Update Linux to v5.4.2

Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/arch/csky/kernel/Makefile b/arch/csky/kernel/Makefile
new file mode 100644
index 0000000..071d659
--- /dev/null
+++ b/arch/csky/kernel/Makefile
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0-only
+extra-y := head.o vmlinux.lds
+
+obj-y += entry.o atomic.o signal.o traps.o irq.o time.o vdso.o
+obj-y += power.o syscall.o syscall_table.o setup.o
+obj-y += process.o cpu-probe.o ptrace.o dumpstack.o
+
+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
+
+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 0000000..9b48b1b
--- /dev/null
+++ b/arch/csky/kernel/asm-offsets.c
@@ -0,0 +1,85 @@
+// 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_STATE,        offsetof(struct task_struct, state));
+	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, ksp));
+	DEFINE(THREAD_SR,         offsetof(struct thread_struct, sr));
+	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_ADDR_LIMIT,  offsetof(struct thread_info, addr_limit));
+	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));
+
+	/* 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 0000000..5b84f11
--- /dev/null
+++ b/arch/csky/kernel/atomic.S
@@ -0,0 +1,69 @@
+/* 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
+	mfcr	a3, epc
+	addi	a3, TRAP0_SIZE
+
+	subi    sp, 8
+	stw     a3, (sp, 0)
+	mfcr    a3, epsr
+	stw     a3, (sp, 4)
+
+	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
+1:
+	ldw	a3, (a2)
+	cmpne	a0, a3
+	bt16	3f
+2:
+	stw	a1, (a2)
+3:
+#endif
+	mvc	a0
+	ldw	a3, (sp, 0)
+	mtcr	a3, epc
+	ldw     a3, (sp, 4)
+	mtcr	a3, epsr
+	addi	sp, 8
+	KSPTOUSP
+	rte
+END(csky_cmpxchg)
+
+#ifndef CONFIG_CPU_HAS_LDSTEX
+/*
+ * Called from tlbmodified exception
+ */
+ENTRY(csky_cmpxchg_fixup)
+	mfcr	a0, epc
+	lrw	a1, 2b
+	cmpne	a1, a0
+	bt	1f
+	subi	a1, (2b - 1b)
+	stw	a1, (sp, LSAVE_PC)
+1:
+	rts
+END(csky_cmpxchg_fixup)
+#endif
diff --git a/arch/csky/kernel/cpu-probe.c b/arch/csky/kernel/cpu-probe.c
new file mode 100644
index 0000000..5f15ca3
--- /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/dumpstack.c b/arch/csky/kernel/dumpstack.c
new file mode 100644
index 0000000..d67f977
--- /dev/null
+++ b/arch/csky/kernel/dumpstack.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/ptrace.h>
+
+int kstack_depth_to_print = 48;
+
+void show_trace(unsigned long *stack)
+{
+	unsigned long *stack_end;
+	unsigned long *stack_start;
+	unsigned long *fp;
+	unsigned long addr;
+
+	addr = (unsigned long) stack & THREAD_MASK;
+	stack_start = (unsigned long *) addr;
+	stack_end = (unsigned long *) (addr + THREAD_SIZE);
+
+	fp = stack;
+	pr_info("\nCall Trace:");
+
+	while (fp > stack_start && fp < stack_end) {
+#ifdef CONFIG_STACKTRACE
+		addr	= fp[1];
+		fp	= (unsigned long *) fp[0];
+#else
+		addr	= *fp++;
+#endif
+		if (__kernel_text_address(addr))
+			pr_cont("\n[<%08lx>] %pS", addr, (void *)addr);
+	}
+	pr_cont("\n");
+}
+
+void show_stack(struct task_struct *task, unsigned long *stack)
+{
+	if (!stack) {
+		if (task)
+			stack = (unsigned long *)thread_saved_fp(task);
+		else
+#ifdef CONFIG_STACKTRACE
+			asm volatile("mov %0, r8\n":"=r"(stack)::"memory");
+#else
+			stack = (unsigned long *)&stack;
+#endif
+	}
+
+	show_trace(stack);
+}
diff --git a/arch/csky/kernel/entry.S b/arch/csky/kernel/entry.S
new file mode 100644
index 0000000..a7a5b67
--- /dev/null
+++ b/arch/csky/kernel/entry.S
@@ -0,0 +1,345 @@
+/* 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/setup.h>
+#include <asm/page.h>
+#include <asm/thread_info.h>
+
+#define PTE_INDX_MSK    0xffc
+#define PTE_INDX_SHIFT  10
+#define _PGDIR_SHIFT    22
+
+.macro	zero_fp
+#ifdef CONFIG_STACKTRACE
+	movi	r8, 0
+#endif
+.endm
+
+.macro tlbop_begin name, val0, val1, val2
+ENTRY(csky_\name)
+	mtcr    a3, ss2
+	mtcr    r6, ss3
+	mtcr    a2, ss4
+
+	RD_PGDR	r6
+	RD_MEH	a3
+#ifdef CONFIG_CPU_HAS_TLBI
+	tlbi.vaas a3
+	sync.is
+
+	btsti	a3, 31
+	bf	1f
+	RD_PGDR_K r6
+1:
+#else
+	bgeni	a2, 31
+	WR_MCIR	a2
+	bgeni	a2, 25
+	WR_MCIR	a2
+#endif
+	bclri   r6, 0
+	lrw	a2, va_pa_offset
+	ld.w	a2, (a2, 0)
+	subu	r6, a2
+	bseti	r6, 31
+
+	mov     a2, a3
+	lsri    a2, _PGDIR_SHIFT
+	lsli    a2, 2
+	addu    r6, a2
+	ldw     r6, (r6)
+
+	lrw	a2, va_pa_offset
+	ld.w	a2, (a2, 0)
+	subu	r6, a2
+	bseti	r6, 31
+
+	lsri    a3, PTE_INDX_SHIFT
+	lrw     a2, PTE_INDX_MSK
+	and     a3, a2
+	addu    r6, a3
+	ldw     a3, (r6)
+
+	movi	a2, (_PAGE_PRESENT | \val0)
+	and     a3, a2
+	cmpne   a3, a2
+	bt	\name
+
+	/* First read/write the page, just update the flags */
+	ldw     a3, (r6)
+	bgeni   a2, PAGE_VALID_BIT
+	bseti   a2, PAGE_ACCESSED_BIT
+	bseti   a2, \val1
+	bseti   a2, \val2
+	or      a3, a2
+	stw     a3, (r6)
+
+	/* Some cpu tlb-hardrefill bypass the cache */
+#ifdef CONFIG_CPU_NEED_TLBSYNC
+	movi	a2, 0x22
+	bseti	a2, 6
+	mtcr	r6, cr22
+	mtcr	a2, cr17
+	sync
+#endif
+
+	mfcr    a3, ss2
+	mfcr    r6, ss3
+	mfcr    a2, ss4
+	rte
+\name:
+	mfcr    a3, ss2
+	mfcr    r6, ss3
+	mfcr    a2, ss4
+	SAVE_ALL 0
+.endm
+.macro tlbop_end is_write
+	zero_fp
+	RD_MEH	a2
+	psrset  ee, ie
+	mov     a0, sp
+	movi    a1, \is_write
+	jbsr    do_page_fault
+	jmpi    ret_from_exception
+.endm
+
+.text
+
+tlbop_begin tlbinvalidl, _PAGE_READ, PAGE_VALID_BIT, PAGE_ACCESSED_BIT
+tlbop_end 0
+
+tlbop_begin tlbinvalids, _PAGE_WRITE, PAGE_DIRTY_BIT, PAGE_MODIFIED_BIT
+tlbop_end 1
+
+tlbop_begin tlbmodified, _PAGE_WRITE, PAGE_DIRTY_BIT, PAGE_MODIFIED_BIT
+#ifndef CONFIG_CPU_HAS_LDSTEX
+jbsr csky_cmpxchg_fixup
+#endif
+tlbop_end 1
+
+ENTRY(csky_systemcall)
+	SAVE_ALL TRAP0_SIZE
+	zero_fp
+
+	psrset  ee, ie
+
+	lrw     r11, __NR_syscalls
+	cmphs   syscallid, r11		/* Check nr of syscall */
+	bt      ret_from_exception
+
+	lrw     r13, sys_call_table
+	ixw     r13, syscallid
+	ldw     r11, (r13)
+	cmpnei  r11, 0
+	bf      ret_from_exception
+
+	mov     r9, sp
+	bmaski  r10, THREAD_SHIFT
+	andn    r9, r10
+	ldw     r12, (r9, TINFO_FLAGS)
+	ANDI_R3	r12, (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT)
+	cmpnei	r12, 0
+	bt      csky_syscall_trace
+#if defined(__CSKYABIV2__)
+	subi    sp, 8
+	stw  	r5, (sp, 0x4)
+	stw  	r4, (sp, 0x0)
+	jsr     r11                      /* Do system call */
+	addi 	sp, 8
+#else
+	jsr     r11
+#endif
+	stw     a0, (sp, LSAVE_A0)      /* Save return value */
+	jmpi    ret_from_exception
+
+csky_syscall_trace:
+	mov	a0, sp                  /* sp = pt_regs pointer */
+	jbsr	syscall_trace_enter
+	/* 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
+	stw	r5, (sp, 0x4)
+	stw	r4, (sp, 0x0)
+#else
+	ldw	r6, (sp, LSAVE_A4)
+	ldw	r7, (sp, LSAVE_A5)
+#endif
+	jsr	r11                     /* Do system call */
+#if defined(__CSKYABIV2__)
+	addi	sp, 8
+#endif
+	stw	a0, (sp, LSAVE_A0)	/* Save return value */
+
+	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	r12, (r9, TINFO_FLAGS)
+	ANDI_R3	r12, (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT)
+	cmpnei	r12, 0
+	bf	ret_from_exception
+	mov	a0, sp			/* sp = pt_regs pointer */
+	jbsr	syscall_trace_exit
+
+ret_from_exception:
+	ld	syscallid, (sp, LSAVE_PSR)
+	btsti	syscallid, 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	r12, (r9, TINFO_FLAGS)
+	andi	r12, (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED)
+	cmpnei	r12, 0
+	bt	exit_work
+1:
+	RESTORE_ALL
+
+exit_work:
+	lrw	syscallid, ret_from_exception
+	mov	lr, syscallid
+
+	btsti	r12, TIF_NEED_RESCHED
+	bt	work_resched
+
+	mov	a0, sp
+	mov	a1, r12
+	jmpi	do_notify_resume
+
+work_resched:
+	jmpi	schedule
+
+ENTRY(csky_trap)
+	SAVE_ALL 0
+	zero_fp
+	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
+
+	/* 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
+	psrset	ee
+
+#ifdef CONFIG_PREEMPT
+	mov	r9, sp			/* Get current stack  pointer */
+	bmaski	r10, THREAD_SHIFT
+	andn	r9, r10			/* Get thread_info */
+
+	/*
+	 * Get task_struct->stack.preempt_count for current,
+	 * and increase 1.
+	 */
+	ldw	r12, (r9, TINFO_PREEMPT)
+	addi	r12, 1
+	stw	r12, (r9, TINFO_PREEMPT)
+#endif
+
+	mov	a0, sp
+	jbsr	csky_do_IRQ
+
+#ifdef CONFIG_PREEMPT
+	subi	r12, 1
+	stw	r12, (r9, TINFO_PREEMPT)
+	cmpnei	r12, 0
+	bt	2f
+	ldw	r12, (r9, TINFO_FLAGS)
+	btsti	r12, TIF_NEED_RESCHED
+	bf	2f
+	jbsr	preempt_schedule_irq	/* irq en/disable is done inside */
+#endif
+2:
+	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
+
+	mfcr	a2, psr			/* Save PSR value */
+	stw	a2, (a3, THREAD_SR)	/* Save PSR in task struct */
+	bclri	a2, 6			/* Disable interrupts */
+	mtcr	a2, psr
+
+	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 */
+
+	ldw	a2, (a3, THREAD_SR)	/* Set next PSR */
+	mtcr	a2, psr
+
+#if  defined(__CSKYABIV2__)
+	addi	r7, a1, TASK_THREAD_INFO
+	ldw	tls, (r7, 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 0000000..44f4880
--- /dev/null
+++ b/arch/csky/kernel/ftrace.c
@@ -0,0 +1,194 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/ftrace.h>
+#include <linux/uaccess.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 (probe_kernel_read((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 = probe_kernel_write((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);
+	return ret;
+}
+
+int __init ftrace_dyn_arch_init(void)
+{
+	return 0;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#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 */
+
+/* _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 0000000..61989f9
--- /dev/null
+++ b/arch/csky/kernel/head.S
@@ -0,0 +1,31 @@
+/* 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
+
+	/* set stack point */
+	lrw     r6, secondary_stack
+	ld.w	r6, (r6, 0)
+	mov	sp, r6
+
+	jmpi	csky_start_secondary
+END(_start_smp_secondary)
+#endif
diff --git a/arch/csky/kernel/irq.c b/arch/csky/kernel/irq.c
new file mode 100644
index 0000000..03a1930
--- /dev/null
+++ b/arch/csky/kernel/irq.c
@@ -0,0 +1,22 @@
+// 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
+}
+
+asmlinkage void __irq_entry csky_do_IRQ(struct pt_regs *regs)
+{
+	handle_arch_irq(regs);
+}
diff --git a/arch/csky/kernel/module.c b/arch/csky/kernel/module.c
new file mode 100644
index 0000000..b5ad7d9
--- /dev/null
+++ b/arch/csky/kernel/module.c
@@ -0,0 +1,98 @@
+// 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>
+#include <asm/pgtable.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 postition */
+			*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 0000000..e68ff37
--- /dev/null
+++ b/arch/csky/kernel/perf_callchain.c
@@ -0,0 +1,119 @@
+// 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)
+{
+	if (kstack_end((void *)frame->fp))
+		return -EPERM;
+	if (frame->fp & 0x3 || frame->fp < TASK_SIZE)
+		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_frame_tail = (unsigned long *)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;
+
+	/* C-SKY does not support virtualization. */
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
+		return;
+
+	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;
+
+	/* C-SKY does not support virtualization. */
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		pr_warn("C-SKY does not support perf in guest mode!");
+		return;
+	}
+
+	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 0000000..1a29f11
--- /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 */
+static 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_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 0000000..eb32838
--- /dev/null
+++ b/arch/csky/kernel/perf_regs.c
@@ -0,0 +1,40 @@
+// 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,
+			struct pt_regs *regs_user_copy)
+{
+	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 0000000..923ee4e
--- /dev/null
+++ b/arch/csky/kernel/power.c
@@ -0,0 +1,30 @@
+// 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();
+	if (pm_power_off)
+		pm_power_off();
+	asm volatile ("bkpt");
+}
+
+void machine_halt(void)
+{
+	local_irq_disable();
+	if (pm_power_off)
+		pm_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/process.c b/arch/csky/kernel/process.c
new file mode 100644
index 0000000..f320d92
--- /dev/null
+++ b/arch/csky/kernel/process.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/module.h>
+#include <linux/version.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/sched/debug.h>
+#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];
+
+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){}
+
+/*
+ * Return saved PC from a blocked thread
+ */
+unsigned long thread_saved_pc(struct task_struct *tsk)
+{
+	struct switch_stack *sw = (struct switch_stack *)tsk->thread.ksp;
+
+	return sw->r15;
+}
+
+int copy_thread(unsigned long clone_flags,
+		unsigned long usp,
+		unsigned long kthread_arg,
+		struct task_struct *p)
+{
+	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 ksp for switch_to !!! */
+	p->thread.ksp = (unsigned long)childstack;
+
+	if (unlikely(p->flags & PF_KTHREAD)) {
+		memset(childregs, 0, sizeof(struct pt_regs));
+		childstack->r15 = (unsigned long) ret_from_kernel_thread;
+		childstack->r10 = kthread_arg;
+		childstack->r9 = usp;
+		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
+						      = childregs->regs[0];
+
+		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;
+}
+
+unsigned long get_wchan(struct task_struct *p)
+{
+	unsigned long lr;
+	unsigned long *fp, *stack_start, *stack_end;
+	int count = 0;
+
+	if (!p || p == current || p->state == TASK_RUNNING)
+		return 0;
+
+	stack_start = (unsigned long *)end_of_stack(p);
+	stack_end = (unsigned long *)(task_stack_page(p) + THREAD_SIZE);
+
+	fp = (unsigned long *) thread_saved_fp(p);
+	do {
+		if (fp < stack_start || fp > stack_end)
+			return 0;
+#ifdef CONFIG_STACKTRACE
+		lr = fp[1];
+		fp = (unsigned long *)fp[0];
+#else
+		lr = *fp++;
+#endif
+		if (!in_sched_functions(lr) &&
+		    __kernel_text_address(lr))
+			return lr;
+	} while (count++ < 16);
+
+	return 0;
+}
+EXPORT_SYMBOL(get_wchan);
+
+#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
+	local_irq_enable();
+}
+#endif
diff --git a/arch/csky/kernel/ptrace.c b/arch/csky/kernel/ptrace.c
new file mode 100644
index 0000000..313623a
--- /dev/null
+++ b/arch/csky/kernel/ptrace.c
@@ -0,0 +1,316 @@
+// 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/tracehook.h>
+#include <linux/uaccess.h>
+#include <linux/user.h>
+
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+#include <asm/asm-offsets.h>
+
+#include <abi/regdef.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;
+}
+
+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;
+}
+
+/*
+ * 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,
+		   unsigned int pos, unsigned int count,
+		   void *kbuf, void __user *ubuf)
+{
+	struct pt_regs *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 user_regset_copyout(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
+}
+
+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;
+
+	regs.sr = task_pt_regs(target)->sr;
+#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,
+		   unsigned int pos, unsigned int count,
+		   void *kbuf, void __user *ubuf)
+{
+	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 user_regset_copyout(&pos, &count, &kbuf, &ubuf, &tmp, 0, -1);
+#else
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
+#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),
+		.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),
+		.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;
+}
+
+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 void syscall_trace_enter(struct pt_regs *regs)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		if (tracehook_report_syscall_entry(regs))
+			syscall_set_nr(current, regs, -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);
+}
+
+asmlinkage void syscall_trace_exit(struct pt_regs *regs)
+{
+	audit_syscall_exit(regs);
+
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		tracehook_report_syscall_exit(regs, 0);
+
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_exit(regs, syscall_get_return_value(current, regs));
+}
+
+extern void show_stack(struct task_struct *task, unsigned long *stack);
+void show_regs(struct pt_regs *fp)
+{
+	unsigned long   *sp;
+	unsigned char   *tp;
+	int	i;
+
+	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);
+	pr_info("orig_a0: 0x%08lx\n", fp->orig_a0);
+	pr_info("PSR: 0x%08lx\n", (long)fp->sr);
+
+	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  r15: 0x%08lx\n",
+		fp->regs[8], fp->regs[9], fp->lr);
+#endif
+
+	pr_info("\nCODE:");
+	tp = ((unsigned char *) fp->pc) - 0x20;
+	tp += ((int)tp % 4) ? 2 : 0;
+	for (sp = (unsigned long *) tp, i = 0; (i < 0x40);  i += 4) {
+		if ((i % 0x10) == 0)
+			pr_cont("\n%08x: ", (int) (tp + i));
+		pr_cont("%08x ", (int) *sp++);
+	}
+	pr_cont("\n");
+
+	pr_info("\nKERNEL STACK:");
+	tp = ((unsigned char *) fp) - 0x40;
+	for (sp = (unsigned long *) tp, i = 0; (i < 0xc0); i += 4) {
+		if ((i % 0x10) == 0)
+			pr_cont("\n%08x: ", (int) (tp + i));
+		pr_cont("%08x ", (int) *sp++);
+	}
+	pr_cont("\n");
+
+	show_stack(NULL, (unsigned long *)fp->regs[4]);
+	return;
+}
diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c
new file mode 100644
index 0000000..23ee604
--- /dev/null
+++ b/arch/csky/kernel/setup.c
@@ -0,0 +1,167 @@
+// 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-contiguous.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
+
+phys_addr_t __init_memblock memblock_end_of_REG0(void)
+{
+	return (memblock.memory.regions[0].base +
+		memblock.memory.regions[0].size);
+}
+
+phys_addr_t __init_memblock memblock_start_of_REG1(void)
+{
+	return memblock.memory.regions[1].base;
+}
+
+size_t __init_memblock memblock_size_of_REG1(void)
+{
+	return memblock.memory.regions[1].size;
+}
+
+static void __init csky_memblock_init(void)
+{
+	unsigned long zone_size[MAX_NR_ZONES];
+	unsigned long zhole_size[MAX_NR_ZONES];
+	signed long size;
+
+	memblock_reserve(__pa(_stext), _end - _stext);
+#ifdef CONFIG_BLK_DEV_INITRD
+	memblock_reserve(__pa(initrd_start), initrd_end - initrd_start);
+#endif
+
+	early_init_fdt_reserve_self();
+	early_init_fdt_scan_reserved_mem();
+
+	memblock_dump_all();
+
+	memset(zone_size, 0, sizeof(zone_size));
+	memset(zhole_size, 0, sizeof(zhole_size));
+
+	min_low_pfn = PFN_UP(memblock_start_of_DRAM());
+	max_pfn	    = PFN_DOWN(memblock_end_of_DRAM());
+
+	max_low_pfn = PFN_UP(memblock_end_of_REG0());
+	if (max_low_pfn == 0)
+		max_low_pfn = max_pfn;
+
+	size = max_pfn - min_low_pfn;
+
+	if (memblock.memory.cnt > 1) {
+		zone_size[ZONE_NORMAL]  =
+			PFN_DOWN(memblock_start_of_REG1()) - min_low_pfn;
+		zhole_size[ZONE_NORMAL] =
+			PFN_DOWN(memblock_start_of_REG1()) - max_low_pfn;
+	} else {
+		if (size <= PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET))
+			zone_size[ZONE_NORMAL] = max_pfn - min_low_pfn;
+		else {
+			zone_size[ZONE_NORMAL] =
+				PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET);
+			max_low_pfn = min_low_pfn + zone_size[ZONE_NORMAL];
+		}
+	}
+
+#ifdef CONFIG_HIGHMEM
+	size = 0;
+	if (memblock.memory.cnt > 1) {
+		size = PFN_DOWN(memblock_size_of_REG1());
+		highstart_pfn = PFN_DOWN(memblock_start_of_REG1());
+	} else {
+		size = max_pfn - min_low_pfn -
+			PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET);
+		highstart_pfn =  min_low_pfn +
+			PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET);
+	}
+
+	if (size > 0)
+		zone_size[ZONE_HIGHMEM] = size;
+
+	highend_pfn = max_pfn;
+#endif
+	memblock_set_current_limit(PFN_PHYS(max_low_pfn));
+
+	dma_contiguous_reserve(0);
+
+	free_area_init_node(0, zone_size, min_low_pfn, zhole_size);
+}
+
+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);
+
+	init_mm.start_code = (unsigned long) _stext;
+	init_mm.end_code = (unsigned long) _etext;
+	init_mm.end_data = (unsigned long) _edata;
+	init_mm.brk = (unsigned long) _end;
+
+	parse_early_param();
+
+	csky_memblock_init();
+
+	unflatten_and_copy_device_tree();
+
+#ifdef CONFIG_SMP
+	setup_smp();
+#endif
+
+	sparse_init();
+
+#ifdef CONFIG_HIGHMEM
+	kmap_init();
+#endif
+
+#if defined(CONFIG_VT) && defined(CONFIG_DUMMY_CONSOLE)
+	conswitchp = &dummy_con;
+#endif
+}
+
+unsigned long va_pa_offset;
+EXPORT_SYMBOL(va_pa_offset);
+
+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_msa0() & ~(SSEG_SIZE - 1);
+
+	pre_trap_init();
+	pre_mmu_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 0000000..9b1b7c0
--- /dev/null
+++ b/arch/csky/kernel/signal.c
@@ -0,0 +1,262 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/signal.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/tracehook.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;
+
+	/* 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));
+
+	/* 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 *frame;
+	int err = 0;
+	struct csky_vdso *vdso = current->mm->context.vdso;
+
+	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->rt_signal_retcode);
+
+	/*
+	 * Set up registers for signal handler.
+	 * Registers that we don't modify keep the value they had from
+	 * user-space at the time we took the signal.
+	 * We always pass siginfo and mcontext, regardless of SA_SIGINFO,
+	 * since some things rely on this (e.g. glibc's debug/segfault.c).
+	 */
+	regs->pc  = (unsigned long)ksig->ka.sa.sa_handler;
+	regs->usp = (unsigned long)frame;
+	regs->a0  = ksig->sig;				/* a0: signal number */
+	regs->a1  = (unsigned long)(&(frame->info));	/* a1: siginfo pointer */
+	regs->a2  = (unsigned long)(&(frame->uc));	/* a2: ucontext pointer */
+
+	return 0;
+}
+
+static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
+{
+	sigset_t *oldset = sigmask_to_save();
+	int ret;
+
+	/* Are we from a system call? */
+	if (in_syscall(regs)) {
+		/* Avoid additional syscall restarting via ret_from_exception */
+		forget_syscall(regs);
+
+		/* If so, check system call restarting.. */
+		switch (regs->a0) {
+		case -ERESTART_RESTARTBLOCK:
+		case -ERESTARTNOHAND:
+			regs->a0 = -EINTR;
+			break;
+
+		case -ERESTARTSYS:
+			if (!(ksig->ka.sa.sa_flags & SA_RESTART)) {
+				regs->a0 = -EINTR;
+				break;
+			}
+			/* fallthrough */
+		case -ERESTARTNOINTR:
+			regs->a0 = regs->orig_a0;
+			regs->pc -= TRAP0_SIZE;
+			break;
+		}
+	}
+
+	/* Set up the stack frame */
+	ret = setup_rt_frame(ksig, oldset, regs);
+
+	signal_setup_done(ret, ksig, 0);
+}
+
+static void do_signal(struct pt_regs *regs)
+{
+	struct ksignal ksig;
+
+	if (get_signal(&ksig)) {
+		/* Actually deliver the signal */
+		handle_signal(&ksig, regs);
+		return;
+	}
+
+	/* Did we come from a system call? */
+	if (in_syscall(regs)) {
+		/* Avoid additional syscall restarting via ret_from_exception */
+		forget_syscall(regs);
+
+		/* Restart the system call - no handlers present */
+		switch (regs->a0) {
+		case -ERESTARTNOHAND:
+		case -ERESTARTSYS:
+		case -ERESTARTNOINTR:
+			regs->a0 = regs->orig_a0;
+			regs->pc -= TRAP0_SIZE;
+			break;
+		case -ERESTART_RESTARTBLOCK:
+			regs->a0 = regs->orig_a0;
+			regs_syscallid(regs) = __NR_restart_syscall;
+			regs->pc -= TRAP0_SIZE;
+			break;
+		}
+	}
+
+	/*
+	 * If there is no signal to deliver, we just put the saved
+	 * sigmask back.
+	 */
+	restore_saved_sigmask();
+}
+
+/*
+ * notification of userspace execution resumption
+ * - triggered by the _TIF_WORK_MASK flags
+ */
+asmlinkage void do_notify_resume(struct pt_regs *regs,
+	unsigned long thread_info_flags)
+{
+	/* Handle pending signal delivery */
+	if (thread_info_flags & _TIF_SIGPENDING)
+		do_signal(regs);
+
+	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+		clear_thread_flag(TIF_NOTIFY_RESUME);
+		tracehook_notify_resume(regs);
+	}
+}
diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c
new file mode 100644
index 0000000..b753d38
--- /dev/null
+++ b/arch/csky/kernel/smp.c
@@ -0,0 +1,277 @@
+// 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/irqdomain.h>
+#include <linux/of.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>
+#include <asm/pgalloc.h>
+
+struct ipi_data_struct {
+	unsigned long bits ____cacheline_aligned;
+};
+static DEFINE_PER_CPU(struct ipi_data_struct, ipi_data);
+
+enum ipi_message_type {
+	IPI_EMPTY,
+	IPI_RESCHEDULE,
+	IPI_CALL_FUNC,
+	IPI_MAX
+};
+
+static irqreturn_t handle_ipi(int irq, void *dev)
+{
+	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))
+			scheduler_ipi();
+
+		if (ops & (1 << IPI_CALL_FUNC))
+			generic_smp_call_function_interrupt();
+
+		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);
+}
+
+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);
+}
+
+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)
+		panic("%s IRQ mapping failed\n", __func__);
+
+	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;
+	int cpu;
+
+	for_each_of_cpu_node(node) {
+		if (!of_device_is_available(node))
+			continue;
+
+		if (of_property_read_u32(node, "reg", &cpu))
+			continue;
+
+		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_ccr;
+volatile unsigned int secondary_stack;
+
+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_ccr  = mfcr("cr18");
+
+	/*
+	 * 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)
+{
+}
+
+int setup_profiling_timer(unsigned int multiplier)
+{
+	return -EINVAL;
+}
+
+void csky_start_secondary(void)
+{
+	struct mm_struct *mm = &init_mm;
+	unsigned int cpu = smp_processor_id();
+
+	mtcr("cr31", secondary_hint);
+	mtcr("cr18", secondary_ccr);
+
+	mtcr("vbr", vec_base);
+
+	flush_tlb_all();
+	write_mmu_pagemask(0);
+	TLBMISS_HANDLER_SETUP_PGD(swapper_pg_dir);
+	TLBMISS_HANDLER_SETUP_PGD_KERNEL(swapper_pg_dir);
+
+#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();
+	preempt_disable();
+	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 0000000..fec777a
--- /dev/null
+++ b/arch/csky/kernel/stacktrace.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
+#include <linux/stacktrace.h>
+#include <linux/ftrace.h>
+
+void save_stack_trace(struct stack_trace *trace)
+{
+	save_stack_trace_tsk(current, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
+
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	unsigned long *fp, *stack_start, *stack_end;
+	unsigned long addr;
+	int skip = trace->skip;
+	int savesched;
+	int graph_idx = 0;
+
+	if (tsk == current) {
+		asm volatile("mov %0, r8\n":"=r"(fp));
+		savesched = 1;
+	} else {
+		fp = (unsigned long *)thread_saved_fp(tsk);
+		savesched = 0;
+	}
+
+	addr = (unsigned long) fp & THREAD_MASK;
+	stack_start = (unsigned long *) addr;
+	stack_end = (unsigned long *) (addr + THREAD_SIZE);
+
+	while (fp > stack_start && fp < stack_end) {
+		unsigned long lpp, fpp;
+
+		fpp = fp[0];
+		lpp = fp[1];
+		if (!__kernel_text_address(lpp))
+			break;
+		else
+			lpp = ftrace_graph_ret_addr(tsk, &graph_idx, lpp, NULL);
+
+		if (savesched || !in_sched_functions(lpp)) {
+			if (skip) {
+				skip--;
+			} else {
+				trace->entries[trace->nr_entries++] = lpp;
+				if (trace->nr_entries >= trace->max_entries)
+					break;
+			}
+		}
+		fp = (unsigned long *)fpp;
+	}
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/csky/kernel/syscall.c b/arch/csky/kernel/syscall.c
new file mode 100644
index 0000000..3d30e58
--- /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 0000000..a0c238c
--- /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 0000000..b5fc944
--- /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/clk-provider.h>
+#include <linux/clocksource.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 0000000..b057480
--- /dev/null
+++ b/arch/csky/kernel/traps.c
@@ -0,0 +1,168 @@
+// 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 <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
+
+/* 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_tlbinvalidl(void);
+asmlinkage void csky_tlbinvalids(void);
+asmlinkage void csky_tlbmodified(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_tlbinvalidl);
+	VEC_INIT(VEC_TLBINVALIDS, csky_tlbinvalids);
+	VEC_INIT(VEC_TLBMODIFIED, csky_tlbmodified);
+
+#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
+}
+
+void die_if_kernel(char *str, struct pt_regs *regs, int nr)
+{
+	if (user_mode(regs))
+		return;
+
+	console_verbose();
+	pr_err("%s: %08x\n", str, nr);
+	show_regs(regs);
+	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
+	do_exit(SIGSEGV);
+}
+
+void buserr(struct pt_regs *regs)
+{
+#ifdef CONFIG_CPU_CK810
+	static unsigned long prev_pc;
+
+	if ((regs->pc == prev_pc) && prev_pc != 0) {
+		prev_pc = 0;
+	} else {
+		prev_pc = regs->pc;
+		return;
+	}
+#endif
+
+	die_if_kernel("Kernel mode BUS error", regs, 0);
+
+	pr_err("User mode Bus Error\n");
+	show_regs(regs);
+
+	force_sig_fault(SIGSEGV, 0, (void __user *)regs->pc);
+}
+
+#define USR_BKPT 0x1464
+asmlinkage void trap_c(struct pt_regs *regs)
+{
+	int sig;
+	unsigned long vector;
+	siginfo_t info;
+
+	vector = (mfcr("psr") >> 16) & 0xff;
+
+	switch (vector) {
+	case VEC_ZERODIV:
+		die_if_kernel("Kernel mode ZERO DIV", regs, vector);
+		sig = SIGFPE;
+		break;
+	/* ptrace */
+	case VEC_TRACE:
+		info.si_code = TRAP_TRACE;
+		sig = SIGTRAP;
+		break;
+	case VEC_ILLEGAL:
+		die_if_kernel("Kernel mode ILLEGAL", regs, vector);
+#ifndef CONFIG_CPU_NO_USER_BKPT
+		if (*(uint16_t *)instruction_pointer(regs) != USR_BKPT)
+#endif
+		{
+			sig = SIGILL;
+			break;
+		}
+	/* gdbserver  breakpoint */
+	case VEC_TRAP1:
+	/* jtagserver breakpoint */
+	case VEC_BREAKPOINT:
+		die_if_kernel("Kernel mode BKPT", regs, vector);
+		info.si_code = TRAP_BRKPT;
+		sig = SIGTRAP;
+		break;
+	case VEC_ACCESS:
+		return buserr(regs);
+#ifdef CONFIG_CPU_NEED_SOFTALIGN
+	case VEC_ALIGN:
+		return csky_alignment(regs);
+#endif
+#ifdef CONFIG_CPU_HAS_FPU
+	case VEC_FPE:
+		die_if_kernel("Kernel mode FPE", regs, vector);
+		return fpu_fpe(regs);
+	case VEC_PRIV:
+		die_if_kernel("Kernel mode PRIV", regs, vector);
+		if (fpu_libc_helper(regs))
+			return;
+#endif
+	default:
+		sig = SIGSEGV;
+		break;
+	}
+	send_sig(sig, current, 0);
+}
diff --git a/arch/csky/kernel/vdso.c b/arch/csky/kernel/vdso.c
new file mode 100644
index 0000000..60ff7ad
--- /dev/null
+++ b/arch/csky/kernel/vdso.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/binfmts.h>
+#include <linux/elf.h>
+#include <linux/vmalloc.h>
+#include <linux/unistd.h>
+#include <linux/uaccess.h>
+
+#include <asm/vdso.h>
+#include <asm/cacheflush.h>
+
+static struct page *vdso_page;
+
+static int __init init_vdso(void)
+{
+	struct csky_vdso *vdso;
+	int err = 0;
+
+	vdso_page = alloc_page(GFP_KERNEL);
+	if (!vdso_page)
+		panic("Cannot allocate vdso");
+
+	vdso = vmap(&vdso_page, 1, 0, PAGE_KERNEL);
+	if (!vdso)
+		panic("Cannot map vdso");
+
+	clear_page(vdso);
+
+	err = setup_vdso_page(vdso->rt_signal_retcode);
+	if (err)
+		panic("Cannot set signal return code, err: %x.", err);
+
+	dcache_wb_range((unsigned long)vdso, (unsigned long)vdso + 16);
+
+	vunmap(vdso);
+
+	return 0;
+}
+subsys_initcall(init_vdso);
+
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	int ret;
+	unsigned long addr;
+	struct mm_struct *mm = current->mm;
+
+	down_write(&mm->mmap_sem);
+
+	addr = get_unmapped_area(NULL, STACK_TOP, PAGE_SIZE, 0, 0);
+	if (IS_ERR_VALUE(addr)) {
+		ret = addr;
+		goto up_fail;
+	}
+
+	ret = install_special_mapping(
+			mm,
+			addr,
+			PAGE_SIZE,
+			VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+			&vdso_page);
+	if (ret)
+		goto up_fail;
+
+	mm->context.vdso = (void *)addr;
+
+up_fail:
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+	if (vma->vm_mm == NULL)
+		return NULL;
+
+	if (vma->vm_start == (long)vma->vm_mm->context.vdso)
+		return "[vdso]";
+	else
+		return NULL;
+}
diff --git a/arch/csky/kernel/vmlinux.lds.S b/arch/csky/kernel/vmlinux.lds.S
new file mode 100644
index 0000000..ae7961b
--- /dev/null
+++ b/arch/csky/kernel/vmlinux.lds.S
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <asm/vmlinux.lds.h>
+#include <asm/page.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;
+
+	_stext = .;
+	__init_begin = .;
+	HEAD_TEXT_SECTION
+	INIT_TEXT_SECTION(PAGE_SIZE)
+	INIT_DATA_SECTION(PAGE_SIZE)
+	PERCPU_SECTION(L1_CACHE_BYTES)
+	. = ALIGN(PAGE_SIZE);
+	__init_end = .;
+
+	.text : AT(ADDR(.text) - LOAD_OFFSET) {
+		_text = .;
+		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);
+
+
+	_sdata = .;
+	RO_DATA_SECTION(PAGE_SIZE)
+	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	_edata = .;
+
+	NOTES
+	EXCEPTION_TABLE(L1_CACHE_BYTES)
+	BSS_SECTION(L1_CACHE_BYTES, PAGE_SIZE, L1_CACHE_BYTES)
+	VBR_BASE
+	_end = . ;
+
+	STABS_DEBUG
+	DWARF_DEBUG
+
+	DISCARDS
+}