Merge tag 'csky-for-linus-5.7-rc1' of git://github.com/c-sky/csky-linux

Pull csky updates from Guo Ren:

 - Add kproobes/uprobes support

 - Add lockdep, rseq, gcov support

 - Fixup init_fpu

 - Fixup ftrace_modify deadlock

 - Fixup speculative execution on IO area

* tag 'csky-for-linus-5.7-rc1' of git://github.com/c-sky/csky-linux:
  csky: Fixup cpu speculative execution to IO area
  csky: Add uprobes support
  csky: Add kprobes supported
  csky: Enable LOCKDEP_SUPPORT
  csky: Enable the gcov function
  csky: Fixup get wrong psr value from phyical reg
  csky/ftrace: Fixup ftrace_modify_code deadlock without CPU_HAS_ICACHE_INS
  csky: Implement ftrace with regs
  csky: Add support for restartable sequence
  csky: Implement ptrace regs and stack API
  csky: Fixup init_fpu compile warning with __init

34 files changed, 1807 insertions, 74 deletions

diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 047427f71d83..94545d50d40f 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -3,6 +3,7 @@ config CSKY
 	def_bool y
 	select ARCH_32BIT_OFF_T
 	select ARCH_HAS_DMA_PREP_COHERENT
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_USE_BUILTIN_BSWAP
@@ -38,16 +39,22 @@ config CSKY
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_COPY_THREAD_TLS
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZO
 	select HAVE_KERNEL_LZMA
+	select HAVE_KPROBES if !CPU_CK610
+	select HAVE_KPROBES_ON_FTRACE if !CPU_CK610
+	select HAVE_KRETPROBES if !CPU_CK610
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_DMA_CONTIGUOUS
+	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select MAY_HAVE_SPARSE_IRQ
@@ -65,6 +72,12 @@ config CSKY
 	select PCI_SYSCALL if PCI
 	select PCI_MSI if PCI
 
+config LOCKDEP_SUPPORT
+	def_bool y
+
+config ARCH_SUPPORTS_UPROBES
+	def_bool y if !CPU_CK610
+
 config CPU_HAS_CACHEV2
 	bool
 
diff --git a/arch/csky/abiv1/inc/abi/entry.h b/arch/csky/abiv1/inc/abi/entry.h
index f35a9f3315ee..5056ebb902d1 100644
--- a/arch/csky/abiv1/inc/abi/entry.h
+++ b/arch/csky/abiv1/inc/abi/entry.h
@@ -172,10 +172,7 @@
 	addi	r6, 0xe
 	cpwcr	r6, cpcr30
 
-	lsri	r6, 28
-	addi	r6, 2
-	lsli	r6, 28
-	addi	r6, 0xe
+	movi	r6, 0
 	cpwcr	r6, cpcr31
 .endm
 
diff --git a/arch/csky/abiv2/fpu.c b/arch/csky/abiv2/fpu.c
index 86d187d4e5af..5acc5c2e544e 100644
--- a/arch/csky/abiv2/fpu.c
+++ b/arch/csky/abiv2/fpu.c
@@ -10,11 +10,6 @@
 #define MTCR_DIST	0xC0006420
 #define MFCR_DIST	0xC0006020
 
-void __init init_fpu(void)
-{
-	mtcr("cr<1, 2>", 0);
-}
-
 /*
  * fpu_libc_helper() is to help libc to excute:
  *  - mfcr %a, cr<1, 2>
diff --git a/arch/csky/abiv2/inc/abi/entry.h b/arch/csky/abiv2/inc/abi/entry.h
index 94a7a58765df..a99aff555a0a 100644
--- a/arch/csky/abiv2/inc/abi/entry.h
+++ b/arch/csky/abiv2/inc/abi/entry.h
@@ -100,6 +100,66 @@
 	rte
 .endm
 
+.macro SAVE_REGS_FTRACE
+	subi    sp, 152
+	stw	tls, (sp, 0)
+	stw	lr, (sp, 4)
+
+	mfcr	lr, psr
+	stw	lr, (sp, 12)
+
+	addi    lr, sp, 152
+	stw	lr, (sp, 16)
+
+	stw     a0, (sp, 20)
+	stw     a0, (sp, 24)
+	stw     a1, (sp, 28)
+	stw     a2, (sp, 32)
+	stw     a3, (sp, 36)
+
+	addi	sp, 40
+	stm	r4-r13, (sp)
+
+	addi    sp, 40
+	stm     r16-r30, (sp)
+#ifdef CONFIG_CPU_HAS_HILO
+	mfhi	lr
+	stw	lr, (sp, 60)
+	mflo	lr
+	stw	lr, (sp, 64)
+	mfcr	lr, cr14
+	stw	lr, (sp, 68)
+#endif
+	subi	sp, 80
+.endm
+
+.macro	RESTORE_REGS_FTRACE
+	ldw	tls, (sp, 0)
+	ldw	a0, (sp, 16)
+	mtcr	a0, ss0
+
+#ifdef CONFIG_CPU_HAS_HILO
+	ldw	a0, (sp, 140)
+	mthi	a0
+	ldw	a0, (sp, 144)
+	mtlo	a0
+	ldw	a0, (sp, 148)
+	mtcr	a0, cr14
+#endif
+
+	ldw     a0, (sp, 24)
+	ldw     a1, (sp, 28)
+	ldw     a2, (sp, 32)
+	ldw     a3, (sp, 36)
+
+	addi	sp, 40
+	ldm	r4-r13, (sp)
+	addi    sp, 40
+	ldm     r16-r30, (sp)
+	addi    sp, 72
+	mfcr	sp, ss0
+.endm
+
 .macro SAVE_SWITCH_STACK
 	subi    sp, 64
 	stm	r4-r11, (sp)
@@ -230,11 +290,8 @@
 	addi	r6, 0x1ce
 	mtcr	r6, cr<30, 15> /* Set MSA0 */
 
-	lsri	r6, 28
-	addi	r6, 2
-	lsli	r6, 28
-	addi	r6, 0x1ce
-	mtcr	r6, cr<31, 15> /* Set MSA1 */
+	movi    r6, 0
+	mtcr	r6, cr<31, 15> /* Clr MSA1 */
 
 	/* enable MMU */
 	mfcr    r6, cr18
diff --git a/arch/csky/abiv2/inc/abi/fpu.h b/arch/csky/abiv2/inc/abi/fpu.h
index 22ca3cf2794a..09e2700a3693 100644
--- a/arch/csky/abiv2/inc/abi/fpu.h
+++ b/arch/csky/abiv2/inc/abi/fpu.h
@@ -9,7 +9,8 @@
 
 int fpu_libc_helper(struct pt_regs *regs);
 void fpu_fpe(struct pt_regs *regs);
-void __init init_fpu(void);
+
+static inline void init_fpu(void) { mtcr("cr<1, 2>", 0); }
 
 void save_to_user_fp(struct user_fp *user_fp);
 void restore_from_user_fp(struct user_fp *user_fp);
diff --git a/arch/csky/abiv2/mcount.S b/arch/csky/abiv2/mcount.S
index 326402e65f9e..9331c7ed5958 100644
--- a/arch/csky/abiv2/mcount.S
+++ b/arch/csky/abiv2/mcount.S
@@ -3,6 +3,8 @@
 
 #include <linux/linkage.h>
 #include <asm/ftrace.h>
+#include <abi/entry.h>
+#include <asm/asm-offsets.h>
 
 /*
  * csky-gcc with -pg will put the following asm after prologue:
@@ -44,6 +46,22 @@
 	jmp	t1
 .endm
 
+.macro mcount_enter_regs
+	subi	sp, 8
+	stw	lr, (sp, 0)
+	stw	r8, (sp, 4)
+	SAVE_REGS_FTRACE
+.endm
+
+.macro mcount_exit_regs
+	RESTORE_REGS_FTRACE
+	ldw	t1, (sp, 0)
+	ldw	r8, (sp, 4)
+	ldw	lr, (sp, 8)
+	addi	sp, 12
+	jmp	t1
+.endm
+
 .macro save_return_regs
 	subi	sp, 16
 	stw	a0, (sp, 0)
@@ -122,6 +140,8 @@ ENTRY(ftrace_caller)
 	ldw	a0, (sp, 16)
 	subi	a0, 4
 	ldw	a1, (sp, 24)
+	lrw	a2, function_trace_op
+	ldw	a2, (a2, 0)
 
 	nop
 GLOBAL(ftrace_call)
@@ -157,3 +177,31 @@ ENTRY(return_to_handler)
 	jmp	lr
 END(return_to_handler)
 #endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+ENTRY(ftrace_regs_caller)
+	mcount_enter_regs
+
+	lrw	t1, PT_FRAME_SIZE
+	add	t1, sp
+
+	ldw	a0, (t1, 0)
+	subi	a0, 4
+	ldw	a1, (t1, 8)
+	lrw	a2, function_trace_op
+	ldw	a2, (a2, 0)
+	mov	a3, sp
+
+	nop
+GLOBAL(ftrace_regs_call)
+	nop32_stub
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	nop
+GLOBAL(ftrace_graph_regs_call)
+	nop32_stub
+#endif
+
+	mcount_exit_regs
+ENDPROC(ftrace_regs_caller)
+#endif /* CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/csky/include/asm/ftrace.h b/arch/csky/include/asm/ftrace.h
index ba35d93ecda2..fae72b0b1374 100644
--- a/arch/csky/include/asm/ftrace.h
+++ b/arch/csky/include/asm/ftrace.h
@@ -10,6 +10,8 @@
 
 #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
 
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+
 #define MCOUNT_ADDR	((unsigned long)_mcount)
 
 #ifndef __ASSEMBLY__
diff --git a/arch/csky/include/asm/kprobes.h b/arch/csky/include/asm/kprobes.h
new file mode 100644
index 000000000000..b647bbde4d6d
--- /dev/null
+++ b/arch/csky/include/asm/kprobes.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_CSKY_KPROBES_H
+#define __ASM_CSKY_KPROBES_H
+
+#include <asm-generic/kprobes.h>
+
+#ifdef CONFIG_KPROBES
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+
+#define __ARCH_WANT_KPROBES_INSN_SLOT
+#define MAX_INSN_SIZE			1
+
+#define flush_insn_slot(p)		do { } while (0)
+#define kretprobe_blacklist_size	0
+
+#include <asm/probes.h>
+
+struct prev_kprobe {
+	struct kprobe *kp;
+	unsigned int status;
+};
+
+/* Single step context for kprobe */
+struct kprobe_step_ctx {
+	unsigned long ss_pending;
+	unsigned long match_addr;
+};
+
+/* per-cpu kprobe control block */
+struct kprobe_ctlblk {
+	unsigned int kprobe_status;
+	unsigned long saved_sr;
+	struct prev_kprobe prev_kprobe;
+	struct kprobe_step_ctx ss_ctx;
+};
+
+void arch_remove_kprobe(struct kprobe *p);
+int kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr);
+int kprobe_breakpoint_handler(struct pt_regs *regs);
+int kprobe_single_step_handler(struct pt_regs *regs);
+void kretprobe_trampoline(void);
+void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
+
+#endif /* CONFIG_KPROBES */
+#endif /* __ASM_CSKY_KPROBES_H */
diff --git a/arch/csky/include/asm/probes.h b/arch/csky/include/asm/probes.h
new file mode 100644
index 000000000000..5e526334e6f9
--- /dev/null
+++ b/arch/csky/include/asm/probes.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_PROBES_H
+#define __ASM_CSKY_PROBES_H
+
+typedef u32 probe_opcode_t;
+typedef void (probes_handler_t) (u32 opcode, long addr, struct pt_regs *);
+
+/* architecture specific copy of original instruction */
+struct arch_probe_insn {
+	probe_opcode_t *insn;
+	probes_handler_t *handler;
+	/* restore address after simulation */
+	unsigned long restore;
+};
+
+#ifdef CONFIG_KPROBES
+typedef u32 kprobe_opcode_t;
+struct arch_specific_insn {
+	struct arch_probe_insn api;
+};
+#endif
+
+#endif /* __ASM_CSKY_PROBES_H */
diff --git a/arch/csky/include/asm/processor.h b/arch/csky/include/asm/processor.h
index 21e0bd5293dd..c6bcd7f7c720 100644
--- a/arch/csky/include/asm/processor.h
+++ b/arch/csky/include/asm/processor.h
@@ -43,6 +43,7 @@ extern struct cpuinfo_csky cpu_data[];
 struct thread_struct {
 	unsigned long  ksp;       /* kernel stack pointer */
 	unsigned long  sr;        /* saved status register */
+	unsigned long  trap_no;   /* saved status register */
 
 	/* FPU regs */
 	struct user_fp __aligned(16) user_fp;
diff --git a/arch/csky/include/asm/ptrace.h b/arch/csky/include/asm/ptrace.h
index d0aba7b32417..aae5aa96cf54 100644
--- a/arch/csky/include/asm/ptrace.h
+++ b/arch/csky/include/asm/ptrace.h
@@ -7,11 +7,14 @@
 #include <uapi/asm/ptrace.h>
 #include <asm/traps.h>
 #include <linux/types.h>
+#include <linux/compiler.h>
 
 #ifndef __ASSEMBLY__
 
 #define PS_S	0x80000000 /* Supervisor Mode */
 
+#define USR_BKPT	0x1464
+
 #define arch_has_single_step() (1)
 #define current_pt_regs() \
 ({ (struct pt_regs *)((char *)current_thread_info() + THREAD_SIZE) - 1; })
@@ -22,6 +25,18 @@
 #define instruction_pointer(regs) ((regs)->pc)
 #define profile_pc(regs) instruction_pointer(regs)
 
+static inline void instruction_pointer_set(struct pt_regs *regs,
+					   unsigned long val)
+{
+	regs->pc = val;
+}
+
+#if defined(__CSKYABIV2__)
+#define MAX_REG_OFFSET offsetof(struct pt_regs, dcsr)
+#else
+#define MAX_REG_OFFSET offsetof(struct pt_regs, regs[9])
+#endif
+
 static inline bool in_syscall(struct pt_regs const *regs)
 {
 	return ((regs->sr >> 16) & 0xff) == VEC_TRAP0;
@@ -37,5 +52,33 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->a0;
 }
 
+/* Valid only for Kernel mode traps. */
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	return regs->usp;
+}
+
+extern int regs_query_register_offset(const char *name);
+extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+						unsigned int n);
+
+/*
+ * regs_get_register() - get register value from its offset
+ * @regs:      pt_regs from which register value is gotten
+ * @offset:    offset of the register.
+ *
+ * regs_get_register returns the value of a register whose offset from @regs.
+ * The @offset is the offset of the register in struct pt_regs.
+ * If @offset is bigger than MAX_REG_OFFSET, this returns 0.
+ */
+static inline unsigned long regs_get_register(struct pt_regs *regs,
+						unsigned int offset)
+{
+	if (unlikely(offset > MAX_REG_OFFSET))
+		return 0;
+
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ASM_CSKY_PTRACE_H */
diff --git a/arch/csky/include/asm/thread_info.h b/arch/csky/include/asm/thread_info.h
index 0b546a55a8bf..442fedad0260 100644
--- a/arch/csky/include/asm/thread_info.h
+++ b/arch/csky/include/asm/thread_info.h
@@ -57,6 +57,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SYSCALL_TRACE	3	/* syscall trace active */
 #define TIF_SYSCALL_TRACEPOINT	4       /* syscall tracepoint instrumentation */
 #define TIF_SYSCALL_AUDIT	5	/* syscall auditing */
+#define TIF_UPROBE		6	/* uprobe breakpoint or singlestep */
 #define TIF_POLLING_NRFLAG	16	/* poll_idle() is TIF_NEED_RESCHED */
 #define TIF_MEMDIE		18      /* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	20	/* restore signal mask in do_signal() */
@@ -68,6 +69,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_MEMDIE		(1 << TIF_MEMDIE)
 #define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
diff --git a/arch/csky/include/asm/uprobes.h b/arch/csky/include/asm/uprobes.h
new file mode 100644
index 000000000000..600388eb93c6
--- /dev/null
+++ b/arch/csky/include/asm/uprobes.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_CSKY_UPROBES_H
+#define __ASM_CSKY_UPROBES_H
+
+#include <asm/probes.h>
+
+#define MAX_UINSN_BYTES		4
+
+#define UPROBE_SWBP_INSN	USR_BKPT
+#define UPROBE_SWBP_INSN_SIZE	2
+#define UPROBE_XOL_SLOT_BYTES	MAX_UINSN_BYTES
+
+typedef u32 uprobe_opcode_t;
+
+struct arch_uprobe_task {
+	unsigned long   saved_trap_no;
+};
+
+struct arch_uprobe {
+	union {
+		u8 insn[MAX_UINSN_BYTES];
+		u8 ixol[MAX_UINSN_BYTES];
+	};
+	struct arch_probe_insn api;
+	unsigned long insn_size;
+	bool simulate;
+};
+
+int uprobe_breakpoint_handler(struct pt_regs *regs);
+int uprobe_single_step_handler(struct pt_regs *regs);
+
+#endif /* __ASM_CSKY_UPROBES_H */
diff --git a/arch/csky/kernel/Makefile b/arch/csky/kernel/Makefile
index 071d659f37b7..fd6d9dc8b7f3 100644
--- a/arch/csky/kernel/Makefile
+++ b/arch/csky/kernel/Makefile
@@ -4,6 +4,7 @@ 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-y += probes/
 
 obj-$(CONFIG_MODULES)			+= module.o
 obj-$(CONFIG_SMP)			+= smp.o
diff --git a/arch/csky/kernel/asm-offsets.c b/arch/csky/kernel/asm-offsets.c
index 9b48b1b1a61b..f8be348df9e4 100644
--- a/arch/csky/kernel/asm-offsets.c
+++ b/arch/csky/kernel/asm-offsets.c
@@ -72,6 +72,7 @@ int main(void)
 	DEFINE(PT_RLO,            offsetof(struct pt_regs, rlo));
 #endif
 	DEFINE(PT_USP,            offsetof(struct pt_regs, usp));
+	DEFINE(PT_FRAME_SIZE,     sizeof(struct pt_regs));
 
 	/* offsets into the irq_cpustat_t struct */
 	DEFINE(CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t,
diff --git a/arch/csky/kernel/entry.S b/arch/csky/kernel/entry.S
index 007706328000..364819536f2e 100644
--- a/arch/csky/kernel/entry.S
+++ b/arch/csky/kernel/entry.S
@@ -128,7 +128,10 @@ tlbop_end 1
 ENTRY(csky_systemcall)
 	SAVE_ALL TRAP0_SIZE
 	zero_fp
-
+#ifdef CONFIG_RSEQ_DEBUG
+	mov	a0, sp
+	jbsr	rseq_syscall
+#endif
 	psrset  ee, ie
 
 	lrw     r11, __NR_syscalls
@@ -218,10 +221,17 @@ ret_from_exception:
 	andn	r9, r10
 
 	ldw	r12, (r9, TINFO_FLAGS)
-	andi	r12, (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED)
+	andi	r12, (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | _TIF_UPROBE)
 	cmpnei	r12, 0
 	bt	exit_work
 1:
+#ifdef CONFIG_TRACE_IRQFLAGS
+	ld	r10, (sp, LSAVE_PSR)
+	btsti	r10, 6
+	bf	2f
+	jbsr	trace_hardirqs_on
+2:
+#endif
 	RESTORE_ALL
 
 exit_work:
@@ -277,6 +287,10 @@ ENTRY(csky_irq)
 	zero_fp
 	psrset	ee
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+	jbsr	trace_hardirqs_off
+#endif
+
 #ifdef CONFIG_PREEMPTION
 	mov	r9, sp			/* Get current stack  pointer */
 	bmaski	r10, THREAD_SHIFT
diff --git a/arch/csky/kernel/ftrace.c b/arch/csky/kernel/ftrace.c
index 44f4880179b7..44628e3f7fa6 100644
--- a/arch/csky/kernel/ftrace.c
+++ b/arch/csky/kernel/ftrace.c
@@ -3,6 +3,7 @@
 
 #include <linux/ftrace.h>
 #include <linux/uaccess.h>
+#include <linux/stop_machine.h>
 #include <asm/cacheflush.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -126,6 +127,9 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	int ret = ftrace_modify_code((unsigned long)&ftrace_call,
 				(unsigned long)func, true, true);
+	if (!ret)
+		ret = ftrace_modify_code((unsigned long)&ftrace_regs_call,
+				(unsigned long)func, true, true);
 	return ret;
 }
 
@@ -135,6 +139,14 @@ int __init ftrace_dyn_arch_init(void)
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+		       unsigned long addr)
+{
+	return ftrace_modify_code(rec->ip, addr, true, true);
+}
+#endif
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 			   unsigned long frame_pointer)
@@ -190,5 +202,35 @@ int ftrace_disable_ftrace_graph_caller(void)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
+#ifndef CONFIG_CPU_HAS_ICACHE_INS
+struct ftrace_modify_param {
+	int command;
+	atomic_t cpu_count;
+};
+
+static int __ftrace_modify_code(void *data)
+{
+	struct ftrace_modify_param *param = data;
+
+	if (atomic_inc_return(&param->cpu_count) == 1) {
+		ftrace_modify_all_code(param->command);
+		atomic_inc(&param->cpu_count);
+	} else {
+		while (atomic_read(&param->cpu_count) <= num_online_cpus())
+			cpu_relax();
+		local_icache_inv_all(NULL);
+	}
+
+	return 0;
+}
+
+void arch_ftrace_update_code(int command)
+{
+	struct ftrace_modify_param param = { command, ATOMIC_INIT(0) };
+
+	stop_machine(__ftrace_modify_code, &param, cpu_online_mask);
+}
+#endif
+
 /* _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
index 61989f9241c0..17ed9d250480 100644
--- a/arch/csky/kernel/head.S
+++ b/arch/csky/kernel/head.S
@@ -21,6 +21,11 @@ END(_start)
 ENTRY(_start_smp_secondary)
 	SETUP_MMU
 
+	/* copy msa1 from CPU0 */
+	lrw     r6, secondary_msa1
+	ld.w	r6, (r6, 0)
+	mtcr	r6, cr<31, 15>
+
 	/* set stack point */
 	lrw     r6, secondary_stack
 	ld.w	r6, (r6, 0)
diff --git a/arch/csky/kernel/probes/Makefile b/arch/csky/kernel/probes/Makefile
new file mode 100644
index 000000000000..1c7c6e6cb25b
--- /dev/null
+++ b/arch/csky/kernel/probes/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_KPROBES)		+= kprobes.o decode-insn.o simulate-insn.o
+obj-$(CONFIG_KPROBES)		+= kprobes_trampoline.o
+obj-$(CONFIG_KPROBES_ON_FTRACE)	+= ftrace.o
+obj-$(CONFIG_UPROBES)		+= uprobes.o decode-insn.o simulate-insn.o
+
+CFLAGS_REMOVE_simulate-insn.o = $(CC_FLAGS_FTRACE)
diff --git a/arch/csky/kernel/probes/decode-insn.c b/arch/csky/kernel/probes/decode-insn.c
new file mode 100644
index 000000000000..bbc4edc25dc9
--- /dev/null
+++ b/arch/csky/kernel/probes/decode-insn.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <asm/sections.h>
+
+#include "decode-insn.h"
+#include "simulate-insn.h"
+
+/* Return:
+ *   INSN_REJECTED     If instruction is one not allowed to kprobe,
+ *   INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot.
+ */
+enum probe_insn __kprobes
+csky_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *api)
+{
+	probe_opcode_t insn = le32_to_cpu(*addr);
+
+	CSKY_INSN_SET_SIMULATE(br16,		insn);
+	CSKY_INSN_SET_SIMULATE(bt16,		insn);
+	CSKY_INSN_SET_SIMULATE(bf16,		insn);
+	CSKY_INSN_SET_SIMULATE(jmp16,		insn);
+	CSKY_INSN_SET_SIMULATE(jsr16,		insn);
+	CSKY_INSN_SET_SIMULATE(lrw16,		insn);
+	CSKY_INSN_SET_SIMULATE(pop16,		insn);
+
+	CSKY_INSN_SET_SIMULATE(br32,		insn);
+	CSKY_INSN_SET_SIMULATE(bt32,		insn);
+	CSKY_INSN_SET_SIMULATE(bf32,		insn);
+	CSKY_INSN_SET_SIMULATE(jmp32,		insn);
+	CSKY_INSN_SET_SIMULATE(jsr32,		insn);
+	CSKY_INSN_SET_SIMULATE(lrw32,		insn);
+	CSKY_INSN_SET_SIMULATE(pop32,		insn);
+
+	CSKY_INSN_SET_SIMULATE(bez32,		insn);
+	CSKY_INSN_SET_SIMULATE(bnez32,		insn);
+	CSKY_INSN_SET_SIMULATE(bnezad32,	insn);
+	CSKY_INSN_SET_SIMULATE(bhsz32,		insn);
+	CSKY_INSN_SET_SIMULATE(bhz32,		insn);
+	CSKY_INSN_SET_SIMULATE(blsz32,		insn);
+	CSKY_INSN_SET_SIMULATE(blz32,		insn);
+	CSKY_INSN_SET_SIMULATE(bsr32,		insn);
+	CSKY_INSN_SET_SIMULATE(jmpi32,		insn);
+	CSKY_INSN_SET_SIMULATE(jsri32,		insn);
+
+	return INSN_GOOD;
+}
diff --git a/arch/csky/kernel/probes/decode-insn.h b/arch/csky/kernel/probes/decode-insn.h
new file mode 100644
index 000000000000..9c4ad48fee0d
--- /dev/null
+++ b/arch/csky/kernel/probes/decode-insn.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef __CSKY_KERNEL_KPROBES_DECODE_INSN_H
+#define __CSKY_KERNEL_KPROBES_DECODE_INSN_H
+
+#include <asm/sections.h>
+#include <asm/kprobes.h>
+
+enum probe_insn {
+	INSN_REJECTED,
+	INSN_GOOD_NO_SLOT,
+	INSN_GOOD,
+};
+
+#define is_insn32(insn) ((insn & 0xc000) == 0xc000)
+
+enum probe_insn __kprobes
+csky_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *asi);
+
+#endif /* __CSKY_KERNEL_KPROBES_DECODE_INSN_H */
diff --git a/arch/csky/kernel/probes/ftrace.c b/arch/csky/kernel/probes/ftrace.c
new file mode 100644
index 000000000000..5264763d05be
--- /dev/null
+++ b/arch/csky/kernel/probes/ftrace.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kprobes.h>
+
+int arch_check_ftrace_location(struct kprobe *p)
+{
+	if (ftrace_location((unsigned long)p->addr))
+		p->flags |= KPROBE_FLAG_FTRACE;
+	return 0;
+}
+
+/* Ftrace callback handler for kprobes -- called under preepmt disabed */
+void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+			   struct ftrace_ops *ops, struct pt_regs *regs)
+{
+	bool lr_saver = false;
+	struct kprobe *p;
+	struct kprobe_ctlblk *kcb;
+
+	/* Preempt is disabled by ftrace */
+	p = get_kprobe((kprobe_opcode_t *)ip);
+	if (!p) {
+		p = get_kprobe((kprobe_opcode_t *)(ip - MCOUNT_INSN_SIZE));
+		if (unlikely(!p) || kprobe_disabled(p))
+			return;
+		lr_saver = true;
+	}
+
+	kcb = get_kprobe_ctlblk();
+	if (kprobe_running()) {
+		kprobes_inc_nmissed_count(p);
+	} else {
+		unsigned long orig_ip = instruction_pointer(regs);
+
+		if (lr_saver)
+			ip -= MCOUNT_INSN_SIZE;
+		instruction_pointer_set(regs, ip);
+		__this_cpu_write(current_kprobe, p);
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+		if (!p->pre_handler || !p->pre_handler(p, regs)) {
+			/*
+			 * Emulate singlestep (and also recover regs->pc)
+			 * as if there is a nop
+			 */
+			instruction_pointer_set(regs,
+				(unsigned long)p->addr + MCOUNT_INSN_SIZE);
+			if (unlikely(p->post_handler)) {
+				kcb->kprobe_status = KPROBE_HIT_SSDONE;
+				p->post_handler(p, regs, 0);
+			}
+			instruction_pointer_set(regs, orig_ip);
+		}
+		/*
+		 * If pre_handler returns !0, it changes regs->pc. We have to
+		 * skip emulating post_handler.
+		 */
+		__this_cpu_write(current_kprobe, NULL);
+	}
+}
+NOKPROBE_SYMBOL(kprobe_ftrace_handler);
+
+int arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+	p->ainsn.api.insn = NULL;
+	return 0;
+}
diff --git a/arch/csky/kernel/probes/kprobes.c b/arch/csky/kernel/probes/kprobes.c
new file mode 100644
index 000000000000..f0f733b7ac5a
--- /dev/null
+++ b/arch/csky/kernel/probes/kprobes.c
@@ -0,0 +1,499 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <linux/kprobes.h>
+#include <linux/extable.h>
+#include <linux/slab.h>
+#include <linux/stop_machine.h>
+#include <asm/ptrace.h>
+#include <linux/uaccess.h>
+#include <asm/sections.h>
+#include <asm/cacheflush.h>
+
+#include "decode-insn.h"
+
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+
+static void __kprobes
+post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *);
+
+struct csky_insn_patch {
+	kprobe_opcode_t	*addr;
+	u32		opcode;
+	atomic_t	cpu_count;
+};
+
+static int __kprobes patch_text_cb(void *priv)
+{
+	struct csky_insn_patch *param = priv;
+	unsigned int addr = (unsigned int)param->addr;
+
+	if (atomic_inc_return(&param->cpu_count) == 1) {
+		*(u16 *) addr = cpu_to_le16(param->opcode);
+		dcache_wb_range(addr, addr + 2);
+		atomic_inc(&param->cpu_count);
+	} else {
+		while (atomic_read(&param->cpu_count) <= num_online_cpus())
+			cpu_relax();
+	}
+
+	icache_inv_range(addr, addr + 2);
+
+	return 0;
+}
+
+static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode)
+{
+	struct csky_insn_patch param = { addr, opcode, ATOMIC_INIT(0) };
+
+	return stop_machine_cpuslocked(patch_text_cb, &param, cpu_online_mask);
+}
+
+static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
+{
+	unsigned long offset = is_insn32(p->opcode) ? 4 : 2;
+
+	p->ainsn.api.restore = (unsigned long)p->addr + offset;
+
+	patch_text(p->ainsn.api.insn, p->opcode);
+}
+
+static void __kprobes arch_prepare_simulate(struct kprobe *p)
+{
+	p->ainsn.api.restore = 0;
+}
+
+static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	if (p->ainsn.api.handler)
+		p->ainsn.api.handler((u32)p->opcode, (long)p->addr, regs);
+
+	post_kprobe_handler(kcb, regs);
+}
+
+int __kprobes arch_prepare_kprobe(struct kprobe *p)
+{
+	unsigned long probe_addr = (unsigned long)p->addr;
+
+	if (probe_addr & 0x1) {
+		pr_warn("Address not aligned.\n");
+		return -EINVAL;
+	}
+
+	/* copy instruction */
+	p->opcode = le32_to_cpu(*p->addr);
+
+	/* decode instruction */
+	switch (csky_probe_decode_insn(p->addr, &p->ainsn.api)) {
+	case INSN_REJECTED:	/* insn not supported */
+		return -EINVAL;
+
+	case INSN_GOOD_NO_SLOT:	/* insn need simulation */
+		p->ainsn.api.insn = NULL;
+		break;
+
+	case INSN_GOOD:	/* instruction uses slot */
+		p->ainsn.api.insn = get_insn_slot();
+		if (!p->ainsn.api.insn)
+			return -ENOMEM;
+		break;
+	}
+
+	/* prepare the instruction */
+	if (p->ainsn.api.insn)
+		arch_prepare_ss_slot(p);
+	else
+		arch_prepare_simulate(p);
+
+	return 0;
+}
+
+/* install breakpoint in text */
+void __kprobes arch_arm_kprobe(struct kprobe *p)
+{
+	patch_text(p->addr, USR_BKPT);
+}
+
+/* remove breakpoint from text */
+void __kprobes arch_disarm_kprobe(struct kprobe *p)
+{
+	patch_text(p->addr, p->opcode);
+}
+
+void __kprobes arch_remove_kprobe(struct kprobe *p)
+{
+}
+
+static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
+{
+	kcb->prev_kprobe.kp = kprobe_running();
+	kcb->prev_kprobe.status = kcb->kprobe_status;
+}
+
+static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
+{
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
+	kcb->kprobe_status = kcb->prev_kprobe.status;
+}
+
+static void __kprobes set_current_kprobe(struct kprobe *p)
+{
+	__this_cpu_write(current_kprobe, p);
+}
+
+/*
+ * Interrupts need to be disabled before single-step mode is set, and not
+ * reenabled until after single-step mode ends.
+ * Without disabling interrupt on local CPU, there is a chance of
+ * interrupt occurrence in the period of exception return and  start of
+ * out-of-line single-step, that result in wrongly single stepping
+ * into the interrupt handler.
+ */
+static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb,
+						struct pt_regs *regs)
+{
+	kcb->saved_sr = regs->sr;
+	regs->sr &= ~BIT(6);
+}
+
+static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
+						struct pt_regs *regs)
+{
+	regs->sr = kcb->saved_sr;
+}
+
+static void __kprobes
+set_ss_context(struct kprobe_ctlblk *kcb, unsigned long addr, struct kprobe *p)
+{
+	unsigned long offset = is_insn32(p->opcode) ? 4 : 2;
+
+	kcb->ss_ctx.ss_pending = true;
+	kcb->ss_ctx.match_addr = addr + offset;
+}
+
+static void __kprobes clear_ss_context(struct kprobe_ctlblk *kcb)
+{
+	kcb->ss_ctx.ss_pending = false;
+	kcb->ss_ctx.match_addr = 0;
+}
+
+#define TRACE_MODE_SI		BIT(14)
+#define TRACE_MODE_MASK		~(0x3 << 14)
+#define TRACE_MODE_RUN		0
+
+static void __kprobes setup_singlestep(struct kprobe *p,
+				       struct pt_regs *regs,
+				       struct kprobe_ctlblk *kcb, int reenter)
+{
+	unsigned long slot;
+
+	if (reenter) {
+		save_previous_kprobe(kcb);
+		set_current_kprobe(p);
+		kcb->kprobe_status = KPROBE_REENTER;
+	} else {
+		kcb->kprobe_status = KPROBE_HIT_SS;
+	}
+
+	if (p->ainsn.api.insn) {
+		/* prepare for single stepping */
+		slot = (unsigned long)p->ainsn.api.insn;
+
+		set_ss_context(kcb, slot, p);	/* mark pending ss */
+
+		/* IRQs and single stepping do not mix well. */
+		kprobes_save_local_irqflag(kcb, regs);
+		regs->sr = (regs->sr & TRACE_MODE_MASK) | TRACE_MODE_SI;
+		instruction_pointer_set(regs, slot);
+	} else {
+		/* insn simulation */
+		arch_simulate_insn(p, regs);
+	}
+}
+
+static int __kprobes reenter_kprobe(struct kprobe *p,
+				    struct pt_regs *regs,
+				    struct kprobe_ctlblk *kcb)
+{
+	switch (kcb->kprobe_status) {
+	case KPROBE_HIT_SSDONE:
+	case KPROBE_HIT_ACTIVE:
+		kprobes_inc_nmissed_count(p);
+		setup_singlestep(p, regs, kcb, 1);
+		break;
+	case KPROBE_HIT_SS:
+	case KPROBE_REENTER:
+		pr_warn("Unrecoverable kprobe detected.\n");
+		dump_kprobe(p);
+		BUG();
+		break;
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+
+	return 1;
+}
+
+static void __kprobes
+post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs)
+{
+	struct kprobe *cur = kprobe_running();
+
+	if (!cur)
+		return;
+
+	/* return addr restore if non-branching insn */
+	if (cur->ainsn.api.restore != 0)
+		regs->pc = cur->ainsn.api.restore;
+
+	/* restore back original saved kprobe variables and continue */
+	if (kcb->kprobe_status == KPROBE_REENTER) {
+		restore_previous_kprobe(kcb);
+		return;
+	}
+
+	/* call post handler */
+	kcb->kprobe_status = KPROBE_HIT_SSDONE;
+	if (cur->post_handler)	{
+		/* post_handler can hit breakpoint and single step
+		 * again, so we enable D-flag for recursive exception.
+		 */
+		cur->post_handler(cur, regs, 0);
+	}
+
+	reset_current_kprobe();
+}
+
+int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr)
+{
+	struct kprobe *cur = kprobe_running();
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	switch (kcb->kprobe_status) {
+	case KPROBE_HIT_SS:
+	case KPROBE_REENTER:
+		/*
+		 * We are here because the instruction being single
+		 * stepped caused a page fault. We reset the current
+		 * kprobe and the ip points back to the probe address
+		 * and allow the page fault handler to continue as a
+		 * normal page fault.
+		 */
+		regs->pc = (unsigned long) cur->addr;
+		if (!instruction_pointer(regs))
+			BUG();
+
+		if (kcb->kprobe_status == KPROBE_REENTER)
+			restore_previous_kprobe(kcb);
+		else
+			reset_current_kprobe();
+
+		break;
+	case KPROBE_HIT_ACTIVE:
+	case KPROBE_HIT_SSDONE:
+		/*
+		 * We increment the nmissed count for accounting,
+		 * we can also use npre/npostfault count for accounting
+		 * these specific fault cases.
+		 */
+		kprobes_inc_nmissed_count(cur);
+
+		/*
+		 * We come here because instructions in the pre/post
+		 * handler caused the page_fault, this could happen
+		 * if handler tries to access user space by
+		 * copy_from_user(), get_user() etc. Let the
+		 * user-specified handler try to fix it first.
+		 */
+		if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
+			return 1;
+
+		/*
+		 * In case the user-specified fault handler returned
+		 * zero, try to fix up.
+		 */
+		if (fixup_exception(regs))
+			return 1;
+	}
+	return 0;
+}
+
+int __kprobes
+kprobe_breakpoint_handler(struct pt_regs *regs)
+{
+	struct kprobe *p, *cur_kprobe;
+	struct kprobe_ctlblk *kcb;
+	unsigned long addr = instruction_pointer(regs);
+
+	kcb = get_kprobe_ctlblk();
+	cur_kprobe = kprobe_running();
+
+	p = get_kprobe((kprobe_opcode_t *) addr);
+
+	if (p) {
+		if (cur_kprobe) {
+			if (reenter_kprobe(p, regs, kcb))
+				return 1;
+		} else {
+			/* Probe hit */
+			set_current_kprobe(p);
+			kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+
+			/*
+			 * If we have no pre-handler or it returned 0, we
+			 * continue with normal processing.  If we have a
+			 * pre-handler and it returned non-zero, it will
+			 * modify the execution path and no need to single
+			 * stepping. Let's just reset current kprobe and exit.
+			 *
+			 * pre_handler can hit a breakpoint and can step thru
+			 * before return.
+			 */
+			if (!p->pre_handler || !p->pre_handler(p, regs))
+				setup_singlestep(p, regs, kcb, 0);
+			else
+				reset_current_kprobe();
+		}
+		return 1;
+	}
+
+	/*
+	 * The breakpoint instruction was removed right
+	 * after we hit it.  Another cpu has removed
+	 * either a probepoint or a debugger breakpoint
+	 * at this address.  In either case, no further
+	 * handling of this interrupt is appropriate.
+	 * Return back to original instruction, and continue.
+	 */
+	return 0;
+}
+
+int __kprobes
+kprobe_single_step_handler(struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	if ((kcb->ss_ctx.ss_pending)
+	    && (kcb->ss_ctx.match_addr == instruction_pointer(regs))) {
+		clear_ss_context(kcb);	/* clear pending ss */
+
+		kprobes_restore_local_irqflag(kcb, regs);
+		regs->sr = (regs->sr & TRACE_MODE_MASK) | TRACE_MODE_RUN;
+
+		post_kprobe_handler(kcb, regs);
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * Provide a blacklist of symbols identifying ranges which cannot be kprobed.
+ * This blacklist is exposed to userspace via debugfs (kprobes/blacklist).
+ */
+int __init arch_populate_kprobe_blacklist(void)
+{
+	int ret;
+
+	ret = kprobe_add_area_blacklist((unsigned long)__irqentry_text_start,
+					(unsigned long)__irqentry_text_end);
+	return ret;
+}
+
+void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs)
+{
+	struct kretprobe_instance *ri = NULL;
+	struct hlist_head *head, empty_rp;
+	struct hlist_node *tmp;
+	unsigned long flags, orig_ret_address = 0;
+	unsigned long trampoline_address =
+		(unsigned long)&kretprobe_trampoline;
+	kprobe_opcode_t *correct_ret_addr = NULL;
+
+	INIT_HLIST_HEAD(&empty_rp);
+	kretprobe_hash_lock(current, &head, &flags);
+
+	/*
+	 * It is possible to have multiple instances associated with a given
+	 * task either because multiple functions in the call path have
+	 * return probes installed on them, and/or more than one
+	 * return probe was registered for a target function.
+	 *
+	 * We can handle this because:
+	 *     - instances are always pushed into the head of the list
+	 *     - when multiple return probes are registered for the same
+	 *	 function, the (chronologically) first instance's ret_addr
+	 *	 will be the real return address, and all the rest will
+	 *	 point to kretprobe_trampoline.
+	 */
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
+	correct_ret_addr = ri->ret_addr;
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
+		if (ri->rp && ri->rp->handler) {
+			__this_cpu_write(current_kprobe, &ri->rp->kp);
+			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
+			ri->ret_addr = correct_ret_addr;
+			ri->rp->handler(ri, regs);
+			__this_cpu_write(current_kprobe, NULL);
+		}
+
+		recycle_rp_inst(ri, &empty_rp);
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	kretprobe_hash_unlock(current, &flags);
+
+	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
+		hlist_del(&ri->hlist);
+		kfree(ri);
+	}
+	return (void *)orig_ret_address;
+}
+
+void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
+				      struct pt_regs *regs)
+{
+	ri->ret_addr = (kprobe_opcode_t *)regs->lr;
+	regs->lr = (unsigned long) &kretprobe_trampoline;
+}
+
+int __kprobes arch_trampoline_kprobe(struct kprobe *p)
+{
+	return 0;
+}
+
+int __init arch_init_kprobes(void)
+{
+	return 0;
+}
diff --git a/arch/csky/kernel/probes/kprobes_trampoline.S b/arch/csky/kernel/probes/kprobes_trampoline.S
new file mode 100644
index 000000000000..b1fe3af24f03
--- /dev/null
+++ b/arch/csky/kernel/probes/kprobes_trampoline.S
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#include <linux/linkage.h>
+
+#include <abi/entry.h>
+
+ENTRY(kretprobe_trampoline)
+	SAVE_REGS_FTRACE
+
+	mov	a0, sp /* pt_regs */
+
+	jbsr	trampoline_probe_handler
+
+	/* use the result as the return-address */
+	mov	lr, a0
+
+	RESTORE_REGS_FTRACE
+	rts
+ENDPROC(kretprobe_trampoline)
diff --git a/arch/csky/kernel/probes/simulate-insn.c b/arch/csky/kernel/probes/simulate-insn.c
new file mode 100644
index 000000000000..4e464fed52ec
--- /dev/null
+++ b/arch/csky/kernel/probes/simulate-insn.c
@@ -0,0 +1,398 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+
+#include "decode-insn.h"
+#include "simulate-insn.h"
+
+static inline bool csky_insn_reg_get_val(struct pt_regs *regs,
+					 unsigned long index,
+					 unsigned long *ptr)
+{
+	if (index < 14)
+		*ptr = *(&regs->a0 + index);
+
+	if (index > 15 && index < 31)
+		*ptr = *(&regs->exregs[0] + index - 16);
+
+	switch (index) {
+	case 14:
+		*ptr = regs->usp;
+		break;
+	case 15:
+		*ptr = regs->lr;
+		break;
+	case 31:
+		*ptr = regs->tls;
+		break;
+	default:
+		goto fail;
+	}
+
+	return true;
+fail:
+	return false;
+}
+
+static inline bool csky_insn_reg_set_val(struct pt_regs *regs,
+					 unsigned long index,
+					 unsigned long val)
+{
+	if (index < 14)
+		*(&regs->a0 + index) = val;
+
+	if (index > 15 && index < 31)
+		*(&regs->exregs[0] + index - 16) = val;
+
+	switch (index) {
+	case 14:
+		regs->usp = val;
+		break;
+	case 15:
+		regs->lr = val;
+		break;
+	case 31:
+		regs->tls = val;
+		break;
+	default:
+		goto fail;
+	}
+
+	return true;
+fail:
+	return false;
+}
+
+void __kprobes
+simulate_br16(u32 opcode, long addr, struct pt_regs *regs)
+{
+	instruction_pointer_set(regs,
+		addr + sign_extend32((opcode & 0x3ff) << 1, 9));
+}
+
+void __kprobes
+simulate_br32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	instruction_pointer_set(regs,
+		addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+}
+
+void __kprobes
+simulate_bt16(u32 opcode, long addr, struct pt_regs *regs)
+{
+	if (regs->sr & 1)
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0x3ff) << 1, 9));
+	else
+		instruction_pointer_set(regs, addr + 2);
+}
+
+void __kprobes
+simulate_bt32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	if (regs->sr & 1)
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	else
+		instruction_pointer_set(regs, addr + 4);
+}
+
+void __kprobes
+simulate_bf16(u32 opcode, long addr, struct pt_regs *regs)
+{
+	if (!(regs->sr & 1))
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0x3ff) << 1, 9));
+	else
+		instruction_pointer_set(regs, addr + 2);
+}
+
+void __kprobes
+simulate_bf32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	if (!(regs->sr & 1))
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	else
+		instruction_pointer_set(regs, addr + 4);
+}
+
+void __kprobes
+simulate_jmp16(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = (opcode >> 2) & 0xf;
+
+	csky_insn_reg_get_val(regs, tmp, &tmp);
+
+	instruction_pointer_set(regs, tmp & 0xfffffffe);
+}
+
+void __kprobes
+simulate_jmp32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+
+	csky_insn_reg_get_val(regs, tmp, &tmp);
+
+	instruction_pointer_set(regs, tmp & 0xfffffffe);
+}
+
+void __kprobes
+simulate_jsr16(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = (opcode >> 2) & 0xf;
+
+	csky_insn_reg_get_val(regs, tmp, &tmp);
+
+	regs->lr = addr + 2;
+
+	instruction_pointer_set(regs, tmp & 0xfffffffe);
+}
+
+void __kprobes
+simulate_jsr32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+
+	csky_insn_reg_get_val(regs, tmp, &tmp);
+
+	regs->lr = addr + 4;
+
+	instruction_pointer_set(regs, tmp & 0xfffffffe);
+}
+
+void __kprobes
+simulate_lrw16(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long val;
+	unsigned long tmp = (opcode & 0x300) >> 3;
+	unsigned long offset = ((opcode & 0x1f) | tmp) << 2;
+
+	tmp = (opcode & 0xe0) >> 5;
+
+	val = *(unsigned int *)(instruction_pointer(regs) + offset);
+
+	csky_insn_reg_set_val(regs, tmp, val);
+}
+
+void __kprobes
+simulate_lrw32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long val;
+	unsigned long offset = (opcode & 0xffff0000) >> 14;
+	unsigned long tmp = opcode & 0x0000001f;
+
+	val = *(unsigned int *)
+		((instruction_pointer(regs) + offset) & 0xfffffffc);
+
+	csky_insn_reg_set_val(regs, tmp, val);
+}
+
+void __kprobes
+simulate_pop16(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long *tmp = (unsigned long *)regs->usp;
+	int i;
+
+	for (i = 0; i < (opcode & 0xf); i++) {
+		csky_insn_reg_set_val(regs, i + 4, *tmp);
+		tmp += 1;
+	}
+
+	if (opcode & 0x10) {
+		csky_insn_reg_set_val(regs, 15, *tmp);
+		tmp += 1;
+	}
+
+	regs->usp = (unsigned long)tmp;
+
+	instruction_pointer_set(regs, regs->lr);
+}
+
+void __kprobes
+simulate_pop32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long *tmp = (unsigned long *)regs->usp;
+	int i;
+
+	for (i = 0; i < ((opcode & 0xf0000) >> 16); i++) {
+		csky_insn_reg_set_val(regs, i + 4, *tmp);
+		tmp += 1;
+	}
+
+	if (opcode & 0x100000) {
+		csky_insn_reg_set_val(regs, 15, *tmp);
+		tmp += 1;
+	}
+
+	for (i = 0; i < ((opcode & 0xe00000) >> 21); i++) {
+		csky_insn_reg_set_val(regs, i + 16, *tmp);
+		tmp += 1;
+	}
+
+	if (opcode & 0x1000000) {
+		csky_insn_reg_set_val(regs, 29, *tmp);
+		tmp += 1;
+	}
+
+	regs->usp = (unsigned long)tmp;
+
+	instruction_pointer_set(regs, regs->lr);
+}
+
+void __kprobes
+simulate_bez32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+
+	csky_insn_reg_get_val(regs, tmp, &tmp);
+
+	if (tmp == 0) {
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	} else
+		instruction_pointer_set(regs, addr + 4);
+}
+
+void __kprobes
+simulate_bnez32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+
+	csky_insn_reg_get_val(regs, tmp, &tmp);
+
+	if (tmp != 0) {
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	} else
+		instruction_pointer_set(regs, addr + 4);
+}
+
+void __kprobes
+simulate_bnezad32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+	unsigned long val;
+
+	csky_insn_reg_get_val(regs, tmp, &val);
+
+	val -= 1;
+
+	if (val > 0) {
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	} else
+		instruction_pointer_set(regs, addr + 4);
+
+	csky_insn_reg_set_val(regs, tmp, val);
+}
+
+void __kprobes
+simulate_bhsz32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+	unsigned long val;
+
+	csky_insn_reg_get_val(regs, tmp, &val);
+
+	if (val >= 0) {
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	} else
+		instruction_pointer_set(regs, addr + 4);
+
+	csky_insn_reg_set_val(regs, tmp, val);
+}
+
+void __kprobes
+simulate_bhz32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+	unsigned long val;
+
+	csky_insn_reg_get_val(regs, tmp, &val);
+
+	if (val > 0) {
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	} else
+		instruction_pointer_set(regs, addr + 4);
+
+	csky_insn_reg_set_val(regs, tmp, val);
+}
+
+void __kprobes
+simulate_blsz32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+	unsigned long val;
+
+	csky_insn_reg_get_val(regs, tmp, &val);
+
+	if (val <= 0) {
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	} else
+		instruction_pointer_set(regs, addr + 4);
+
+	csky_insn_reg_set_val(regs, tmp, val);
+}
+
+void __kprobes
+simulate_blz32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp = opcode & 0x1f;
+	unsigned long val;
+
+	csky_insn_reg_get_val(regs, tmp, &val);
+
+	if (val < 0) {
+		instruction_pointer_set(regs,
+			addr + sign_extend32((opcode & 0xffff0000) >> 15, 15));
+	} else
+		instruction_pointer_set(regs, addr + 4);
+
+	csky_insn_reg_set_val(regs, tmp, val);
+}
+
+void __kprobes
+simulate_bsr32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long tmp;
+
+	tmp = (opcode & 0xffff) << 16;
+	tmp |= (opcode & 0xffff0000) >> 16;
+
+	instruction_pointer_set(regs,
+		addr + sign_extend32((tmp & 0x3ffffff) << 1, 15));
+
+	regs->lr = addr + 4;
+}
+
+void __kprobes
+simulate_jmpi32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long val;
+	unsigned long offset = ((opcode & 0xffff0000) >> 14);
+
+	val = *(unsigned int *)
+		((instruction_pointer(regs) + offset) & 0xfffffffc);
+
+	instruction_pointer_set(regs, val);
+}
+
+void __kprobes
+simulate_jsri32(u32 opcode, long addr, struct pt_regs *regs)
+{
+	unsigned long val;
+	unsigned long offset = ((opcode & 0xffff0000) >> 14);
+
+	val = *(unsigned int *)
+		((instruction_pointer(regs) + offset) & 0xfffffffc);
+
+	regs->lr = addr + 4;
+
+	instruction_pointer_set(regs, val);
+}
diff --git a/arch/csky/kernel/probes/simulate-insn.h b/arch/csky/kernel/probes/simulate-insn.h
new file mode 100644
index 000000000000..ba4cb7ef062e
--- /dev/null
+++ b/arch/csky/kernel/probes/simulate-insn.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef __CSKY_KERNEL_PROBES_SIMULATE_INSN_H
+#define __CSKY_KERNEL_PROBES_SIMULATE_INSN_H
+
+#define __CSKY_INSN_FUNCS(name, mask, val)				\
+static __always_inline bool csky_insn_is_##name(probe_opcode_t code)	\
+{									\
+	BUILD_BUG_ON(~(mask) & (val));					\
+	return (code & (mask)) == (val);				\
+}									\
+void simulate_##name(u32 opcode, long addr, struct pt_regs *regs);
+
+#define CSKY_INSN_SET_SIMULATE(name, code)				\
+	do {								\
+		if (csky_insn_is_##name(code)) {			\
+			api->handler = simulate_##name;			\
+			return INSN_GOOD_NO_SLOT;			\
+		}							\
+	} while (0)
+
+__CSKY_INSN_FUNCS(br16,		0xfc00, 0x0400)
+__CSKY_INSN_FUNCS(bt16,		0xfc00, 0x0800)
+__CSKY_INSN_FUNCS(bf16,		0xfc00, 0x0c00)
+__CSKY_INSN_FUNCS(jmp16,	0xffc3, 0x7800)
+__CSKY_INSN_FUNCS(jsr16,	0xffc3, 0x7801)
+__CSKY_INSN_FUNCS(lrw16,	0xfc00, 0x1000)
+__CSKY_INSN_FUNCS(pop16,	0xffe0, 0x1480)
+
+__CSKY_INSN_FUNCS(br32,		0x0000ffff, 0x0000e800)
+__CSKY_INSN_FUNCS(bt32,		0x0000ffff, 0x0000e860)
+__CSKY_INSN_FUNCS(bf32,		0x0000ffff, 0x0000e840)
+__CSKY_INSN_FUNCS(jmp32,	0xffffffe0, 0x0000e8c0)
+__CSKY_INSN_FUNCS(jsr32,	0xffffffe0, 0x0000e8e0)
+__CSKY_INSN_FUNCS(lrw32,	0x0000ffe0, 0x0000ea80)
+__CSKY_INSN_FUNCS(pop32,	0xfe00ffff, 0x0000ebc0)
+
+__CSKY_INSN_FUNCS(bez32,	0x0000ffe0, 0x0000e900)
+__CSKY_INSN_FUNCS(bnez32,	0x0000ffe0, 0x0000e920)
+__CSKY_INSN_FUNCS(bnezad32,	0x0000ffe0, 0x0000e820)
+__CSKY_INSN_FUNCS(bhsz32,	0x0000ffe0, 0x0000e9a0)
+__CSKY_INSN_FUNCS(bhz32,	0x0000ffe0, 0x0000e940)
+__CSKY_INSN_FUNCS(blsz32,	0x0000ffe0, 0x0000e960)
+__CSKY_INSN_FUNCS(blz32,	0x0000ffe0, 0x0000e980)
+__CSKY_INSN_FUNCS(bsr32,	0x0000fc00, 0x0000e000)
+__CSKY_INSN_FUNCS(jmpi32,	0x0000ffff, 0x0000eac0)
+__CSKY_INSN_FUNCS(jsri32,	0x0000ffff, 0x0000eae0)
+
+#endif /* __CSKY_KERNEL_PROBES_SIMULATE_INSN_H */
diff --git a/arch/csky/kernel/probes/uprobes.c b/arch/csky/kernel/probes/uprobes.c
new file mode 100644
index 000000000000..b3a56c260e3e
--- /dev/null
+++ b/arch/csky/kernel/probes/uprobes.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2014-2016 Pratyush Anand <panand@redhat.com>
+ */
+#include <linux/highmem.h>
+#include <linux/ptrace.h>
+#include <linux/uprobes.h>
+#include <asm/cacheflush.h>
+
+#include "decode-insn.h"
+
+#define UPROBE_TRAP_NR	UINT_MAX
+
+unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
+{
+	return instruction_pointer(regs);
+}
+
+int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
+		unsigned long addr)
+{
+	probe_opcode_t insn;
+
+	insn = *(probe_opcode_t *)(&auprobe->insn[0]);
+
+	auprobe->insn_size = is_insn32(insn) ? 4 : 2;
+
+	switch (csky_probe_decode_insn(&insn, &auprobe->api)) {
+	case INSN_REJECTED:
+		return -EINVAL;
+
+	case INSN_GOOD_NO_SLOT:
+		auprobe->simulate = true;
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	utask->autask.saved_trap_no = current->thread.trap_no;
+	current->thread.trap_no = UPROBE_TRAP_NR;
+
+	instruction_pointer_set(regs, utask->xol_vaddr);
+
+	user_enable_single_step(current);
+
+	return 0;
+}
+
+int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	WARN_ON_ONCE(current->thread.trap_no != UPROBE_TRAP_NR);
+
+	instruction_pointer_set(regs, utask->vaddr + auprobe->insn_size);
+
+	user_disable_single_step(current);
+
+	return 0;
+}
+
+bool arch_uprobe_xol_was_trapped(struct task_struct *t)
+{
+	if (t->thread.trap_no != UPROBE_TRAP_NR)
+		return true;
+
+	return false;
+}
+
+bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	probe_opcode_t insn;
+	unsigned long addr;
+
+	if (!auprobe->simulate)
+		return false;
+
+	insn = *(probe_opcode_t *)(&auprobe->insn[0]);
+	addr = instruction_pointer(regs);
+
+	if (auprobe->api.handler)
+		auprobe->api.handler(insn, addr, regs);
+
+	return true;
+}
+
+void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	/*
+	 * Task has received a fatal signal, so reset back to probbed
+	 * address.
+	 */
+	instruction_pointer_set(regs, utask->vaddr);
+
+	user_disable_single_step(current);
+}
+
+bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
+		struct pt_regs *regs)
+{
+	if (ctx == RP_CHECK_CHAIN_CALL)
+		return regs->usp <= ret->stack;
+	else
+		return regs->usp < ret->stack;
+}
+
+unsigned long
+arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr,
+				  struct pt_regs *regs)
+{
+	unsigned long ra;
+
+	ra = regs->lr;
+
+	regs->lr = trampoline_vaddr;
+
+	return ra;
+}
+
+int arch_uprobe_exception_notify(struct notifier_block *self,
+				 unsigned long val, void *data)
+{
+	return NOTIFY_DONE;
+}
+
+int uprobe_breakpoint_handler(struct pt_regs *regs)
+{
+	if (uprobe_pre_sstep_notifier(regs))
+		return 1;
+
+	return 0;
+}
+
+int uprobe_single_step_handler(struct pt_regs *regs)
+{
+	if (uprobe_post_sstep_notifier(regs))
+		return 1;
+
+	return 0;
+}
diff --git a/arch/csky/kernel/ptrace.c b/arch/csky/kernel/ptrace.c
index 313623a19ecb..21ac2608f205 100644
--- a/arch/csky/kernel/ptrace.c
+++ b/arch/csky/kernel/ptrace.c
@@ -193,6 +193,109 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 	return &user_csky_view;
 }
 
+struct pt_regs_offset {
+	const char *name;
+	int offset;
+};
+
+#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+static const struct pt_regs_offset regoffset_table[] = {
+	REG_OFFSET_NAME(tls),
+	REG_OFFSET_NAME(lr),
+	REG_OFFSET_NAME(pc),
+	REG_OFFSET_NAME(sr),
+	REG_OFFSET_NAME(usp),
+	REG_OFFSET_NAME(orig_a0),
+	REG_OFFSET_NAME(a0),
+	REG_OFFSET_NAME(a1),
+	REG_OFFSET_NAME(a2),
+	REG_OFFSET_NAME(a3),
+	REG_OFFSET_NAME(regs[0]),
+	REG_OFFSET_NAME(regs[1]),
+	REG_OFFSET_NAME(regs[2]),
+	REG_OFFSET_NAME(regs[3]),
+	REG_OFFSET_NAME(regs[4]),
+	REG_OFFSET_NAME(regs[5]),
+	REG_OFFSET_NAME(regs[6]),
+	REG_OFFSET_NAME(regs[7]),
+	REG_OFFSET_NAME(regs[8]),
+	REG_OFFSET_NAME(regs[9]),
+#if defined(__CSKYABIV2__)
+	REG_OFFSET_NAME(exregs[0]),
+	REG_OFFSET_NAME(exregs[1]),
+	REG_OFFSET_NAME(exregs[2]),
+	REG_OFFSET_NAME(exregs[3]),
+	REG_OFFSET_NAME(exregs[4]),
+	REG_OFFSET_NAME(exregs[5]),
+	REG_OFFSET_NAME(exregs[6]),
+	REG_OFFSET_NAME(exregs[7]),
+	REG_OFFSET_NAME(exregs[8]),
+	REG_OFFSET_NAME(exregs[9]),
+	REG_OFFSET_NAME(exregs[10]),
+	REG_OFFSET_NAME(exregs[11]),
+	REG_OFFSET_NAME(exregs[12]),
+	REG_OFFSET_NAME(exregs[13]),
+	REG_OFFSET_NAME(exregs[14]),
+	REG_OFFSET_NAME(rhi),
+	REG_OFFSET_NAME(rlo),
+	REG_OFFSET_NAME(dcsr),
+#endif
+	REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name:	the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_offset *roff;
+
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->offset;
+	return -EINVAL;
+}
+
+/**
+ * regs_within_kernel_stack() - check the address in the stack
+ * @regs:      pt_regs which contains kernel stack pointer.
+ * @addr:      address which is checked.
+ *
+ * regs_within_kernel_stack() checks @addr is within the kernel stack page(s).
+ * If @addr is within the kernel stack, it returns true. If not, returns false.
+ */
+static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
+{
+	return (addr & ~(THREAD_SIZE - 1))  ==
+		(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1));
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs:	pt_regs which contains kernel stack pointer.
+ * @n:		stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
+{
+	unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
+
+	addr += n;
+	if (regs_within_kernel_stack(regs, (unsigned long)addr))
+		return *addr;
+	else
+		return 0;
+}
+
 void ptrace_disable(struct task_struct *child)
 {
 	singlestep_disable(child);
diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c
index 3821e55742f4..819a9a7bf786 100644
--- a/arch/csky/kernel/setup.c
+++ b/arch/csky/kernel/setup.c
@@ -24,26 +24,9 @@ struct screen_info screen_info = {
 };
 #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);
@@ -54,54 +37,36 @@ static void __init csky_memblock_init(void)
 	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;
+	max_low_pfn = max_pfn = PFN_DOWN(memblock_end_of_DRAM());
 
 	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;
+	if (size <= PFN_DOWN(SSEG_SIZE - PHYS_OFFSET_OFFSET))
+		zone_size[ZONE_NORMAL] = size;
+	else if (size < PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET)) {
+		zone_size[ZONE_NORMAL] =
+				PFN_DOWN(SSEG_SIZE - PHYS_OFFSET_OFFSET);
+		max_low_pfn = min_low_pfn + zone_size[ZONE_NORMAL];
 	} else {
-		if (size <= PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET))
-			zone_size[ZONE_NORMAL] = max_pfn - min_low_pfn;
-		else {
-			zone_size[ZONE_NORMAL] =
+		zone_size[ZONE_NORMAL] =
 				PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET);
-			max_low_pfn = min_low_pfn + zone_size[ZONE_NORMAL];
-		}
+		max_low_pfn = min_low_pfn + zone_size[ZONE_NORMAL];
+		write_mmu_msa1(read_mmu_msa0() + SSEG_SIZE);
 	}
 
 #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;
+	zone_size[ZONE_HIGHMEM] = max_pfn - max_low_pfn;
 
-	highend_pfn = max_pfn;
+	highstart_pfn = max_low_pfn;
+	highend_pfn   = max_pfn;
 #endif
 	memblock_set_current_limit(PFN_PHYS(max_low_pfn));
 
 	dma_contiguous_reserve(0);
 
-	free_area_init_node(0, zone_size, min_low_pfn, zhole_size);
+	free_area_init_node(0, zone_size, min_low_pfn, NULL);
 }
 
 void __init setup_arch(char **cmdline_p)
diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c
index 9b1b7c039ddf..9452d6570b7e 100644
--- a/arch/csky/kernel/signal.c
+++ b/arch/csky/kernel/signal.c
@@ -175,6 +175,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	sigset_t *oldset = sigmask_to_save();
 	int ret;
 
+	rseq_signal_deliver(ksig, regs);
+
 	/* Are we from a system call? */
 	if (in_syscall(regs)) {
 		/* Avoid additional syscall restarting via ret_from_exception */
@@ -251,6 +253,9 @@ static void do_signal(struct pt_regs *regs)
 asmlinkage void do_notify_resume(struct pt_regs *regs,
 	unsigned long thread_info_flags)
 {
+	if (thread_info_flags & _TIF_UPROBE)
+		uprobe_notify_resume(regs);
+
 	/* Handle pending signal delivery */
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs);
@@ -258,5 +263,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
 		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
+		rseq_handle_notify_resume(NULL, regs);
 	}
 }
diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c
index 0bb0954d5570..b5c5bc3afeb5 100644
--- a/arch/csky/kernel/smp.c
+++ b/arch/csky/kernel/smp.c
@@ -22,6 +22,9 @@
 #include <asm/sections.h>
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
+#ifdef CONFIG_CPU_HAS_FPU
+#include <abi/fpu.h>
+#endif
 
 struct ipi_data_struct {
 	unsigned long bits ____cacheline_aligned;
@@ -156,6 +159,8 @@ volatile unsigned int secondary_hint;
 volatile unsigned int secondary_ccr;
 volatile unsigned int secondary_stack;
 
+unsigned long secondary_msa1;
+
 int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	unsigned long mask = 1 << cpu;
@@ -164,6 +169,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 		(unsigned int) task_stack_page(tidle) + THREAD_SIZE - 8;
 	secondary_hint = mfcr("cr31");
 	secondary_ccr  = mfcr("cr18");
+	secondary_msa1 = read_mmu_msa1();
 
 	/*
 	 * Because other CPUs are in reset status, we must flush data
diff --git a/arch/csky/kernel/traps.c b/arch/csky/kernel/traps.c
index b057480e7463..fcc3a69831ad 100644
--- a/arch/csky/kernel/traps.c
+++ b/arch/csky/kernel/traps.c
@@ -14,6 +14,7 @@
 #include <linux/kallsyms.h>
 #include <linux/rtc.h>
 #include <linux/uaccess.h>
+#include <linux/kprobes.h>
 
 #include <asm/setup.h>
 #include <asm/traps.h>
@@ -109,14 +110,14 @@ void buserr(struct pt_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;
+	struct task_struct *tsk = current;
 
-	vector = (mfcr("psr") >> 16) & 0xff;
+	vector = (regs->sr >> 16) & 0xff;
 
 	switch (vector) {
 	case VEC_ZERODIV:
@@ -125,10 +126,27 @@ asmlinkage void trap_c(struct pt_regs *regs)
 		break;
 	/* ptrace */
 	case VEC_TRACE:
+#ifdef CONFIG_KPROBES
+		if (kprobe_single_step_handler(regs))
+			return;
+#endif
+#ifdef CONFIG_UPROBES
+		if (uprobe_single_step_handler(regs))
+			return;
+#endif
 		info.si_code = TRAP_TRACE;
 		sig = SIGTRAP;
 		break;
 	case VEC_ILLEGAL:
+		tsk->thread.trap_no = vector;
+#ifdef CONFIG_KPROBES
+		if (kprobe_breakpoint_handler(regs))
+			return;
+#endif
+#ifdef CONFIG_UPROBES
+		if (uprobe_breakpoint_handler(regs))
+			return;
+#endif
 		die_if_kernel("Kernel mode ILLEGAL", regs, vector);
 #ifndef CONFIG_CPU_NO_USER_BKPT
 		if (*(uint16_t *)instruction_pointer(regs) != USR_BKPT)
@@ -146,16 +164,20 @@ asmlinkage void trap_c(struct pt_regs *regs)
 		sig = SIGTRAP;
 		break;
 	case VEC_ACCESS:
+		tsk->thread.trap_no = vector;
 		return buserr(regs);
 #ifdef CONFIG_CPU_NEED_SOFTALIGN
 	case VEC_ALIGN:
+		tsk->thread.trap_no = vector;
 		return csky_alignment(regs);
 #endif
 #ifdef CONFIG_CPU_HAS_FPU
 	case VEC_FPE:
+		tsk->thread.trap_no = vector;
 		die_if_kernel("Kernel mode FPE", regs, vector);
 		return fpu_fpe(regs);
 	case VEC_PRIV:
+		tsk->thread.trap_no = vector;
 		die_if_kernel("Kernel mode PRIV", regs, vector);
 		if (fpu_libc_helper(regs))
 			return;
@@ -164,5 +186,8 @@ asmlinkage void trap_c(struct pt_regs *regs)
 		sig = SIGSEGV;
 		break;
 	}
+
+	tsk->thread.trap_no = vector;
+
 	send_sig(sig, current, 0);
 }
diff --git a/arch/csky/mm/cachev2.c b/arch/csky/mm/cachev2.c
index bc419f8039d3..7a9664adce43 100644
--- a/arch/csky/mm/cachev2.c
+++ b/arch/csky/mm/cachev2.c
@@ -7,8 +7,12 @@
 #include <asm/cache.h>
 #include <asm/barrier.h>
 
+/* for L1-cache */
 #define INS_CACHE		(1 << 0)
+#define DATA_CACHE		(1 << 1)
 #define CACHE_INV		(1 << 4)
+#define CACHE_CLR		(1 << 5)
+#define CACHE_OMS		(1 << 6)
 
 void local_icache_inv_all(void *priv)
 {
@@ -16,11 +20,6 @@ void local_icache_inv_all(void *priv)
 	sync_is();
 }
 
-void icache_inv_all(void)
-{
-	on_each_cpu(local_icache_inv_all, NULL, 1);
-}
-
 #ifdef CONFIG_CPU_HAS_ICACHE_INS
 void icache_inv_range(unsigned long start, unsigned long end)
 {
@@ -31,9 +30,43 @@ void icache_inv_range(unsigned long start, unsigned long end)
 	sync_is();
 }
 #else
+struct cache_range {
+	unsigned long start;
+	unsigned long end;
+};
+
+static DEFINE_SPINLOCK(cache_lock);
+
+static inline void cache_op_line(unsigned long i, unsigned int val)
+{
+	mtcr("cr22", i);
+	mtcr("cr17", val);
+}
+
+void local_icache_inv_range(void *priv)
+{
+	struct cache_range *param = priv;
+	unsigned long i = param->start & ~(L1_CACHE_BYTES - 1);
+	unsigned long flags;
+
+	spin_lock_irqsave(&cache_lock, flags);
+
+	for (; i < param->end; i += L1_CACHE_BYTES)
+		cache_op_line(i, INS_CACHE | CACHE_INV | CACHE_OMS);
+
+	spin_unlock_irqrestore(&cache_lock, flags);
+
+	sync_is();
+}
+
 void icache_inv_range(unsigned long start, unsigned long end)
 {
-	icache_inv_all();
+	struct cache_range param = { start, end };
+
+	if (irqs_disabled())
+		local_icache_inv_range(&param);
+	else
+		on_each_cpu(local_icache_inv_range, &param, 1);
 }
 #endif
 
diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c
index f76618b630f9..d3c61b83e195 100644
--- a/arch/csky/mm/fault.c
+++ b/arch/csky/mm/fault.c
@@ -18,6 +18,7 @@
 #include <linux/extable.h>
 #include <linux/uaccess.h>
 #include <linux/perf_event.h>
+#include <linux/kprobes.h>
 
 #include <asm/hardirq.h>
 #include <asm/mmu_context.h>
@@ -53,6 +54,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
 	int fault;
 	unsigned long address = mmu_meh & PAGE_MASK;
 
+	if (kprobe_page_fault(regs, tsk->thread.trap_no))
+		return;
+
 	si_code = SEGV_MAPERR;
 
 #ifndef CONFIG_CPU_HAS_TLBI
@@ -179,11 +183,14 @@ bad_area:
 bad_area_nosemaphore:
 	/* User mode accesses just cause a SIGSEGV */
 	if (user_mode(regs)) {
+		tsk->thread.trap_no = (regs->sr >> 16) & 0xff;
 		force_sig_fault(SIGSEGV, si_code, (void __user *)address);
 		return;
 	}
 
 no_context:
+	tsk->thread.trap_no = (regs->sr >> 16) & 0xff;
+
 	/* Are we prepared to handle this kernel fault? */
 	if (fixup_exception(regs))
 		return;
@@ -198,6 +205,8 @@ no_context:
 	die_if_kernel("Oops", regs, write);
 
 out_of_memory:
+	tsk->thread.trap_no = (regs->sr >> 16) & 0xff;
+
 	/*
 	 * We ran out of memory, call the OOM killer, and return the userspace
 	 * (which will retry the fault, or kill us if we got oom-killed).
@@ -206,6 +215,8 @@ out_of_memory:
 	return;
 
 do_sigbus:
+	tsk->thread.trap_no = (regs->sr >> 16) & 0xff;
+
 	up_read(&mm->mmap_sem);
 
 	/* Kernel mode? Handle exceptions or die */