Adding upstream version 6.1.76.upstream/6.1.76

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

44 files changed, 6051 insertions, 0 deletions

diff --git a/arch/csky/kernel/Makefile b/arch/csky/kernel/Makefile
new file mode 100644
index 000000000..8a868316b
--- /dev/null
+++ b/arch/csky/kernel/Makefile
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0-only
+extra-y := 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 io.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/asm-offsets.c b/arch/csky/kernel/asm-offsets.c
new file mode 100644
index 000000000..d1e903579
--- /dev/null
+++ b/arch/csky/kernel/asm-offsets.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#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..547b4cd1b
--- /dev/null
+++ b/arch/csky/kernel/entry.S
@@ -0,0 +1,283 @@
+/* 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      1f
+
+	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 */
+1:
+#ifdef CONFIG_DEBUG_RSEQ
+	mov	a0, sp
+	jbsr	rseq_syscall
+#endif
+	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__)
+	subi	sp, 8
+	ldw	r9, (sp, LSAVE_A4)
+	stw	r9, (sp, 0x0)
+	ldw	r9, (sp, LSAVE_A5)
+	stw	r9, (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:
+#ifdef CONFIG_DEBUG_RSEQ
+	mov	a0, sp
+	jbsr	rseq_syscall
+#endif
+	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/io.c b/arch/csky/kernel/io.c
new file mode 100644
index 000000000..5883f13fa
--- /dev/null
+++ b/arch/csky/kernel/io.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/io.h>
+
+/*
+ * Copy data from IO memory space to "real" memory space.
+ */
+void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count)
+{
+	while (count && !IS_ALIGNED((unsigned long)from, 4)) {
+		*(u8 *)to = __raw_readb(from);
+		from++;
+		to++;
+		count--;
+	}
+
+	while (count >= 4) {
+		*(u32 *)to = __raw_readl(from);
+		from += 4;
+		to += 4;
+		count -= 4;
+	}
+
+	while (count) {
+		*(u8 *)to = __raw_readb(from);
+		from++;
+		to++;
+		count--;
+	}
+}
+EXPORT_SYMBOL(__memcpy_fromio);
+
+/*
+ * Copy data from "real" memory space to IO memory space.
+ */
+void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count)
+{
+	while (count && !IS_ALIGNED((unsigned long)to, 4)) {
+		__raw_writeb(*(u8 *)from, to);
+		from++;
+		to++;
+		count--;
+	}
+
+	while (count >= 4) {
+		__raw_writel(*(u32 *)from, to);
+		from += 4;
+		to += 4;
+		count -= 4;
+	}
+
+	while (count) {
+		__raw_writeb(*(u8 *)from, to);
+		from++;
+		to++;
+		count--;
+	}
+}
+EXPORT_SYMBOL(__memcpy_toio);
+
+/*
+ * "memset" on IO memory space.
+ */
+void __memset_io(volatile void __iomem *dst, int c, size_t count)
+{
+	u32 qc = (u8)c;
+
+	qc |= qc << 8;
+	qc |= qc << 16;
+
+	while (count && !IS_ALIGNED((unsigned long)dst, 4)) {
+		__raw_writeb(c, dst);
+		dst++;
+		count--;
+	}
+
+	while (count >= 4) {
+		__raw_writel(qc, dst);
+		dst += 4;
+		count -= 4;
+	}
+
+	while (count) {
+		__raw_writeb(c, dst);
+		dst++;
+		count--;
+	}
+}
+EXPORT_SYMBOL(__memset_io);
diff --git a/arch/csky/kernel/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..f11b3e573
--- /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 void inline 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..e5f18420c
--- /dev/null
+++ b/arch/csky/kernel/perf_event.c
@@ -0,0 +1,1371 @@
+// 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);
+
+		if (perf_event_overflow(event, &data, regs))
+			csky_pmu_stop_event(event);
+	}
+
+	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..834cffcfb
--- /dev/null
+++ b/arch/csky/kernel/probes/ftrace.c
@@ -0,0 +1,67 @@
+// 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;
+
+	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..2d31a12e4
--- /dev/null
+++ b/arch/csky/kernel/probes/uprobes.c
@@ -0,0 +1,155 @@
+// 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);
+
+	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;
+
+	/*
+	 * 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..eedddb155
--- /dev/null
+++ b/arch/csky/kernel/process.c
@@ -0,0 +1,105 @@
+// 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 <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)
+{
+	unsigned long 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 dump_fpu(struct pt_regs *regs, struct user_fp *fpu)
+{
+	memcpy(fpu, &current->thread.user_fp, sizeof(*fpu));
+	return 1;
+}
+EXPORT_SYMBOL(dump_fpu);
+
+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
+	raw_local_irq_enable();
+}
+#endif
diff --git a/arch/csky/kernel/ptrace.c b/arch/csky/kernel/ptrace.c
new file mode 100644
index 000000000..0f7e7b653
--- /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] = {
+		.core_note_type = NT_PRSTATUS,
+		.n = sizeof(struct pt_regs) / sizeof(u32),
+		.size = sizeof(u32),
+		.align = sizeof(u32),
+		.regset_get = gpr_get,
+		.set = gpr_set,
+	},
+	[REGSET_FPR] = {
+		.core_note_type = NT_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_entry(regs))
+			return -1;
+
+	if (secure_computing() == -1)
+		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..106fbf0b6
--- /dev/null
+++ b/arch/csky/kernel/setup.c
@@ -0,0 +1,134 @@
+// 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 <linux/screen_info.h>
+#include <asm/sections.h>
+#include <asm/mmu_context.h>
+#include <asm/pgalloc.h>
+
+#ifdef CONFIG_DUMMY_CONSOLE
+struct screen_info screen_info = {
+	.orig_video_lines	= 30,
+	.orig_video_cols	= 80,
+	.orig_video_mode	= 0,
+	.orig_video_ega_bx	= 0,
+	.orig_video_isVGA	= 1,
+	.orig_video_points	= 8
+};
+#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);
+	unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 };
+	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;
+	}
+
+	max_zone_pfn[ZONE_NORMAL] = max_low_pfn;
+
+	mmu_init(min_low_pfn, max_low_pfn);
+
+#ifdef CONFIG_HIGHMEM
+	max_zone_pfn[ZONE_HIGHMEM] = max_pfn;
+
+	highstart_pfn = max_low_pfn;
+	highend_pfn   = max_pfn;
+#endif
+	memblock_set_current_limit(PFN_PHYS(max_low_pfn));
+
+	dma_contiguous_reserve(0);
+
+	free_area_init(max_zone_pfn);
+}
+
+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
+
+	sparse_init();
+
+	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);
+	else
+		early_init_dt_scan(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..b7b368528
--- /dev/null
+++ b/arch/csky/kernel/signal.c
@@ -0,0 +1,269 @@
+// 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;
+
+	rseq_signal_deliver(ksig, regs);
+
+	/* 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..4b605aa2e
--- /dev/null
+++ b/arch/csky/kernel/smp.c
@@ -0,0 +1,321 @@
+// 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 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_boot_cpu(void)
+{
+}
+
+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 __cpu_die(unsigned int cpu)
+{
+	if (!cpu_wait_death(cpu, 5)) {
+		pr_crit("CPU%u: shutdown failed\n", cpu);
+		return;
+	}
+	pr_notice("CPU%u: shutdown\n", cpu);
+}
+
+void arch_cpu_idle_dead(void)
+{
+	idle_task_exit();
+
+	cpu_report_death();
+
+	while (!secondary_stack)
+		arch_cpu_idle();
+
+	local_irq_disable();
+
+	asm volatile(
+		"mov	sp, %0\n"
+		"mov	r8, %0\n"
+		"jmpi	csky_start_secondary"
+		:
+		: "r" (secondary_stack));
+}
+#endif
diff --git a/arch/csky/kernel/stacktrace.c b/arch/csky/kernel/stacktrace.c
new file mode 100644
index 000000000..9f78f5d21
--- /dev/null
+++ b/arch/csky/kernel/stacktrace.c
@@ -0,0 +1,158 @@
+// 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_sp __asm__ ("sp");
+		const register unsigned long current_fp __asm__ ("r8");
+		fp = current_fp;
+		sp = current_sp;
+		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) {
+		const register unsigned long current_sp __asm__ ("sp");
+		sp = current_sp;
+		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..3d30e58a4
--- /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,
+	off_t, 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..a0c238c53
--- /dev/null
+++ b/arch/csky/kernel/syscall_table.c
@@ -0,0 +1,14 @@
+// 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 sys_fadvise64_64 sys_csky_fadvise64_64
+void * const sys_call_table[__NR_syscalls] __page_aligned_data = {
+	[0 ... __NR_syscalls - 1] = sys_ni_syscall,
+#include <asm/unistd.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..6e426fba0
--- /dev/null
+++ b/arch/csky/kernel/traps.c
@@ -0,0 +1,262 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#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..16c20d64d
--- /dev/null
+++ b/arch/csky/kernel/vdso.c
@@ -0,0 +1,107 @@
+// 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>
+#ifdef GENERIC_TIME_VSYSCALL
+#include <vdso/datapage.h>
+#else
+#include <asm/vdso.h>
+#endif
+
+extern char vdso_start[], vdso_end[];
+
+static unsigned int vdso_pages;
+static struct page **vdso_pagelist;
+
+/*
+ * The vDSO data page.
+ */
+static union {
+	struct vdso_data	data;
+	u8			page[PAGE_SIZE];
+} vdso_data_store __page_aligned_data;
+struct vdso_data *vdso_data = &vdso_data_store.data;
+
+static int __init vdso_init(void)
+{
+	unsigned int i;
+
+	vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
+	vdso_pagelist =
+		kcalloc(vdso_pages + 1, sizeof(struct page *), GFP_KERNEL);
+	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;
+	}
+	vdso_pagelist[i] = virt_to_page(vdso_data);
+
+	return 0;
+}
+arch_initcall(vdso_init);
+
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+	int uses_interp)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long vdso_base, vdso_len;
+	int ret;
+
+	vdso_len = (vdso_pages + 1) << 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;
+
+	ret =
+	   install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
+		(VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
+		vdso_pagelist);
+
+	if (unlikely(ret)) {
+		mm->context.vdso = NULL;
+		goto end;
+	}
+
+	vdso_base += (vdso_pages << PAGE_SHIFT);
+	ret = install_special_mapping(mm, vdso_base, PAGE_SIZE,
+		(VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]);
+
+	if (unlikely(ret))
+		mm->context.vdso = NULL;
+end:
+	mmap_write_unlock(mm);
+	return ret;
+}
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+	if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso))
+		return "[vdso]";
+	if (vma->vm_mm && (vma->vm_start ==
+			   (long)vma->vm_mm->context.vdso + PAGE_SIZE))
+		return "[vdso_data]";
+	return NULL;
+}
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..0b6909f10
--- /dev/null
+++ b/arch/csky/kernel/vdso/Makefile
@@ -0,0 +1,72 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before
+# the inclusion of generic Makefile.
+ARCH_REL_TYPE_ABS := R_CKCORE_ADDR32|R_CKCORE_JUMP_SLOT
+include $(srctree)/lib/vdso/Makefile
+
+# Symbols present in the vdso
+vdso-syms  += rt_sigreturn
+vdso-syms  += vgettimeofday
+
+# 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)
+
+# Disable gcov profiling for VDSO code
+GCOV_PROFILE := n
+KCOV_INSTRUMENT := n
+
+# Force dependency
+$(obj)/vdso.o: $(obj)/vdso.so
+
+SYSCFLAGS_vdso.so.dbg = $(c_flags)
+$(obj)/vdso.so.dbg: $(src)/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 $< | $(srctree)/$(src)/so2s.sh > $@
+
+# install commands for the unstripped file
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
+
+vdso.so: $(obj)/vdso.so.dbg
+	@mkdir -p $(MODLIB)/vdso
+	$(call cmd,vdso_install)
+
+vdso_install: vdso.so
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..590a6c79f
--- /dev/null
+++ b/arch/csky/kernel/vdso/vdso.lds.S
@@ -0,0 +1,58 @@
+/* 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;
+		__vdso_clock_gettime;
+		__vdso_clock_gettime64;
+		__vdso_gettimeofday;
+		__vdso_clock_getres;
+	local: *;
+	};
+}
diff --git a/arch/csky/kernel/vdso/vgettimeofday.c b/arch/csky/kernel/vdso/vgettimeofday.c
new file mode 100644
index 000000000..da491832c
--- /dev/null
+++ b/arch/csky/kernel/vdso/vgettimeofday.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/time.h>
+#include <linux/types.h>
+
+int __vdso_clock_gettime(clockid_t clock,
+			 struct old_timespec32 *ts)
+{
+	return __cvdso_clock_gettime32(clock, ts);
+}
+
+int __vdso_clock_gettime64(clockid_t clock,
+			   struct __kernel_timespec *ts)
+{
+	return __cvdso_clock_gettime(clock, ts);
+}
+
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv,
+			struct timezone *tz)
+{
+	return __cvdso_gettimeofday(tv, tz);
+}
+
+int __vdso_clock_getres(clockid_t clock_id,
+			struct old_timespec32 *res)
+{
+	return __cvdso_clock_getres_time32(clock_id, res);
+}
diff --git a/arch/csky/kernel/vmlinux.lds.S b/arch/csky/kernel/vmlinux.lds.S
new file mode 100644
index 000000000..68c980d08
--- /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
+		CPUIDLE_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
+	ELF_DETAILS
+
+	DISCARDS
+}