw     a3, (sp, 8)
+	mtcr	a3, usp
+	addi	sp, 16
+	KSPTOUSP
+	rte
+END(csky_cmpxchg)
diff --git a/arch/csky/kernel/cpu-probe.c b/arch/csky/kernel/cpu-probe.c
new file mode 100644
index 000000000..5f15ca31d
--- /dev/null
+++ b/arch/csky/kernel/cpu-probe.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/of.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/memblock.h>
+
+#include <abi/reg_ops.h>
+
+static void percpu_print(void *arg)
+{
+	struct seq_file *m = (struct seq_file *)arg;
+	unsigned int cur, next, i;
+
+	seq_printf(m, "processor       : %d\n", smp_processor_id());
+	seq_printf(m, "C-SKY CPU model : %s\n", CSKYCPU_DEF_NAME);
+
+	/* read processor id, max is 100 */
+	cur  = mfcr("cr13");
+	for (i = 0; i < 100; i++) {
+		seq_printf(m, "product info[%d] : 0x%08x\n", i, cur);
+
+		next = mfcr("cr13");
+
+		/* some CPU only has one id reg */
+		if (cur == next)
+			break;
+
+		cur = next;
+
+		/* cpid index is 31-28, reset */
+		if (!(next >> 28)) {
+			while ((mfcr("cr13") >> 28) != i);
+			break;
+		}
+	}
+
+	/* CPU feature regs, setup by bootloader or gdbinit */
+	seq_printf(m, "hint (CPU funcs): 0x%08x\n", mfcr_hint());
+	seq_printf(m, "ccr  (L1C & MMU): 0x%08x\n", mfcr("cr18"));
+	seq_printf(m, "ccr2 (L2C)      : 0x%08x\n", mfcr_ccr2());
+	seq_printf(m, "\n");
+}
+
+static int c_show(struct seq_file *m, void *v)
+{
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		smp_call_function_single(cpu, percpu_print, m, true);
+
+#ifdef CSKY_ARCH_VERSION
+	seq_printf(m, "arch-version : %s\n", CSKY_ARCH_VERSION);
+	seq_printf(m, "\n");
+#endif
+
+	return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+	return *pos < 1 ? (void *)1 : NULL;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	++*pos;
+	return NULL;
+}
+
+static void c_stop(struct seq_file *m, void *v) {}
+
+const struct seq_operations cpuinfo_op = {
+	.start	= c_start,
+	.next	= c_next,
+	.stop	= c_stop,
+	.show	= c_show,
+};
diff --git a/arch/csky/kernel/entry.S b/arch/csky/kernel/entry.S
new file mode 100644
index 000000000..3261f46f2
--- /dev/null
+++ b/arch/csky/kernel/entry.S
@@ -0,0 +1,274 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/linkage.h>
+#include <abi/entry.h>
+#include <abi/pgtable-bits.h>
+#include <asm/errno.h>
+#include <asm/setup.h>
+#include <asm/unistd.h>
+#include <asm/asm-offsets.h>
+#include <linux/threads.h>
+#include <asm/page.h>
+#include <asm/thread_info.h>
+
+.macro	zero_fp
+#ifdef CONFIG_STACKTRACE
+	movi	r8, 0
+#endif
+.endm
+
+.macro	context_tracking
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+	mfcr	a0, epsr
+	btsti	a0, 31
+	bt	1f
+	jbsr	user_exit_callable
+	ldw	a0, (sp, LSAVE_A0)
+	ldw	a1, (sp, LSAVE_A1)
+	ldw	a2, (sp, LSAVE_A2)
+	ldw	a3, (sp, LSAVE_A3)
+#if defined(__CSKYABIV1__)
+	ldw	r6, (sp, LSAVE_A4)
+	ldw	r7, (sp, LSAVE_A5)
+#endif
+1:
+#endif
+.endm
+
+.text
+ENTRY(csky_pagefault)
+	SAVE_ALL 0
+	zero_fp
+	context_tracking
+	psrset  ee
+	mov     a0, sp
+	jbsr    do_page_fault
+	jmpi    ret_from_exception
+
+ENTRY(csky_systemcall)
+	SAVE_ALL TRAP0_SIZE
+	zero_fp
+	context_tracking
+	psrset  ee, ie
+
+	lrw     r9, __NR_syscalls
+	cmphs   syscallid, r9		/* Check nr of syscall */
+	bt      ret_from_exception
+
+	lrw     r9, sys_call_table
+	ixw     r9, syscallid
+	ldw     syscallid, (r9)
+	cmpnei  syscallid, 0
+	bf      ret_from_exception
+
+	mov     r9, sp
+	bmaski  r10, THREAD_SHIFT
+	andn    r9, r10
+	ldw     r10, (r9, TINFO_FLAGS)
+	lrw	r9, _TIF_SYSCALL_WORK
+	and	r10, r9
+	cmpnei	r10, 0
+	bt      csky_syscall_trace
+#if defined(__CSKYABIV2__)
+	subi    sp, 8
+	stw  	r5, (sp, 0x4)
+	stw  	r4, (sp, 0x0)
+	jsr     syscallid                      /* Do system call */
+	addi 	sp, 8
+#else
+	jsr     syscallid
+#endif
+	stw     a0, (sp, LSAVE_A0)      /* Save return value */
+	jmpi    ret_from_exception
+
+csky_syscall_trace:
+	mov	a0, sp                  /* sp = pt_regs pointer */
+	jbsr	syscall_trace_enter
+	cmpnei	a0, 0
+	bt	1f
+	/* Prepare args before do system call */
+	ldw	a0, (sp, LSAVE_A0)
+	ldw	a1, (sp, LSAVE_A1)
+	ldw	a2, (sp, LSAVE_A2)
+	ldw	a3, (sp, LSAVE_A3)
+#if defined(__CSKYABIV2__)
+	ldw	r9, (sp, LSAVE_A4)
+	ldw	r10, (sp, LSAVE_A5)
+	subi	sp, 8
+	stw	r9, (sp, 0x0)
+	stw	r10, (sp, 0x4)
+	jsr	syscallid                     /* Do system call */
+	addi	sp, 8
+#else
+	ldw	r6, (sp, LSAVE_A4)
+	ldw	r7, (sp, LSAVE_A5)
+	jsr	syscallid                     /* Do system call */
+#endif
+	stw	a0, (sp, LSAVE_A0)	/* Save return value */
+
+1:
+	mov     a0, sp                  /* right now, sp --> pt_regs */
+	jbsr    syscall_trace_exit
+	br	ret_from_exception
+
+ENTRY(ret_from_kernel_thread)
+	jbsr	schedule_tail
+	mov	a0, r10
+	jsr	r9
+	jbsr	ret_from_exception
+
+ENTRY(ret_from_fork)
+	jbsr	schedule_tail
+	mov	r9, sp
+	bmaski	r10, THREAD_SHIFT
+	andn	r9, r10
+	ldw	r10, (r9, TINFO_FLAGS)
+	lrw	r9, _TIF_SYSCALL_WORK
+	and	r10, r9
+	cmpnei	r10, 0
+	bf	ret_from_exception
+	mov	a0, sp			/* sp = pt_regs pointer */
+	jbsr	syscall_trace_exit
+
+ret_from_exception:
+	psrclr	ie
+	ld	r9, (sp, LSAVE_PSR)
+	btsti	r9, 31
+
+	bt	1f
+	/*
+	 * Load address of current->thread_info, Then get address of task_struct
+	 * Get task_needreshed in task_struct
+	 */
+	mov	r9, sp
+	bmaski	r10, THREAD_SHIFT
+	andn	r9, r10
+
+	ldw	r10, (r9, TINFO_FLAGS)
+	lrw	r9, _TIF_WORK_MASK
+	and	r10, r9
+	cmpnei	r10, 0
+	bt	exit_work
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+	jbsr	user_enter_callable
+#endif
+1:
+#ifdef CONFIG_PREEMPTION
+	mov	r9, sp
+	bmaski	r10, THREAD_SHIFT
+	andn	r9, r10
+
+	ldw	r10, (r9, TINFO_PREEMPT)
+	cmpnei	r10, 0
+	bt	2f
+	jbsr	preempt_schedule_irq	/* irq en/disable is done inside */
+2:
+#endif
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+	ld	r10, (sp, LSAVE_PSR)
+	btsti	r10, 6
+	bf	2f
+	jbsr	trace_hardirqs_on
+2:
+#endif
+	RESTORE_ALL
+
+exit_work:
+	lrw	r9, ret_from_exception
+	mov	lr, r9
+
+	btsti	r10, TIF_NEED_RESCHED
+	bt	work_resched
+
+	psrset	ie
+	mov	a0, sp
+	mov	a1, r10
+	jmpi	do_notify_resume
+
+work_resched:
+	jmpi	schedule
+
+ENTRY(csky_trap)
+	SAVE_ALL 0
+	zero_fp
+	context_tracking
+	psrset	ee
+	mov	a0, sp                 /* Push Stack pointer arg */
+	jbsr	trap_c                 /* Call C-level trap handler */
+	jmpi	ret_from_exception
+
+/*
+ * Prototype from libc for abiv1:
+ * register unsigned int __result asm("a0");
+ * asm( "trap 3" :"=r"(__result)::);
+ */
+ENTRY(csky_get_tls)
+	USPTOKSP
+
+	RD_MEH	a0
+	WR_MEH	a0
+
+	/* increase epc for continue */
+	mfcr	a0, epc
+	addi	a0, TRAP0_SIZE
+	mtcr	a0, epc
+
+	/* get current task thread_info with kernel 8K stack */
+	bmaski	a0, THREAD_SHIFT
+	not	a0
+	subi	sp, 1
+	and	a0, sp
+	addi	sp, 1
+
+	/* get tls */
+	ldw	a0, (a0, TINFO_TP_VALUE)
+
+	KSPTOUSP
+	rte
+
+ENTRY(csky_irq)
+	SAVE_ALL 0
+	zero_fp
+	context_tracking
+	psrset	ee
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+	jbsr	trace_hardirqs_off
+#endif
+
+
+	mov	a0, sp
+	jbsr	generic_handle_arch_irq
+
+	jmpi	ret_from_exception
+
+/*
+ * a0 =  prev task_struct *
+ * a1 =  next task_struct *
+ * a0 =  return next
+ */
+ENTRY(__switch_to)
+	lrw	a3, TASK_THREAD
+	addu	a3, a0
+
+	SAVE_SWITCH_STACK
+
+	stw	sp, (a3, THREAD_KSP)
+
+	/* Set up next process to run */
+	lrw	a3, TASK_THREAD
+	addu	a3, a1
+
+	ldw	sp, (a3, THREAD_KSP)	/* Set next kernel sp */
+
+#if  defined(__CSKYABIV2__)
+	addi	a3, a1, TASK_THREAD_INFO
+	ldw	tls, (a3, TINFO_TP_VALUE)
+#endif
+
+	RESTORE_SWITCH_STACK
+
+	rts
+ENDPROC(__switch_to)
diff --git a/arch/csky/kernel/ftrace.c b/arch/csky/kernel/ftrace.c
new file mode 100644
index 000000000..50bfcf129
--- /dev/null
+++ b/arch/csky/kernel/ftrace.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/ftrace.h>
+#include <linux/uaccess.h>
+#include <linux/stop_machine.h>
+#include <asm/cacheflush.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+#define NOP		0x4000
+#define NOP32_HI	0xc400
+#define NOP32_LO	0x4820
+#define PUSH_LR		0x14d0
+#define MOVIH_LINK	0xea3a
+#define ORI_LINK	0xef5a
+#define JSR_LINK	0xe8fa
+#define BSR_LINK	0xe000
+
+/*
+ * Gcc-csky with -pg will insert stub in function prologue:
+ *	push	lr
+ *	jbsr	_mcount
+ *	nop32
+ *	nop32
+ *
+ * If the (callee - current_pc) is less then 64MB, we'll use bsr:
+ *	push	lr
+ *	bsr	_mcount
+ *	nop32
+ *	nop32
+ * else we'll use (movih + ori + jsr):
+ *	push	lr
+ *	movih	r26, ...
+ *	ori	r26, ...
+ *	jsr	r26
+ *
+ * (r26 is our reserved link-reg)
+ *
+ */
+static inline void make_jbsr(unsigned long callee, unsigned long pc,
+			     uint16_t *call, bool nolr)
+{
+	long offset;
+
+	call[0]	= nolr ? NOP : PUSH_LR;
+
+	offset = (long) callee - (long) pc;
+
+	if (unlikely(offset < -67108864 || offset > 67108864)) {
+		call[1] = MOVIH_LINK;
+		call[2] = callee >> 16;
+		call[3] = ORI_LINK;
+		call[4] = callee & 0xffff;
+		call[5] = JSR_LINK;
+		call[6] = 0;
+	} else {
+		offset = offset >> 1;
+
+		call[1] = BSR_LINK |
+			 ((uint16_t)((unsigned long) offset >> 16) & 0x3ff);
+		call[2] = (uint16_t)((unsigned long) offset & 0xffff);
+		call[3] = call[5] = NOP32_HI;
+		call[4] = call[6] = NOP32_LO;
+	}
+}
+
+static uint16_t nops[7] = {NOP, NOP32_HI, NOP32_LO, NOP32_HI, NOP32_LO,
+				NOP32_HI, NOP32_LO};
+static int ftrace_check_current_nop(unsigned long hook)
+{
+	uint16_t olds[7];
+	unsigned long hook_pos = hook - 2;
+
+	if (copy_from_kernel_nofault((void *)olds, (void *)hook_pos,
+			sizeof(nops)))
+		return -EFAULT;
+
+	if (memcmp((void *)nops, (void *)olds, sizeof(nops))) {
+		pr_err("%p: nop but get (%04x %04x %04x %04x %04x %04x %04x)\n",
+			(void *)hook_pos,
+			olds[0], olds[1], olds[2], olds[3], olds[4], olds[5],
+			olds[6]);
+
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ftrace_modify_code(unsigned long hook, unsigned long target,
+			      bool enable, bool nolr)
+{
+	uint16_t call[7];
+
+	unsigned long hook_pos = hook - 2;
+	int ret = 0;
+
+	make_jbsr(target, hook, call, nolr);
+
+	ret = copy_to_kernel_nofault((void *)hook_pos, enable ? call : nops,
+				 sizeof(nops));
+	if (ret)
+		return -EPERM;
+
+	flush_icache_range(hook_pos, hook_pos + MCOUNT_INSN_SIZE);
+
+	return 0;
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	int ret = ftrace_check_current_nop(rec->ip);
+
+	if (ret)
+		return ret;
+
+	return ftrace_modify_code(rec->ip, addr, true, false);
+}
+
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
+		    unsigned long addr)
+{
+	return ftrace_modify_code(rec->ip, addr, false, false);
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	int ret = ftrace_modify_code((unsigned long)&ftrace_call,
+				(unsigned long)func, true, true);
+	if (!ret)
+		ret = ftrace_modify_code((unsigned long)&ftrace_regs_call,
+				(unsigned long)func, true, true);
+	return ret;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+		       unsigned long addr)
+{
+	return ftrace_modify_code(rec->ip, addr, true, true);
+}
+#endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer)
+{
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long old;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	old = *parent;
+
+	if (!function_graph_enter(old, self_addr,
+			*(unsigned long *)frame_pointer, parent)) {
+		/*
+		 * For csky-gcc function has sub-call:
+		 * subi	sp,	sp, 8
+		 * stw	r8,	(sp, 0)
+		 * mov	r8,	sp
+		 * st.w r15,	(sp, 0x4)
+		 * push	r15
+		 * jl	_mcount
+		 * We only need set *parent for resume
+		 *
+		 * For csky-gcc function has no sub-call:
+		 * subi	sp,	sp, 4
+		 * stw	r8,	(sp, 0)
+		 * mov	r8,	sp
+		 * push	r15
+		 * jl	_mcount
+		 * We need set *parent and *(frame_pointer + 4) for resume,
+		 * because lr is resumed twice.
+		 */
+		*parent = return_hooker;
+		frame_pointer += 4;
+		if (*(unsigned long *)frame_pointer == old)
+			*(unsigned long *)frame_pointer = return_hooker;
+	}
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_code((unsigned long)&ftrace_graph_call,
+			(unsigned long)&ftrace_graph_caller, true, true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_code((unsigned long)&ftrace_graph_call,
+			(unsigned long)&ftrace_graph_caller, false, true);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+#ifndef CONFIG_CPU_HAS_ICACHE_INS
+struct ftrace_modify_param {
+	int command;
+	atomic_t cpu_count;
+};
+
+static int __ftrace_modify_code(void *data)
+{
+	struct ftrace_modify_param *param = data;
+
+	if (atomic_inc_return(&param->cpu_count) == 1) {
+		ftrace_modify_all_code(param->command);
+		atomic_inc(&param->cpu_count);
+	} else {
+		while (atomic_read(&param->cpu_count) <= num_online_cpus())
+			cpu_relax();
+		local_icache_inv_all(NULL);
+	}
+
+	return 0;
+}
+
+void arch_ftrace_update_code(int command)
+{
+	struct ftrace_modify_param param = { command, ATOMIC_INIT(0) };
+
+	stop_machine(__ftrace_modify_code, &param, cpu_online_mask);
+}
+#endif
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+/* _mcount is defined in abi's mcount.S */
+EXPORT_SYMBOL(_mcount);
diff --git a/arch/csky/kernel/head.S b/arch/csky/kernel/head.S
new file mode 100644
index 000000000..7e3e4f15b
--- /dev/null
+++ b/arch/csky/kernel/head.S
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/linkage.h>
+#include <linux/init.h>
+#include <asm/page.h>
+#include <abi/entry.h>
+
+__HEAD
+ENTRY(_start)
+	SETUP_MMU
+
+	/* set stack point */
+	lrw     r6, init_thread_union + THREAD_SIZE
+	mov	sp, r6
+
+	jmpi	csky_start
+END(_start)
+
+#ifdef CONFIG_SMP
+.align 10
+ENTRY(_start_smp_secondary)
+	SETUP_MMU
+
+#ifdef CONFIG_PAGE_OFFSET_80000000
+	lrw	r6, secondary_msa1
+	ld.w	r6, (r6, 0)
+	mtcr	r6, cr<31, 15>
+#endif
+
+	lrw     r6, secondary_pgd
+	ld.w	r6, (r6, 0)
+	mtcr	r6, cr<28, 15>
+	mtcr	r6, cr<29, 15>
+
+	/* set stack point */
+	lrw     r6, secondary_stack
+	ld.w	r6, (r6, 0)
+	mov	sp, r6
+
+	jmpi	csky_start_secondary
+END(_start_smp_secondary)
+#endif
diff --git a/arch/csky/kernel/irq.c b/arch/csky/kernel/irq.c
new file mode 100644
index 000000000..fcdaf3156
--- /dev/null
+++ b/arch/csky/kernel/irq.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <asm/traps.h>
+#include <asm/smp.h>
+
+void __init init_IRQ(void)
+{
+	irqchip_init();
+#ifdef CONFIG_SMP
+	setup_smp_ipi();
+#endif
+}
diff --git a/arch/csky/kernel/jump_label.c b/arch/csky/kernel/jump_label.c
new file mode 100644
index 000000000..d0e8b2144
--- /dev/null
+++ b/arch/csky/kernel/jump_label.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/memory.h>
+#include <linux/mutex.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+
+#define NOP32_HI	0xc400
+#define NOP32_LO	0x4820
+#define BSR_LINK	0xe000
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	unsigned long addr = jump_entry_code(entry);
+	u16 insn[2];
+	int ret = 0;
+
+	if (type == JUMP_LABEL_JMP) {
+		long offset = jump_entry_target(entry) - jump_entry_code(entry);
+
+		if (WARN_ON(offset & 1 || offset < -67108864 || offset >= 67108864))
+			return;
+
+		offset = offset >> 1;
+
+		insn[0] = BSR_LINK |
+			((uint16_t)((unsigned long) offset >> 16) & 0x3ff);
+		insn[1] = (uint16_t)((unsigned long) offset & 0xffff);
+	} else {
+		insn[0] = NOP32_HI;
+		insn[1] = NOP32_LO;
+	}
+
+	ret = copy_to_kernel_nofault((void *)addr, insn, 4);
+	WARN_ON(ret);
+
+	flush_icache_range(addr, addr + 4);
+}
+
+void arch_jump_label_transform_static(struct jump_entry *entry,
+				      enum jump_label_type type)
+{
+	/*
+	 * We use the same instructions in the arch_static_branch and
+	 * arch_static_branch_jump inline functions, so there's no
+	 * need to patch them up here.
+	 * The core will call arch_jump_label_transform  when those
+	 * instructions need to be replaced.
+	 */
+	arch_jump_label_transform(entry, type);
+}
diff --git a/arch/csky/kernel/module.c b/arch/csky/kernel/module.c
new file mode 100644
index 000000000..0b56a8cd1
--- /dev/null
+++ b/arch/csky/kernel/module.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/moduleloader.h>
+#include <linux/elf.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+
+#ifdef CONFIG_CPU_CK810
+#define IS_BSR32(hi16, lo16)		(((hi16) & 0xFC00) == 0xE000)
+#define IS_JSRI32(hi16, lo16)		((hi16) == 0xEAE0)
+
+#define CHANGE_JSRI_TO_LRW(addr) do {					\
+	*(uint16_t *)(addr) = (*(uint16_t *)(addr) & 0xFF9F) | 0x001a;	\
+	*((uint16_t *)(addr) + 1) = *((uint16_t *)(addr) + 1) & 0xFFFF;	\
+} while (0)
+
+#define SET_JSR32_R26(addr) do {		\
+	*(uint16_t *)(addr) = 0xE8Fa;		\
+	*((uint16_t *)(addr) + 1) = 0x0000;	\
+} while (0)
+
+static void jsri_2_lrw_jsr(uint32_t *location)
+{
+	uint16_t *location_tmp = (uint16_t *)location;
+
+	if (IS_BSR32(*location_tmp, *(location_tmp + 1)))
+		return;
+
+	if (IS_JSRI32(*location_tmp, *(location_tmp + 1))) {
+		/* jsri 0x...  --> lrw r26, 0x... */
+		CHANGE_JSRI_TO_LRW(location);
+		/* lsli r0, r0 --> jsr r26 */
+		SET_JSR32_R26(location + 1);
+	}
+}
+#else
+static inline void jsri_2_lrw_jsr(uint32_t *location)
+{
+	return;
+}
+#endif
+
+int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab,
+		unsigned int symindex, unsigned int relsec, struct module *me)
+{
+	unsigned int i;
+	Elf32_Rela	*rel = (void *) sechdrs[relsec].sh_addr;
+	Elf32_Sym	*sym;
+	uint32_t	*location;
+	short		*temp;
+
+	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
+		/* This is where to make the change */
+		location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
+							+ rel[i].r_offset;
+		sym = (Elf32_Sym *)sechdrs[symindex].sh_addr
+						+ ELF32_R_SYM(rel[i].r_info);
+
+		switch (ELF32_R_TYPE(rel[i].r_info)) {
+		case R_CSKY_32:
+			/* We add the value into the location given */
+			*location = rel[i].r_addend + sym->st_value;
+			break;
+		case R_CSKY_PC32:
+			/* Add the value, subtract its position */
+			*location = rel[i].r_addend + sym->st_value
+							- (uint32_t)location;
+			break;
+		case R_CSKY_PCRELJSR_IMM11BY2:
+			break;
+		case R_CSKY_PCRELJSR_IMM26BY2:
+			jsri_2_lrw_jsr(location);
+			break;
+		case R_CSKY_ADDR_HI16:
+			temp = ((short  *)location) + 1;
+			*temp = (short)
+				((rel[i].r_addend + sym->st_value) >> 16);
+			break;
+		case R_CSKY_ADDR_LO16:
+			temp = ((short  *)location) + 1;
+			*temp = (short)
+				((rel[i].r_addend + sym->st_value) & 0xffff);
+			break;
+		default:
+			pr_err("module %s: Unknown relocation: %u\n",
+				me->name, ELF32_R_TYPE(rel[i].r_info));
+			return -ENOEXEC;
+		}
+	}
+	return 0;
+}
diff --git a/arch/csky/kernel/perf_callchain.c b/arch/csky/kernel/perf_callchain.c
new file mode 100644
index 000000000..1612f4354
--- /dev/null
+++ b/arch/csky/kernel/perf_callchain.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/perf_event.h>
+#include <linux/uaccess.h>
+
+/* Kernel callchain */
+struct stackframe {
+	unsigned long fp;
+	unsigned long lr;
+};
+
+static int unwind_frame_kernel(struct stackframe *frame)
+{
+	unsigned long low = (unsigned long)task_stack_page(current);
+	unsigned long high = low + THREAD_SIZE;
+
+	if (unlikely(frame->fp < low || frame->fp > high))
+		return -EPERM;
+
+	if (kstack_end((void *)frame->fp) || frame->fp & 0x3)
+		return -EPERM;
+
+	*frame = *(struct stackframe *)frame->fp;
+
+	if (__kernel_text_address(frame->lr)) {
+		int graph = 0;
+
+		frame->lr = ftrace_graph_ret_addr(NULL, &graph, frame->lr,
+				NULL);
+	}
+	return 0;
+}
+
+static void notrace walk_stackframe(struct stackframe *fr,
+			struct perf_callchain_entry_ctx *entry)
+{
+	do {
+		perf_callchain_store(entry, fr->lr);
+	} while (unwind_frame_kernel(fr) >= 0);
+}
+
+/*
+ * Get the return address for a single stackframe and return a pointer to the
+ * next frame tail.
+ */
+static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry,
+			unsigned long fp, unsigned long reg_lr)
+{
+	struct stackframe buftail;
+	unsigned long lr = 0;
+	unsigned long __user *user_frame_tail = (unsigned long __user *)fp;
+
+	/* Check accessibility of one struct frame_tail beyond */
+	if (!access_ok(user_frame_tail, sizeof(buftail)))
+		return 0;
+	if (__copy_from_user_inatomic(&buftail, user_frame_tail,
+				      sizeof(buftail)))
+		return 0;
+
+	if (reg_lr != 0)
+		lr = reg_lr;
+	else
+		lr = buftail.lr;
+
+	fp = buftail.fp;
+	perf_callchain_store(entry, lr);
+
+	return fp;
+}
+
+/*
+ * This will be called when the target is in user mode
+ * This function will only be called when we use
+ * "PERF_SAMPLE_CALLCHAIN" in
+ * kernel/events/core.c:perf_prepare_sample()
+ *
+ * How to trigger perf_callchain_[user/kernel] :
+ * $ perf record -e cpu-clock --call-graph fp ./program
+ * $ perf report --call-graph
+ *
+ * On C-SKY platform, the program being sampled and the C library
+ * need to be compiled with * -mbacktrace, otherwise the user
+ * stack will not contain function frame.
+ */
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
+			 struct pt_regs *regs)
+{
+	unsigned long fp = 0;
+
+	fp = regs->regs[4];
+	perf_callchain_store(entry, regs->pc);
+
+	/*
+	 * While backtrace from leaf function, lr is normally
+	 * not saved inside frame on C-SKY, so get lr from pt_regs
+	 * at the sample point. However, lr value can be incorrect if
+	 * lr is used as temp register
+	 */
+	fp = user_backtrace(entry, fp, regs->lr);
+
+	while (fp && !(fp & 0x3) && entry->nr < entry->max_stack)
+		fp = user_backtrace(entry, fp, 0);
+}
+
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
+			   struct pt_regs *regs)
+{
+	struct stackframe fr;
+
+	fr.fp = regs->regs[4];
+	fr.lr = regs->lr;
+	walk_stackframe(&fr, entry);
+}
diff --git a/arch/csky/kernel/perf_event.c b/arch/csky/kernel/perf_event.c
new file mode 100644
index 000000000..e0a36acd2
--- /dev/null
+++ b/arch/csky/kernel/perf_event.c
@@ -0,0 +1,1370 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+
+#define CSKY_PMU_MAX_EVENTS 32
+#define DEFAULT_COUNT_WIDTH 48
+
+#define HPCR		"<0, 0x0>"      /* PMU Control reg */
+#define HPSPR		"<0, 0x1>"      /* Start PC reg */
+#define HPEPR		"<0, 0x2>"      /* End PC reg */
+#define HPSIR		"<0, 0x3>"      /* Soft Counter reg */
+#define HPCNTENR	"<0, 0x4>"      /* Count Enable reg */
+#define HPINTENR	"<0, 0x5>"      /* Interrupt Enable reg */
+#define HPOFSR		"<0, 0x6>"      /* Interrupt Status reg */
+
+/* The events for a given PMU register set. */
+struct pmu_hw_events {
+	/*
+	 * The events that are active on the PMU for the given index.
+	 */
+	struct perf_event *events[CSKY_PMU_MAX_EVENTS];
+
+	/*
+	 * A 1 bit for an index indicates that the counter is being used for
+	 * an event. A 0 means that the counter can be used.
+	 */
+	unsigned long used_mask[BITS_TO_LONGS(CSKY_PMU_MAX_EVENTS)];
+};
+
+static uint64_t (*hw_raw_read_mapping[CSKY_PMU_MAX_EVENTS])(void);
+static void (*hw_raw_write_mapping[CSKY_PMU_MAX_EVENTS])(uint64_t val);
+
+static struct csky_pmu_t {
+	struct pmu			pmu;
+	struct pmu_hw_events __percpu	*hw_events;
+	struct platform_device		*plat_device;
+	uint32_t			count_width;
+	uint32_t			hpcr;
+	u64				max_period;
+} csky_pmu;
+static int csky_pmu_irq;
+
+#define to_csky_pmu(p)  (container_of(p, struct csky_pmu, pmu))
+
+#define cprgr(reg)				\
+({						\
+	unsigned int tmp;			\
+	asm volatile("cprgr %0, "reg"\n"	\
+		     : "=r"(tmp)		\
+		     :				\
+		     : "memory");		\
+	tmp;					\
+})
+
+#define cpwgr(reg, val)		\
+({				\
+	asm volatile(		\
+	"cpwgr %0, "reg"\n"	\
+	:			\
+	: "r"(val)		\
+	: "memory");		\
+})
+
+#define cprcr(reg)				\
+({						\
+	unsigned int tmp;			\
+	asm volatile("cprcr %0, "reg"\n"	\
+		     : "=r"(tmp)		\
+		     :				\
+		     : "memory");		\
+	tmp;					\
+})
+
+#define cpwcr(reg, val)		\
+({				\
+	asm volatile(		\
+	"cpwcr %0, "reg"\n"	\
+	:			\
+	: "r"(val)		\
+	: "memory");		\
+})
+
+/* cycle counter */
+uint64_t csky_pmu_read_cc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x3>");
+		lo  = cprgr("<0, 0x2>");
+		hi  = cprgr("<0, 0x3>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_cc(uint64_t val)
+{
+	cpwgr("<0, 0x2>", (uint32_t)  val);
+	cpwgr("<0, 0x3>", (uint32_t) (val >> 32));
+}
+
+/* instruction counter */
+static uint64_t csky_pmu_read_ic(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x5>");
+		lo  = cprgr("<0, 0x4>");
+		hi  = cprgr("<0, 0x5>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_ic(uint64_t val)
+{
+	cpwgr("<0, 0x4>", (uint32_t)  val);
+	cpwgr("<0, 0x5>", (uint32_t) (val >> 32));
+}
+
+/* l1 icache access counter */
+static uint64_t csky_pmu_read_icac(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x7>");
+		lo  = cprgr("<0, 0x6>");
+		hi  = cprgr("<0, 0x7>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_icac(uint64_t val)
+{
+	cpwgr("<0, 0x6>", (uint32_t)  val);
+	cpwgr("<0, 0x7>", (uint32_t) (val >> 32));
+}
+
+/* l1 icache miss counter */
+static uint64_t csky_pmu_read_icmc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x9>");
+		lo  = cprgr("<0, 0x8>");
+		hi  = cprgr("<0, 0x9>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_icmc(uint64_t val)
+{
+	cpwgr("<0, 0x8>", (uint32_t)  val);
+	cpwgr("<0, 0x9>", (uint32_t) (val >> 32));
+}
+
+/* l1 dcache access counter */
+static uint64_t csky_pmu_read_dcac(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0xb>");
+		lo  = cprgr("<0, 0xa>");
+		hi  = cprgr("<0, 0xb>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_dcac(uint64_t val)
+{
+	cpwgr("<0, 0xa>", (uint32_t)  val);
+	cpwgr("<0, 0xb>", (uint32_t) (val >> 32));
+}
+
+/* l1 dcache miss counter */
+static uint64_t csky_pmu_read_dcmc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0xd>");
+		lo  = cprgr("<0, 0xc>");
+		hi  = cprgr("<0, 0xd>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_dcmc(uint64_t val)
+{
+	cpwgr("<0, 0xc>", (uint32_t)  val);
+	cpwgr("<0, 0xd>", (uint32_t) (val >> 32));
+}
+
+/* l2 cache access counter */
+static uint64_t csky_pmu_read_l2ac(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0xf>");
+		lo  = cprgr("<0, 0xe>");
+		hi  = cprgr("<0, 0xf>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_l2ac(uint64_t val)
+{
+	cpwgr("<0, 0xe>", (uint32_t)  val);
+	cpwgr("<0, 0xf>", (uint32_t) (val >> 32));
+}
+
+/* l2 cache miss counter */
+static uint64_t csky_pmu_read_l2mc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x11>");
+		lo  = cprgr("<0, 0x10>");
+		hi  = cprgr("<0, 0x11>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_l2mc(uint64_t val)
+{
+	cpwgr("<0, 0x10>", (uint32_t)  val);
+	cpwgr("<0, 0x11>", (uint32_t) (val >> 32));
+}
+
+/* I-UTLB miss counter */
+static uint64_t csky_pmu_read_iutlbmc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x15>");
+		lo  = cprgr("<0, 0x14>");
+		hi  = cprgr("<0, 0x15>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_iutlbmc(uint64_t val)
+{
+	cpwgr("<0, 0x14>", (uint32_t)  val);
+	cpwgr("<0, 0x15>", (uint32_t) (val >> 32));
+}
+
+/* D-UTLB miss counter */
+static uint64_t csky_pmu_read_dutlbmc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x17>");
+		lo  = cprgr("<0, 0x16>");
+		hi  = cprgr("<0, 0x17>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_dutlbmc(uint64_t val)
+{
+	cpwgr("<0, 0x16>", (uint32_t)  val);
+	cpwgr("<0, 0x17>", (uint32_t) (val >> 32));
+}
+
+/* JTLB miss counter */
+static uint64_t csky_pmu_read_jtlbmc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x19>");
+		lo  = cprgr("<0, 0x18>");
+		hi  = cprgr("<0, 0x19>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_jtlbmc(uint64_t val)
+{
+	cpwgr("<0, 0x18>", (uint32_t)  val);
+	cpwgr("<0, 0x19>", (uint32_t) (val >> 32));
+}
+
+/* software counter */
+static uint64_t csky_pmu_read_softc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x1b>");
+		lo  = cprgr("<0, 0x1a>");
+		hi  = cprgr("<0, 0x1b>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_softc(uint64_t val)
+{
+	cpwgr("<0, 0x1a>", (uint32_t)  val);
+	cpwgr("<0, 0x1b>", (uint32_t) (val >> 32));
+}
+
+/* conditional branch mispredict counter */
+static uint64_t csky_pmu_read_cbmc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x1d>");
+		lo  = cprgr("<0, 0x1c>");
+		hi  = cprgr("<0, 0x1d>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_cbmc(uint64_t val)
+{
+	cpwgr("<0, 0x1c>", (uint32_t)  val);
+	cpwgr("<0, 0x1d>", (uint32_t) (val >> 32));
+}
+
+/* conditional branch instruction counter */
+static uint64_t csky_pmu_read_cbic(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x1f>");
+		lo  = cprgr("<0, 0x1e>");
+		hi  = cprgr("<0, 0x1f>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_cbic(uint64_t val)
+{
+	cpwgr("<0, 0x1e>", (uint32_t)  val);
+	cpwgr("<0, 0x1f>", (uint32_t) (val >> 32));
+}
+
+/* indirect branch mispredict counter */
+static uint64_t csky_pmu_read_ibmc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x21>");
+		lo  = cprgr("<0, 0x20>");
+		hi  = cprgr("<0, 0x21>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_ibmc(uint64_t val)
+{
+	cpwgr("<0, 0x20>", (uint32_t)  val);
+	cpwgr("<0, 0x21>", (uint32_t) (val >> 32));
+}
+
+/* indirect branch instruction counter */
+static uint64_t csky_pmu_read_ibic(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x23>");
+		lo  = cprgr("<0, 0x22>");
+		hi  = cprgr("<0, 0x23>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_ibic(uint64_t val)
+{
+	cpwgr("<0, 0x22>", (uint32_t)  val);
+	cpwgr("<0, 0x23>", (uint32_t) (val >> 32));
+}
+
+/* LSU spec fail counter */
+static uint64_t csky_pmu_read_lsfc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x25>");
+		lo  = cprgr("<0, 0x24>");
+		hi  = cprgr("<0, 0x25>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_lsfc(uint64_t val)
+{
+	cpwgr("<0, 0x24>", (uint32_t)  val);
+	cpwgr("<0, 0x25>", (uint32_t) (val >> 32));
+}
+
+/* store instruction counter */
+static uint64_t csky_pmu_read_sic(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x27>");
+		lo  = cprgr("<0, 0x26>");
+		hi  = cprgr("<0, 0x27>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_sic(uint64_t val)
+{
+	cpwgr("<0, 0x26>", (uint32_t)  val);
+	cpwgr("<0, 0x27>", (uint32_t) (val >> 32));
+}
+
+/* dcache read access counter */
+static uint64_t csky_pmu_read_dcrac(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x29>");
+		lo  = cprgr("<0, 0x28>");
+		hi  = cprgr("<0, 0x29>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_dcrac(uint64_t val)
+{
+	cpwgr("<0, 0x28>", (uint32_t)  val);
+	cpwgr("<0, 0x29>", (uint32_t) (val >> 32));
+}
+
+/* dcache read miss counter */
+static uint64_t csky_pmu_read_dcrmc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x2b>");
+		lo  = cprgr("<0, 0x2a>");
+		hi  = cprgr("<0, 0x2b>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_dcrmc(uint64_t val)
+{
+	cpwgr("<0, 0x2a>", (uint32_t)  val);
+	cpwgr("<0, 0x2b>", (uint32_t) (val >> 32));
+}
+
+/* dcache write access counter */
+static uint64_t csky_pmu_read_dcwac(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x2d>");
+		lo  = cprgr("<0, 0x2c>");
+		hi  = cprgr("<0, 0x2d>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_dcwac(uint64_t val)
+{
+	cpwgr("<0, 0x2c>", (uint32_t)  val);
+	cpwgr("<0, 0x2d>", (uint32_t) (val >> 32));
+}
+
+/* dcache write miss counter */
+static uint64_t csky_pmu_read_dcwmc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x2f>");
+		lo  = cprgr("<0, 0x2e>");
+		hi  = cprgr("<0, 0x2f>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_dcwmc(uint64_t val)
+{
+	cpwgr("<0, 0x2e>", (uint32_t)  val);
+	cpwgr("<0, 0x2f>", (uint32_t) (val >> 32));
+}
+
+/* l2cache read access counter */
+static uint64_t csky_pmu_read_l2rac(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x31>");
+		lo  = cprgr("<0, 0x30>");
+		hi  = cprgr("<0, 0x31>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_l2rac(uint64_t val)
+{
+	cpwgr("<0, 0x30>", (uint32_t)  val);
+	cpwgr("<0, 0x31>", (uint32_t) (val >> 32));
+}
+
+/* l2cache read miss counter */
+static uint64_t csky_pmu_read_l2rmc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x33>");
+		lo  = cprgr("<0, 0x32>");
+		hi  = cprgr("<0, 0x33>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_l2rmc(uint64_t val)
+{
+	cpwgr("<0, 0x32>", (uint32_t)  val);
+	cpwgr("<0, 0x33>", (uint32_t) (val >> 32));
+}
+
+/* l2cache write access counter */
+static uint64_t csky_pmu_read_l2wac(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x35>");
+		lo  = cprgr("<0, 0x34>");
+		hi  = cprgr("<0, 0x35>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_l2wac(uint64_t val)
+{
+	cpwgr("<0, 0x34>", (uint32_t)  val);
+	cpwgr("<0, 0x35>", (uint32_t) (val >> 32));
+}
+
+/* l2cache write miss counter */
+static uint64_t csky_pmu_read_l2wmc(void)
+{
+	uint32_t lo, hi, tmp;
+	uint64_t result;
+
+	do {
+		tmp = cprgr("<0, 0x37>");
+		lo  = cprgr("<0, 0x36>");
+		hi  = cprgr("<0, 0x37>");
+	} while (hi != tmp);
+
+	result = (uint64_t) (hi) << 32;
+	result |= lo;
+
+	return result;
+}
+
+static void csky_pmu_write_l2wmc(uint64_t val)
+{
+	cpwgr("<0, 0x36>", (uint32_t)  val);
+	cpwgr("<0, 0x37>", (uint32_t) (val >> 32));
+}
+
+#define HW_OP_UNSUPPORTED	0xffff
+static const int csky_pmu_hw_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0x1,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x2,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_CACHE_MISSES]		= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0xf,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0xe,
+	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_REF_CPU_CYCLES]		= HW_OP_UNSUPPORTED,
+};
+
+#define C(_x)			PERF_COUNT_HW_CACHE_##_x
+#define CACHE_OP_UNSUPPORTED	0xffff
+static const int csky_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {
+#ifdef CONFIG_CPU_CK810
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x5,
+			[C(RESULT_MISS)]	= 0x6,
+		},
+#else
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x14,
+			[C(RESULT_MISS)]	= 0x15,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x16,
+			[C(RESULT_MISS)]	= 0x17,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+#endif
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x3,
+			[C(RESULT_MISS)]	= 0x4,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+#ifdef CONFIG_CPU_CK810
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x7,
+			[C(RESULT_MISS)]	= 0x8,
+		},
+#else
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x18,
+			[C(RESULT_MISS)]	= 0x19,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x1a,
+			[C(RESULT_MISS)]	= 0x1b,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+#endif
+	},
+	[C(DTLB)] = {
+#ifdef CONFIG_CPU_CK810
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+#else
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x14,
+			[C(RESULT_MISS)]	= 0xb,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x16,
+			[C(RESULT_MISS)]	= 0xb,
+		},
+#endif
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(ITLB)] = {
+#ifdef CONFIG_CPU_CK810
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+#else
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x3,
+			[C(RESULT_MISS)]	= 0xa,
+		},
+#endif
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(NODE)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
+int  csky_pmu_event_set_period(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	s64 left = local64_read(&hwc->period_left);
+	s64 period = hwc->sample_period;
+	int ret = 0;
+
+	if (unlikely(left <= -period)) {
+		left = period;
+		local64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		ret = 1;
+	}
+
+	if (unlikely(left <= 0)) {
+		left += period;
+		local64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		ret = 1;
+	}
+
+	if (left > (s64)csky_pmu.max_period)
+		left = csky_pmu.max_period;
+
+	/*
+	 * The hw event starts counting from this event offset,
+	 * mark it to be able to extract future "deltas":
+	 */
+	local64_set(&hwc->prev_count, (u64)(-left));
+
+	if (hw_raw_write_mapping[hwc->idx] != NULL)
+		hw_raw_write_mapping[hwc->idx]((u64)(-left) &
+						csky_pmu.max_period);
+
+	cpwcr(HPOFSR, ~BIT(hwc->idx) & cprcr(HPOFSR));
+
+	perf_event_update_userpage(event);
+
+	return ret;
+}
+
+static void csky_perf_event_update(struct perf_event *event,
+				   struct hw_perf_event *hwc)
+{
+	uint64_t prev_raw_count = local64_read(&hwc->prev_count);
+	/*
+	 * Sign extend count value to 64bit, otherwise delta calculation
+	 * would be incorrect when overflow occurs.
+	 */
+	uint64_t new_raw_count = sign_extend64(
+		hw_raw_read_mapping[hwc->idx](), csky_pmu.count_width - 1);
+	int64_t delta = new_raw_count - prev_raw_count;
+
+	/*
+	 * We aren't afraid of hwc->prev_count changing beneath our feet
+	 * because there's no way for us to re-enter this function anytime.
+	 */
+	local64_set(&hwc->prev_count, new_raw_count);
+	local64_add(delta, &event->count);
+	local64_sub(delta, &hwc->period_left);
+}
+
+static void csky_pmu_reset(void *info)
+{
+	cpwcr(HPCR, BIT(31) | BIT(30) | BIT(1));
+}
+
+static void csky_pmu_read(struct perf_event *event)
+{
+	csky_perf_event_update(event, &event->hw);
+}
+
+static int csky_pmu_cache_event(u64 config)
+{
+	unsigned int cache_type, cache_op, cache_result;
+
+	cache_type	= (config >>  0) & 0xff;
+	cache_op	= (config >>  8) & 0xff;
+	cache_result	= (config >> 16) & 0xff;
+
+	if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
+		return -EINVAL;
+	if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
+		return -EINVAL;
+	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
+		return -EINVAL;
+
+	return csky_pmu_cache_map[cache_type][cache_op][cache_result];
+}
+
+static int csky_pmu_event_init(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int ret;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_HARDWARE:
+		if (event->attr.config >= PERF_COUNT_HW_MAX)
+			return -ENOENT;
+		ret = csky_pmu_hw_map[event->attr.config];
+		if (ret == HW_OP_UNSUPPORTED)
+			return -ENOENT;
+		hwc->idx = ret;
+		break;
+	case PERF_TYPE_HW_CACHE:
+		ret = csky_pmu_cache_event(event->attr.config);
+		if (ret == CACHE_OP_UNSUPPORTED)
+			return -ENOENT;
+		hwc->idx = ret;
+		break;
+	case PERF_TYPE_RAW:
+		if (hw_raw_read_mapping[event->attr.config] == NULL)
+			return -ENOENT;
+		hwc->idx = event->attr.config;
+		break;
+	default:
+		return -ENOENT;
+	}
+
+	if (event->attr.exclude_user)
+		csky_pmu.hpcr = BIT(2);
+	else if (event->attr.exclude_kernel)
+		csky_pmu.hpcr = BIT(3);
+	else
+		csky_pmu.hpcr = BIT(2) | BIT(3);
+
+	csky_pmu.hpcr |= BIT(1) | BIT(0);
+
+	return 0;
+}
+
+/* starts all counters */
+static void csky_pmu_enable(struct pmu *pmu)
+{
+	cpwcr(HPCR, csky_pmu.hpcr);
+}
+
+/* stops all counters */
+static void csky_pmu_disable(struct pmu *pmu)
+{
+	cpwcr(HPCR, BIT(1));
+}
+
+static void csky_pmu_start(struct perf_event *event, int flags)
+{
+	unsigned long flg;
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	if (WARN_ON_ONCE(idx == -1))
+		return;
+
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+
+	hwc->state = 0;
+
+	csky_pmu_event_set_period(event);
+
+	local_irq_save(flg);
+
+	cpwcr(HPINTENR, BIT(idx) | cprcr(HPINTENR));
+	cpwcr(HPCNTENR, BIT(idx) | cprcr(HPCNTENR));
+
+	local_irq_restore(flg);
+}
+
+static void csky_pmu_stop_event(struct perf_event *event)
+{
+	unsigned long flg;
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	local_irq_save(flg);
+
+	cpwcr(HPINTENR, ~BIT(idx) & cprcr(HPINTENR));
+	cpwcr(HPCNTENR, ~BIT(idx) & cprcr(HPCNTENR));
+
+	local_irq_restore(flg);
+}
+
+static void csky_pmu_stop(struct perf_event *event, int flags)
+{
+	if (!(event->hw.state & PERF_HES_STOPPED)) {
+		csky_pmu_stop_event(event);
+		event->hw.state |= PERF_HES_STOPPED;
+	}
+
+	if ((flags & PERF_EF_UPDATE) &&
+	    !(event->hw.state & PERF_HES_UPTODATE)) {
+		csky_perf_event_update(event, &event->hw);
+		event->hw.state |= PERF_HES_UPTODATE;
+	}
+}
+
+static void csky_pmu_del(struct perf_event *event, int flags)
+{
+	struct pmu_hw_events *hw_events = this_cpu_ptr(csky_pmu.hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	csky_pmu_stop(event, PERF_EF_UPDATE);
+
+	hw_events->events[hwc->idx] = NULL;
+
+	perf_event_update_userpage(event);
+}
+
+/* allocate hardware counter and optionally start counting */
+static int csky_pmu_add(struct perf_event *event, int flags)
+{
+	struct pmu_hw_events *hw_events = this_cpu_ptr(csky_pmu.hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	hw_events->events[hwc->idx] = event;
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	if (flags & PERF_EF_START)
+		csky_pmu_start(event, PERF_EF_RELOAD);
+
+	perf_event_update_userpage(event);
+
+	return 0;
+}
+
+static irqreturn_t csky_pmu_handle_irq(int irq_num, void *dev)
+{
+	struct perf_sample_data data;
+	struct pmu_hw_events *cpuc = this_cpu_ptr(csky_pmu.hw_events);
+	struct pt_regs *regs;
+	int idx;
+
+	/*
+	 * Did an overflow occur?
+	 */
+	if (!cprcr(HPOFSR))
+		return IRQ_NONE;
+
+	/*
+	 * Handle the counter(s) overflow(s)
+	 */
+	regs = get_irq_regs();
+
+	csky_pmu_disable(&csky_pmu.pmu);
+
+	for (idx = 0; idx < CSKY_PMU_MAX_EVENTS; ++idx) {
+		struct perf_event *event = cpuc->events[idx];
+		struct hw_perf_event *hwc;
+
+		/* Ignore if we don't have an event. */
+		if (!event)
+			continue;
+		/*
+		 * We have a single interrupt for all counters. Check that
+		 * each counter has overflowed before we process it.
+		 */
+		if (!(cprcr(HPOFSR) & BIT(idx)))
+			continue;
+
+		hwc = &event->hw;
+		csky_perf_event_update(event, &event->hw);
+		perf_sample_data_init(&data, 0, hwc->last_period);
+		csky_pmu_event_set_period(event);
+
+		perf_event_overflow(event, &data, regs);
+	}
+
+	csky_pmu_enable(&csky_pmu.pmu);
+
+	/*
+	 * Handle the pending perf events.
+	 *
+	 * Note: this call *must* be run with interrupts disabled. For
+	 * platforms that can have the PMU interrupts raised as an NMI, this
+	 * will not work.
+	 */
+	irq_work_run();
+
+	return IRQ_HANDLED;
+}
+
+static int csky_pmu_request_irq(irq_handler_t handler)
+{
+	int err, irqs;
+	struct platform_device *pmu_device = csky_pmu.plat_device;
+
+	if (!pmu_device)
+		return -ENODEV;
+
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+	if (irqs < 1) {
+		pr_err("no irqs for PMUs defined\n");
+		return -ENODEV;
+	}
+
+	csky_pmu_irq = platform_get_irq(pmu_device, 0);
+	if (csky_pmu_irq < 0)
+		return -ENODEV;
+	err = request_percpu_irq(csky_pmu_irq, handler, "csky-pmu",
+				 this_cpu_ptr(csky_pmu.hw_events));
+	if (err) {
+		pr_err("unable to request IRQ%d for CSKY PMU counters\n",
+		       csky_pmu_irq);
+		return err;
+	}
+
+	return 0;
+}
+
+static void csky_pmu_free_irq(void)
+{
+	int irq;
+	struct platform_device *pmu_device = csky_pmu.plat_device;
+
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq >= 0)
+		free_percpu_irq(irq, this_cpu_ptr(csky_pmu.hw_events));
+}
+
+int init_hw_perf_events(void)
+{
+	csky_pmu.hw_events = alloc_percpu_gfp(struct pmu_hw_events,
+					      GFP_KERNEL);
+	if (!csky_pmu.hw_events) {
+		pr_info("failed to allocate per-cpu PMU data.\n");
+		return -ENOMEM;
+	}
+
+	csky_pmu.pmu = (struct pmu) {
+		.pmu_enable	= csky_pmu_enable,
+		.pmu_disable	= csky_pmu_disable,
+		.event_init	= csky_pmu_event_init,
+		.add		= csky_pmu_add,
+		.del		= csky_pmu_del,
+		.start		= csky_pmu_start,
+		.stop		= csky_pmu_stop,
+		.read		= csky_pmu_read,
+	};
+
+	memset((void *)hw_raw_read_mapping, 0,
+		sizeof(hw_raw_read_mapping[CSKY_PMU_MAX_EVENTS]));
+
+	hw_raw_read_mapping[0x1]  = csky_pmu_read_cc;
+	hw_raw_read_mapping[0x2]  = csky_pmu_read_ic;
+	hw_raw_read_mapping[0x3]  = csky_pmu_read_icac;
+	hw_raw_read_mapping[0x4]  = csky_pmu_read_icmc;
+	hw_raw_read_mapping[0x5]  = csky_pmu_read_dcac;
+	hw_raw_read_mapping[0x6]  = csky_pmu_read_dcmc;
+	hw_raw_read_mapping[0x7]  = csky_pmu_read_l2ac;
+	hw_raw_read_mapping[0x8]  = csky_pmu_read_l2mc;
+	hw_raw_read_mapping[0xa]  = csky_pmu_read_iutlbmc;
+	hw_raw_read_mapping[0xb]  = csky_pmu_read_dutlbmc;
+	hw_raw_read_mapping[0xc]  = csky_pmu_read_jtlbmc;
+	hw_raw_read_mapping[0xd]  = csky_pmu_read_softc;
+	hw_raw_read_mapping[0xe]  = csky_pmu_read_cbmc;
+	hw_raw_read_mapping[0xf]  = csky_pmu_read_cbic;
+	hw_raw_read_mapping[0x10] = csky_pmu_read_ibmc;
+	hw_raw_read_mapping[0x11] = csky_pmu_read_ibic;
+	hw_raw_read_mapping[0x12] = csky_pmu_read_lsfc;
+	hw_raw_read_mapping[0x13] = csky_pmu_read_sic;
+	hw_raw_read_mapping[0x14] = csky_pmu_read_dcrac;
+	hw_raw_read_mapping[0x15] = csky_pmu_read_dcrmc;
+	hw_raw_read_mapping[0x16] = csky_pmu_read_dcwac;
+	hw_raw_read_mapping[0x17] = csky_pmu_read_dcwmc;
+	hw_raw_read_mapping[0x18] = csky_pmu_read_l2rac;
+	hw_raw_read_mapping[0x19] = csky_pmu_read_l2rmc;
+	hw_raw_read_mapping[0x1a] = csky_pmu_read_l2wac;
+	hw_raw_read_mapping[0x1b] = csky_pmu_read_l2wmc;
+
+	memset((void *)hw_raw_write_mapping, 0,
+		sizeof(hw_raw_write_mapping[CSKY_PMU_MAX_EVENTS]));
+
+	hw_raw_write_mapping[0x1]  = csky_pmu_write_cc;
+	hw_raw_write_mapping[0x2]  = csky_pmu_write_ic;
+	hw_raw_write_mapping[0x3]  = csky_pmu_write_icac;
+	hw_raw_write_mapping[0x4]  = csky_pmu_write_icmc;
+	hw_raw_write_mapping[0x5]  = csky_pmu_write_dcac;
+	hw_raw_write_mapping[0x6]  = csky_pmu_write_dcmc;
+	hw_raw_write_mapping[0x7]  = csky_pmu_write_l2ac;
+	hw_raw_write_mapping[0x8]  = csky_pmu_write_l2mc;
+	hw_raw_write_mapping[0xa]  = csky_pmu_write_iutlbmc;
+	hw_raw_write_mapping[0xb]  = csky_pmu_write_dutlbmc;
+	hw_raw_write_mapping[0xc]  = csky_pmu_write_jtlbmc;
+	hw_raw_write_mapping[0xd]  = csky_pmu_write_softc;
+	hw_raw_write_mapping[0xe]  = csky_pmu_write_cbmc;
+	hw_raw_write_mapping[0xf]  = csky_pmu_write_cbic;
+	hw_raw_write_mapping[0x10] = csky_pmu_write_ibmc;
+	hw_raw_write_mapping[0x11] = csky_pmu_write_ibic;
+	hw_raw_write_mapping[0x12] = csky_pmu_write_lsfc;
+	hw_raw_write_mapping[0x13] = csky_pmu_write_sic;
+	hw_raw_write_mapping[0x14] = csky_pmu_write_dcrac;
+	hw_raw_write_mapping[0x15] = csky_pmu_write_dcrmc;
+	hw_raw_write_mapping[0x16] = csky_pmu_write_dcwac;
+	hw_raw_write_mapping[0x17] = csky_pmu_write_dcwmc;
+	hw_raw_write_mapping[0x18] = csky_pmu_write_l2rac;
+	hw_raw_write_mapping[0x19] = csky_pmu_write_l2rmc;
+	hw_raw_write_mapping[0x1a] = csky_pmu_write_l2wac;
+	hw_raw_write_mapping[0x1b] = csky_pmu_write_l2wmc;
+
+	return 0;
+}
+
+static int csky_pmu_starting_cpu(unsigned int cpu)
+{
+	enable_percpu_irq(csky_pmu_irq, 0);
+	return 0;
+}
+
+static int csky_pmu_dying_cpu(unsigned int cpu)
+{
+	disable_percpu_irq(csky_pmu_irq);
+	return 0;
+}
+
+int csky_pmu_device_probe(struct platform_device *pdev,
+			  const struct of_device_id *of_table)
+{
+	struct device_node *node = pdev->dev.of_node;
+	int ret;
+
+	ret = init_hw_perf_events();
+	if (ret) {
+		pr_notice("[perf] failed to probe PMU!\n");
+		return ret;
+	}
+
+	if (of_property_read_u32(node, "count-width",
+				 &csky_pmu.count_width)) {
+		csky_pmu.count_width = DEFAULT_COUNT_WIDTH;
+	}
+	csky_pmu.max_period = BIT_ULL(csky_pmu.count_width) - 1;
+
+	csky_pmu.plat_device = pdev;
+
+	/* Ensure the PMU has sane values out of reset. */
+	on_each_cpu(csky_pmu_reset, &csky_pmu, 1);
+
+	ret = csky_pmu_request_irq(csky_pmu_handle_irq);
+	if (ret) {
+		csky_pmu.pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+		pr_notice("[perf] PMU request irq fail!\n");
+	}
+
+	ret = cpuhp_setup_state(CPUHP_AP_PERF_CSKY_ONLINE, "AP_PERF_ONLINE",
+				csky_pmu_starting_cpu,
+				csky_pmu_dying_cpu);
+	if (ret) {
+		csky_pmu_free_irq();
+		free_percpu(csky_pmu.hw_events);
+		return ret;
+	}
+
+	ret = perf_pmu_register(&csky_pmu.pmu, "cpu", PERF_TYPE_RAW);
+	if (ret) {
+		csky_pmu_free_irq();
+		free_percpu(csky_pmu.hw_events);
+	}
+
+	return ret;
+}
+
+static const struct of_device_id csky_pmu_of_device_ids[] = {
+	{.compatible = "csky,csky-pmu"},
+	{},
+};
+
+static int csky_pmu_dev_probe(struct platform_device *pdev)
+{
+	return csky_pmu_device_probe(pdev, csky_pmu_of_device_ids);
+}
+
+static struct platform_driver csky_pmu_driver = {
+	.driver = {
+		   .name = "csky-pmu",
+		   .of_match_table = csky_pmu_of_device_ids,
+		   },
+	.probe = csky_pmu_dev_probe,
+};
+
+static int __init csky_pmu_probe(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&csky_pmu_driver);
+	if (ret)
+		pr_notice("[perf] PMU initialization failed\n");
+	else
+		pr_notice("[perf] PMU initialization done\n");
+
+	return ret;
+}
+
+device_initcall(csky_pmu_probe);
diff --git a/arch/csky/kernel/perf_regs.c b/arch/csky/kernel/perf_regs.c
new file mode 100644
index 000000000..09b7f88a2
--- /dev/null
+++ b/arch/csky/kernel/perf_regs.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_CSKY_MAX))
+		return 0;
+
+	return (u64)*((u32 *)regs + idx);
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_CSKY_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask || mask & REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+	return PERF_SAMPLE_REGS_ABI_32;
+}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/csky/kernel/power.c b/arch/csky/kernel/power.c
new file mode 100644
index 000000000..86ee20290
--- /dev/null
+++ b/arch/csky/kernel/power.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/reboot.h>
+
+void (*pm_power_off)(void);
+EXPORT_SYMBOL(pm_power_off);
+
+void machine_power_off(void)
+{
+	local_irq_disable();
+	do_kernel_power_off();
+	asm volatile ("bkpt");
+}
+
+void machine_halt(void)
+{
+	local_irq_disable();
+	do_kernel_power_off();
+	asm volatile ("bkpt");
+}
+
+void machine_restart(char *cmd)
+{
+	local_irq_disable();
+	do_kernel_restart(cmd);
+	asm volatile ("bkpt");
+}
diff --git a/arch/csky/kernel/probes/Makefile b/arch/csky/kernel/probes/Makefile
new file mode 100644
index 000000000..1c7c6e6cb
--- /dev/null
+++ b/arch/csky/kernel/probes/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_KPROBES)		+= kprobes.o decode-insn.o simulate-insn.o
+obj-$(CONFIG_KPROBES)		+= kprobes_trampoline.o
+obj-$(CONFIG_KPROBES_ON_FTRACE)	+= ftrace.o
+obj-$(CONFIG_UPROBES)		+= uprobes.o decode-insn.o simulate-insn.o
+
+CFLAGS_REMOVE_simulate-insn.o = $(CC_FLAGS_FTRACE)
diff --git a/arch/csky/kernel/probes/decode-insn.c b/arch/csky/kernel/probes/decode-insn.c
new file mode 100644
index 000000000..bbc4edc25
--- /dev/null
+++ b/arch/csky/kernel/probes/decode-insn.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <asm/sections.h>
+
+#include "decode-insn.h"
+#include "simulate-insn.h"
+
+/* Return:
+ *   INSN_REJECTED     If instruction is one not allowed to kprobe,
+ *   INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot.
+ */
+enum probe_insn __kprobes
+csky_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *api)
+{
+	probe_opcode_t insn = le32_to_cpu(*addr);
+
+	CSKY_INSN_SET_SIMULATE(br16,		insn);
+	CSKY_INSN_SET_SIMULATE(bt16,		insn);
+	CSKY_INSN_SET_SIMULATE(bf16,		insn);
+	CSKY_INSN_SET_SIMULATE(jmp16,		insn);
+	CSKY_INSN_SET_SIMULATE(jsr16,		insn);
+	CSKY_INSN_SET_SIMULATE(lrw16,		insn);
+	CSKY_INSN_SET_SIMULATE(pop16,		insn);
+
+	CSKY_INSN_SET_SIMULATE(br32,		insn);
+	CSKY_INSN_SET_SIMULATE(bt32,		insn);
+	CSKY_INSN_SET_SIMULATE(bf32,		insn);
+	CSKY_INSN_SET_SIMULATE(jmp32,		insn);
+	CSKY_INSN_SET_SIMULATE(jsr32,		insn);
+	CSKY_INSN_SET_SIMULATE(lrw32,		insn);
+	CSKY_INSN_SET_SIMULATE(pop32,		insn);
+
+	CSKY_INSN_SET_SIMULATE(bez32,		insn);
+	CSKY_INSN_SET_SIMULATE(bnez32,		insn);
+	CSKY_INSN_SET_SIMULATE(bnezad32,	insn);
+	CSKY_INSN_SET_SIMULATE(bhsz32,		insn);
+	CSKY_INSN_SET_SIMULATE(bhz32,		insn);
+	CSKY_INSN_SET_SIMULATE(blsz32,		insn);
+	CSKY_INSN_SET_SIMULATE(blz32,		insn);
+	CSKY_INSN_SET_SIMULATE(bsr32,		insn);
+	CSKY_INSN_SET_SIMULATE(jmpi32,		insn);
+	CSKY_INSN_SET_SIMULATE(jsri32,		insn);
+
+	return INSN_GOOD;
+}
diff --git a/arch/csky/kernel/probes/decode-insn.h b/arch/csky/kernel/probes/decode-insn.h
new file mode 100644
index 000000000..9c4ad48fe
--- /dev/null
+++ b/arch/csky/kernel/probes/decode-insn.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef __CSKY_KERNEL_KPROBES_DECODE_INSN_H
+#define __CSKY_KERNEL_KPROBES_DECODE_INSN_H
+
+#include <asm/sections.h>
+#include <asm/kprobes.h>
+
+enum probe_insn {
+	INSN_REJECTED,
+	INSN_GOOD_NO_SLOT,
+	INSN_GOOD,
+};
+
+#define is_insn32(insn) ((insn & 0xc000) == 0xc000)
+
+enum probe_insn __kprobes
+csky_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *asi);
+
+#endif /* __CSKY_KERNEL_KPROBES_DECODE_INSN_H */
diff --git a/arch/csky/kernel/probes/ftrace.c b/arch/csky/kernel/probes/ftrace.c
new file mode 100644
index 000000000..7ba4b9807
--- /dev/null
+++ b/arch/csky/kernel/probes/ftrace.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kprobes.h>
+
+/* Ftrace callback handler for kprobes -- called under preepmt disabled */
+void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
+{
+	int bit;
+	bool lr_saver = false;
+	struct kprobe *p;
+	struct kprobe_ctlblk *kcb;
+	struct pt_regs *regs;
+
+	if (unlikely(kprobe_ftrace_disabled))
+		return;
+
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
+	if (bit < 0)
+		return;
+
+	regs = ftrace_get_regs(fregs);
+	p = get_kprobe((kprobe_opcode_t *)ip);
+	if (!p) {
+		p = get_kprobe((kprobe_opcode_t *)(ip - MCOUNT_INSN_SIZE));
+		if (unlikely(!p) || kprobe_disabled(p))
+			goto out;
+		lr_saver = true;
+	}
+
+	kcb = get_kprobe_ctlblk();
+	if (kprobe_running()) {
+		kprobes_inc_nmissed_count(p);
+	} else {
+		unsigned long orig_ip = instruction_pointer(regs);
+
+		if (lr_saver)
+			ip -= MCOUNT_INSN_SIZE;
+		instruction_pointer_set(regs, ip);
+		__this_cpu_write(current_kprobe, p);
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+		if (!p->pre_handler || !p->pre_handler(p, regs)) {
+			/*
+			 * Emulate singlestep (and also recover regs->pc)
+			 * as if there is a nop
+			 */
+			instruction_pointer_set(regs,
+				(unsigned long)p->addr + MCOUNT_INSN_SIZE);
+			if (unlikely(p->post_handler)) {
+				kcb->kprobe_status = KPROBE_HIT_SSDONE;
+				p->post_handler(p, regs, 0);
+			}
+			instruction_pointer_set(regs, orig_ip);
+		}
+		/*
+		 * If pre_handler returns !0, it changes regs->pc. We have to
+		 * skip emulating post_handler.
+		 */
+		__this_cpu_write(current_kprobe, NULL);
+	}
+out:
+	ftrace_test_recursion_unlock(bit);
+}
+NOKPROBE_SYMBOL(kprobe_ftrace_handler);
+
+int arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+	p->ainsn.api.insn = NULL;
+	return 0;
+}
diff --git a/arch/csky/kernel/probes/kprobes.c b/arch/csky/kernel/probes/kprobes.c
new file mode 100644
index 000000000..3c6e5c725
--- /dev/null
+++ b/arch/csky/kernel/probes/kprobes.c
@@ -0,0 +1,412 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#define pr_fmt(fmt) "kprobes: " fmt
+
+#include <linux/kprobes.h>
+#include <linux/extable.h>
+#include <linux/slab.h>
+#include <linux/stop_machine.h>
+#include <asm/ptrace.h>
+#include <linux/uaccess.h>
+#include <asm/sections.h>
+#include <asm/cacheflush.h>
+
+#include "decode-insn.h"
+
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+
+static void __kprobes
+post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *);
+
+struct csky_insn_patch {
+	kprobe_opcode_t	*addr;
+	u32		opcode;
+	atomic_t	cpu_count;
+};
+
+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) == num_online_cpus()) {
+		*(u16 *) addr = cpu_to_le16(param->opcode);
+		dcache_wb_range(addr, addr + 2);
+		atomic_inc(&param->cpu_count);
+	} else {
+		while (atomic_read(&param->cpu_count) <= num_online_cpus())
+			cpu_relax();
+	}
+
+	icache_inv_range(addr, addr + 2);
+
+	return 0;
+}
+
+static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode)
+{
+	struct csky_insn_patch param = { addr, opcode, ATOMIC_INIT(0) };
+
+	return stop_machine_cpuslocked(patch_text_cb, &param, cpu_online_mask);
+}
+
+static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
+{
+	unsigned long offset = is_insn32(p->opcode) ? 4 : 2;
+
+	p->ainsn.api.restore = (unsigned long)p->addr + offset;
+
+	patch_text(p->ainsn.api.insn, p->opcode);
+}
+
+static void __kprobes arch_prepare_simulate(struct kprobe *p)
+{
+	p->ainsn.api.restore = 0;
+}
+
+static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	if (p->ainsn.api.handler)
+		p->ainsn.api.handler((u32)p->opcode, (long)p->addr, regs);
+
+	post_kprobe_handler(kcb, regs);
+}
+
+int __kprobes arch_prepare_kprobe(struct kprobe *p)
+{
+	unsigned long probe_addr = (unsigned long)p->addr;
+
+	if (probe_addr & 0x1)
+		return -EILSEQ;
+
+	/* copy instruction */
+	p->opcode = le32_to_cpu(*p->addr);
+
+	/* decode instruction */
+	switch (csky_probe_decode_insn(p->addr, &p->ainsn.api)) {
+	case INSN_REJECTED:	/* insn not supported */
+		return -EINVAL;
+
+	case INSN_GOOD_NO_SLOT:	/* insn need simulation */
+		p->ainsn.api.insn = NULL;
+		break;
+
+	case INSN_GOOD:	/* instruction uses slot */
+		p->ainsn.api.insn = get_insn_slot();
+		if (!p->ainsn.api.insn)
+			return -ENOMEM;
+		break;
+	}
+
+	/* prepare the instruction */
+	if (p->ainsn.api.insn)
+		arch_prepare_ss_slot(p);
+	else
+		arch_prepare_simulate(p);
+
+	return 0;
+}
+
+/* install breakpoint in text */
+void __kprobes arch_arm_kprobe(struct kprobe *p)
+{
+	patch_text(p->addr, USR_BKPT);
+}
+
+/* remove breakpoint from text */
+void __kprobes arch_disarm_kprobe(struct kprobe *p)
+{
+	patch_text(p->addr, p->opcode);
+}
+
+void __kprobes arch_remove_kprobe(struct kprobe *p)
+{
+	if (p->ainsn.api.insn) {
+		free_insn_slot(p->ainsn.api.insn, 0);
+		p->ainsn.api.insn = NULL;
+	}
+}
+
+static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
+{
+	kcb->prev_kprobe.kp = kprobe_running();
+	kcb->prev_kprobe.status = kcb->kprobe_status;
+}
+
+static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
+{
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
+	kcb->kprobe_status = kcb->prev_kprobe.status;
+}
+
+static void __kprobes set_current_kprobe(struct kprobe *p)
+{
+	__this_cpu_write(current_kprobe, p);
+}
+
+/*
+ * Interrupts need to be disabled before single-step mode is set, and not
+ * reenabled until after single-step mode ends.
+ * Without disabling interrupt on local CPU, there is a chance of
+ * interrupt occurrence in the period of exception return and  start of
+ * out-of-line single-step, that result in wrongly single stepping
+ * into the interrupt handler.
+ */
+static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb,
+						struct pt_regs *regs)
+{
+	kcb->saved_sr = regs->sr;
+	regs->sr &= ~BIT(6);
+}
+
+static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
+						struct pt_regs *regs)
+{
+	regs->sr = kcb->saved_sr;
+}
+
+static void __kprobes
+set_ss_context(struct kprobe_ctlblk *kcb, unsigned long addr, struct kprobe *p)
+{
+	unsigned long offset = is_insn32(p->opcode) ? 4 : 2;
+
+	kcb->ss_ctx.ss_pending = true;
+	kcb->ss_ctx.match_addr = addr + offset;
+}
+
+static void __kprobes clear_ss_context(struct kprobe_ctlblk *kcb)
+{
+	kcb->ss_ctx.ss_pending = false;
+	kcb->ss_ctx.match_addr = 0;
+}
+
+#define TRACE_MODE_SI		BIT(14)
+#define TRACE_MODE_MASK		~(0x3 << 14)
+#define TRACE_MODE_RUN		0
+
+static void __kprobes setup_singlestep(struct kprobe *p,
+				       struct pt_regs *regs,
+				       struct kprobe_ctlblk *kcb, int reenter)
+{
+	unsigned long slot;
+
+	if (reenter) {
+		save_previous_kprobe(kcb);
+		set_current_kprobe(p);
+		kcb->kprobe_status = KPROBE_REENTER;
+	} else {
+		kcb->kprobe_status = KPROBE_HIT_SS;
+	}
+
+	if (p->ainsn.api.insn) {
+		/* prepare for single stepping */
+		slot = (unsigned long)p->ainsn.api.insn;
+
+		set_ss_context(kcb, slot, p);	/* mark pending ss */
+
+		/* IRQs and single stepping do not mix well. */
+		kprobes_save_local_irqflag(kcb, regs);
+		regs->sr = (regs->sr & TRACE_MODE_MASK) | TRACE_MODE_SI;
+		instruction_pointer_set(regs, slot);
+	} else {
+		/* insn simulation */
+		arch_simulate_insn(p, regs);
+	}
+}
+
+static int __kprobes reenter_kprobe(struct kprobe *p,
+				    struct pt_regs *regs,
+				    struct kprobe_ctlblk *kcb)
+{
+	switch (kcb->kprobe_status) {
+	case KPROBE_HIT_SSDONE:
+	case KPROBE_HIT_ACTIVE:
+		kprobes_inc_nmissed_count(p);
+		setup_singlestep(p, regs, kcb, 1);
+		break;
+	case KPROBE_HIT_SS:
+	case KPROBE_REENTER:
+		pr_warn("Failed to recover from reentered kprobes.\n");
+		dump_kprobe(p);
+		BUG();
+		break;
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+
+	return 1;
+}
+
+static void __kprobes
+post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs)
+{
+	struct kprobe *cur = kprobe_running();
+
+	if (!cur)
+		return;
+
+	/* return addr restore if non-branching insn */
+	if (cur->ainsn.api.restore != 0)
+		regs->pc = cur->ainsn.api.restore;
+
+	/* restore back original saved kprobe variables and continue */
+	if (kcb->kprobe_status == KPROBE_REENTER) {
+		restore_previous_kprobe(kcb);
+		return;
+	}
+
+	/* call post handler */
+	kcb->kprobe_status = KPROBE_HIT_SSDONE;
+	if (cur->post_handler)	{
+		/* post_handler can hit breakpoint and single step
+		 * again, so we enable D-flag for recursive exception.
+		 */
+		cur->post_handler(cur, regs, 0);
+	}
+
+	reset_current_kprobe();
+}
+
+int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr)
+{
+	struct kprobe *cur = kprobe_running();
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	switch (kcb->kprobe_status) {
+	case KPROBE_HIT_SS:
+	case KPROBE_REENTER:
+		/*
+		 * We are here because the instruction being single
+		 * stepped caused a page fault. We reset the current
+		 * kprobe and the ip points back to the probe address
+		 * and allow the page fault handler to continue as a
+		 * normal page fault.
+		 */
+		regs->pc = (unsigned long) cur->addr;
+		BUG_ON(!instruction_pointer(regs));
+
+		if (kcb->kprobe_status == KPROBE_REENTER)
+			restore_previous_kprobe(kcb);
+		else
+			reset_current_kprobe();
+
+		break;
+	case KPROBE_HIT_ACTIVE:
+	case KPROBE_HIT_SSDONE:
+		/*
+		 * In case the user-specified fault handler returned
+		 * zero, try to fix up.
+		 */
+		if (fixup_exception(regs))
+			return 1;
+	}
+	return 0;
+}
+
+int __kprobes
+kprobe_breakpoint_handler(struct pt_regs *regs)
+{
+	struct kprobe *p, *cur_kprobe;
+	struct kprobe_ctlblk *kcb;
+	unsigned long addr = instruction_pointer(regs);
+
+	kcb = get_kprobe_ctlblk();
+	cur_kprobe = kprobe_running();
+
+	p = get_kprobe((kprobe_opcode_t *) addr);
+
+	if (p) {
+		if (cur_kprobe) {
+			if (reenter_kprobe(p, regs, kcb))
+				return 1;
+		} else {
+			/* Probe hit */
+			set_current_kprobe(p);
+			kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+
+			/*
+			 * If we have no pre-handler or it returned 0, we
+			 * continue with normal processing.  If we have a
+			 * pre-handler and it returned non-zero, it will
+			 * modify the execution path and no need to single
+			 * stepping. Let's just reset current kprobe and exit.
+			 *
+			 * pre_handler can hit a breakpoint and can step thru
+			 * before return.
+			 */
+			if (!p->pre_handler || !p->pre_handler(p, regs))
+				setup_singlestep(p, regs, kcb, 0);
+			else
+				reset_current_kprobe();
+		}
+		return 1;
+	}
+
+	/*
+	 * The breakpoint instruction was removed right
+	 * after we hit it.  Another cpu has removed
+	 * either a probepoint or a debugger breakpoint
+	 * at this address.  In either case, no further
+	 * handling of this interrupt is appropriate.
+	 * Return back to original instruction, and continue.
+	 */
+	return 0;
+}
+
+int __kprobes
+kprobe_single_step_handler(struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	if ((kcb->ss_ctx.ss_pending)
+	    && (kcb->ss_ctx.match_addr == instruction_pointer(regs))) {
+		clear_ss_context(kcb);	/* clear pending ss */
+
+		kprobes_restore_local_irqflag(kcb, regs);
+		regs->sr = (regs->sr & TRACE_MODE_MASK) | TRACE_MODE_RUN;
+
+		post_kprobe_handler(kcb, regs);
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * Provide a blacklist of symbols identifying ranges which cannot be kprobed.
+ * This blacklist is exposed to userspace via debugfs (kprobes/blacklist).
+ */
+int __init arch_populate_kprobe_blacklist(void)
+{
+	int ret;
+
+	ret = kprobe_add_area_blacklist((unsigned long)__irqentry_text_start,
+					(unsigned long)__irqentry_text_end);
+	return ret;
+}
+
+void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs)
+{
+	return (void *)kretprobe_trampoline_handler(regs, NULL);
+}
+
+void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
+				      struct pt_regs *regs)
+{
+	ri->ret_addr = (kprobe_opcode_t *)regs->lr;
+	ri->fp = NULL;
+	regs->lr = (unsigned long) &__kretprobe_trampoline;
+}
+
+int __kprobes arch_trampoline_kprobe(struct kprobe *p)
+{
+	return 0;
+}
+
+int __init arch_init_kprobes(void)
+{
+	return 0;
+}
diff --git a/arch/csky/kernel/probes/kprobes_trampoline.S b/arch/csky/kernel/probes/kprobes_trampoline.S
new file mode 100644
index 000000000..ba48ad04a
--- /dev/null
+++ b/arch/csky/kernel/probes/kprobes_trampoline.S
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#include <linux/linkage.h>
+
+#include <abi/entry.h>
+
+ENTRY(__kretprobe_trampoline)
+	SAVE_REGS_FTRACE
+
+	mov	a0, sp /* pt_regs */
+
+	jbsr	trampoline_probe_handler
+
+	/* use the result as the return-address */
+	mov	lr, a0
+
+	RESTORE_REGS_FTRACE
+	rts
+ENDPROC(__kretprobe_trampoline)
diff --git a/arch/csky/kernel/probes/simulate-insn.c b/arch/csky/kernel/probes/simulate-insn.c
new file mode 100644
index 000000000..d6e8d092c
--- /dev/null
+++ b/arch/csky/kernel/probes/simulate-insn.c
@@ -0,0 +1,390 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+
+#include "decode-insn.h"
+#include "simulate-insn.h"
+
+static inline bool csky_insn_reg_get_val(struct pt_regs *regs,
+					 unsigned long index,
+					 unsigned long *ptr)
+{
+	if (index < 14)
+		*ptr = *(&regs->a0 + index);
+
+	if (index > 15 && index < 31)
+		*ptr = *(&regs->exregs[0] + index - 16);
+
+	switch (index) {
+	case 14:
+		*ptr = regs->usp;
+		break;
+	case 15:
+		*ptr = regs->lr;
+		break;
+	case 31:
+		*ptr = regs->tls;
+		break;
+	default:
+		goto fail;
+	}
+
+	return true;
+fail:
+	return false;
+}
+
+static inline bool csky_insn_reg_set_val(struct pt_regs *regs,
+					 unsigned long index,
+					 unsigned long val)
+{
+	if (index < 14)
+		*(&regs->a0 + index) = val;
+
+	if (index > 15 && index < 31)
+		*(&regs->exregs[0] + index - 16) = val;
+
+	switch (index) {
+	case 14:
+		regs->usp = val;
+		break;
+	case 15:
+		regs->lr = val;
+		break;
+	case 31:
+		regs->tls = val;
+		break;
+	default:
+		goto fail;
+	}
+
+	return true;
+fail:
+	return false;
+}
+
+void __kprobes
+simulate_br16(u32 opcode, long addr, struct pt_regs *regs)
+{
+	instruction_pointer_set(regs,
+		addr + sign_extend32((opcode & 0x3ff) << 1, 9));
+}
+
+void __kprobes
+simulate_br32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	instruction_pointer_set(regs,
+		addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+}
+
+void __kprobes
+simulate_bt16(u32 opcode, long addr, struct pt_regs *regs)
+{
+	if (regs->sr & 1)
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0x3ff) << 1, 9));
+	else
+		instruction_pointer_set(regs, addr + 2);
+}
+
+void __kprobes
+simulate_bt32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	if (regs->sr & 1)
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	else
+		instruction_pointer_set(regs, addr + 4);
+}
+
+void __kprobes
+simulate_bf16(u32 opcode, long addr, struct pt_regs *regs)
+{
+	if (!(regs->sr & 1))
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0x3ff) << 1, 9));
+	else
+		instruction_pointer_set(regs, addr + 2);
+}
+
+void __kprobes
+simulate_bf32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	if (!(regs->sr & 1))
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	else
+		instruction_pointer_set(regs, addr + 4);
+}
+
+void __kprobes
+simulate_jmp16(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = (opcode >> 2) & 0xf;
+
+	csky_insn_reg_get_val(regs, tmp, &tmp);
+
+	instruction_pointer_set(regs, tmp & 0xfffffffe);
+}
+
+void __kprobes
+simulate_jmp32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+
+	csky_insn_reg_get_val(regs, tmp, &tmp);
+
+	instruction_pointer_set(regs, tmp & 0xfffffffe);
+}
+
+void __kprobes
+simulate_jsr16(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = (opcode >> 2) & 0xf;
+
+	csky_insn_reg_get_val(regs, tmp, &tmp);
+
+	regs->lr = addr + 2;
+
+	instruction_pointer_set(regs, tmp & 0xfffffffe);
+}
+
+void __kprobes
+simulate_jsr32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+
+	csky_insn_reg_get_val(regs, tmp, &tmp);
+
+	regs->lr = addr + 4;
+
+	instruction_pointer_set(regs, tmp & 0xfffffffe);
+}
+
+void __kprobes
+simulate_lrw16(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long val;
+	unsigned long tmp = (opcode & 0x300) >> 3;
+	unsigned long offset = ((opcode & 0x1f) | tmp) << 2;
+
+	tmp = (opcode & 0xe0) >> 5;
+
+	val = *(unsigned int *)(instruction_pointer(regs) + offset);
+
+	csky_insn_reg_set_val(regs, tmp, val);
+}
+
+void __kprobes
+simulate_lrw32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long val;
+	unsigned long offset = (opcode & 0xffff0000) >> 14;
+	unsigned long tmp = opcode & 0x0000001f;
+
+	val = *(unsigned int *)
+		((instruction_pointer(regs) + offset) & 0xfffffffc);
+
+	csky_insn_reg_set_val(regs, tmp, val);
+}
+
+void __kprobes
+simulate_pop16(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long *tmp = (unsigned long *)regs->usp;
+	int i;
+
+	for (i = 0; i < (opcode & 0xf); i++) {
+		csky_insn_reg_set_val(regs, i + 4, *tmp);
+		tmp += 1;
+	}
+
+	if (opcode & 0x10) {
+		csky_insn_reg_set_val(regs, 15, *tmp);
+		tmp += 1;
+	}
+
+	regs->usp = (unsigned long)tmp;
+
+	instruction_pointer_set(regs, regs->lr);
+}
+
+void __kprobes
+simulate_pop32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long *tmp = (unsigned long *)regs->usp;
+	int i;
+
+	for (i = 0; i < ((opcode & 0xf0000) >> 16); i++) {
+		csky_insn_reg_set_val(regs, i + 4, *tmp);
+		tmp += 1;
+	}
+
+	if (opcode & 0x100000) {
+		csky_insn_reg_set_val(regs, 15, *tmp);
+		tmp += 1;
+	}
+
+	for (i = 0; i < ((opcode & 0xe00000) >> 21); i++) {
+		csky_insn_reg_set_val(regs, i + 16, *tmp);
+		tmp += 1;
+	}
+
+	if (opcode & 0x1000000) {
+		csky_insn_reg_set_val(regs, 29, *tmp);
+		tmp += 1;
+	}
+
+	regs->usp = (unsigned long)tmp;
+
+	instruction_pointer_set(regs, regs->lr);
+}
+
+void __kprobes
+simulate_bez32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+
+	csky_insn_reg_get_val(regs, tmp, &tmp);
+
+	if (tmp == 0) {
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	} else
+		instruction_pointer_set(regs, addr + 4);
+}
+
+void __kprobes
+simulate_bnez32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+
+	csky_insn_reg_get_val(regs, tmp, &tmp);
+
+	if (tmp != 0) {
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	} else
+		instruction_pointer_set(regs, addr + 4);
+}
+
+void __kprobes
+simulate_bnezad32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+	long val;
+
+	csky_insn_reg_get_val(regs, tmp, (unsigned long *)&val);
+
+	val -= 1;
+
+	if (val > 0) {
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	} else
+		instruction_pointer_set(regs, addr + 4);
+
+	csky_insn_reg_set_val(regs, tmp, (unsigned long)val);
+}
+
+void __kprobes
+simulate_bhsz32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+	unsigned long val;
+
+	csky_insn_reg_get_val(regs, tmp, &val);
+
+	if ((long) val >= 0) {
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	} else
+		instruction_pointer_set(regs, addr + 4);
+}
+
+void __kprobes
+simulate_bhz32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+	unsigned long val;
+
+	csky_insn_reg_get_val(regs, tmp, &val);
+
+	if ((long) val > 0) {
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	} else
+		instruction_pointer_set(regs, addr + 4);
+}
+
+void __kprobes
+simulate_blsz32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+	unsigned long val;
+
+	csky_insn_reg_get_val(regs, tmp, &val);
+
+	if ((long) val <= 0) {
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	} else
+		instruction_pointer_set(regs, addr + 4);
+}
+
+void __kprobes
+simulate_blz32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+	unsigned long val;
+
+	csky_insn_reg_get_val(regs, tmp, &val);
+
+	if ((long) val < 0) {
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	} else
+		instruction_pointer_set(regs, addr + 4);
+}
+
+void __kprobes
+simulate_bsr32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp;
+
+	tmp = (opcode & 0xffff) << 16;
+	tmp |= (opcode & 0xffff0000) >> 16;
+
+	instruction_pointer_set(regs,
+		addr + sign_extend32((tmp & 0x3ffffff) << 1, 15));
+
+	regs->lr = addr + 4;
+}
+
+void __kprobes
+simulate_jmpi32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long val;
+	unsigned long offset = ((opcode & 0xffff0000) >> 14);
+
+	val = *(unsigned int *)
+		((instruction_pointer(regs) + offset) & 0xfffffffc);
+
+	instruction_pointer_set(regs, val);
+}
+
+void __kprobes
+simulate_jsri32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long val;
+	unsigned long offset = ((opcode & 0xffff0000) >> 14);
+
+	val = *(unsigned int *)
+		((instruction_pointer(regs) + offset) & 0xfffffffc);
+
+	regs->lr = addr + 4;
+
+	instruction_pointer_set(regs, val);
+}
diff --git a/arch/csky/kernel/probes/simulate-insn.h b/arch/csky/kernel/probes/simulate-insn.h
new file mode 100644
index 000000000..ba4cb7ef0
--- /dev/null
+++ b/arch/csky/kernel/probes/simulate-insn.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef __CSKY_KERNEL_PROBES_SIMULATE_INSN_H
+#define __CSKY_KERNEL_PROBES_SIMULATE_INSN_H
+
+#define __CSKY_INSN_FUNCS(name, mask, val)				\
+static __always_inline bool csky_insn_is_##name(probe_opcode_t code)	\
+{									\
+	BUILD_BUG_ON(~(mask) & (val));					\
+	return (code & (mask)) == (val);				\
+}									\
+void simulate_##name(u32 opcode, long addr, struct pt_regs *regs);
+
+#define CSKY_INSN_SET_SIMULATE(name, code)				\
+	do {								\
+		if (csky_insn_is_##name(code)) {			\
+			api->handler = simulate_##name;			\
+			return INSN_GOOD_NO_SLOT;			\
+		}							\
+	} while (0)
+
+__CSKY_INSN_FUNCS(br16,		0xfc00, 0x0400)
+__CSKY_INSN_FUNCS(bt16,		0xfc00, 0x0800)
+__CSKY_INSN_FUNCS(bf16,		0xfc00, 0x0c00)
+__CSKY_INSN_FUNCS(jmp16,	0xffc3, 0x7800)
+__CSKY_INSN_FUNCS(jsr16,	0xffc3, 0x7801)
+__CSKY_INSN_FUNCS(lrw16,	0xfc00, 0x1000)
+__CSKY_INSN_FUNCS(pop16,	0xffe0, 0x1480)
+
+__CSKY_INSN_FUNCS(br32,		0x0000ffff, 0x0000e800)
+__CSKY_INSN_FUNCS(bt32,		0x0000ffff, 0x0000e860)
+__CSKY_INSN_FUNCS(bf32,		0x0000ffff, 0x0000e840)
+__CSKY_INSN_FUNCS(jmp32,	0xffffffe0, 0x0000e8c0)
+__CSKY_INSN_FUNCS(jsr32,	0xffffffe0, 0x0000e8e0)
+__CSKY_INSN_FUNCS(lrw32,	0x0000ffe0, 0x0000ea80)
+__CSKY_INSN_FUNCS(pop32,	0xfe00ffff, 0x0000ebc0)
+
+__CSKY_INSN_FUNCS(bez32,	0x0000ffe0, 0x0000e900)
+__CSKY_INSN_FUNCS(bnez32,	0x0000ffe0, 0x0000e920)
+__CSKY_INSN_FUNCS(bnezad32,	0x0000ffe0, 0x0000e820)
+__CSKY_INSN_FUNCS(bhsz32,	0x0000ffe0, 0x0000e9a0)
+__CSKY_INSN_FUNCS(bhz32,	0x0000ffe0, 0x0000e940)
+__CSKY_INSN_FUNCS(blsz32,	0x0000ffe0, 0x0000e960)
+__CSKY_INSN_FUNCS(blz32,	0x0000ffe0, 0x0000e980)
+__CSKY_INSN_FUNCS(bsr32,	0x0000fc00, 0x0000e000)
+__CSKY_INSN_FUNCS(jmpi32,	0x0000ffff, 0x0000eac0)
+__CSKY_INSN_FUNCS(jsri32,	0x0000ffff, 0x0000eae0)
+
+#endif /* __CSKY_KERNEL_PROBES_SIMULATE_INSN_H */
diff --git a/arch/csky/kernel/probes/uprobes.c b/arch/csky/kernel/probes/uprobes.c
new file mode 100644
index 000000000..936bea6fd
--- /dev/null
+++ b/arch/csky/kernel/probes/uprobes.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2014-2016 Pratyush Anand <panand@redhat.com>
+ */
+#include <linux/highmem.h>
+#include <linux/ptrace.h>
+#include <linux/uprobes.h>
+#include <asm/cacheflush.h>
+
+#include "decode-insn.h"
+
+#define UPROBE_TRAP_NR	UINT_MAX
+
+bool is_swbp_insn(uprobe_opcode_t *insn)
+{
+	return (*insn & 0xffff) == UPROBE_SWBP_INSN;
+}
+
+unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
+{
+	return instruction_pointer(regs);
+}
+
+int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
+		unsigned long addr)
+{
+	probe_opcode_t insn;
+
+	insn = *(probe_opcode_t *)(&auprobe->insn[0]);
+
+	auprobe->insn_size = is_insn32(insn) ? 4 : 2;
+
+	switch (csky_probe_decode_insn(&insn, &auprobe->api)) {
+	case INSN_REJECTED:
+		return -EINVAL;
+
+	case INSN_GOOD_NO_SLOT:
+		auprobe->simulate = true;
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	utask->autask.saved_trap_no = current->thread.trap_no;
+	current->thread.trap_no = UPROBE_TRAP_NR;
+
+	instruction_pointer_set(regs, utask->xol_vaddr);
+
+	user_enable_single_step(current);
+
+	return 0;
+}
+
+int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	WARN_ON_ONCE(current->thread.trap_no != UPROBE_TRAP_NR);
+	current->thread.trap_no = utask->autask.saved_trap_no;
+
+	instruction_pointer_set(regs, utask->vaddr + auprobe->insn_size);
+
+	user_disable_single_step(current);
+
+	return 0;
+}
+
+bool arch_uprobe_xol_was_trapped(struct task_struct *t)
+{
+	if (t->thread.trap_no != UPROBE_TRAP_NR)
+		return true;
+
+	return false;
+}
+
+bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	probe_opcode_t insn;
+	unsigned long addr;
+
+	if (!auprobe->simulate)
+		return false;
+
+	insn = *(probe_opcode_t *)(&auprobe->insn[0]);
+	addr = instruction_pointer(regs);
+
+	if (auprobe->api.handler)
+		auprobe->api.handler(insn, addr, regs);
+
+	return true;
+}
+
+void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	current->thread.trap_no = utask->autask.saved_trap_no;
+
+	/*
+	 * Task has received a fatal signal, so reset back to probed
+	 * address.
+	 */
+	instruction_pointer_set(regs, utask->vaddr);
+
+	user_disable_single_step(current);
+}
+
+bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
+		struct pt_regs *regs)
+{
+	if (ctx == RP_CHECK_CHAIN_CALL)
+		return regs->usp <= ret->stack;
+	else
+		return regs->usp < ret->stack;
+}
+
+unsigned long
+arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr,
+				  struct pt_regs *regs)
+{
+	unsigned long ra;
+
+	ra = regs->lr;
+
+	regs->lr = trampoline_vaddr;
+
+	return ra;
+}
+
+int arch_uprobe_exception_notify(struct notifier_block *self,
+				 unsigned long val, void *data)
+{
+	return NOTIFY_DONE;
+}
+
+int uprobe_breakpoint_handler(struct pt_regs *regs)
+{
+	if (uprobe_pre_sstep_notifier(regs))
+		return 1;
+
+	return 0;
+}
+
+int uprobe_single_step_handler(struct pt_regs *regs)
+{
+	if (uprobe_post_sstep_notifier(regs))
+		return 1;
+
+	return 0;
+}
diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c
new file mode 100644
index 000000000..a7a903400
--- /dev/null
+++ b/arch/csky/kernel/process.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/sched/debug.h>
+#include <linux/delay.h>
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/ptrace.h>
+#include <linux/elfcore.h>
+
+#include <asm/elf.h>
+#include <abi/reg_ops.h>
+
+struct cpuinfo_csky cpu_data[NR_CPUS];
+
+#ifdef CONFIG_STACKPROTECTOR
+#include <linux/stackprotector.h>
+unsigned long __stack_chk_guard __read_mostly;
+EXPORT_SYMBOL(__stack_chk_guard);
+#endif
+
+asmlinkage void ret_from_fork(void);
+asmlinkage void ret_from_kernel_thread(void);
+
+/*
+ * Some archs flush debug and FPU info here
+ */
+void flush_thread(void){}
+
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
+{
+	u64 clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long tls = args->tls;
+	struct switch_stack *childstack;
+	struct pt_regs *childregs = task_pt_regs(p);
+
+#ifdef CONFIG_CPU_HAS_FPU
+	save_to_user_fp(&p->thread.user_fp);
+#endif
+
+	childstack = ((struct switch_stack *) childregs) - 1;
+	memset(childstack, 0, sizeof(struct switch_stack));
+
+	/* setup thread.sp for switch_to !!! */
+	p->thread.sp = (unsigned long)childstack;
+
+	if (unlikely(args->fn)) {
+		memset(childregs, 0, sizeof(struct pt_regs));
+		childstack->r15 = (unsigned long) ret_from_kernel_thread;
+		childstack->r10 = (unsigned long) args->fn_arg;
+		childstack->r9 = (unsigned long) args->fn;
+		childregs->sr = mfcr("psr");
+	} else {
+		*childregs = *(current_pt_regs());
+		if (usp)
+			childregs->usp = usp;
+		if (clone_flags & CLONE_SETTLS)
+			task_thread_info(p)->tp_value = childregs->tls
+						      = tls;
+
+		childregs->a0 = 0;
+		childstack->r15 = (unsigned long) ret_from_fork;
+	}
+
+	return 0;
+}
+
+/* Fill in the fpu structure for a core dump.  */
+int elf_core_copy_task_fpregs(struct task_struct *t, elf_fpregset_t *fpu)
+{
+	memcpy(fpu, &current->thread.user_fp, sizeof(*fpu));
+	return 1;
+}
+
+int dump_task_regs(struct task_struct *tsk, elf_gregset_t *pr_regs)
+{
+	struct pt_regs *regs = task_pt_regs(tsk);
+
+	/* NOTE: usp is error value. */
+	ELF_CORE_COPY_REGS((*pr_regs), regs)
+
+	return 1;
+}
+
+#ifndef CONFIG_CPU_PM_NONE
+void arch_cpu_idle(void)
+{
+#ifdef CONFIG_CPU_PM_WAIT
+	asm volatile("wait\n");
+#endif
+
+#ifdef CONFIG_CPU_PM_DOZE
+	asm volatile("doze\n");
+#endif
+
+#ifdef CONFIG_CPU_PM_STOP
+	asm volatile("stop\n");
+#endif
+}
+#endif
diff --git a/arch/csky/kernel/ptrace.c b/arch/csky/kernel/ptrace.c
new file mode 100644
index 000000000..ee2867a15
--- /dev/null
+++ b/arch/csky/kernel/ptrace.c
@@ -0,0 +1,521 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/audit.h>
+#include <linux/elf.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/ptrace.h>
+#include <linux/regset.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/signal.h>
+#include <linux/smp.h>
+#include <linux/uaccess.h>
+#include <linux/user.h>
+
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include <asm/processor.h>
+#include <asm/asm-offsets.h>
+
+#include <abi/regdef.h>
+#include <abi/ckmmu.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+/* sets the trace bits. */
+#define TRACE_MODE_SI      (1 << 14)
+#define TRACE_MODE_RUN     0
+#define TRACE_MODE_MASK    ~(0x3 << 14)
+
+/*
+ * Make sure the single step bit is not set.
+ */
+static void singlestep_disable(struct task_struct *tsk)
+{
+	struct pt_regs *regs;
+
+	regs = task_pt_regs(tsk);
+	regs->sr = (regs->sr & TRACE_MODE_MASK) | TRACE_MODE_RUN;
+
+	/* Enable irq */
+	regs->sr |= BIT(6);
+}
+
+static void singlestep_enable(struct task_struct *tsk)
+{
+	struct pt_regs *regs;
+
+	regs = task_pt_regs(tsk);
+	regs->sr = (regs->sr & TRACE_MODE_MASK) | TRACE_MODE_SI;
+
+	/* Disable irq */
+	regs->sr &= ~BIT(6);
+}
+
+/*
+ * Make sure the single step bit is set.
+ */
+void user_enable_single_step(struct task_struct *child)
+{
+	singlestep_enable(child);
+}
+
+void user_disable_single_step(struct task_struct *child)
+{
+	singlestep_disable(child);
+}
+
+enum csky_regset {
+	REGSET_GPR,
+	REGSET_FPR,
+};
+
+static int gpr_get(struct task_struct *target,
+		   const struct user_regset *regset,
+		   struct membuf to)
+{
+	struct pt_regs *regs = task_pt_regs(target);
+
+	/* Abiv1 regs->tls is fake and we need sync here. */
+	regs->tls = task_thread_info(target)->tp_value;
+
+	return membuf_write(&to, regs, sizeof(*regs));
+}
+
+static int gpr_set(struct task_struct *target,
+		    const struct user_regset *regset,
+		    unsigned int pos, unsigned int count,
+		    const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+	struct pt_regs regs;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &regs, 0, -1);
+	if (ret)
+		return ret;
+
+	/* BIT(0) of regs.sr is Condition Code/Carry bit */
+	regs.sr = (regs.sr & BIT(0)) | (task_pt_regs(target)->sr & ~BIT(0));
+#ifdef CONFIG_CPU_HAS_HILO
+	regs.dcsr = task_pt_regs(target)->dcsr;
+#endif
+	task_thread_info(target)->tp_value = regs.tls;
+
+	*task_pt_regs(target) = regs;
+
+	return 0;
+}
+
+static int fpr_get(struct task_struct *target,
+		   const struct user_regset *regset,
+		   struct membuf to)
+{
+	struct user_fp *regs = (struct user_fp *)&target->thread.user_fp;
+
+#if defined(CONFIG_CPU_HAS_FPUV2) && !defined(CONFIG_CPU_HAS_VDSP)
+	int i;
+	struct user_fp tmp = *regs;
+
+	for (i = 0; i < 16; i++) {
+		tmp.vr[i*4] = regs->vr[i*2];
+		tmp.vr[i*4 + 1] = regs->vr[i*2 + 1];
+	}
+
+	for (i = 0; i < 32; i++)
+		tmp.vr[64 + i] = regs->vr[32 + i];
+
+	return membuf_write(&to, &tmp, sizeof(tmp));
+#else
+	return membuf_write(&to, regs, sizeof(*regs));
+#endif
+}
+
+static int fpr_set(struct task_struct *target,
+		   const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+	struct user_fp *regs = (struct user_fp *)&target->thread.user_fp;
+
+#if defined(CONFIG_CPU_HAS_FPUV2) && !defined(CONFIG_CPU_HAS_VDSP)
+	int i;
+	struct user_fp tmp;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tmp, 0, -1);
+
+	*regs = tmp;
+
+	for (i = 0; i < 16; i++) {
+		regs->vr[i*2] = tmp.vr[i*4];
+		regs->vr[i*2 + 1] = tmp.vr[i*4 + 1];
+	}
+
+	for (i = 0; i < 32; i++)
+		regs->vr[32 + i] = tmp.vr[64 + i];
+#else
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
+#endif
+
+	return ret;
+}
+
+static const struct user_regset csky_regsets[] = {
+	[REGSET_GPR] = {
+		USER_REGSET_NOTE_TYPE(PRSTATUS),
+		.n = sizeof(struct pt_regs) / sizeof(u32),
+		.size = sizeof(u32),
+		.align = sizeof(u32),
+		.regset_get = gpr_get,
+		.set = gpr_set,
+	},
+	[REGSET_FPR] = {
+		USER_REGSET_NOTE_TYPE(PRFPREG),
+		.n = sizeof(struct user_fp) / sizeof(u32),
+		.size = sizeof(u32),
+		.align = sizeof(u32),
+		.regset_get = fpr_get,
+		.set = fpr_set,
+	},
+};
+
+static const struct user_regset_view user_csky_view = {
+	.name = "csky",
+	.e_machine = ELF_ARCH,
+	.regsets = csky_regsets,
+	.n = ARRAY_SIZE(csky_regsets),
+};
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+	return &user_csky_view;
+}
+
+struct pt_regs_offset {
+	const char *name;
+	int offset;
+};
+
+#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+static const struct pt_regs_offset regoffset_table[] = {
+	REG_OFFSET_NAME(tls),
+	REG_OFFSET_NAME(lr),
+	REG_OFFSET_NAME(pc),
+	REG_OFFSET_NAME(sr),
+	REG_OFFSET_NAME(usp),
+	REG_OFFSET_NAME(orig_a0),
+	REG_OFFSET_NAME(a0),
+	REG_OFFSET_NAME(a1),
+	REG_OFFSET_NAME(a2),
+	REG_OFFSET_NAME(a3),
+	REG_OFFSET_NAME(regs[0]),
+	REG_OFFSET_NAME(regs[1]),
+	REG_OFFSET_NAME(regs[2]),
+	REG_OFFSET_NAME(regs[3]),
+	REG_OFFSET_NAME(regs[4]),
+	REG_OFFSET_NAME(regs[5]),
+	REG_OFFSET_NAME(regs[6]),
+	REG_OFFSET_NAME(regs[7]),
+	REG_OFFSET_NAME(regs[8]),
+	REG_OFFSET_NAME(regs[9]),
+#if defined(__CSKYABIV2__)
+	REG_OFFSET_NAME(exregs[0]),
+	REG_OFFSET_NAME(exregs[1]),
+	REG_OFFSET_NAME(exregs[2]),
+	REG_OFFSET_NAME(exregs[3]),
+	REG_OFFSET_NAME(exregs[4]),
+	REG_OFFSET_NAME(exregs[5]),
+	REG_OFFSET_NAME(exregs[6]),
+	REG_OFFSET_NAME(exregs[7]),
+	REG_OFFSET_NAME(exregs[8]),
+	REG_OFFSET_NAME(exregs[9]),
+	REG_OFFSET_NAME(exregs[10]),
+	REG_OFFSET_NAME(exregs[11]),
+	REG_OFFSET_NAME(exregs[12]),
+	REG_OFFSET_NAME(exregs[13]),
+	REG_OFFSET_NAME(exregs[14]),
+	REG_OFFSET_NAME(rhi),
+	REG_OFFSET_NAME(rlo),
+	REG_OFFSET_NAME(dcsr),
+#endif
+	REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name:	the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_offset *roff;
+
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->offset;
+	return -EINVAL;
+}
+
+/**
+ * regs_within_kernel_stack() - check the address in the stack
+ * @regs:      pt_regs which contains kernel stack pointer.
+ * @addr:      address which is checked.
+ *
+ * regs_within_kernel_stack() checks @addr is within the kernel stack page(s).
+ * If @addr is within the kernel stack, it returns true. If not, returns false.
+ */
+static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
+{
+	return (addr & ~(THREAD_SIZE - 1))  ==
+		(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1));
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs:	pt_regs which contains kernel stack pointer.
+ * @n:		stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
+{
+	unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
+
+	addr += n;
+	if (regs_within_kernel_stack(regs, (unsigned long)addr))
+		return *addr;
+	else
+		return 0;
+}
+
+void ptrace_disable(struct task_struct *child)
+{
+	singlestep_disable(child);
+}
+
+long arch_ptrace(struct task_struct *child, long request,
+		 unsigned long addr, unsigned long data)
+{
+	long ret = -EIO;
+
+	switch (request) {
+	default:
+		ret = ptrace_request(child, request, addr, data);
+		break;
+	}
+
+	return ret;
+}
+
+asmlinkage int syscall_trace_enter(struct pt_regs *regs)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		if (!ptrace_report_syscall_permit_entry(regs))
+			return -1;
+
+	if (!seccomp_permit_syscall())
+		return -1;
+
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_enter(regs, syscall_get_nr(current, regs));
+
+	audit_syscall_entry(regs_syscallid(regs), regs->a0, regs->a1, regs->a2, regs->a3);
+	return 0;
+}
+
+asmlinkage void syscall_trace_exit(struct pt_regs *regs)
+{
+	audit_syscall_exit(regs);
+
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		ptrace_report_syscall_exit(regs, 0);
+
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_exit(regs, syscall_get_return_value(current, regs));
+}
+
+#ifdef CONFIG_CPU_CK860
+static void show_iutlb(void)
+{
+	int entry, i;
+	unsigned long flags;
+	unsigned long oldpid;
+	unsigned long entryhi[16], entrylo0[16], entrylo1[16];
+
+	oldpid = read_mmu_entryhi();
+
+	entry = 0x8000;
+
+	local_irq_save(flags);
+
+	for (i = 0; i < 16; i++) {
+		write_mmu_index(entry);
+		tlb_read();
+		entryhi[i]  = read_mmu_entryhi();
+		entrylo0[i] = read_mmu_entrylo0();
+		entrylo1[i] = read_mmu_entrylo1();
+
+		entry++;
+	}
+
+	local_irq_restore(flags);
+
+	write_mmu_entryhi(oldpid);
+
+	printk("\n\n\n");
+	for (i = 0; i < 16; i++)
+		printk("iutlb[%d]:	entryhi - 0x%lx;	entrylo0 - 0x%lx;"
+		       "	entrylo1 - 0x%lx\n",
+			 i, entryhi[i], entrylo0[i], entrylo1[i]);
+	printk("\n\n\n");
+}
+
+static void show_dutlb(void)
+{
+	int entry, i;
+	unsigned long flags;
+	unsigned long oldpid;
+	unsigned long entryhi[16], entrylo0[16], entrylo1[16];
+
+	oldpid = read_mmu_entryhi();
+
+	entry = 0x4000;
+
+	local_irq_save(flags);
+
+	for (i = 0; i < 16; i++) {
+		write_mmu_index(entry);
+		tlb_read();
+		entryhi[i]  = read_mmu_entryhi();
+		entrylo0[i] = read_mmu_entrylo0();
+		entrylo1[i] = read_mmu_entrylo1();
+
+		entry++;
+	}
+
+	local_irq_restore(flags);
+
+	write_mmu_entryhi(oldpid);
+
+	printk("\n\n\n");
+	for (i = 0; i < 16; i++)
+		printk("dutlb[%d]:	entryhi - 0x%lx;	entrylo0 - 0x%lx;"
+		       "	entrylo1 - 0x%lx\n",
+			 i, entryhi[i], entrylo0[i], entrylo1[i]);
+	printk("\n\n\n");
+}
+
+static unsigned long entryhi[1024], entrylo0[1024], entrylo1[1024];
+static void show_jtlb(void)
+{
+	int entry;
+	unsigned long flags;
+	unsigned long oldpid;
+
+	oldpid = read_mmu_entryhi();
+
+	entry = 0;
+
+	local_irq_save(flags);
+	while (entry < 1024) {
+		write_mmu_index(entry);
+		tlb_read();
+		entryhi[entry]  = read_mmu_entryhi();
+		entrylo0[entry] = read_mmu_entrylo0();
+		entrylo1[entry] = read_mmu_entrylo1();
+
+		entry++;
+	}
+	local_irq_restore(flags);
+
+	write_mmu_entryhi(oldpid);
+
+	printk("\n\n\n");
+
+	for (entry = 0; entry < 1024; entry++)
+		printk("jtlb[%x]:	entryhi - 0x%lx;	entrylo0 - 0x%lx;"
+		       "	entrylo1 - 0x%lx\n",
+			 entry, entryhi[entry], entrylo0[entry], entrylo1[entry]);
+	printk("\n\n\n");
+}
+
+static void show_tlb(void)
+{
+	show_iutlb();
+	show_dutlb();
+	show_jtlb();
+}
+#else
+static void show_tlb(void)
+{
+	return;
+}
+#endif
+
+void show_regs(struct pt_regs *fp)
+{
+	pr_info("\nCURRENT PROCESS:\n\n");
+	pr_info("COMM=%s PID=%d\n", current->comm, current->pid);
+
+	if (current->mm) {
+		pr_info("TEXT=%08x-%08x DATA=%08x-%08x BSS=%08x-%08x\n",
+		       (int) current->mm->start_code,
+		       (int) current->mm->end_code,
+		       (int) current->mm->start_data,
+		       (int) current->mm->end_data,
+		       (int) current->mm->end_data,
+		       (int) current->mm->brk);
+		pr_info("USER-STACK=%08x  KERNEL-STACK=%08x\n\n",
+		       (int) current->mm->start_stack,
+		       (int) (((unsigned long) current) + 2 * PAGE_SIZE));
+	}
+
+	pr_info("PC: 0x%08lx (%pS)\n", (long)fp->pc, (void *)fp->pc);
+	pr_info("LR: 0x%08lx (%pS)\n", (long)fp->lr, (void *)fp->lr);
+	pr_info("SP: 0x%08lx\n", (long)fp->usp);
+	pr_info("PSR: 0x%08lx\n", (long)fp->sr);
+	pr_info("orig_a0: 0x%08lx\n", fp->orig_a0);
+	pr_info("PT_REGS: 0x%08lx\n", (long)fp);
+
+	pr_info(" a0: 0x%08lx   a1: 0x%08lx   a2: 0x%08lx   a3: 0x%08lx\n",
+		fp->a0, fp->a1, fp->a2, fp->a3);
+#if defined(__CSKYABIV2__)
+	pr_info(" r4: 0x%08lx   r5: 0x%08lx   r6: 0x%08lx   r7: 0x%08lx\n",
+		fp->regs[0], fp->regs[1], fp->regs[2], fp->regs[3]);
+	pr_info(" r8: 0x%08lx   r9: 0x%08lx  r10: 0x%08lx  r11: 0x%08lx\n",
+		fp->regs[4], fp->regs[5], fp->regs[6], fp->regs[7]);
+	pr_info("r12: 0x%08lx  r13: 0x%08lx  r15: 0x%08lx\n",
+		fp->regs[8], fp->regs[9], fp->lr);
+	pr_info("r16: 0x%08lx  r17: 0x%08lx  r18: 0x%08lx  r19: 0x%08lx\n",
+		fp->exregs[0], fp->exregs[1], fp->exregs[2], fp->exregs[3]);
+	pr_info("r20: 0x%08lx  r21: 0x%08lx  r22: 0x%08lx  r23: 0x%08lx\n",
+		fp->exregs[4], fp->exregs[5], fp->exregs[6], fp->exregs[7]);
+	pr_info("r24: 0x%08lx  r25: 0x%08lx  r26: 0x%08lx  r27: 0x%08lx\n",
+		fp->exregs[8], fp->exregs[9], fp->exregs[10], fp->exregs[11]);
+	pr_info("r28: 0x%08lx  r29: 0x%08lx  r30: 0x%08lx  tls: 0x%08lx\n",
+		fp->exregs[12], fp->exregs[13], fp->exregs[14], fp->tls);
+	pr_info(" hi: 0x%08lx   lo: 0x%08lx\n",
+		fp->rhi, fp->rlo);
+#else
+	pr_info(" r6: 0x%08lx   r7: 0x%08lx   r8: 0x%08lx   r9: 0x%08lx\n",
+		fp->regs[0], fp->regs[1], fp->regs[2], fp->regs[3]);
+	pr_info("r10: 0x%08lx  r11: 0x%08lx  r12: 0x%08lx  r13: 0x%08lx\n",
+		fp->regs[4], fp->regs[5], fp->regs[6], fp->regs[7]);
+	pr_info("r14: 0x%08lx   r1: 0x%08lx\n",
+		fp->regs[8], fp->regs[9]);
+#endif
+
+	show_tlb();
+
+	return;
+}
diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c
new file mode 100644
index 000000000..45c98dcf7
--- /dev/null
+++ b/arch/csky/kernel/setup.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/console.h>
+#include <linux/memblock.h>
+#include <linux/initrd.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/start_kernel.h>
+#include <linux/dma-map-ops.h>
+#include <asm/sections.h>
+#include <asm/mmu_context.h>
+#include <asm/pgalloc.h>
+
+#ifdef CONFIG_BLK_DEV_INITRD
+static void __init setup_initrd(void)
+{
+	unsigned long size;
+
+	if (initrd_start >= initrd_end) {
+		pr_err("initrd not found or empty");
+		goto disable;
+	}
+
+	if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) {
+		pr_err("initrd extends beyond end of memory");
+		goto disable;
+	}
+
+	size = initrd_end - initrd_start;
+
+	if (memblock_is_region_reserved(__pa(initrd_start), size)) {
+		pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region",
+		       __pa(initrd_start), size);
+		goto disable;
+	}
+
+	memblock_reserve(__pa(initrd_start), size);
+
+	pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n",
+		(void *)(initrd_start), size);
+
+	initrd_below_start_ok = 1;
+
+	return;
+
+disable:
+	initrd_start = initrd_end = 0;
+
+	pr_err(" - disabling initrd\n");
+}
+#endif
+
+void __init arch_zone_limits_init(unsigned long *max_zone_pfns)
+{
+	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
+#ifdef CONFIG_HIGHMEM
+	max_zone_pfns[ZONE_HIGHMEM] = max_pfn;
+#endif
+}
+
+static void __init csky_memblock_init(void)
+{
+	unsigned long lowmem_size = PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET);
+	unsigned long sseg_size = PFN_DOWN(SSEG_SIZE - PHYS_OFFSET_OFFSET);
+	signed long size;
+
+	memblock_reserve(__pa(_start), _end - _start);
+
+	early_init_fdt_reserve_self();
+	early_init_fdt_scan_reserved_mem();
+
+	memblock_dump_all();
+
+	min_low_pfn = PFN_UP(memblock_start_of_DRAM());
+	max_low_pfn = max_pfn = PFN_DOWN(memblock_end_of_DRAM());
+
+	size = max_pfn - min_low_pfn;
+
+	if (size >= lowmem_size) {
+		max_low_pfn = min_low_pfn + lowmem_size;
+#ifdef CONFIG_PAGE_OFFSET_80000000
+		write_mmu_msa1(read_mmu_msa0() + SSEG_SIZE);
+#endif
+	} else if (size > sseg_size) {
+		max_low_pfn = min_low_pfn + sseg_size;
+	}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	setup_initrd();
+#endif
+
+	mmu_init(min_low_pfn, max_low_pfn);
+
+#ifdef CONFIG_HIGHMEM
+
+	highstart_pfn = max_low_pfn;
+	highend_pfn   = max_pfn;
+#endif
+	memblock_set_current_limit(PFN_PHYS(max_low_pfn));
+
+	dma_contiguous_reserve(0);
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+	*cmdline_p = boot_command_line;
+
+	console_verbose();
+
+	pr_info("Phys. mem: %ldMB\n",
+		(unsigned long) memblock_phys_mem_size()/1024/1024);
+
+	setup_initial_init_mm(_start, _etext, _edata, _end);
+
+	parse_early_param();
+
+	csky_memblock_init();
+
+	unflatten_and_copy_device_tree();
+
+#ifdef CONFIG_SMP
+	setup_smp();
+#endif
+
+	fixaddr_init();
+
+#ifdef CONFIG_HIGHMEM
+	kmap_init();
+#endif
+}
+
+unsigned long va_pa_offset;
+EXPORT_SYMBOL(va_pa_offset);
+
+static inline unsigned long read_mmu_msa(void)
+{
+#ifdef CONFIG_PAGE_OFFSET_80000000
+	return read_mmu_msa0();
+#endif
+
+#ifdef CONFIG_PAGE_OFFSET_A0000000
+	return read_mmu_msa1();
+#endif
+}
+
+asmlinkage __visible void __init csky_start(unsigned int unused,
+					    void *dtb_start)
+{
+	/* Clean up bss section */
+	memset(__bss_start, 0, __bss_stop - __bss_start);
+
+	va_pa_offset = read_mmu_msa() & ~(SSEG_SIZE - 1);
+
+	pre_trap_init();
+
+	if (dtb_start == NULL)
+		early_init_dt_scan(__dtb_start, __pa(dtb_start));
+	else
+		early_init_dt_scan(dtb_start, __pa(dtb_start));
+
+	start_kernel();
+
+	asm volatile("br .\n");
+}
diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c
new file mode 100644
index 000000000..10da0fefd
--- /dev/null
+++ b/arch/csky/kernel/signal.c
@@ -0,0 +1,267 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/signal.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/resume_user_mode.h>
+
+#include <asm/traps.h>
+#include <asm/ucontext.h>
+#include <asm/vdso.h>
+
+#include <abi/regdef.h>
+
+#ifdef CONFIG_CPU_HAS_FPU
+#include <abi/fpu.h>
+static int restore_fpu_state(struct sigcontext __user *sc)
+{
+	int err = 0;
+	struct user_fp user_fp;
+
+	err = __copy_from_user(&user_fp, &sc->sc_user_fp, sizeof(user_fp));
+
+	restore_from_user_fp(&user_fp);
+
+	return err;
+}
+
+static int save_fpu_state(struct sigcontext __user *sc)
+{
+	struct user_fp user_fp;
+
+	save_to_user_fp(&user_fp);
+
+	return __copy_to_user(&sc->sc_user_fp, &user_fp, sizeof(user_fp));
+}
+#else
+#define restore_fpu_state(sigcontext)	(0)
+#define save_fpu_state(sigcontext)	(0)
+#endif
+
+struct rt_sigframe {
+	/*
+	 * pad[3] is compatible with the same struct defined in
+	 * gcc/libgcc/config/csky/linux-unwind.h
+	 */
+	int pad[3];
+	struct siginfo info;
+	struct ucontext uc;
+};
+
+static long restore_sigcontext(struct pt_regs *regs,
+	struct sigcontext __user *sc)
+{
+	int err = 0;
+	unsigned long sr = regs->sr;
+
+	/* sc_pt_regs is structured the same as the start of pt_regs */
+	err |= __copy_from_user(regs, &sc->sc_pt_regs, sizeof(struct pt_regs));
+
+	/* BIT(0) of regs->sr is Condition Code/Carry bit */
+	regs->sr = (sr & ~1) | (regs->sr & 1);
+
+	/* Restore the floating-point state. */
+	err |= restore_fpu_state(sc);
+
+	return err;
+}
+
+SYSCALL_DEFINE0(rt_sigreturn)
+{
+	struct pt_regs *regs = current_pt_regs();
+	struct rt_sigframe __user *frame;
+	sigset_t set;
+
+	/* Always make any pending restarted system calls return -EINTR */
+	current->restart_block.fn = do_no_restart_syscall;
+
+	frame = (struct rt_sigframe __user *)regs->usp;
+
+	if (!access_ok(frame, sizeof(*frame)))
+		goto badframe;
+
+	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+		goto badframe;
+
+	set_current_blocked(&set);
+
+	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
+		goto badframe;
+
+	if (restore_altstack(&frame->uc.uc_stack))
+		goto badframe;
+
+	return regs->a0;
+
+badframe:
+	force_sig(SIGSEGV);
+	return 0;
+}
+
+static int setup_sigcontext(struct rt_sigframe __user *frame,
+	struct pt_regs *regs)
+{
+	struct sigcontext __user *sc = &frame->uc.uc_mcontext;
+	int err = 0;
+
+	err |= __copy_to_user(&sc->sc_pt_regs, regs, sizeof(struct pt_regs));
+	err |= save_fpu_state(sc);
+
+	return err;
+}
+
+static inline void __user *get_sigframe(struct ksignal *ksig,
+	struct pt_regs *regs, size_t framesize)
+{
+	unsigned long sp;
+	/* Default to using normal stack */
+	sp = regs->usp;
+
+	/*
+	 * If we are on the alternate signal stack and would overflow it, don't.
+	 * Return an always-bogus address instead so we will die with SIGSEGV.
+	 */
+	if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize)))
+		return (void __user __force *)(-1UL);
+
+	/* This is the X/Open sanctioned signal stack switching. */
+	sp = sigsp(sp, ksig) - framesize;
+
+	/* Align the stack frame. */
+	sp &= -8UL;
+
+	return (void __user *)sp;
+}
+
+static int
+setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs)
+{
+	struct rt_sigframe __user *frame;
+	int err = 0;
+
+	frame = get_sigframe(ksig, regs, sizeof(*frame));
+	if (!access_ok(frame, sizeof(*frame)))
+		return -EFAULT;
+
+	err |= copy_siginfo_to_user(&frame->info, &ksig->info);
+
+	/* Create the ucontext. */
+	err |= __put_user(0, &frame->uc.uc_flags);
+	err |= __put_user(NULL, &frame->uc.uc_link);
+	err |= __save_altstack(&frame->uc.uc_stack, regs->usp);
+	err |= setup_sigcontext(frame, regs);
+	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+	if (err)
+		return -EFAULT;
+
+	/* Set up to return from userspace. */
+	regs->lr = (unsigned long)VDSO_SYMBOL(
+		current->mm->context.vdso, rt_sigreturn);
+
+	/*
+	 * Set up registers for signal handler.
+	 * Registers that we don't modify keep the value they had from
+	 * user-space at the time we took the signal.
+	 * We always pass siginfo and mcontext, regardless of SA_SIGINFO,
+	 * since some things rely on this (e.g. glibc's debug/segfault.c).
+	 */
+	regs->pc  = (unsigned long)ksig->ka.sa.sa_handler;
+	regs->usp = (unsigned long)frame;
+	regs->a0  = ksig->sig;				/* a0: signal number */
+	regs->a1  = (unsigned long)(&(frame->info));	/* a1: siginfo pointer */
+	regs->a2  = (unsigned long)(&(frame->uc));	/* a2: ucontext pointer */
+
+	return 0;
+}
+
+static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
+{
+	sigset_t *oldset = sigmask_to_save();
+	int ret;
+
+	/* Are we from a system call? */
+	if (in_syscall(regs)) {
+		/* Avoid additional syscall restarting via ret_from_exception */
+		forget_syscall(regs);
+
+		/* If so, check system call restarting.. */
+		switch (regs->a0) {
+		case -ERESTART_RESTARTBLOCK:
+		case -ERESTARTNOHAND:
+			regs->a0 = -EINTR;
+			break;
+
+		case -ERESTARTSYS:
+			if (!(ksig->ka.sa.sa_flags & SA_RESTART)) {
+				regs->a0 = -EINTR;
+				break;
+			}
+			fallthrough;
+		case -ERESTARTNOINTR:
+			regs->a0 = regs->orig_a0;
+			regs->pc -= TRAP0_SIZE;
+			break;
+		}
+	}
+
+	/* Set up the stack frame */
+	ret = setup_rt_frame(ksig, oldset, regs);
+
+	signal_setup_done(ret, ksig, 0);
+}
+
+static void do_signal(struct pt_regs *regs)
+{
+	struct ksignal ksig;
+
+	if (get_signal(&ksig)) {
+		/* Actually deliver the signal */
+		handle_signal(&ksig, regs);
+		return;
+	}
+
+	/* Did we come from a system call? */
+	if (in_syscall(regs)) {
+		/* Avoid additional syscall restarting via ret_from_exception */
+		forget_syscall(regs);
+
+		/* Restart the system call - no handlers present */
+		switch (regs->a0) {
+		case -ERESTARTNOHAND:
+		case -ERESTARTSYS:
+		case -ERESTARTNOINTR:
+			regs->a0 = regs->orig_a0;
+			regs->pc -= TRAP0_SIZE;
+			break;
+		case -ERESTART_RESTARTBLOCK:
+			regs->a0 = regs->orig_a0;
+			regs_syscallid(regs) = __NR_restart_syscall;
+			regs->pc -= TRAP0_SIZE;
+			break;
+		}
+	}
+
+	/*
+	 * If there is no signal to deliver, we just put the saved
+	 * sigmask back.
+	 */
+	restore_saved_sigmask();
+}
+
+/*
+ * notification of userspace execution resumption
+ * - triggered by the _TIF_WORK_MASK flags
+ */
+asmlinkage void do_notify_resume(struct pt_regs *regs,
+	unsigned long thread_info_flags)
+{
+	if (thread_info_flags & _TIF_UPROBE)
+		uprobe_notify_resume(regs);
+
+	/* Handle pending signal delivery */
+	if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
+		do_signal(regs);
+
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
+		resume_user_mode_work(regs);
+}
diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c
new file mode 100644
index 000000000..92dbbf3e0
--- /dev/null
+++ b/arch/csky/kernel/smp.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/kernel_stat.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/percpu.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/irq.h>
+#include <linux/irq_work.h>
+#include <linux/irqdomain.h>
+#include <linux/of.h>
+#include <linux/seq_file.h>
+#include <linux/sched/task_stack.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/hotplug.h>
+#include <asm/irq.h>
+#include <asm/traps.h>
+#include <asm/sections.h>
+#include <asm/mmu_context.h>
+#ifdef CONFIG_CPU_HAS_FPU
+#include <abi/fpu.h>
+#endif
+
+enum ipi_message_type {
+	IPI_EMPTY,
+	IPI_RESCHEDULE,
+	IPI_CALL_FUNC,
+	IPI_IRQ_WORK,
+	IPI_MAX
+};
+
+struct ipi_data_struct {
+	unsigned long bits ____cacheline_aligned;
+	unsigned long stats[IPI_MAX] ____cacheline_aligned;
+};
+static DEFINE_PER_CPU(struct ipi_data_struct, ipi_data);
+
+static irqreturn_t handle_ipi(int irq, void *dev)
+{
+	unsigned long *stats = this_cpu_ptr(&ipi_data)->stats;
+
+	while (true) {
+		unsigned long ops;
+
+		ops = xchg(&this_cpu_ptr(&ipi_data)->bits, 0);
+		if (ops == 0)
+			return IRQ_HANDLED;
+
+		if (ops & (1 << IPI_RESCHEDULE)) {
+			stats[IPI_RESCHEDULE]++;
+			scheduler_ipi();
+		}
+
+		if (ops & (1 << IPI_CALL_FUNC)) {
+			stats[IPI_CALL_FUNC]++;
+			generic_smp_call_function_interrupt();
+		}
+
+		if (ops & (1 << IPI_IRQ_WORK)) {
+			stats[IPI_IRQ_WORK]++;
+			irq_work_run();
+		}
+
+		BUG_ON((ops >> IPI_MAX) != 0);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void (*send_arch_ipi)(const struct cpumask *mask);
+
+static int ipi_irq;
+void __init set_send_ipi(void (*func)(const struct cpumask *mask), int irq)
+{
+	if (send_arch_ipi)
+		return;
+
+	send_arch_ipi = func;
+	ipi_irq = irq;
+}
+
+static void
+send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
+{
+	int i;
+
+	for_each_cpu(i, to_whom)
+		set_bit(operation, &per_cpu_ptr(&ipi_data, i)->bits);
+
+	smp_mb();
+	send_arch_ipi(to_whom);
+}
+
+static const char * const ipi_names[] = {
+	[IPI_EMPTY]		= "Empty interrupts",
+	[IPI_RESCHEDULE]	= "Rescheduling interrupts",
+	[IPI_CALL_FUNC]		= "Function call interrupts",
+	[IPI_IRQ_WORK]		= "Irq work interrupts",
+};
+
+int arch_show_interrupts(struct seq_file *p, int prec)
+{
+	unsigned int cpu, i;
+
+	for (i = 0; i < IPI_MAX; i++) {
+		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
+			   prec >= 4 ? " " : "");
+		for_each_online_cpu(cpu)
+			seq_printf(p, "%10lu ",
+				per_cpu_ptr(&ipi_data, cpu)->stats[i]);
+		seq_printf(p, " %s\n", ipi_names[i]);
+	}
+
+	return 0;
+}
+
+void arch_send_call_function_ipi_mask(struct cpumask *mask)
+{
+	send_ipi_message(mask, IPI_CALL_FUNC);
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC);
+}
+
+static void ipi_stop(void *unused)
+{
+	while (1);
+}
+
+void smp_send_stop(void)
+{
+	on_each_cpu(ipi_stop, NULL, 1);
+}
+
+void arch_smp_send_reschedule(int cpu)
+{
+	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
+}
+
+#ifdef CONFIG_IRQ_WORK
+void arch_irq_work_raise(void)
+{
+	send_ipi_message(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
+}
+#endif
+
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+}
+
+static int ipi_dummy_dev;
+
+void __init setup_smp_ipi(void)
+{
+	int rc;
+
+	if (ipi_irq == 0)
+		return;
+
+	rc = request_percpu_irq(ipi_irq, handle_ipi, "IPI Interrupt",
+				&ipi_dummy_dev);
+	if (rc)
+		panic("%s IRQ request failed\n", __func__);
+
+	enable_percpu_irq(ipi_irq, 0);
+}
+
+void __init setup_smp(void)
+{
+	struct device_node *node = NULL;
+	unsigned int cpu;
+
+	for_each_of_cpu_node(node) {
+		if (!of_device_is_available(node))
+			continue;
+
+		cpu = of_get_cpu_hwid(node, 0);
+		if (cpu >= NR_CPUS)
+			continue;
+
+		set_cpu_possible(cpu, true);
+		set_cpu_present(cpu, true);
+	}
+}
+
+extern void _start_smp_secondary(void);
+
+volatile unsigned int secondary_hint;
+volatile unsigned int secondary_hint2;
+volatile unsigned int secondary_ccr;
+volatile unsigned int secondary_stack;
+volatile unsigned int secondary_msa1;
+volatile unsigned int secondary_pgd;
+
+int __cpu_up(unsigned int cpu, struct task_struct *tidle)
+{
+	unsigned long mask = 1 << cpu;
+
+	secondary_stack =
+		(unsigned int) task_stack_page(tidle) + THREAD_SIZE - 8;
+	secondary_hint = mfcr("cr31");
+	secondary_hint2 = mfcr("cr<21, 1>");
+	secondary_ccr  = mfcr("cr18");
+	secondary_msa1 = read_mmu_msa1();
+	secondary_pgd = mfcr("cr<29, 15>");
+
+	/*
+	 * Because other CPUs are in reset status, we must flush data
+	 * from cache to out and secondary CPUs use them in
+	 * csky_start_secondary(void)
+	 */
+	mtcr("cr17", 0x22);
+
+	if (mask & mfcr("cr<29, 0>")) {
+		send_arch_ipi(cpumask_of(cpu));
+	} else {
+		/* Enable cpu in SMP reset ctrl reg */
+		mask |= mfcr("cr<29, 0>");
+		mtcr("cr<29, 0>", mask);
+	}
+
+	/* Wait for the cpu online */
+	while (!cpu_online(cpu));
+
+	secondary_stack = 0;
+
+	return 0;
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+}
+
+void csky_start_secondary(void)
+{
+	struct mm_struct *mm = &init_mm;
+	unsigned int cpu = smp_processor_id();
+
+	mtcr("cr31", secondary_hint);
+	mtcr("cr<21, 1>", secondary_hint2);
+	mtcr("cr18", secondary_ccr);
+
+	mtcr("vbr", vec_base);
+
+	flush_tlb_all();
+	write_mmu_pagemask(0);
+
+#ifdef CONFIG_CPU_HAS_FPU
+	init_fpu();
+#endif
+
+	enable_percpu_irq(ipi_irq, 0);
+
+	mmget(mm);
+	mmgrab(mm);
+	current->active_mm = mm;
+	cpumask_set_cpu(cpu, mm_cpumask(mm));
+
+	notify_cpu_starting(cpu);
+	set_cpu_online(cpu, true);
+
+	pr_info("CPU%u Online: %s...\n", cpu, __func__);
+
+	local_irq_enable();
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+int __cpu_disable(void)
+{
+	unsigned int cpu = smp_processor_id();
+
+	set_cpu_online(cpu, false);
+
+	irq_migrate_all_off_this_cpu();
+
+	clear_tasks_mm_cpumask(cpu);
+
+	return 0;
+}
+
+void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
+{
+	pr_notice("CPU%u: shutdown\n", cpu);
+}
+
+void __noreturn arch_cpu_idle_dead(void)
+{
+	idle_task_exit();
+
+	cpuhp_ap_report_dead();
+
+	while (!secondary_stack)
+		arch_cpu_idle();
+
+	raw_local_irq_disable();
+
+	asm volatile(
+		"mov	sp, %0\n"
+		"mov	r8, %0\n"
+		"jmpi	csky_start_secondary"
+		:
+		: "r" (secondary_stack));
+
+	BUG();
+}
+#endif
diff --git a/arch/csky/kernel/stacktrace.c b/arch/csky/kernel/stacktrace.c
new file mode 100644
index 000000000..27ecd63e3
--- /dev/null
+++ b/arch/csky/kernel/stacktrace.c
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
+#include <linux/stacktrace.h>
+#include <linux/ftrace.h>
+#include <linux/ptrace.h>
+
+#ifdef CONFIG_FRAME_POINTER
+
+struct stackframe {
+	unsigned long fp;
+	unsigned long ra;
+};
+
+void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
+			     bool (*fn)(unsigned long, void *), void *arg)
+{
+	unsigned long fp, sp, pc;
+
+	if (regs) {
+		fp = frame_pointer(regs);
+		sp = user_stack_pointer(regs);
+		pc = instruction_pointer(regs);
+	} else if (task == NULL || task == current) {
+		const register unsigned long current_fp __asm__ ("r8");
+		fp = current_fp;
+		sp = current_stack_pointer;
+		pc = (unsigned long)walk_stackframe;
+	} else {
+		/* task blocked in __switch_to */
+		fp = thread_saved_fp(task);
+		sp = thread_saved_sp(task);
+		pc = thread_saved_lr(task);
+	}
+
+	for (;;) {
+		unsigned long low, high;
+		struct stackframe *frame;
+
+		if (unlikely(!__kernel_text_address(pc) || fn(pc, arg)))
+			break;
+
+		/* Validate frame pointer */
+		low = sp;
+		high = ALIGN(sp, THREAD_SIZE);
+		if (unlikely(fp < low || fp > high || fp & 0x3))
+			break;
+		/* Unwind stack frame */
+		frame = (struct stackframe *)fp;
+		sp = fp;
+		fp = frame->fp;
+		pc = ftrace_graph_ret_addr(current, NULL, frame->ra,
+					   (unsigned long *)(fp - 8));
+	}
+}
+
+#else /* !CONFIG_FRAME_POINTER */
+
+static void notrace walk_stackframe(struct task_struct *task,
+	struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg)
+{
+	unsigned long sp, pc;
+	unsigned long *ksp;
+
+	if (regs) {
+		sp = user_stack_pointer(regs);
+		pc = instruction_pointer(regs);
+	} else if (task == NULL || task == current) {
+		sp = current_stack_pointer;
+		pc = (unsigned long)walk_stackframe;
+	} else {
+		/* task blocked in __switch_to */
+		sp = thread_saved_sp(task);
+		pc = thread_saved_lr(task);
+	}
+
+	if (unlikely(sp & 0x3))
+		return;
+
+	ksp = (unsigned long *)sp;
+	while (!kstack_end(ksp)) {
+		if (__kernel_text_address(pc) && unlikely(fn(pc, arg)))
+			break;
+		pc = (*ksp++) - 0x4;
+	}
+}
+#endif /* CONFIG_FRAME_POINTER */
+
+static bool print_trace_address(unsigned long pc, void *arg)
+{
+	print_ip_sym((const char *)arg, pc);
+	return false;
+}
+
+void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl)
+{
+	pr_cont("Call Trace:\n");
+	walk_stackframe(task, NULL, print_trace_address, (void *)loglvl);
+}
+
+static bool save_wchan(unsigned long pc, void *arg)
+{
+	if (!in_sched_functions(pc)) {
+		unsigned long *p = arg;
+		*p = pc;
+		return true;
+	}
+	return false;
+}
+
+unsigned long __get_wchan(struct task_struct *task)
+{
+	unsigned long pc = 0;
+
+	walk_stackframe(task, NULL, save_wchan, &pc);
+	return pc;
+}
+
+#ifdef CONFIG_STACKTRACE
+static bool __save_trace(unsigned long pc, void *arg, bool nosched)
+{
+	struct stack_trace *trace = arg;
+
+	if (unlikely(nosched && in_sched_functions(pc)))
+		return false;
+	if (unlikely(trace->skip > 0)) {
+		trace->skip--;
+		return false;
+	}
+
+	trace->entries[trace->nr_entries++] = pc;
+	return (trace->nr_entries >= trace->max_entries);
+}
+
+static bool save_trace(unsigned long pc, void *arg)
+{
+	return __save_trace(pc, arg, false);
+}
+
+/*
+ * Save stack-backtrace addresses into a stack_trace buffer.
+ */
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	walk_stackframe(tsk, NULL, save_trace, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+
+void save_stack_trace(struct stack_trace *trace)
+{
+	save_stack_trace_tsk(NULL, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
+
+#endif /* CONFIG_STACKTRACE */
diff --git a/arch/csky/kernel/syscall.c b/arch/csky/kernel/syscall.c
new file mode 100644
index 000000000..4540a271e
--- /dev/null
+++ b/arch/csky/kernel/syscall.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/syscalls.h>
+
+SYSCALL_DEFINE1(set_thread_area, unsigned long, addr)
+{
+	struct thread_info *ti = task_thread_info(current);
+	struct pt_regs *reg = current_pt_regs();
+
+	reg->tls = addr;
+	ti->tp_value = addr;
+
+	return 0;
+}
+
+SYSCALL_DEFINE6(mmap2,
+	unsigned long, addr,
+	unsigned long, len,
+	unsigned long, prot,
+	unsigned long, flags,
+	unsigned long, fd,
+	unsigned long, offset)
+{
+	if (unlikely(offset & (~PAGE_MASK >> 12)))
+		return -EINVAL;
+
+	return ksys_mmap_pgoff(addr, len, prot, flags, fd,
+			       offset >> (PAGE_SHIFT - 12));
+}
+
+/*
+ * for abiv1 the 64bits args should be even th, So we need mov the advice
+ * forward.
+ */
+SYSCALL_DEFINE4(csky_fadvise64_64,
+	int, fd,
+	int, advice,
+	loff_t, offset,
+	loff_t, len)
+{
+	return ksys_fadvise64_64(fd, offset, len, advice);
+}
diff --git a/arch/csky/kernel/syscall_table.c b/arch/csky/kernel/syscall_table.c
new file mode 100644
index 000000000..a6eb91a0e
--- /dev/null
+++ b/arch/csky/kernel/syscall_table.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/syscalls.h>
+#include <asm/syscalls.h>
+
+#undef __SYSCALL
+#define __SYSCALL(nr, call)[nr] = (call),
+#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native)
+
+#define sys_fadvise64_64 sys_csky_fadvise64_64
+#define sys_sync_file_range sys_sync_file_range2
+void * const sys_call_table[__NR_syscalls] __page_aligned_data = {
+	[0 ... __NR_syscalls - 1] = sys_ni_syscall,
+#include <asm/syscall_table_32.h>
+};
diff --git a/arch/csky/kernel/time.c b/arch/csky/kernel/time.c
new file mode 100644
index 000000000..52379d866
--- /dev/null
+++ b/arch/csky/kernel/time.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/clocksource.h>
+#include <linux/of_clk.h>
+
+void __init time_init(void)
+{
+	of_clk_init(NULL);
+	timer_probe();
+}
diff --git a/arch/csky/kernel/traps.c b/arch/csky/kernel/traps.c
new file mode 100644
index 000000000..c2246b07c
--- /dev/null
+++ b/arch/csky/kernel/traps.c
@@ -0,0 +1,263 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/cpu.h>
+#include <linux/sched.h>
+#include <linux/signal.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/user.h>
+#include <linux/string.h>
+#include <linux/linkage.h>
+#include <linux/init.h>
+#include <linux/ptrace.h>
+#include <linux/kallsyms.h>
+#include <linux/rtc.h>
+#include <linux/uaccess.h>
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+#include <linux/sched/debug.h>
+
+#include <asm/setup.h>
+#include <asm/traps.h>
+#include <asm/pgalloc.h>
+#include <asm/siginfo.h>
+
+#include <asm/mmu_context.h>
+
+#ifdef CONFIG_CPU_HAS_FPU
+#include <abi/fpu.h>
+#endif
+
+int show_unhandled_signals = 1;
+
+/* Defined in entry.S */
+asmlinkage void csky_trap(void);
+
+asmlinkage void csky_systemcall(void);
+asmlinkage void csky_cmpxchg(void);
+asmlinkage void csky_get_tls(void);
+asmlinkage void csky_irq(void);
+
+asmlinkage void csky_pagefault(void);
+
+/* Defined in head.S */
+asmlinkage void _start_smp_secondary(void);
+
+void __init pre_trap_init(void)
+{
+	int i;
+
+	mtcr("vbr", vec_base);
+
+	for (i = 1; i < 128; i++)
+		VEC_INIT(i, csky_trap);
+}
+
+void __init trap_init(void)
+{
+	VEC_INIT(VEC_AUTOVEC, csky_irq);
+
+	/* setup trap0 trap2 trap3 */
+	VEC_INIT(VEC_TRAP0, csky_systemcall);
+	VEC_INIT(VEC_TRAP2, csky_cmpxchg);
+	VEC_INIT(VEC_TRAP3, csky_get_tls);
+
+	/* setup MMU TLB exception */
+	VEC_INIT(VEC_TLBINVALIDL, csky_pagefault);
+	VEC_INIT(VEC_TLBINVALIDS, csky_pagefault);
+	VEC_INIT(VEC_TLBMODIFIED, csky_pagefault);
+
+#ifdef CONFIG_CPU_HAS_FPU
+	init_fpu();
+#endif
+
+#ifdef CONFIG_SMP
+	mtcr("cr<28, 0>", virt_to_phys(vec_base));
+
+	VEC_INIT(VEC_RESET, (void *)virt_to_phys(_start_smp_secondary));
+#endif
+}
+
+static DEFINE_SPINLOCK(die_lock);
+
+void die(struct pt_regs *regs, const char *str)
+{
+	static int die_counter;
+	int ret;
+
+	oops_enter();
+
+	spin_lock_irq(&die_lock);
+	console_verbose();
+	bust_spinlocks(1);
+
+	pr_emerg("%s [#%d]\n", str, ++die_counter);
+	print_modules();
+	show_regs(regs);
+	show_stack(current, (unsigned long *)regs->regs[4], KERN_INFO);
+
+	ret = notify_die(DIE_OOPS, str, regs, 0, trap_no(regs), SIGSEGV);
+
+	bust_spinlocks(0);
+	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
+	spin_unlock_irq(&die_lock);
+	oops_exit();
+
+	if (in_interrupt())
+		panic("Fatal exception in interrupt");
+	if (panic_on_oops)
+		panic("Fatal exception");
+	if (ret != NOTIFY_STOP)
+		make_task_dead(SIGSEGV);
+}
+
+void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr)
+{
+	struct task_struct *tsk = current;
+
+	if (show_unhandled_signals && unhandled_signal(tsk, signo)
+	    && printk_ratelimit()) {
+		pr_info("%s[%d]: unhandled signal %d code 0x%x at 0x%08lx",
+			tsk->comm, task_pid_nr(tsk), signo, code, addr);
+		print_vma_addr(KERN_CONT " in ", instruction_pointer(regs));
+		pr_cont("\n");
+		show_regs(regs);
+	}
+
+	force_sig_fault(signo, code, (void __user *)addr);
+}
+
+static void do_trap_error(struct pt_regs *regs, int signo, int code,
+	unsigned long addr, const char *str)
+{
+	current->thread.trap_no = trap_no(regs);
+
+	if (user_mode(regs)) {
+		do_trap(regs, signo, code, addr);
+	} else {
+		if (!fixup_exception(regs))
+			die(regs, str);
+	}
+}
+
+#define DO_ERROR_INFO(name, signo, code, str)				\
+asmlinkage __visible void name(struct pt_regs *regs)			\
+{									\
+	do_trap_error(regs, signo, code, regs->pc, "Oops - " str);	\
+}
+
+DO_ERROR_INFO(do_trap_unknown,
+	SIGILL, ILL_ILLTRP, "unknown exception");
+DO_ERROR_INFO(do_trap_zdiv,
+	SIGFPE, FPE_INTDIV, "error zero div exception");
+DO_ERROR_INFO(do_trap_buserr,
+	SIGSEGV, ILL_ILLADR, "error bus error exception");
+
+asmlinkage void do_trap_misaligned(struct pt_regs *regs)
+{
+#ifdef CONFIG_CPU_NEED_SOFTALIGN
+	csky_alignment(regs);
+#else
+	current->thread.trap_no = trap_no(regs);
+	do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->pc,
+		      "Oops - load/store address misaligned");
+#endif
+}
+
+asmlinkage void do_trap_bkpt(struct pt_regs *regs)
+{
+#ifdef CONFIG_KPROBES
+	if (kprobe_single_step_handler(regs))
+		return;
+#endif
+#ifdef CONFIG_UPROBES
+	if (uprobe_single_step_handler(regs))
+		return;
+#endif
+	if (user_mode(regs)) {
+		send_sig(SIGTRAP, current, 0);
+		return;
+	}
+
+	do_trap_error(regs, SIGILL, ILL_ILLTRP, regs->pc,
+		      "Oops - illegal trap exception");
+}
+
+asmlinkage void do_trap_illinsn(struct pt_regs *regs)
+{
+	current->thread.trap_no = trap_no(regs);
+
+#ifdef CONFIG_KPROBES
+	if (kprobe_breakpoint_handler(regs))
+		return;
+#endif
+#ifdef CONFIG_UPROBES
+	if (uprobe_breakpoint_handler(regs))
+		return;
+#endif
+#ifndef CONFIG_CPU_NO_USER_BKPT
+	if (*(uint16_t *)instruction_pointer(regs) != USR_BKPT) {
+		send_sig(SIGTRAP, current, 0);
+		return;
+	}
+#endif
+
+	do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->pc,
+		      "Oops - illegal instruction exception");
+}
+
+asmlinkage void do_trap_fpe(struct pt_regs *regs)
+{
+#ifdef CONFIG_CPU_HAS_FPU
+	return fpu_fpe(regs);
+#else
+	do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->pc,
+		      "Oops - fpu instruction exception");
+#endif
+}
+
+asmlinkage void do_trap_priv(struct pt_regs *regs)
+{
+#ifdef CONFIG_CPU_HAS_FPU
+	if (user_mode(regs) && fpu_libc_helper(regs))
+		return;
+#endif
+	do_trap_error(regs, SIGILL, ILL_PRVOPC, regs->pc,
+		      "Oops - illegal privileged exception");
+}
+
+asmlinkage void trap_c(struct pt_regs *regs)
+{
+	switch (trap_no(regs)) {
+	case VEC_ZERODIV:
+		do_trap_zdiv(regs);
+		break;
+	case VEC_TRACE:
+		do_trap_bkpt(regs);
+		break;
+	case VEC_ILLEGAL:
+		do_trap_illinsn(regs);
+		break;
+	case VEC_TRAP1:
+	case VEC_BREAKPOINT:
+		do_trap_bkpt(regs);
+		break;
+	case VEC_ACCESS:
+		do_trap_buserr(regs);
+		break;
+	case VEC_ALIGN:
+		do_trap_misaligned(regs);
+		break;
+	case VEC_FPE:
+		do_trap_fpe(regs);
+		break;
+	case VEC_PRIV:
+		do_trap_priv(regs);
+		break;
+	default:
+		do_trap_unknown(regs);
+		break;
+	}
+}
diff --git a/arch/csky/kernel/vdso.c b/arch/csky/kernel/vdso.c
new file mode 100644
index 000000000..6886c0b3f
--- /dev/null
+++ b/arch/csky/kernel/vdso.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/binfmts.h>
+#include <linux/elf.h>
+#include <linux/err.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+#include <asm/page.h>
+
+extern char vdso_start[], vdso_end[];
+
+static unsigned int vdso_pages;
+static struct page **vdso_pagelist;
+
+static int __init vdso_init(void)
+{
+	unsigned int i;
+
+	vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
+	vdso_pagelist =
+		kzalloc_objs(struct page *, vdso_pages);
+	if (unlikely(vdso_pagelist == NULL)) {
+		pr_err("vdso: pagelist allocation failed\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < vdso_pages; i++) {
+		struct page *pg;
+
+		pg = virt_to_page(vdso_start + (i << PAGE_SHIFT));
+		vdso_pagelist[i] = pg;
+	}
+
+	return 0;
+}
+arch_initcall(vdso_init);
+
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+	int uses_interp)
+{
+	struct vm_area_struct *vma;
+	struct mm_struct *mm = current->mm;
+	unsigned long vdso_base, vdso_len;
+	int ret;
+	static struct vm_special_mapping vdso_mapping = {
+		.name = "[vdso]",
+	};
+
+	vdso_len = vdso_pages << PAGE_SHIFT;
+
+	mmap_write_lock(mm);
+	vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0);
+	if (IS_ERR_VALUE(vdso_base)) {
+		ret = vdso_base;
+		goto end;
+	}
+
+	/*
+	 * Put vDSO base into mm struct. We need to do this before calling
+	 * install_special_mapping or the perf counter mmap tracking code
+	 * will fail to recognise it as a vDSO (since arch_vma_name fails).
+	 */
+	mm->context.vdso = (void *)vdso_base;
+
+	vdso_mapping.pages = vdso_pagelist;
+	vma =
+	   _install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
+		(VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
+		&vdso_mapping);
+
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		mm->context.vdso = NULL;
+		goto end;
+	}
+
+	vdso_base += (vdso_pages << PAGE_SHIFT);
+	ret = 0;
+end:
+	mmap_write_unlock(mm);
+	return ret;
+}
diff --git a/arch/csky/kernel/vdso/.gitignore b/arch/csky/kernel/vdso/.gitignore
new file mode 100644
index 000000000..3a19def86
--- /dev/null
+++ b/arch/csky/kernel/vdso/.gitignore
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+vdso.lds
+*.tmp
+vdso-syms.S
diff --git a/arch/csky/kernel/vdso/Makefile b/arch/csky/kernel/vdso/Makefile
new file mode 100644
index 000000000..a3042287a
--- /dev/null
+++ b/arch/csky/kernel/vdso/Makefile
@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+# Include the generic Makefile to check the built vdso.
+include $(srctree)/lib/vdso/Makefile.include
+
+# Symbols present in the vdso
+vdso-syms  += rt_sigreturn
+
+# Files to link into the vdso
+obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
+
+ifneq ($(c-gettimeofday-y),)
+	CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
+endif
+
+ccflags-y := -fno-stack-protector -DBUILD_VDSO32
+
+# Build rules
+targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-dummy.o
+obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
+
+obj-y += vdso.o vdso-syms.o
+CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
+
+# Force dependency
+$(obj)/vdso.o: $(obj)/vdso.so
+
+SYSCFLAGS_vdso.so.dbg = $(c_flags)
+$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
+	$(call if_changed,vdsold)
+SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
+	-Wl,--build-id=sha1 -Wl,--hash-style=both
+
+$(obj)/vdso-syms.S: $(obj)/vdso.so FORCE
+	$(call if_changed,so2s)
+
+# strip rule for the .so file
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+	$(call if_changed,objcopy)
+
+# actual build commands
+# The DSO images are built using a special linker script
+# Make sure only to export the intended __vdso_xxx symbol offsets.
+quiet_cmd_vdsold = VDSOLD  $@
+      cmd_vdsold = $(CC) $(KBUILD_CFLAGS) $(call cc-option, -no-pie) -nostdlib -nostartfiles $(SYSCFLAGS_$(@F)) \
+                           -Wl,-T,$(filter-out FORCE,$^) -o $@.tmp && \
+                   $(CROSS_COMPILE)objcopy \
+                           $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \
+                   rm $@.tmp
+
+# Extracts symbol offsets from the VDSO, converting them into an assembly file
+# that contains the same symbols at the same offsets.
+quiet_cmd_so2s = SO2S    $@
+      cmd_so2s = $(NM) -D $< | $(src)/so2s.sh > $@
diff --git a/arch/csky/kernel/vdso/note.S b/arch/csky/kernel/vdso/note.S
new file mode 100644
index 000000000..2a956c942
--- /dev/null
+++ b/arch/csky/kernel/vdso/note.S
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/elfnote.h>
+#include <linux/version.h>
+
+ELFNOTE_START(Linux, 0, "a")
+	.long LINUX_VERSION_CODE
+ELFNOTE_END
diff --git a/arch/csky/kernel/vdso/rt_sigreturn.S b/arch/csky/kernel/vdso/rt_sigreturn.S
new file mode 100644
index 000000000..0a6bd1216
--- /dev/null
+++ b/arch/csky/kernel/vdso/rt_sigreturn.S
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+#include <abi/vdso.h>
+
+	.text
+ENTRY(__vdso_rt_sigreturn)
+	.cfi_startproc
+	.cfi_signal_frame
+	SET_SYSCALL_ID
+	trap	0
+	.cfi_endproc
+ENDPROC(__vdso_rt_sigreturn)
diff --git a/arch/csky/kernel/vdso/so2s.sh b/arch/csky/kernel/vdso/so2s.sh
new file mode 100755
index 000000000..69da3d529
--- /dev/null
+++ b/arch/csky/kernel/vdso/so2s.sh
@@ -0,0 +1,5 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+
+sed 's!\([0-9a-f]*\) T \([a-z0-9_]*\)\(@@LINUX_5.10\)*!.global \2\n.set \2,0x\1!' \
+| grep '^\.'
diff --git a/arch/csky/kernel/vdso/vdso.S b/arch/csky/kernel/vdso/vdso.S
new file mode 100644
index 000000000..5162ca069
--- /dev/null
+++ b/arch/csky/kernel/vdso/vdso.S
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/page.h>
+
+	__PAGE_ALIGNED_DATA
+
+	.globl vdso_start, vdso_end
+	.balign PAGE_SIZE
+vdso_start:
+	.incbin "arch/csky/kernel/vdso/vdso.so"
+	.balign PAGE_SIZE
+vdso_end:
+
+	.previous
diff --git a/arch/csky/kernel/vdso/vdso.lds.S b/arch/csky/kernel/vdso/vdso.lds.S
new file mode 100644
index 000000000..8d226252d
--- /dev/null
+++ b/arch/csky/kernel/vdso/vdso.lds.S
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <asm/page.h>
+
+OUTPUT_ARCH(csky)
+
+SECTIONS
+{
+	PROVIDE(_vdso_data = . + PAGE_SIZE);
+	. = SIZEOF_HEADERS;
+
+	.hash		: { *(.hash) }			:text
+	.gnu.hash	: { *(.gnu.hash) }
+	.dynsym		: { *(.dynsym) }
+	.dynstr		: { *(.dynstr) }
+	.gnu.version	: { *(.gnu.version) }
+	.gnu.version_d	: { *(.gnu.version_d) }
+	.gnu.version_r	: { *(.gnu.version_r) }
+
+	.note		: { *(.note.*) }		:text	:note
+	.dynamic	: { *(.dynamic) }		:text	:dynamic
+
+	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
+	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
+
+	.rodata		: { *(.rodata .rodata.* .gnu.linkonce.r.*) }
+
+	. = 0x800;
+	.text		: { *(.text .text.*) }		:text
+
+	.data		: {
+		*(.got.plt) *(.got)
+		*(.data .data.* .gnu.linkonce.d.*)
+		*(.dynbss)
+		*(.bss .bss.* .gnu.linkonce.b.*)
+	}
+}
+
+PHDRS
+{
+	text		PT_LOAD		FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
+	dynamic		PT_DYNAMIC	FLAGS(4);		/* PF_R */
+	note		PT_NOTE		FLAGS(4);		/* PF_R */
+	eh_frame_hdr	PT_GNU_EH_FRAME;
+}
+
+VERSION
+{
+	LINUX_5.10 {
+	global:
+		__vdso_rt_sigreturn;
+	local: *;
+	};
+}
diff --git a/arch/csky/kernel/vmlinux.lds.S b/arch/csky/kernel/vmlinux.lds.S
new file mode 100644
index 000000000..81943981b
--- /dev/null
+++ b/arch/csky/kernel/vmlinux.lds.S
@@ -0,0 +1,116 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <asm/vmlinux.lds.h>
+#include <asm/page.h>
+#include <asm/memory.h>
+
+OUTPUT_ARCH(csky)
+ENTRY(_start)
+
+#ifndef __cskyBE__
+jiffies = jiffies_64;
+#else
+jiffies = jiffies_64 + 4;
+#endif
+
+#define VBR_BASE \
+	. = ALIGN(1024); \
+	vec_base = .; \
+	. += 512;
+
+SECTIONS
+{
+	. = PAGE_OFFSET + PHYS_OFFSET_OFFSET;
+
+	_start = .;
+	HEAD_TEXT_SECTION
+	. = ALIGN(PAGE_SIZE);
+
+	.text : AT(ADDR(.text) - LOAD_OFFSET) {
+		_text = .;
+		_stext = .;
+		VBR_BASE
+		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
+		TEXT_TEXT
+		SCHED_TEXT
+		LOCK_TEXT
+		KPROBES_TEXT
+		*(.fixup)
+		*(.gnu.warning)
+	} = 0
+	_etext = .;
+
+	/* __init_begin __init_end must be page aligned for free_initmem */
+	. = ALIGN(PAGE_SIZE);
+	__init_begin = .;
+	INIT_TEXT_SECTION(PAGE_SIZE)
+	INIT_DATA_SECTION(PAGE_SIZE)
+	PERCPU_SECTION(L1_CACHE_BYTES)
+	. = ALIGN(PAGE_SIZE);
+	__init_end = .;
+
+	_sdata = .;
+	RO_DATA(PAGE_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	_edata = .;
+
+#ifdef CONFIG_HAVE_TCM
+	.tcm_start : {
+		. = ALIGN(PAGE_SIZE);
+		__tcm_start = .;
+	}
+
+	.text_data_tcm FIXADDR_TCM : AT(__tcm_start)
+	{
+		. = ALIGN(4);
+		__stcm_text_data = .;
+		*(.tcm.text)
+		*(.tcm.rodata)
+#ifndef CONFIG_HAVE_DTCM
+		*(.tcm.data)
+#endif
+		. = ALIGN(4);
+		__etcm_text_data = .;
+	}
+
+	. = ADDR(.tcm_start) + SIZEOF(.tcm_start) + SIZEOF(.text_data_tcm);
+
+#ifdef CONFIG_HAVE_DTCM
+	#define ITCM_SIZE	CONFIG_ITCM_NR_PAGES * PAGE_SIZE
+
+	.dtcm_start : {
+		__dtcm_start = .;
+	}
+
+	.data_tcm FIXADDR_TCM + ITCM_SIZE : AT(__dtcm_start)
+	{
+		. = ALIGN(4);
+		__stcm_data = .;
+		*(.tcm.data)
+		. = ALIGN(4);
+		__etcm_data = .;
+	}
+
+	. = ADDR(.dtcm_start) + SIZEOF(.data_tcm);
+
+	.tcm_end : AT(ADDR(.dtcm_start) + SIZEOF(.data_tcm)) {
+#else
+	.tcm_end : AT(ADDR(.tcm_start) + SIZEOF(.text_data_tcm)) {
+#endif
+		. = ALIGN(PAGE_SIZE);
+		__tcm_end = .;
+	}
+#endif
+
+	EXCEPTION_TABLE(L1_CACHE_BYTES)
+	BSS_SECTION(L1_CACHE_BYTES, PAGE_SIZE, L1_CACHE_BYTES)
+	_end = . ;
+
+	STABS_DEBUG
+	DWARF_DEBUG
+	MODINFO
+	ELF_DETAILS
+
+	DISCARDS
+}
diff --git a/arch/csky/lib/Makefile b/arch/csky/lib/Makefile
new file mode 100644
index 000000000..d0ce6e2d7
--- /dev/null
+++ b/arch/csky/lib/Makefile
@@ -0,0 +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/delay.c b/arch/csky/lib/delay.c
new file mode 100644
index 000000000..f5db31731
--- /dev/null
+++ b/arch/csky/lib/delay.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+
+void __aligned(8) __delay(unsigned long loops)
+{
+	asm volatile (
+		"mov r0, r0\n"
+		"1:declt %0\n"
+		"bf	1b"
+		: "=r"(loops)
+		: "0"(loops));
+}
+EXPORT_SYMBOL(__delay);
+
+void __const_udelay(unsigned long xloops)
+{
+	unsigned long long loops;
+
+	loops = (unsigned long long)xloops * loops_per_jiffy * HZ;
+
+	__delay(loops >> 32);
+}
+EXPORT_SYMBOL(__const_udelay);
+
+void __udelay(unsigned long usecs)
+{
+	__const_udelay(usecs * 0x10C7UL); /* 2**32 / 1000000 (rounded up) */
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long nsecs)
+{
+	__const_udelay(nsecs * 0x5UL); /* 2**32 / 1000000000 (rounded up) */
+}
+EXPORT_SYMBOL(__ndelay);
diff --git a/arch/csky/lib/error-inject.c b/arch/csky/lib/error-inject.c
new file mode 100644
index 000000000..c15fb36fe
--- /dev/null
+++ b/arch/csky/lib/error-inject.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/error-injection.h>
+#include <linux/kprobes.h>
+
+void override_function_with_return(struct pt_regs *regs)
+{
+	instruction_pointer_set(regs, regs->lr);
+}
+NOKPROBE_SYMBOL(override_function_with_return);
diff --git a/arch/csky/lib/string.c b/arch/csky/lib/string.c
new file mode 100644
index 000000000..d65626fca
--- /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/lib/usercopy.c b/arch/csky/lib/usercopy.c
new file mode 100644
index 000000000..3c01c5442
--- /dev/null
+++ b/arch/csky/lib/usercopy.c
@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/uaccess.h>
+#include <linux/types.h>
+
+unsigned long raw_copy_from_user(void *to, const void *from,
+			unsigned long n)
+{
+	int tmp, nsave;
+
+	__asm__ __volatile__(
+	"0:     cmpnei  %1, 0           \n"
+	"       bf      7f              \n"
+	"       mov     %3, %1          \n"
+	"       or      %3, %2          \n"
+	"       andi    %3, 3           \n"
+	"       cmpnei  %3, 0           \n"
+	"       bf      1f              \n"
+	"       br      5f              \n"
+	"1:     cmplti  %0, 16          \n"
+	"       bt      3f              \n"
+	"2:     ldw     %3, (%2, 0)     \n"
+	"10:    ldw     %4, (%2, 4)     \n"
+	"       stw     %3, (%1, 0)     \n"
+	"       stw     %4, (%1, 4)     \n"
+	"11:    ldw     %3, (%2, 8)     \n"
+	"12:    ldw     %4, (%2, 12)    \n"
+	"       stw     %3, (%1, 8)     \n"
+	"       stw     %4, (%1, 12)    \n"
+	"       addi    %2, 16          \n"
+	"       addi    %1, 16          \n"
+	"       subi    %0, 16          \n"
+	"       br      1b              \n"
+	"3:     cmplti  %0, 4           \n"
+	"       bt      5f              \n"
+	"4:     ldw     %3, (%2, 0)     \n"
+	"       stw     %3, (%1, 0)     \n"
+	"       addi    %2, 4           \n"
+	"       addi    %1, 4           \n"
+	"       subi    %0, 4           \n"
+	"       br      3b              \n"
+	"5:     cmpnei  %0, 0           \n"
+	"       bf      7f              \n"
+	"6:     ldb     %3, (%2, 0)     \n"
+	"       stb     %3, (%1, 0)     \n"
+	"       addi    %2,  1          \n"
+	"       addi    %1,  1          \n"
+	"       subi    %0,  1          \n"
+	"       br      5b              \n"
+	"8:     stw     %3, (%1, 0)     \n"
+	"       subi    %0, 4           \n"
+	"       bf      7f              \n"
+	"9:     subi    %0, 8           \n"
+	"       bf      7f              \n"
+	"13:    stw     %3, (%1, 8)     \n"
+	"       subi    %0, 12          \n"
+	"       bf      7f              \n"
+	".section __ex_table, \"a\"     \n"
+	".align   2                     \n"
+	".long    2b, 7f                \n"
+	".long    4b, 7f                \n"
+	".long    6b, 7f                \n"
+	".long   10b, 8b                \n"
+	".long   11b, 9b                \n"
+	".long   12b,13b                \n"
+	".previous                      \n"
+	"7:                             \n"
+	: "=r"(n), "=r"(to), "=r"(from), "=r"(nsave),
+	  "=r"(tmp)
+	: "0"(n), "1"(to), "2"(from)
+	: "memory");
+
+	return n;
+}
+EXPORT_SYMBOL(raw_copy_from_user);
+
+unsigned long raw_copy_to_user(void *to, const void *from,
+			unsigned long n)
+{
+	int w0, w1, w2, w3;
+
+	__asm__ __volatile__(
+	"0:     cmpnei  %1, 0           \n"
+	"       bf      8f              \n"
+	"       mov     %3, %1          \n"
+	"       or      %3, %2          \n"
+	"       andi    %3, 3           \n"
+	"       cmpnei  %3, 0           \n"
+	"       bf      1f              \n"
+	"       br      5f              \n"
+	"1:     cmplti  %0, 16          \n" /* 4W */
+	"       bt      3f              \n"
+	"       ldw     %3, (%2, 0)     \n"
+	"       ldw     %4, (%2, 4)     \n"
+	"       ldw     %5, (%2, 8)     \n"
+	"       ldw     %6, (%2, 12)    \n"
+	"2:     stw     %3, (%1, 0)     \n"
+	"9:     stw     %4, (%1, 4)     \n"
+	"10:    stw     %5, (%1, 8)     \n"
+	"11:    stw     %6, (%1, 12)    \n"
+	"       addi    %2, 16          \n"
+	"       addi    %1, 16          \n"
+	"       subi    %0, 16          \n"
+	"       br      1b              \n"
+	"3:     cmplti  %0, 4           \n" /* 1W */
+	"       bt      5f              \n"
+	"       ldw     %3, (%2, 0)     \n"
+	"4:     stw     %3, (%1, 0)     \n"
+	"       addi    %2, 4           \n"
+	"       addi    %1, 4           \n"
+	"       subi    %0, 4           \n"
+	"       br      3b              \n"
+	"5:     cmpnei  %0, 0           \n"  /* 1B */
+	"       bf      13f             \n"
+	"       ldb     %3, (%2, 0)     \n"
+	"6:     stb     %3, (%1, 0)     \n"
+	"       addi    %2,  1          \n"
+	"       addi    %1,  1          \n"
+	"       subi    %0,  1          \n"
+	"       br      5b              \n"
+	"7:     subi	%0,  4          \n"
+	"8:     subi	%0,  4          \n"
+	"12:    subi	%0,  4          \n"
+	"       br      13f             \n"
+	".section __ex_table, \"a\"     \n"
+	".align   2                     \n"
+	".long    2b, 13f               \n"
+	".long    4b, 13f               \n"
+	".long    6b, 13f               \n"
+	".long    9b, 12b               \n"
+	".long   10b, 8b                \n"
+	".long   11b, 7b                \n"
+	".previous                      \n"
+	"13:                            \n"
+	: "=r"(n), "=r"(to), "=r"(from), "=r"(w0),
+	  "=r"(w1), "=r"(w2), "=r"(w3)
+	: "0"(n), "1"(to), "2"(from)
+	: "memory");
+
+	return n;
+}
+EXPORT_SYMBOL(raw_copy_to_user);
+
+/*
+ * __clear_user: - Zero a block of memory in user space, with less checking.
+ * @to:   Destination address, in user space.
+ * @n:    Number of bytes to zero.
+ *
+ * Zero a block of memory in user space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be cleared.
+ * On success, this will be zero.
+ */
+unsigned long
+__clear_user(void __user *to, unsigned long n)
+{
+	int data, value, tmp;
+
+	__asm__ __volatile__(
+	"0:     cmpnei  %1, 0           \n"
+	"       bf      7f              \n"
+	"       mov     %3, %1          \n"
+	"       andi    %3, 3           \n"
+	"       cmpnei  %3, 0           \n"
+	"       bf      1f              \n"
+	"       br      5f              \n"
+	"1:     cmplti  %0, 32          \n" /* 4W */
+	"       bt      3f              \n"
+	"8:     stw     %2, (%1, 0)     \n"
+	"10:    stw     %2, (%1, 4)     \n"
+	"11:    stw     %2, (%1, 8)     \n"
+	"12:    stw     %2, (%1, 12)    \n"
+	"13:    stw     %2, (%1, 16)    \n"
+	"14:    stw     %2, (%1, 20)    \n"
+	"15:    stw     %2, (%1, 24)    \n"
+	"16:    stw     %2, (%1, 28)    \n"
+	"       addi    %1, 32          \n"
+	"       subi    %0, 32          \n"
+	"       br      1b              \n"
+	"3:     cmplti  %0, 4           \n" /* 1W */
+	"       bt      5f              \n"
+	"4:     stw     %2, (%1, 0)     \n"
+	"       addi    %1, 4           \n"
+	"       subi    %0, 4           \n"
+	"       br      3b              \n"
+	"5:     cmpnei  %0, 0           \n" /* 1B */
+	"9:     bf      7f              \n"
+	"6:     stb     %2, (%1, 0)     \n"
+	"       addi    %1,  1          \n"
+	"       subi    %0,  1          \n"
+	"       br      5b              \n"
+	".section __ex_table,\"a\"      \n"
+	".align   2                     \n"
+	".long    8b, 9b                \n"
+	".long    10b, 9b               \n"
+	".long    11b, 9b               \n"
+	".long    12b, 9b               \n"
+	".long    13b, 9b               \n"
+	".long    14b, 9b               \n"
+	".long    15b, 9b               \n"
+	".long    16b, 9b               \n"
+	".long    4b, 9b                \n"
+	".long    6b, 9b                \n"
+	".previous                      \n"
+	"7:                             \n"
+	: "=r"(n), "=r" (data), "=r"(value), "=r"(tmp)
+	: "0"(n), "1"(to), "2"(0)
+	: "memory");
+
+	return n;
+}
+EXPORT_SYMBOL(__clear_user);
diff --git a/arch/csky/mm/Makefile b/arch/csky/mm/Makefile
new file mode 100644
index 000000000..6e7696e55
--- /dev/null
+++ b/arch/csky/mm/Makefile
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0-only
+ifeq ($(CONFIG_CPU_HAS_CACHEV2),y)
+obj-y +=			cachev2.o
+CFLAGS_REMOVE_cachev2.o = $(CC_FLAGS_FTRACE)
+else
+obj-y +=			cachev1.o
+CFLAGS_REMOVE_cachev1.o = $(CC_FLAGS_FTRACE)
+endif
+
+obj-y +=			dma-mapping.o
+obj-y +=			fault.o
+obj-$(CONFIG_HIGHMEM) +=	highmem.o
+obj-y +=			init.o
+obj-y +=			ioremap.o
+obj-y +=			syscache.o
+obj-y +=			tlb.o
+obj-y +=			asid.o
+obj-y +=			context.o
+obj-$(CONFIG_HAVE_TCM) +=	tcm.o
diff --git a/arch/csky/mm/asid.c b/arch/csky/mm/asid.c
new file mode 100644
index 000000000..7fb6c417b
--- /dev/null
+++ b/arch/csky/mm/asid.c
@@ -0,0 +1,188 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Generic ASID allocator.
+ *
+ * Based on arch/arm/mm/context.c
+ *
+ * Copyright (C) 2002-2003 Deep Blue Solutions Ltd, all rights reserved.
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#include <linux/slab.h>
+#include <linux/mm_types.h>
+
+#include <asm/asid.h>
+
+#define reserved_asid(info, cpu) *per_cpu_ptr((info)->reserved, cpu)
+
+#define ASID_MASK(info)			(~GENMASK((info)->bits - 1, 0))
+#define ASID_FIRST_VERSION(info)	(1UL << ((info)->bits))
+
+#define asid2idx(info, asid)		(((asid) & ~ASID_MASK(info)) >> (info)->ctxt_shift)
+#define idx2asid(info, idx)		(((idx) << (info)->ctxt_shift) & ~ASID_MASK(info))
+
+static void flush_context(struct asid_info *info)
+{
+	int i;
+	u64 asid;
+
+	/* Update the list of reserved ASIDs and the ASID bitmap. */
+	bitmap_zero(info->map, NUM_CTXT_ASIDS(info));
+
+	for_each_possible_cpu(i) {
+		asid = atomic64_xchg_relaxed(&active_asid(info, i), 0);
+		/*
+		 * If this CPU has already been through a
+		 * rollover, but hasn't run another task in
+		 * the meantime, we must preserve its reserved
+		 * ASID, as this is the only trace we have of
+		 * the process it is still running.
+		 */
+		if (asid == 0)
+			asid = reserved_asid(info, i);
+		__set_bit(asid2idx(info, asid), info->map);
+		reserved_asid(info, i) = asid;
+	}
+
+	/*
+	 * Queue a TLB invalidation for each CPU to perform on next
+	 * context-switch
+	 */
+	cpumask_setall(&info->flush_pending);
+}
+
+static bool check_update_reserved_asid(struct asid_info *info, u64 asid,
+				       u64 newasid)
+{
+	int cpu;
+	bool hit = false;
+
+	/*
+	 * Iterate over the set of reserved ASIDs looking for a match.
+	 * If we find one, then we can update our mm to use newasid
+	 * (i.e. the same ASID in the current generation) but we can't
+	 * exit the loop early, since we need to ensure that all copies
+	 * of the old ASID are updated to reflect the mm. Failure to do
+	 * so could result in us missing the reserved ASID in a future
+	 * generation.
+	 */
+	for_each_possible_cpu(cpu) {
+		if (reserved_asid(info, cpu) == asid) {
+			hit = true;
+			reserved_asid(info, cpu) = newasid;
+		}
+	}
+
+	return hit;
+}
+
+static u64 new_context(struct asid_info *info, atomic64_t *pasid,
+		       struct mm_struct *mm)
+{
+	static u32 cur_idx = 1;
+	u64 asid = atomic64_read(pasid);
+	u64 generation = atomic64_read(&info->generation);
+
+	if (asid != 0) {
+		u64 newasid = generation | (asid & ~ASID_MASK(info));
+
+		/*
+		 * If our current ASID was active during a rollover, we
+		 * can continue to use it and this was just a false alarm.
+		 */
+		if (check_update_reserved_asid(info, asid, newasid))
+			return newasid;
+
+		/*
+		 * We had a valid ASID in a previous life, so try to re-use
+		 * it if possible.
+		 */
+		if (!__test_and_set_bit(asid2idx(info, asid), info->map))
+			return newasid;
+	}
+
+	/*
+	 * Allocate a free ASID. If we can't find one, take a note of the
+	 * currently active ASIDs and mark the TLBs as requiring flushes.  We
+	 * always count from ASID #2 (index 1), as we use ASID #0 when setting
+	 * a reserved TTBR0 for the init_mm and we allocate ASIDs in even/odd
+	 * pairs.
+	 */
+	asid = find_next_zero_bit(info->map, NUM_CTXT_ASIDS(info), cur_idx);
+	if (asid != NUM_CTXT_ASIDS(info))
+		goto set_asid;
+
+	/* We're out of ASIDs, so increment the global generation count */
+	generation = atomic64_add_return_relaxed(ASID_FIRST_VERSION(info),
+						 &info->generation);
+	flush_context(info);
+
+	/* We have more ASIDs than CPUs, so this will always succeed */
+	asid = find_next_zero_bit(info->map, NUM_CTXT_ASIDS(info), 1);
+
+set_asid:
+	__set_bit(asid, info->map);
+	cur_idx = asid;
+	cpumask_clear(mm_cpumask(mm));
+	return idx2asid(info, asid) | generation;
+}
+
+/*
+ * Generate a new ASID for the context.
+ *
+ * @pasid: Pointer to the current ASID batch allocated. It will be updated
+ * with the new ASID batch.
+ * @cpu: current CPU ID. Must have been acquired through get_cpu()
+ */
+void asid_new_context(struct asid_info *info, atomic64_t *pasid,
+		      unsigned int cpu, struct mm_struct *mm)
+{
+	unsigned long flags;
+	u64 asid;
+
+	raw_spin_lock_irqsave(&info->lock, flags);
+	/* Check that our ASID belongs to the current generation. */
+	asid = atomic64_read(pasid);
+	if ((asid ^ atomic64_read(&info->generation)) >> info->bits) {
+		asid = new_context(info, pasid, mm);
+		atomic64_set(pasid, asid);
+	}
+
+	if (cpumask_test_and_clear_cpu(cpu, &info->flush_pending))
+		info->flush_cpu_ctxt_cb();
+
+	atomic64_set(&active_asid(info, cpu), asid);
+	cpumask_set_cpu(cpu, mm_cpumask(mm));
+	raw_spin_unlock_irqrestore(&info->lock, flags);
+}
+
+/*
+ * Initialize the ASID allocator
+ *
+ * @info: Pointer to the asid allocator structure
+ * @bits: Number of ASIDs available
+ * @asid_per_ctxt: Number of ASIDs to allocate per-context. ASIDs are
+ * allocated contiguously for a given context. This value should be a power of
+ * 2.
+ */
+int asid_allocator_init(struct asid_info *info,
+			u32 bits, unsigned int asid_per_ctxt,
+			void (*flush_cpu_ctxt_cb)(void))
+{
+	info->bits = bits;
+	info->ctxt_shift = ilog2(asid_per_ctxt);
+	info->flush_cpu_ctxt_cb = flush_cpu_ctxt_cb;
+	/*
+	 * Expect allocation after rollover to fail if we don't have at least
+	 * one more ASID than CPUs. ASID #0 is always reserved.
+	 */
+	WARN_ON(NUM_CTXT_ASIDS(info) - 1 <= num_possible_cpus());
+	atomic64_set(&info->generation, ASID_FIRST_VERSION(info));
+	info->map = bitmap_zalloc(NUM_CTXT_ASIDS(info), GFP_KERNEL);
+	if (!info->map)
+		return -ENOMEM;
+
+	raw_spin_lock_init(&info->lock);
+
+	return 0;
+}
diff --git a/arch/csky/mm/cachev1.c b/arch/csky/mm/cachev1.c
new file mode 100644
index 000000000..5a5a9804a
--- /dev/null
+++ b/arch/csky/mm/cachev1.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/spinlock.h>
+#include <asm/cache.h>
+#include <abi/reg_ops.h>
+
+/* for L1-cache */
+#define INS_CACHE		(1 << 0)
+#define DATA_CACHE		(1 << 1)
+#define CACHE_INV		(1 << 4)
+#define CACHE_CLR		(1 << 5)
+#define CACHE_OMS		(1 << 6)
+#define CACHE_ITS		(1 << 7)
+#define CACHE_LICF		(1 << 31)
+
+/* for L2-cache */
+#define CR22_LEVEL_SHIFT	(1)
+#define CR22_SET_SHIFT		(7)
+#define CR22_WAY_SHIFT		(30)
+#define CR22_WAY_SHIFT_L2	(29)
+
+static DEFINE_SPINLOCK(cache_lock);
+
+static inline void cache_op_line(unsigned long i, unsigned int val)
+{
+	mtcr("cr22", i);
+	mtcr("cr17", val);
+}
+
+#define CCR2_L2E (1 << 3)
+static void cache_op_all(unsigned int value, unsigned int l2)
+{
+	mtcr("cr17", value | CACHE_CLR);
+	mb();
+
+	if (l2 && (mfcr_ccr2() & CCR2_L2E)) {
+		mtcr("cr24", value | CACHE_CLR);
+		mb();
+	}
+}
+
+static void cache_op_range(
+	unsigned int start,
+	unsigned int end,
+	unsigned int value,
+	unsigned int l2)
+{
+	unsigned long i, flags;
+	unsigned int val = value | CACHE_CLR | CACHE_OMS;
+	bool l2_sync;
+
+	if (unlikely((end - start) >= PAGE_SIZE) ||
+	    unlikely(start < PAGE_OFFSET) ||
+	    unlikely(start >= PAGE_OFFSET + LOWMEM_LIMIT)) {
+		cache_op_all(value, l2);
+		return;
+	}
+
+	if ((mfcr_ccr2() & CCR2_L2E) && l2)
+		l2_sync = 1;
+	else
+		l2_sync = 0;
+
+	spin_lock_irqsave(&cache_lock, flags);
+
+	i = start & ~(L1_CACHE_BYTES - 1);
+	for (; i < end; i += L1_CACHE_BYTES) {
+		cache_op_line(i, val);
+		if (l2_sync) {
+			mb();
+			mtcr("cr24", val);
+		}
+	}
+	spin_unlock_irqrestore(&cache_lock, flags);
+
+	mb();
+}
+
+void dcache_wb_line(unsigned long start)
+{
+	asm volatile("idly4\n":::"memory");
+	cache_op_line(start, DATA_CACHE|CACHE_CLR);
+	mb();
+}
+
+void icache_inv_range(unsigned long start, unsigned long end)
+{
+	cache_op_range(start, end, INS_CACHE|CACHE_INV, 0);
+}
+
+void icache_inv_all(void)
+{
+	cache_op_all(INS_CACHE|CACHE_INV, 0);
+}
+
+void local_icache_inv_all(void *priv)
+{
+	cache_op_all(INS_CACHE|CACHE_INV, 0);
+}
+
+void dcache_wb_range(unsigned long start, unsigned long end)
+{
+	cache_op_range(start, end, DATA_CACHE|CACHE_CLR, 0);
+}
+
+void dcache_wbinv_all(void)
+{
+	cache_op_all(DATA_CACHE|CACHE_CLR|CACHE_INV, 0);
+}
+
+void cache_wbinv_range(unsigned long start, unsigned long end)
+{
+	cache_op_range(start, end, INS_CACHE|DATA_CACHE|CACHE_CLR|CACHE_INV, 0);
+}
+EXPORT_SYMBOL(cache_wbinv_range);
+
+void cache_wbinv_all(void)
+{
+	cache_op_all(INS_CACHE|DATA_CACHE|CACHE_CLR|CACHE_INV, 0);
+}
+
+void dma_wbinv_range(unsigned long start, unsigned long end)
+{
+	cache_op_range(start, end, DATA_CACHE|CACHE_CLR|CACHE_INV, 1);
+}
+
+void dma_inv_range(unsigned long start, unsigned long end)
+{
+	cache_op_range(start, end, DATA_CACHE|CACHE_CLR|CACHE_INV, 1);
+}
+
+void dma_wb_range(unsigned long start, unsigned long end)
+{
+	cache_op_range(start, end, DATA_CACHE|CACHE_CLR|CACHE_INV, 1);
+}
diff --git a/arch/csky/mm/cachev2.c b/arch/csky/mm/cachev2.c
new file mode 100644
index 000000000..7a9664adc
--- /dev/null
+++ b/arch/csky/mm/cachev2.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/mm.h>
+#include <asm/cache.h>
+#include <asm/barrier.h>
+
+/* for L1-cache */
+#define INS_CACHE		(1 << 0)
+#define DATA_CACHE		(1 << 1)
+#define CACHE_INV		(1 << 4)
+#define CACHE_CLR		(1 << 5)
+#define CACHE_OMS		(1 << 6)
+
+void local_icache_inv_all(void *priv)
+{
+	mtcr("cr17", INS_CACHE|CACHE_INV);
+	sync_is();
+}
+
+#ifdef CONFIG_CPU_HAS_ICACHE_INS
+void icache_inv_range(unsigned long start, unsigned long end)
+{
+	unsigned long i = start & ~(L1_CACHE_BYTES - 1);
+
+	for (; i < end; i += L1_CACHE_BYTES)
+		asm volatile("icache.iva %0\n"::"r"(i):"memory");
+	sync_is();
+}
+#else
+struct cache_range {
+	unsigned long start;
+	unsigned long end;
+};
+
+static DEFINE_SPINLOCK(cache_lock);
+
+static inline void cache_op_line(unsigned long i, unsigned int val)
+{
+	mtcr("cr22", i);
+	mtcr("cr17", val);
+}
+
+void local_icache_inv_range(void *priv)
+{
+	struct cache_range *param = priv;
+	unsigned long i = param->start & ~(L1_CACHE_BYTES - 1);
+	unsigned long flags;
+
+	spin_lock_irqsave(&cache_lock, flags);
+
+	for (; i < param->end; i += L1_CACHE_BYTES)
+		cache_op_line(i, INS_CACHE | CACHE_INV | CACHE_OMS);
+
+	spin_unlock_irqrestore(&cache_lock, flags);
+
+	sync_is();
+}
+
+void icache_inv_range(unsigned long start, unsigned long end)
+{
+	struct cache_range param = { start, end };
+
+	if (irqs_disabled())
+		local_icache_inv_range(&param);
+	else
+		on_each_cpu(local_icache_inv_range, &param, 1);
+}
+#endif
+
+inline void dcache_wb_line(unsigned long start)
+{
+	asm volatile("dcache.cval1 %0\n"::"r"(start):"memory");
+	sync_is();
+}
+
+void dcache_wb_range(unsigned long start, unsigned long end)
+{
+	unsigned long i = start & ~(L1_CACHE_BYTES - 1);
+
+	for (; i < end; i += L1_CACHE_BYTES)
+		asm volatile("dcache.cval1 %0\n"::"r"(i):"memory");
+	sync_is();
+}
+
+void cache_wbinv_range(unsigned long start, unsigned long end)
+{
+	dcache_wb_range(start, end);
+	icache_inv_range(start, end);
+}
+EXPORT_SYMBOL(cache_wbinv_range);
+
+void dma_wbinv_range(unsigned long start, unsigned long end)
+{
+	unsigned long i = start & ~(L1_CACHE_BYTES - 1);
+
+	for (; i < end; i += L1_CACHE_BYTES)
+		asm volatile("dcache.civa %0\n"::"r"(i):"memory");
+	sync_is();
+}
+
+void dma_inv_range(unsigned long start, unsigned long end)
+{
+	unsigned long i = start & ~(L1_CACHE_BYTES - 1);
+
+	for (; i < end; i += L1_CACHE_BYTES)
+		asm volatile("dcache.iva %0\n"::"r"(i):"memory");
+	sync_is();
+}
+
+void dma_wb_range(unsigned long start, unsigned long end)
+{
+	unsigned long i = start & ~(L1_CACHE_BYTES - 1);
+
+	for (; i < end; i += L1_CACHE_BYTES)
+		asm volatile("dcache.cva %0\n"::"r"(i):"memory");
+	sync_is();
+}
diff --git a/arch/csky/mm/context.c b/arch/csky/mm/context.c
new file mode 100644
index 000000000..0d95bdd93
--- /dev/null
+++ b/arch/csky/mm/context.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/bitops.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+
+#include <asm/asid.h>
+#include <asm/mmu_context.h>
+#include <asm/smp.h>
+#include <asm/tlbflush.h>
+
+static DEFINE_PER_CPU(atomic64_t, active_asids);
+static DEFINE_PER_CPU(u64, reserved_asids);
+
+struct asid_info asid_info;
+
+void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
+{
+	asid_check_context(&asid_info, &mm->context.asid, cpu, mm);
+}
+
+static void asid_flush_cpu_ctxt(void)
+{
+	local_tlb_invalid_all();
+}
+
+static int asids_init(void)
+{
+	BUG_ON(((1 << CONFIG_CPU_ASID_BITS) - 1) <= num_possible_cpus());
+
+	if (asid_allocator_init(&asid_info, CONFIG_CPU_ASID_BITS, 1,
+				asid_flush_cpu_ctxt))
+		panic("Unable to initialize ASID allocator for %lu ASIDs\n",
+		      NUM_ASIDS(&asid_info));
+
+	asid_info.active = &active_asids;
+	asid_info.reserved = &reserved_asids;
+
+	pr_info("ASID allocator initialised with %lu entries\n",
+		NUM_CTXT_ASIDS(&asid_info));
+
+	return 0;
+}
+early_initcall(asids_init);
diff --git a/arch/csky/mm/dma-mapping.c b/arch/csky/mm/dma-mapping.c
new file mode 100644
index 000000000..82447029f
--- /dev/null
+++ b/arch/csky/mm/dma-mapping.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/cache.h>
+#include <linux/dma-map-ops.h>
+#include <linux/genalloc.h>
+#include <linux/highmem.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/scatterlist.h>
+#include <linux/types.h>
+#include <asm/cache.h>
+
+static inline void cache_op(phys_addr_t paddr, size_t size,
+			    void (*fn)(unsigned long start, unsigned long end))
+{
+	struct page *page    = phys_to_page(paddr);
+	void *start          = __va(page_to_phys(page));
+	unsigned long offset = offset_in_page(paddr);
+	size_t left          = size;
+
+	do {
+		size_t len = left;
+
+		if (offset + len > PAGE_SIZE)
+			len = PAGE_SIZE - offset;
+
+		if (PageHighMem(page)) {
+			start = kmap_atomic(page);
+
+			fn((unsigned long)start + offset,
+					(unsigned long)start + offset + len);
+
+			kunmap_atomic(start);
+		} else {
+			fn((unsigned long)start + offset,
+					(unsigned long)start + offset + len);
+		}
+		offset = 0;
+
+		page++;
+		start += PAGE_SIZE;
+		left -= len;
+	} while (left);
+}
+
+static void dma_wbinv_set_zero_range(unsigned long start, unsigned long end)
+{
+	memset((void *)start, 0, end - start);
+	dma_wbinv_range(start, end);
+}
+
+void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+	cache_op(page_to_phys(page), size, dma_wbinv_set_zero_range);
+}
+
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		cache_op(paddr, size, dma_wb_range);
+		break;
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		cache_op(paddr, size, dma_wbinv_range);
+		break;
+	default:
+		BUG();
+	}
+}
+
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		return;
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		cache_op(paddr, size, dma_inv_range);
+		break;
+	default:
+		BUG();
+	}
+}
diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c
new file mode 100644
index 000000000..7ff401108
--- /dev/null
+++ b/arch/csky/mm/fault.c
@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/extable.h>
+#include <linux/kprobes.h>
+#include <linux/mmu_context.h>
+#include <linux/perf_event.h>
+
+int fixup_exception(struct pt_regs *regs)
+{
+	const struct exception_table_entry *fixup;
+
+	fixup = search_exception_tables(instruction_pointer(regs));
+	if (fixup) {
+		regs->pc = fixup->fixup;
+
+		return 1;
+	}
+
+	return 0;
+}
+
+static inline bool is_write(struct pt_regs *regs)
+{
+	switch (trap_no(regs)) {
+	case VEC_TLBINVALIDS:
+		return true;
+	case VEC_TLBMODIFIED:
+		return true;
+	}
+
+	return false;
+}
+
+#ifdef CONFIG_CPU_HAS_LDSTEX
+static inline void csky_cmpxchg_fixup(struct pt_regs *regs)
+{
+	return;
+}
+#else
+extern unsigned long csky_cmpxchg_ldw;
+extern unsigned long csky_cmpxchg_stw;
+static inline void csky_cmpxchg_fixup(struct pt_regs *regs)
+{
+	if (trap_no(regs) != VEC_TLBMODIFIED)
+		return;
+
+	if (instruction_pointer(regs) == (unsigned long)&csky_cmpxchg_stw)
+		instruction_pointer_set(regs, (unsigned long)&csky_cmpxchg_ldw);
+	return;
+}
+#endif
+
+static inline void no_context(struct pt_regs *regs, unsigned long addr)
+{
+	current->thread.trap_no = trap_no(regs);
+
+	/* Are we prepared to handle this kernel fault? */
+	if (fixup_exception(regs))
+		return;
+
+	/*
+	 * Oops. The kernel tried to access some bad page. We'll have to
+	 * terminate things with extreme prejudice.
+	 */
+	bust_spinlocks(1);
+	pr_alert("Unable to handle kernel paging request at virtual "
+		 "addr 0x%08lx, pc: 0x%08lx\n", addr, regs->pc);
+	die(regs, "Oops");
+	make_task_dead(SIGKILL);
+}
+
+static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault)
+{
+	current->thread.trap_no = trap_no(regs);
+
+	if (fault & VM_FAULT_OOM) {
+		/*
+		 * We ran out of memory, call the OOM killer, and return the userspace
+		 * (which will retry the fault, or kill us if we got oom-killed).
+		 */
+		if (!user_mode(regs)) {
+			no_context(regs, addr);
+			return;
+		}
+		pagefault_out_of_memory();
+		return;
+	} else if (fault & VM_FAULT_SIGBUS) {
+		/* Kernel mode? Handle exceptions or die */
+		if (!user_mode(regs)) {
+			no_context(regs, addr);
+			return;
+		}
+		do_trap(regs, SIGBUS, BUS_ADRERR, addr);
+		return;
+	}
+	BUG();
+}
+
+static inline void bad_area_nosemaphore(struct pt_regs *regs, struct mm_struct *mm, int code, unsigned long addr)
+{
+	/*
+	 * Something tried to access memory that isn't in our memory map.
+	 * Fix it, but check if it's kernel or user first.
+	 */
+	/* User mode accesses just cause a SIGSEGV */
+	if (user_mode(regs)) {
+		do_trap(regs, SIGSEGV, code, addr);
+		return;
+	}
+
+	no_context(regs, addr);
+}
+
+static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long addr)
+{
+	pgd_t *pgd, *pgd_k;
+	pud_t *pud, *pud_k;
+	pmd_t *pmd, *pmd_k;
+	pte_t *pte_k;
+	int offset;
+
+	/* User mode accesses just cause a SIGSEGV */
+	if (user_mode(regs)) {
+		do_trap(regs, SIGSEGV, code, addr);
+		return;
+	}
+
+	/*
+	 * Synchronize this task's top level page-table
+	 * with the 'reference' page table.
+	 *
+	 * Do _not_ use "tsk" here. We might be inside
+	 * an interrupt in the middle of a task switch..
+	 */
+	offset = pgd_index(addr);
+
+	pgd = get_pgd() + offset;
+	pgd_k = init_mm.pgd + offset;
+
+	if (!pgd_present(*pgd_k)) {
+		no_context(regs, addr);
+		return;
+	}
+	set_pgd(pgd, *pgd_k);
+
+	pud = (pud_t *)pgd;
+	pud_k = (pud_t *)pgd_k;
+	if (!pud_present(*pud_k)) {
+		no_context(regs, addr);
+		return;
+	}
+
+	pmd = pmd_offset(pud, addr);
+	pmd_k = pmd_offset(pud_k, addr);
+	if (!pmd_present(*pmd_k)) {
+		no_context(regs, addr);
+		return;
+	}
+	set_pmd(pmd, *pmd_k);
+
+	pte_k = pte_offset_kernel(pmd_k, addr);
+	if (!pte_present(*pte_k)) {
+		no_context(regs, addr);
+		return;
+	}
+
+	flush_tlb_one(addr);
+}
+
+static inline bool access_error(struct pt_regs *regs, struct vm_area_struct *vma)
+{
+	if (is_write(regs)) {
+		if (!(vma->vm_flags & VM_WRITE))
+			return true;
+	} else {
+		if (unlikely(!vma_is_accessible(vma)))
+			return true;
+	}
+	return false;
+}
+
+/*
+ * This routine handles page faults.  It determines the address and the
+ * problem, and then passes it off to one of the appropriate routines.
+ */
+asmlinkage void do_page_fault(struct pt_regs *regs)
+{
+	struct task_struct *tsk;
+	struct vm_area_struct *vma;
+	struct mm_struct *mm;
+	unsigned long addr = read_mmu_entryhi() & PAGE_MASK;
+	unsigned int flags = FAULT_FLAG_DEFAULT;
+	int code = SEGV_MAPERR;
+	vm_fault_t fault;
+
+	tsk = current;
+	mm = tsk->mm;
+
+	csky_cmpxchg_fixup(regs);
+
+	if (kprobe_page_fault(regs, tsk->thread.trap_no))
+		return;
+
+	/*
+	 * Fault-in kernel-space virtual memory on-demand.
+	 * The 'reference' page table is init_mm.pgd.
+	 *
+	 * NOTE! We MUST NOT take any locks for this case. We may
+	 * be in an interrupt or a critical region, and should
+	 * only copy the information from the master page table,
+	 * nothing more.
+	 */
+	if (unlikely((addr >= VMALLOC_START) && (addr <= VMALLOC_END))) {
+		vmalloc_fault(regs, code, addr);
+		return;
+	}
+
+	/* Enable interrupts if they were enabled in the parent context. */
+	if (likely(regs->sr & BIT(6)))
+		local_irq_enable();
+
+	/*
+	 * If we're in an interrupt, have no user context, or are running
+	 * in an atomic region, then we must not take the fault.
+	 */
+	if (unlikely(faulthandler_disabled() || !mm)) {
+		no_context(regs, addr);
+		return;
+	}
+
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
+	if (is_write(regs))
+		flags |= FAULT_FLAG_WRITE;
+retry:
+	vma = lock_mm_and_find_vma(mm, addr, regs);
+	if (unlikely(!vma)) {
+		bad_area_nosemaphore(regs, mm, code, addr);
+		return;
+	}
+
+	/*
+	 * Ok, we have a good vm_area for this memory access, so
+	 * we can handle it.
+	 */
+	code = SEGV_ACCERR;
+
+	if (unlikely(access_error(regs, vma))) {
+		mmap_read_unlock(mm);
+		bad_area_nosemaphore(regs, mm, code, addr);
+		return;
+	}
+
+	/*
+	 * If for any reason at all we could not handle the fault,
+	 * make sure we exit gracefully rather than endlessly redo
+	 * the fault.
+	 */
+	fault = handle_mm_fault(vma, addr, flags, regs);
+
+	/*
+	 * If we need to retry but a fatal signal is pending, handle the
+	 * signal first. We do not need to release the mmap_lock because it
+	 * would already be released in __lock_page_or_retry in mm/filemap.c.
+	 */
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			no_context(regs, addr);
+		return;
+	}
+
+	/* The fault is fully completed (including releasing mmap lock) */
+	if (fault & VM_FAULT_COMPLETED)
+		return;
+
+	if (unlikely(fault & VM_FAULT_RETRY)) {
+		flags |= FAULT_FLAG_TRIED;
+
+		/*
+		 * No need to mmap_read_unlock(mm) as we would
+		 * have already released it in __lock_page_or_retry
+		 * in mm/filemap.c.
+		 */
+		goto retry;
+	}
+
+	mmap_read_unlock(mm);
+
+	if (unlikely(fault & VM_FAULT_ERROR)) {
+		mm_fault_error(regs, addr, fault);
+		return;
+	}
+	return;
+}
diff --git a/arch/csky/mm/highmem.c b/arch/csky/mm/highmem.c
new file mode 100644
index 000000000..4161df3c6
--- /dev/null
+++ b/arch/csky/mm/highmem.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/module.h>
+#include <linux/highmem.h>
+#include <linux/smp.h>
+#include <linux/memblock.h>
+#include <asm/fixmap.h>
+#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+
+unsigned long highstart_pfn, highend_pfn;
+
+void kmap_flush_tlb(unsigned long addr)
+{
+	flush_tlb_one(addr);
+}
+EXPORT_SYMBOL(kmap_flush_tlb);
+
+void __init kmap_init(void)
+{
+	unsigned long vaddr;
+	pgd_t *pgd;
+	pmd_t *pmd;
+	pud_t *pud;
+	pte_t *pte;
+
+	vaddr = PKMAP_BASE;
+	fixrange_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, swapper_pg_dir);
+
+	pgd = swapper_pg_dir + pgd_index(vaddr);
+	pud = (pud_t *)pgd;
+	pmd = pmd_offset(pud, vaddr);
+	pte = pte_offset_kernel(pmd, vaddr);
+	pkmap_page_table = pte;
+}
diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c
new file mode 100644
index 000000000..fa16015ea
--- /dev/null
+++ b/arch/csky/mm/init.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/bug.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/pagemap.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/memblock.h>
+#include <linux/swap.h>
+#include <linux/proc_fs.h>
+#include <linux/pfn.h>
+#include <linux/initrd.h>
+
+#include <asm/setup.h>
+#include <asm/cachectl.h>
+#include <asm/dma.h>
+#include <asm/pgalloc.h>
+#include <asm/mmu_context.h>
+#include <asm/sections.h>
+#include <asm/tlb.h>
+#include <asm/cacheflush.h>
+
+#define PTRS_KERN_TABLE \
+		((PTRS_PER_PGD - USER_PTRS_PER_PGD) * PTRS_PER_PTE)
+
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
+pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned_bss;
+pte_t kernel_pte_tables[PTRS_KERN_TABLE] __page_aligned_bss;
+
+EXPORT_SYMBOL(invalid_pte_table);
+
+void free_initmem(void)
+{
+	free_initmem_default(-1);
+}
+
+void pgd_init(unsigned long *p)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PGD; i++)
+		p[i] = __pa(invalid_pte_table);
+
+	flush_tlb_all();
+	local_icache_inv_all(NULL);
+}
+
+void __init mmu_init(unsigned long min_pfn, unsigned long max_pfn)
+{
+	int i;
+
+	for (i = 0; i < USER_PTRS_PER_PGD; i++)
+		swapper_pg_dir[i].pgd = __pa(invalid_pte_table);
+
+	for (i = USER_PTRS_PER_PGD; i < PTRS_PER_PGD; i++)
+		swapper_pg_dir[i].pgd =
+			__pa(kernel_pte_tables + (PTRS_PER_PTE * (i - USER_PTRS_PER_PGD)));
+
+	for (i = 0; i < PTRS_KERN_TABLE; i++)
+		set_pte(&kernel_pte_tables[i], __pte(_PAGE_GLOBAL));
+
+	for (i = min_pfn; i < max_pfn; i++)
+		set_pte(&kernel_pte_tables[i - PFN_DOWN(va_pa_offset)], pfn_pte(i, PAGE_KERNEL));
+
+	flush_tlb_all();
+	local_icache_inv_all(NULL);
+
+	/* Setup page mask to 4k */
+	write_mmu_pagemask(0);
+
+	setup_pgd(swapper_pg_dir, 0);
+}
+
+void __init fixrange_init(unsigned long start, unsigned long end,
+			pgd_t *pgd_base)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	int i, j, k;
+	unsigned long vaddr;
+
+	vaddr = start;
+	i = pgd_index(vaddr);
+	j = pud_index(vaddr);
+	k = pmd_index(vaddr);
+	pgd = pgd_base + i;
+
+	for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) {
+		pud = (pud_t *)pgd;
+		for ( ; (j < PTRS_PER_PUD) && (vaddr != end); pud++, j++) {
+			pmd = (pmd_t *)pud;
+			for (; (k < PTRS_PER_PMD) && (vaddr != end); pmd++, k++) {
+				if (pmd_none(*pmd)) {
+					pte = (pte_t *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
+					if (!pte)
+						panic("%s: Failed to allocate %lu bytes align=%lx\n",
+						      __func__, PAGE_SIZE,
+						      PAGE_SIZE);
+
+					set_pmd(pmd, __pmd(__pa(pte)));
+					BUG_ON(pte != pte_offset_kernel(pmd, 0));
+				}
+				vaddr += PMD_SIZE;
+			}
+			k = 0;
+		}
+		j = 0;
+	}
+}
+
+void __init fixaddr_init(void)
+{
+	unsigned long vaddr;
+
+	vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
+	fixrange_init(vaddr, vaddr + PMD_SIZE, swapper_pg_dir);
+}
+
+static const pgprot_t protection_map[16] = {
+	[VM_NONE]					= PAGE_NONE,
+	[VM_READ]					= PAGE_READ,
+	[VM_WRITE]					= PAGE_READ,
+	[VM_WRITE | VM_READ]				= PAGE_READ,
+	[VM_EXEC]					= PAGE_READ,
+	[VM_EXEC | VM_READ]				= PAGE_READ,
+	[VM_EXEC | VM_WRITE]				= PAGE_READ,
+	[VM_EXEC | VM_WRITE | VM_READ]			= PAGE_READ,
+	[VM_SHARED]					= PAGE_NONE,
+	[VM_SHARED | VM_READ]				= PAGE_READ,
+	[VM_SHARED | VM_WRITE]				= PAGE_WRITE,
+	[VM_SHARED | VM_WRITE | VM_READ]		= PAGE_WRITE,
+	[VM_SHARED | VM_EXEC]				= PAGE_READ,
+	[VM_SHARED | VM_EXEC | VM_READ]			= PAGE_READ,
+	[VM_SHARED | VM_EXEC | VM_WRITE]		= PAGE_WRITE,
+	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= PAGE_WRITE
+};
+DECLARE_VM_GET_PAGE_PROT
diff --git a/arch/csky/mm/ioremap.c b/arch/csky/mm/ioremap.c
new file mode 100644
index 000000000..70c8268d3
--- /dev/null
+++ b/arch/csky/mm/ioremap.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/io.h>
+
+pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+			      unsigned long size, pgprot_t vma_prot)
+{
+	if (!pfn_valid(pfn)) {
+		return pgprot_noncached(vma_prot);
+	} else if (file->f_flags & O_SYNC) {
+		return pgprot_writecombine(vma_prot);
+	}
+
+	return vma_prot;
+}
+EXPORT_SYMBOL(phys_mem_access_prot);
diff --git a/arch/csky/mm/syscache.c b/arch/csky/mm/syscache.c
new file mode 100644
index 000000000..cd847ad62
--- /dev/null
+++ b/arch/csky/mm/syscache.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/syscalls.h>
+#include <asm/page.h>
+#include <asm/cacheflush.h>
+#include <asm/cachectl.h>
+
+SYSCALL_DEFINE3(cacheflush,
+		void __user *, addr,
+		unsigned long, bytes,
+		int, cache)
+{
+	switch (cache) {
+	case BCACHE:
+	case DCACHE:
+		dcache_wb_range((unsigned long)addr,
+				(unsigned long)addr + bytes);
+		if (cache != BCACHE)
+			break;
+		fallthrough;
+	case ICACHE:
+		flush_icache_mm_range(current->mm,
+				(unsigned long)addr,
+				(unsigned long)addr + bytes);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/arch/csky/mm/tcm.c b/arch/csky/mm/tcm.c
new file mode 100644
index 000000000..ddeb36328
--- /dev/null
+++ b/arch/csky/mm/tcm.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/highmem.h>
+#include <linux/genalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/fixmap.h>
+
+#if (CONFIG_ITCM_RAM_BASE == 0xffffffff)
+#error "You should define ITCM_RAM_BASE"
+#endif
+
+#ifdef CONFIG_HAVE_DTCM
+#if (CONFIG_DTCM_RAM_BASE == 0xffffffff)
+#error "You should define DTCM_RAM_BASE"
+#endif
+
+#if (CONFIG_DTCM_RAM_BASE == CONFIG_ITCM_RAM_BASE)
+#error "You should define correct DTCM_RAM_BASE"
+#endif
+#endif
+
+extern char __tcm_start, __tcm_end, __dtcm_start;
+
+static struct gen_pool *tcm_pool;
+
+static void __init tcm_mapping_init(void)
+{
+	pte_t *tcm_pte;
+	unsigned long vaddr, paddr;
+	int i;
+
+	paddr = CONFIG_ITCM_RAM_BASE;
+
+	if (pfn_valid(PFN_DOWN(CONFIG_ITCM_RAM_BASE)))
+		goto panic;
+
+#ifndef CONFIG_HAVE_DTCM
+	for (i = 0; i < TCM_NR_PAGES; i++) {
+#else
+	for (i = 0; i < CONFIG_ITCM_NR_PAGES; i++) {
+#endif
+		vaddr = __fix_to_virt(FIX_TCM - i);
+
+		tcm_pte =
+			pte_offset_kernel((pmd_t *)pgd_offset_k(vaddr), vaddr);
+
+		set_pte(tcm_pte, pfn_pte(__phys_to_pfn(paddr), PAGE_KERNEL));
+
+		flush_tlb_one(vaddr);
+
+		paddr = paddr + PAGE_SIZE;
+	}
+
+#ifdef CONFIG_HAVE_DTCM
+	if (pfn_valid(PFN_DOWN(CONFIG_DTCM_RAM_BASE)))
+		goto panic;
+
+	paddr = CONFIG_DTCM_RAM_BASE;
+
+	for (i = 0; i < CONFIG_DTCM_NR_PAGES; i++) {
+		vaddr = __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES - i);
+
+		tcm_pte =
+			pte_offset_kernel((pmd_t *) pgd_offset_k(vaddr), vaddr);
+
+		set_pte(tcm_pte, pfn_pte(__phys_to_pfn(paddr), PAGE_KERNEL));
+
+		flush_tlb_one(vaddr);
+
+		paddr = paddr + PAGE_SIZE;
+	}
+#endif
+
+#ifndef CONFIG_HAVE_DTCM
+	memcpy((void *)__fix_to_virt(FIX_TCM),
+				&__tcm_start, &__tcm_end - &__tcm_start);
+
+	pr_info("%s: mapping tcm va:0x%08lx to pa:0x%08x\n",
+			__func__, __fix_to_virt(FIX_TCM), CONFIG_ITCM_RAM_BASE);
+
+	pr_info("%s: __tcm_start va:0x%08lx size:%d\n",
+			__func__, (unsigned long)&__tcm_start, &__tcm_end - &__tcm_start);
+#else
+	memcpy((void *)__fix_to_virt(FIX_TCM),
+				&__tcm_start, &__dtcm_start - &__tcm_start);
+
+	pr_info("%s: mapping itcm va:0x%08lx to pa:0x%08x\n",
+			__func__, __fix_to_virt(FIX_TCM), CONFIG_ITCM_RAM_BASE);
+
+	pr_info("%s: __itcm_start va:0x%08lx size:%d\n",
+			__func__, (unsigned long)&__tcm_start, &__dtcm_start - &__tcm_start);
+
+	memcpy((void *)__fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES),
+				&__dtcm_start, &__tcm_end - &__dtcm_start);
+
+	pr_info("%s: mapping dtcm va:0x%08lx to pa:0x%08x\n",
+			__func__, __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES),
+						CONFIG_DTCM_RAM_BASE);
+
+	pr_info("%s: __dtcm_start va:0x%08lx size:%d\n",
+			__func__, (unsigned long)&__dtcm_start, &__tcm_end - &__dtcm_start);
+
+#endif
+	return;
+panic:
+	panic("TCM init error");
+}
+
+void *tcm_alloc(size_t len)
+{
+	unsigned long vaddr;
+
+	if (!tcm_pool)
+		return NULL;
+
+	vaddr = gen_pool_alloc(tcm_pool, len);
+	if (!vaddr)
+		return NULL;
+
+	return (void *) vaddr;
+}
+EXPORT_SYMBOL(tcm_alloc);
+
+void tcm_free(void *addr, size_t len)
+{
+	gen_pool_free(tcm_pool, (unsigned long) addr, len);
+}
+EXPORT_SYMBOL(tcm_free);
+
+static int __init tcm_setup_pool(void)
+{
+#ifndef CONFIG_HAVE_DTCM
+	u32 pool_size = (u32) (TCM_NR_PAGES * PAGE_SIZE)
+				- (u32) (&__tcm_end - &__tcm_start);
+
+	u32 tcm_pool_start = __fix_to_virt(FIX_TCM)
+				+ (u32) (&__tcm_end - &__tcm_start);
+#else
+	u32 pool_size = (u32) (CONFIG_DTCM_NR_PAGES * PAGE_SIZE)
+				- (u32) (&__tcm_end - &__dtcm_start);
+
+	u32 tcm_pool_start = __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES)
+				+ (u32) (&__tcm_end - &__dtcm_start);
+#endif
+	int ret;
+
+	tcm_pool = gen_pool_create(2, -1);
+
+	ret = gen_pool_add(tcm_pool, tcm_pool_start, pool_size, -1);
+	if (ret) {
+		pr_err("%s: gen_pool add failed!\n", __func__);
+		return ret;
+	}
+
+	pr_info("%s: Added %d bytes @ 0x%08x to memory pool\n",
+		__func__, pool_size, tcm_pool_start);
+
+	return 0;
+}
+
+static int __init tcm_init(void)
+{
+	tcm_mapping_init();
+
+	tcm_setup_pool();
+
+	return 0;
+}
+arch_initcall(tcm_init);
diff --git a/arch/csky/mm/tlb.c b/arch/csky/mm/tlb.c
new file mode 100644
index 000000000..9234c5e5c
--- /dev/null
+++ b/arch/csky/mm/tlb.c
@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+
+#include <asm/mmu_context.h>
+#include <asm/setup.h>
+
+/*
+ * One C-SKY MMU TLB entry contain two PFN/page entry, ie:
+ * 1VPN -> 2PFN
+ */
+#define TLB_ENTRY_SIZE		(PAGE_SIZE * 2)
+#define TLB_ENTRY_SIZE_MASK	(PAGE_MASK << 1)
+
+void flush_tlb_all(void)
+{
+	tlb_invalid_all();
+}
+
+void flush_tlb_mm(struct mm_struct *mm)
+{
+#ifdef CONFIG_CPU_HAS_TLBI
+	sync_is();
+	asm volatile(
+		"tlbi.asids %0	\n"
+		"sync.i		\n"
+		:
+		: "r" (cpu_asid(mm))
+		: "memory");
+#else
+	tlb_invalid_all();
+#endif
+}
+
+/*
+ * MMU operation regs only could invalid tlb entry in jtlb and we
+ * need change asid field to invalid I-utlb & D-utlb.
+ */
+#ifndef CONFIG_CPU_HAS_TLBI
+#define restore_asid_inv_utlb(oldpid, newpid) \
+do { \
+	if (oldpid == newpid) \
+		write_mmu_entryhi(oldpid + 1); \
+	write_mmu_entryhi(oldpid); \
+} while (0)
+#endif
+
+void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			unsigned long end)
+{
+	unsigned long newpid = cpu_asid(vma->vm_mm);
+
+	start &= TLB_ENTRY_SIZE_MASK;
+	end   += TLB_ENTRY_SIZE - 1;
+	end   &= TLB_ENTRY_SIZE_MASK;
+
+#ifdef CONFIG_CPU_HAS_TLBI
+	sync_is();
+	while (start < end) {
+		asm volatile(
+			"tlbi.vas %0	\n"
+			:
+			: "r" (start | newpid)
+			: "memory");
+
+		start += 2*PAGE_SIZE;
+	}
+	asm volatile("sync.i\n");
+#else
+	{
+	unsigned long flags, oldpid;
+
+	local_irq_save(flags);
+	oldpid = read_mmu_entryhi() & ASID_MASK;
+	while (start < end) {
+		int idx;
+
+		write_mmu_entryhi(start | newpid);
+		start += 2*PAGE_SIZE;
+		tlb_probe();
+		idx = read_mmu_index();
+		if (idx >= 0)
+			tlb_invalid_indexed();
+	}
+	restore_asid_inv_utlb(oldpid, newpid);
+	local_irq_restore(flags);
+	}
+#endif
+}
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	start &= TLB_ENTRY_SIZE_MASK;
+	end   += TLB_ENTRY_SIZE - 1;
+	end   &= TLB_ENTRY_SIZE_MASK;
+
+#ifdef CONFIG_CPU_HAS_TLBI
+	sync_is();
+	while (start < end) {
+		asm volatile(
+			"tlbi.vaas %0	\n"
+			:
+			: "r" (start)
+			: "memory");
+
+		start += 2*PAGE_SIZE;
+	}
+	asm volatile("sync.i\n");
+#else
+	{
+	unsigned long flags, oldpid;
+
+	local_irq_save(flags);
+	oldpid = read_mmu_entryhi() & ASID_MASK;
+	while (start < end) {
+		int idx;
+
+		write_mmu_entryhi(start | oldpid);
+		start += 2*PAGE_SIZE;
+		tlb_probe();
+		idx = read_mmu_index();
+		if (idx >= 0)
+			tlb_invalid_indexed();
+	}
+	restore_asid_inv_utlb(oldpid, oldpid);
+	local_irq_restore(flags);
+	}
+#endif
+}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
+{
+	int newpid = cpu_asid(vma->vm_mm);
+
+	addr &= TLB_ENTRY_SIZE_MASK;
+
+#ifdef CONFIG_CPU_HAS_TLBI
+	sync_is();
+	asm volatile(
+		"tlbi.vas %0	\n"
+		"sync.i		\n"
+		:
+		: "r" (addr | newpid)
+		: "memory");
+#else
+	{
+	int oldpid, idx;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	oldpid = read_mmu_entryhi() & ASID_MASK;
+	write_mmu_entryhi(addr | newpid);
+	tlb_probe();
+	idx = read_mmu_index();
+	if (idx >= 0)
+		tlb_invalid_indexed();
+
+	restore_asid_inv_utlb(oldpid, newpid);
+	local_irq_restore(flags);
+	}
+#endif
+}
+
+void flush_tlb_one(unsigned long addr)
+{
+	addr &= TLB_ENTRY_SIZE_MASK;
+
+#ifdef CONFIG_CPU_HAS_TLBI
+	sync_is();
+	asm volatile(
+		"tlbi.vaas %0	\n"
+		"sync.i		\n"
+		:
+		: "r" (addr)
+		: "memory");
+#else
+	{
+	int oldpid, idx;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	oldpid = read_mmu_entryhi() & ASID_MASK;
+	write_mmu_entryhi(addr | oldpid);
+	tlb_probe();
+	idx = read_mmu_index();
+	if (idx >= 0)
+		tlb_invalid_indexed();
+
+	restore_asid_inv_utlb(oldpid, oldpid);
+	local_irq_restore(flags);
+	}
+#endif
+}
+EXPORT_SYMBOL(flush_tlb_one);