Merge tag 'riscv-for-linus-5.12-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:
 "A handful of new RISC-V related patches for this merge window:

   - A check to ensure drivers are properly using uaccess. This isn't
     manifesting with any of the drivers I'm currently using, but may
     catch errors in new drivers.

   - Some preliminary support for the FU740, along with the HiFive
     Unleashed it will appear on.

   - NUMA support for RISC-V, which involves making the arm64 code
     generic.

   - Support for kasan on the vmalloc region.

   - A handful of new drivers for the Kendryte K210, along with the DT
     plumbing required to boot on a handful of K210-based boards.

   - Support for allocating ASIDs.

   - Preliminary support for kernels larger than 128MiB.

   - Various other improvements to our KASAN support, including the
     utilization of huge pages when allocating the KASAN regions.

  We may have already found a bug with the KASAN_VMALLOC code, but it's
  passing my tests. There's a fix in the works, but that will probably
  miss the merge window.

* tag 'riscv-for-linus-5.12-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (75 commits)
  riscv: Improve kasan population by using hugepages when possible
  riscv: Improve kasan population function
  riscv: Use KASAN_SHADOW_INIT define for kasan memory initialization
  riscv: Improve kasan definitions
  riscv: Get rid of MAX_EARLY_MAPPING_SIZE
  soc: canaan: Sort the Makefile alphabetically
  riscv: Disable KSAN_SANITIZE for vDSO
  riscv: Remove unnecessary declaration
  riscv: Add Canaan Kendryte K210 SD card defconfig
  riscv: Update Canaan Kendryte K210 defconfig
  riscv: Add Kendryte KD233 board device tree
  riscv: Add SiPeed MAIXDUINO board device tree
  riscv: Add SiPeed MAIX GO board device tree
  riscv: Add SiPeed MAIX DOCK board device tree
  riscv: Add SiPeed MAIX BiT board device tree
  riscv: Update Canaan Kendryte K210 device tree
  dt-bindings: add resets property to dw-apb-timer
  dt-bindings: fix sifive gpio properties
  dt-bindings: update sifive uart compatible string
  dt-bindings: update sifive clint compatible string
  ...

26 files changed, 1357 insertions, 302 deletions

diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index f6caf4d9ca15..3dc0abde988a 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -4,8 +4,9 @@
 #
 
 ifdef CONFIG_FTRACE
-CFLAGS_REMOVE_ftrace.o	= -pg
-CFLAGS_REMOVE_patch.o	= -pg
+CFLAGS_REMOVE_ftrace.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_patch.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_sbi.o	= $(CC_FLAGS_FTRACE)
 endif
 
 extra-y += head.o
@@ -29,6 +30,7 @@ obj-y	+= riscv_ksyms.o
 obj-y	+= stacktrace.o
 obj-y	+= cacheinfo.o
 obj-y	+= patch.o
+obj-y	+= probes/
 obj-$(CONFIG_MMU) += vdso.o vdso/
 
 obj-$(CONFIG_RISCV_M_MODE)	+= traps_misaligned.o
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index b79ffa3561fd..9ef33346853c 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -68,6 +68,9 @@ void asm_offsets(void)
 	OFFSET(TASK_THREAD_F30, task_struct, thread.fstate.f[30]);
 	OFFSET(TASK_THREAD_F31, task_struct, thread.fstate.f[31]);
 	OFFSET(TASK_THREAD_FCSR, task_struct, thread.fstate.fcsr);
+#ifdef CONFIG_STACKPROTECTOR
+	OFFSET(TSK_STACK_CANARY, task_struct, stack_canary);
+#endif
 
 	DEFINE(PT_SIZE, sizeof(struct pt_regs));
 	OFFSET(PT_EPC, pt_regs, epc);
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 765b62434f30..7f1e5203de88 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -72,29 +72,56 @@ static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target,
 	return 0;
 }
 
+/*
+ * Put 5 instructions with 16 bytes at the front of function within
+ * patchable function entry nops' area.
+ *
+ * 0: REG_S  ra, -SZREG(sp)
+ * 1: auipc  ra, 0x?
+ * 2: jalr   -?(ra)
+ * 3: REG_L  ra, -SZREG(sp)
+ *
+ * So the opcodes is:
+ * 0: 0xfe113c23 (sd)/0xfe112e23 (sw)
+ * 1: 0x???????? -> auipc
+ * 2: 0x???????? -> jalr
+ * 3: 0xff813083 (ld)/0xffc12083 (lw)
+ */
+#if __riscv_xlen == 64
+#define INSN0	0xfe113c23
+#define INSN3	0xff813083
+#elif __riscv_xlen == 32
+#define INSN0	0xfe112e23
+#define INSN3	0xffc12083
+#endif
+
+#define FUNC_ENTRY_SIZE	16
+#define FUNC_ENTRY_JMP	4
+
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-	int ret = ftrace_check_current_call(rec->ip, NULL);
+	unsigned int call[4] = {INSN0, 0, 0, INSN3};
+	unsigned long target = addr;
+	unsigned long caller = rec->ip + FUNC_ENTRY_JMP;
 
-	if (ret)
-		return ret;
+	call[1] = to_auipc_insn((unsigned int)(target - caller));
+	call[2] = to_jalr_insn((unsigned int)(target - caller));
 
-	return __ftrace_modify_call(rec->ip, addr, true);
+	if (patch_text_nosync((void *)rec->ip, call, FUNC_ENTRY_SIZE))
+		return -EPERM;
+
+	return 0;
 }
 
 int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 		    unsigned long addr)
 {
-	unsigned int call[2];
-	int ret;
+	unsigned int nops[4] = {NOP4, NOP4, NOP4, NOP4};
 
-	make_call(rec->ip, addr, call);
-	ret = ftrace_check_current_call(rec->ip, call);
-
-	if (ret)
-		return ret;
+	if (patch_text_nosync((void *)rec->ip, nops, FUNC_ENTRY_SIZE))
+		return -EPERM;
 
-	return __ftrace_modify_call(rec->ip, addr, false);
+	return 0;
 }
 
 
@@ -139,15 +166,16 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 		       unsigned long addr)
 {
 	unsigned int call[2];
+	unsigned long caller = rec->ip + FUNC_ENTRY_JMP;
 	int ret;
 
-	make_call(rec->ip, old_addr, call);
-	ret = ftrace_check_current_call(rec->ip, call);
+	make_call(caller, old_addr, call);
+	ret = ftrace_check_current_call(caller, call);
 
 	if (ret)
 		return ret;
 
-	return __ftrace_modify_call(rec->ip, addr, true);
+	return __ftrace_modify_call(caller, addr, true);
 }
 #endif
 
@@ -176,53 +204,30 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 extern void ftrace_graph_call(void);
+extern void ftrace_graph_regs_call(void);
 int ftrace_enable_ftrace_graph_caller(void)
 {
-	unsigned int call[2];
-	static int init_graph = 1;
 	int ret;
 
-	make_call(&ftrace_graph_call, &ftrace_stub, call);
-
-	/*
-	 * When enabling graph tracer for the first time, ftrace_graph_call
-	 * should contains a call to ftrace_stub.  Once it has been disabled,
-	 * the 8-bytes at the position becomes NOPs.
-	 */
-	if (init_graph) {
-		ret = ftrace_check_current_call((unsigned long)&ftrace_graph_call,
-						call);
-		init_graph = 0;
-	} else {
-		ret = ftrace_check_current_call((unsigned long)&ftrace_graph_call,
-						NULL);
-	}
-
+	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
+				    (unsigned long)&prepare_ftrace_return, true);
 	if (ret)
 		return ret;
 
-	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
 				    (unsigned long)&prepare_ftrace_return, true);
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
-	unsigned int call[2];
 	int ret;
 
-	make_call(&ftrace_graph_call, &prepare_ftrace_return, call);
-
-	/*
-	 * This is to make sure that ftrace_enable_ftrace_graph_caller
-	 * did the right thing.
-	 */
-	ret = ftrace_check_current_call((unsigned long)&ftrace_graph_call,
-					call);
-
+	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
+				    (unsigned long)&prepare_ftrace_return, false);
 	if (ret)
 		return ret;
 
-	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
 				    (unsigned long)&prepare_ftrace_return, false);
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 16e9941900c4..f5a9bad86e58 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -260,7 +260,11 @@ clear_bss_done:
 
 	/* Initialize page tables and relocate to virtual addresses */
 	la sp, init_thread_union + THREAD_SIZE
+#ifdef CONFIG_BUILTIN_DTB
+	la a0, __dtb_start
+#else
 	mv a0, s1
+#endif /* CONFIG_BUILTIN_DTB */
 	call setup_vm
 #ifdef CONFIG_MMU
 	la a0, early_pg_dir
diff --git a/arch/riscv/kernel/image-vars.h b/arch/riscv/kernel/image-vars.h
index 8c212efb37a6..71a76a623257 100644
--- a/arch/riscv/kernel/image-vars.h
+++ b/arch/riscv/kernel/image-vars.h
@@ -3,7 +3,7 @@
  * Copyright (C) 2020 Western Digital Corporation or its affiliates.
  * Linker script variables to be set after section resolution, as
  * ld.lld does not like variables assigned before SECTIONS is processed.
- * Based on arch/arm64/kerne/image-vars.h
+ * Based on arch/arm64/kernel/image-vars.h
  */
 #ifndef __RISCV_KERNEL_IMAGE_VARS_H
 #define __RISCV_KERNEL_IMAGE_VARS_H
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index 35a6ed76cb8b..d171eca623b6 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -13,224 +13,186 @@
 
 	.text
 
-	.macro SAVE_ABI_STATE
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	addi    sp, sp, -48
-	sd      s0, 32(sp)
-	sd      ra, 40(sp)
-	addi    s0, sp, 48
-	sd      t0, 24(sp)
-	sd      t1, 16(sp)
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	sd      t2, 8(sp)
-#endif
-#else
-	addi	sp, sp, -16
-	sd	s0, 0(sp)
-	sd	ra, 8(sp)
-	addi	s0, sp, 16
-#endif
+#define FENTRY_RA_OFFSET	12
+#define ABI_SIZE_ON_STACK	72
+#define ABI_A0			0
+#define ABI_A1			8
+#define ABI_A2			16
+#define ABI_A3			24
+#define ABI_A4			32
+#define ABI_A5			40
+#define ABI_A6			48
+#define ABI_A7			56
+#define ABI_RA			64
+
+	.macro SAVE_ABI
+	addi	sp, sp, -SZREG
+	addi	sp, sp, -ABI_SIZE_ON_STACK
+
+	REG_S	a0, ABI_A0(sp)
+	REG_S	a1, ABI_A1(sp)
+	REG_S	a2, ABI_A2(sp)
+	REG_S	a3, ABI_A3(sp)
+	REG_S	a4, ABI_A4(sp)
+	REG_S	a5, ABI_A5(sp)
+	REG_S	a6, ABI_A6(sp)
+	REG_S	a7, ABI_A7(sp)
+	REG_S	ra, ABI_RA(sp)
 	.endm
 
-	.macro RESTORE_ABI_STATE
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	ld	s0, 32(sp)
-	ld	ra, 40(sp)
-	addi	sp, sp, 48
-#else
-	ld	ra, 8(sp)
-	ld	s0, 0(sp)
-	addi	sp, sp, 16
-#endif
+	.macro RESTORE_ABI
+	REG_L	a0, ABI_A0(sp)
+	REG_L	a1, ABI_A1(sp)
+	REG_L	a2, ABI_A2(sp)
+	REG_L	a3, ABI_A3(sp)
+	REG_L	a4, ABI_A4(sp)
+	REG_L	a5, ABI_A5(sp)
+	REG_L	a6, ABI_A6(sp)
+	REG_L	a7, ABI_A7(sp)
+	REG_L	ra, ABI_RA(sp)
+
+	addi	sp, sp, ABI_SIZE_ON_STACK
+	addi	sp, sp, SZREG
 	.endm
 
-	.macro RESTORE_GRAPH_ARGS
-	ld	a0, 24(sp)
-	ld	a1, 16(sp)
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	ld	a2, 8(sp)
-#endif
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+	.macro SAVE_ALL
+	addi	sp, sp, -SZREG
+	addi	sp, sp, -PT_SIZE_ON_STACK
+
+	REG_S x1,  PT_EPC(sp)
+	addi	sp, sp, PT_SIZE_ON_STACK
+	REG_L x1,  (sp)
+	addi	sp, sp, -PT_SIZE_ON_STACK
+	REG_S x1,  PT_RA(sp)
+	REG_L x1,  PT_EPC(sp)
+
+	REG_S x2,  PT_SP(sp)
+	REG_S x3,  PT_GP(sp)
+	REG_S x4,  PT_TP(sp)
+	REG_S x5,  PT_T0(sp)
+	REG_S x6,  PT_T1(sp)
+	REG_S x7,  PT_T2(sp)
+	REG_S x8,  PT_S0(sp)
+	REG_S x9,  PT_S1(sp)
+	REG_S x10, PT_A0(sp)
+	REG_S x11, PT_A1(sp)
+	REG_S x12, PT_A2(sp)
+	REG_S x13, PT_A3(sp)
+	REG_S x14, PT_A4(sp)
+	REG_S x15, PT_A5(sp)
+	REG_S x16, PT_A6(sp)
+	REG_S x17, PT_A7(sp)
+	REG_S x18, PT_S2(sp)
+	REG_S x19, PT_S3(sp)
+	REG_S x20, PT_S4(sp)
+	REG_S x21, PT_S5(sp)
+	REG_S x22, PT_S6(sp)
+	REG_S x23, PT_S7(sp)
+	REG_S x24, PT_S8(sp)
+	REG_S x25, PT_S9(sp)
+	REG_S x26, PT_S10(sp)
+	REG_S x27, PT_S11(sp)
+	REG_S x28, PT_T3(sp)
+	REG_S x29, PT_T4(sp)
+	REG_S x30, PT_T5(sp)
+	REG_S x31, PT_T6(sp)
 	.endm
 
-ENTRY(ftrace_graph_caller)
-	addi	sp, sp, -16
-	sd	s0, 0(sp)
-	sd	ra, 8(sp)
-	addi	s0, sp, 16
-ftrace_graph_call:
-	.global ftrace_graph_call
-	/*
-	 * Calling ftrace_enable/disable_ftrace_graph_caller would overwrite the
-	 * call below.  Check ftrace_modify_all_code for details.
-	 */
-	call	ftrace_stub
-	ld	ra, 8(sp)
-	ld	s0, 0(sp)
-	addi	sp, sp, 16
-	ret
-ENDPROC(ftrace_graph_caller)
+	.macro RESTORE_ALL
+	REG_L x1,  PT_RA(sp)
+	addi	sp, sp, PT_SIZE_ON_STACK
+	REG_S x1,  (sp)
+	addi	sp, sp, -PT_SIZE_ON_STACK
+	REG_L x1,  PT_EPC(sp)
+	REG_L x2,  PT_SP(sp)
+	REG_L x3,  PT_GP(sp)
+	REG_L x4,  PT_TP(sp)
+	REG_L x5,  PT_T0(sp)
+	REG_L x6,  PT_T1(sp)
+	REG_L x7,  PT_T2(sp)
+	REG_L x8,  PT_S0(sp)
+	REG_L x9,  PT_S1(sp)
+	REG_L x10, PT_A0(sp)
+	REG_L x11, PT_A1(sp)
+	REG_L x12, PT_A2(sp)
+	REG_L x13, PT_A3(sp)
+	REG_L x14, PT_A4(sp)
+	REG_L x15, PT_A5(sp)
+	REG_L x16, PT_A6(sp)
+	REG_L x17, PT_A7(sp)
+	REG_L x18, PT_S2(sp)
+	REG_L x19, PT_S3(sp)
+	REG_L x20, PT_S4(sp)
+	REG_L x21, PT_S5(sp)
+	REG_L x22, PT_S6(sp)
+	REG_L x23, PT_S7(sp)
+	REG_L x24, PT_S8(sp)
+	REG_L x25, PT_S9(sp)
+	REG_L x26, PT_S10(sp)
+	REG_L x27, PT_S11(sp)
+	REG_L x28, PT_T3(sp)
+	REG_L x29, PT_T4(sp)
+	REG_L x30, PT_T5(sp)
+	REG_L x31, PT_T6(sp)
+
+	addi	sp, sp, PT_SIZE_ON_STACK
+	addi	sp, sp, SZREG
+	.endm
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
 ENTRY(ftrace_caller)
-	/*
-	 * a0: the address in the caller when calling ftrace_caller
-	 * a1: the caller's return address
-	 * a2: the address of global variable function_trace_op
-	 */
-	ld	a1, -8(s0)
-	addi	a0, ra, -MCOUNT_INSN_SIZE
-	la	t5, function_trace_op
-	ld	a2, 0(t5)
+	SAVE_ABI
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	/*
-	 * the graph tracer (specifically, prepare_ftrace_return) needs these
-	 * arguments but for now the function tracer occupies the regs, so we
-	 * save them in temporary regs to recover later.
-	 */
-	addi	t0, s0, -8
-	mv	t1, a0
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	ld	t2, -16(s0)
-#endif
-#endif
+	addi	a0, ra, -FENTRY_RA_OFFSET
+	la	a1, function_trace_op
+	REG_L	a2, 0(a1)
+	REG_L	a1, ABI_SIZE_ON_STACK(sp)
+	mv	a3, sp
 
-	SAVE_ABI_STATE
 ftrace_call:
 	.global ftrace_call
-	/*
-	 * For the dynamic ftrace to work, here we should reserve at least
-	 * 8 bytes for a functional auipc-jalr pair.  The following call
-	 * serves this purpose.
-	 *
-	 * Calling ftrace_update_ftrace_func would overwrite the nops below.
-	 * Check ftrace_modify_all_code for details.
-	 */
 	call	ftrace_stub
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	RESTORE_GRAPH_ARGS
-	call	ftrace_graph_caller
+	addi	a0, sp, ABI_SIZE_ON_STACK
+	REG_L	a1, ABI_RA(sp)
+	addi	a1, a1, -FENTRY_RA_OFFSET
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	mv	a2, s0
 #endif
-
-	RESTORE_ABI_STATE
+ftrace_graph_call:
+	.global ftrace_graph_call
+	call	ftrace_stub
+#endif
+	RESTORE_ABI
 	ret
 ENDPROC(ftrace_caller)
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-	.macro SAVE_ALL
-	addi	sp, sp, -(PT_SIZE_ON_STACK+16)
-	sd	s0, (PT_SIZE_ON_STACK)(sp)
-	sd	ra, (PT_SIZE_ON_STACK+8)(sp)
-	addi	s0, sp, (PT_SIZE_ON_STACK+16)
-
-	sd x1,  PT_RA(sp)
-	sd x2,  PT_SP(sp)
-	sd x3,  PT_GP(sp)
-	sd x4,  PT_TP(sp)
-	sd x5,  PT_T0(sp)
-	sd x6,  PT_T1(sp)
-	sd x7,  PT_T2(sp)
-	sd x8,  PT_S0(sp)
-	sd x9,  PT_S1(sp)
-	sd x10, PT_A0(sp)
-	sd x11, PT_A1(sp)
-	sd x12, PT_A2(sp)
-	sd x13, PT_A3(sp)
-	sd x14, PT_A4(sp)
-	sd x15, PT_A5(sp)
-	sd x16, PT_A6(sp)
-	sd x17, PT_A7(sp)
-	sd x18, PT_S2(sp)
-	sd x19, PT_S3(sp)
-	sd x20, PT_S4(sp)
-	sd x21, PT_S5(sp)
-	sd x22, PT_S6(sp)
-	sd x23, PT_S7(sp)
-	sd x24, PT_S8(sp)
-	sd x25, PT_S9(sp)
-	sd x26, PT_S10(sp)
-	sd x27, PT_S11(sp)
-	sd x28, PT_T3(sp)
-	sd x29, PT_T4(sp)
-	sd x30, PT_T5(sp)
-	sd x31, PT_T6(sp)
-	.endm
-
-	.macro RESTORE_ALL
-	ld x1,  PT_RA(sp)
-	ld x2,  PT_SP(sp)
-	ld x3,  PT_GP(sp)
-	ld x4,  PT_TP(sp)
-	ld x5,  PT_T0(sp)
-	ld x6,  PT_T1(sp)
-	ld x7,  PT_T2(sp)
-	ld x8,  PT_S0(sp)
-	ld x9,  PT_S1(sp)
-	ld x10, PT_A0(sp)
-	ld x11, PT_A1(sp)
-	ld x12, PT_A2(sp)
-	ld x13, PT_A3(sp)
-	ld x14, PT_A4(sp)
-	ld x15, PT_A5(sp)
-	ld x16, PT_A6(sp)
-	ld x17, PT_A7(sp)
-	ld x18, PT_S2(sp)
-	ld x19, PT_S3(sp)
-	ld x20, PT_S4(sp)
-	ld x21, PT_S5(sp)
-	ld x22, PT_S6(sp)
-	ld x23, PT_S7(sp)
-	ld x24, PT_S8(sp)
-	ld x25, PT_S9(sp)
-	ld x26, PT_S10(sp)
-	ld x27, PT_S11(sp)
-	ld x28, PT_T3(sp)
-	ld x29, PT_T4(sp)
-	ld x30, PT_T5(sp)
-	ld x31, PT_T6(sp)
-
-	ld	s0, (PT_SIZE_ON_STACK)(sp)
-	ld	ra, (PT_SIZE_ON_STACK+8)(sp)
-	addi	sp, sp, (PT_SIZE_ON_STACK+16)
-	.endm
-
-	.macro RESTORE_GRAPH_REG_ARGS
-	ld	a0, PT_T0(sp)
-	ld	a1, PT_T1(sp)
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	ld	a2, PT_T2(sp)
-#endif
-	.endm
-
-/*
- * Most of the contents are the same as ftrace_caller.
- */
 ENTRY(ftrace_regs_caller)
-	/*
-	 * a3: the address of all registers in the stack
-	 */
-	ld	a1, -8(s0)
-	addi	a0, ra, -MCOUNT_INSN_SIZE
-	la	t5, function_trace_op
-	ld	a2, 0(t5)
-	addi	a3, sp, -(PT_SIZE_ON_STACK+16)
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	addi	t0, s0, -8
-	mv	t1, a0
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	ld	t2, -16(s0)
-#endif
-#endif
 	SAVE_ALL
 
+	addi	a0, ra, -FENTRY_RA_OFFSET
+	la	a1, function_trace_op
+	REG_L	a2, 0(a1)
+	REG_L	a1, PT_SIZE_ON_STACK(sp)
+	mv	a3, sp
+
 ftrace_regs_call:
 	.global ftrace_regs_call
 	call	ftrace_stub
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	RESTORE_GRAPH_REG_ARGS
-	call	ftrace_graph_caller
+	addi	a0, sp, PT_RA
+	REG_L	a1, PT_EPC(sp)
+	addi	a1, a1, -FENTRY_RA_OFFSET
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	mv	a2, s0
+#endif
+ftrace_graph_regs_call:
+	.global ftrace_graph_regs_call
+	call	ftrace_stub
 #endif
 
 	RESTORE_ALL
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index 3fe7a5296aa5..0b552873a577 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -20,7 +20,12 @@ struct patch_insn {
 };
 
 #ifdef CONFIG_MMU
-static void *patch_map(void *addr, int fixmap)
+/*
+ * The fix_to_virt(, idx) needs a const value (not a dynamic variable of
+ * reg-a0) or BUILD_BUG_ON failed with "idx >= __end_of_fixed_addresses".
+ * So use '__always_inline' and 'const unsigned int fixmap' here.
+ */
+static __always_inline void *patch_map(void *addr, const unsigned int fixmap)
 {
 	uintptr_t uintaddr = (uintptr_t) addr;
 	struct page *page;
@@ -37,7 +42,6 @@ static void *patch_map(void *addr, int fixmap)
 	return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
 					 (uintaddr & ~PAGE_MASK));
 }
-NOKPROBE_SYMBOL(patch_map);
 
 static void patch_unmap(int fixmap)
 {
diff --git a/arch/riscv/kernel/probes/Makefile b/arch/riscv/kernel/probes/Makefile
new file mode 100644
index 000000000000..7f0840dcc31b
--- /dev/null
+++ b/arch/riscv/kernel/probes/Makefile
@@ -0,0 +1,6 @@
+# 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/riscv/kernel/probes/decode-insn.c b/arch/riscv/kernel/probes/decode-insn.c
new file mode 100644
index 000000000000..0ed043acc882
--- /dev/null
+++ b/arch/riscv/kernel/probes/decode-insn.c
@@ -0,0 +1,48 @@
+// 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
+riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *api)
+{
+	probe_opcode_t insn = *addr;
+
+	/*
+	 * Reject instructions list:
+	 */
+	RISCV_INSN_REJECTED(system,		insn);
+	RISCV_INSN_REJECTED(fence,		insn);
+
+	/*
+	 * Simulate instructions list:
+	 * TODO: the REJECTED ones below need to be implemented
+	 */
+#ifdef CONFIG_RISCV_ISA_C
+	RISCV_INSN_REJECTED(c_j,		insn);
+	RISCV_INSN_REJECTED(c_jr,		insn);
+	RISCV_INSN_REJECTED(c_jal,		insn);
+	RISCV_INSN_REJECTED(c_jalr,		insn);
+	RISCV_INSN_REJECTED(c_beqz,		insn);
+	RISCV_INSN_REJECTED(c_bnez,		insn);
+	RISCV_INSN_REJECTED(c_ebreak,		insn);
+#endif
+
+	RISCV_INSN_REJECTED(auipc,		insn);
+	RISCV_INSN_REJECTED(branch,		insn);
+
+	RISCV_INSN_SET_SIMULATE(jal,		insn);
+	RISCV_INSN_SET_SIMULATE(jalr,		insn);
+
+	return INSN_GOOD;
+}
diff --git a/arch/riscv/kernel/probes/decode-insn.h b/arch/riscv/kernel/probes/decode-insn.h
new file mode 100644
index 000000000000..42269a7d676d
--- /dev/null
+++ b/arch/riscv/kernel/probes/decode-insn.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _RISCV_KERNEL_KPROBES_DECODE_INSN_H
+#define _RISCV_KERNEL_KPROBES_DECODE_INSN_H
+
+#include <asm/sections.h>
+#include <asm/kprobes.h>
+
+enum probe_insn {
+	INSN_REJECTED,
+	INSN_GOOD_NO_SLOT,
+	INSN_GOOD,
+};
+
+enum probe_insn __kprobes
+riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *asi);
+
+#endif /* _RISCV_KERNEL_KPROBES_DECODE_INSN_H */
diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c
new file mode 100644
index 000000000000..e6372490aa0b
--- /dev/null
+++ b/arch/riscv/kernel/probes/ftrace.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kprobes.h>
+
+/* 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 ftrace_regs *regs)
+{
+	struct kprobe *p;
+	struct kprobe_ctlblk *kcb;
+
+	p = get_kprobe((kprobe_opcode_t *)ip);
+	if (unlikely(!p) || kprobe_disabled(p))
+		return;
+
+	kcb = get_kprobe_ctlblk();
+	if (kprobe_running()) {
+		kprobes_inc_nmissed_count(p);
+	} else {
+		unsigned long orig_ip = instruction_pointer(&(regs->regs));
+
+		instruction_pointer_set(&(regs->regs), ip);
+
+		__this_cpu_write(current_kprobe, p);
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+		if (!p->pre_handler || !p->pre_handler(p, &(regs->regs))) {
+			/*
+			 * Emulate singlestep (and also recover regs->pc)
+			 * as if there is a nop
+			 */
+			instruction_pointer_set(&(regs->regs),
+				(unsigned long)p->addr + MCOUNT_INSN_SIZE);
+			if (unlikely(p->post_handler)) {
+				kcb->kprobe_status = KPROBE_HIT_SSDONE;
+				p->post_handler(p, &(regs->regs), 0);
+			}
+			instruction_pointer_set(&(regs->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/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c
new file mode 100644
index 000000000000..a2ec18662fee
--- /dev/null
+++ b/arch/riscv/kernel/probes/kprobes.c
@@ -0,0 +1,398 @@
+// 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 <asm/bug.h>
+#include <asm/patch.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 *);
+
+static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
+{
+	unsigned long offset = GET_INSN_LENGTH(p->opcode);
+
+	p->ainsn.api.restore = (unsigned long)p->addr + offset;
+
+	patch_text(p->ainsn.api.insn, p->opcode);
+	patch_text((void *)((unsigned long)(p->ainsn.api.insn) + offset),
+		   __BUG_INSN_32);
+}
+
+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,
+					(unsigned 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 = *p->addr;
+
+	/* decode instruction */
+	switch (riscv_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)
+{
+	if ((p->opcode & __INSN_LENGTH_MASK) == __INSN_LENGTH_32)
+		patch_text(p->addr, __BUG_INSN_32);
+	else
+		patch_text(p->addr, __BUG_INSN_16);
+}
+
+/* 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_status = regs->status;
+	regs->status &= ~SR_SPIE;
+}
+
+static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
+						struct pt_regs *regs)
+{
+	regs->status = kcb->saved_status;
+}
+
+static void __kprobes
+set_ss_context(struct kprobe_ctlblk *kcb, unsigned long addr, struct kprobe *p)
+{
+	unsigned long offset = GET_INSN_LENGTH(p->opcode);
+
+	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;
+}
+
+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);
+
+		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->epc = 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->epc = (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;
+}
+
+bool __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 true;
+		} 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 true;
+	}
+
+	/*
+	 * 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 false;
+}
+
+bool __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);
+
+		post_kprobe_handler(kcb, regs);
+		return true;
+	}
+	return false;
+}
+
+/*
+ * Provide a blacklist of symbols identifying ranges which cannot be kprobed.
+ * This blacklist is exposed to userspace via debugfs (kprobes/blacklist).
+ */
+int __init arch_populate_kprobe_blacklist(void)
+{
+	int ret;
+
+	ret = kprobe_add_area_blacklist((unsigned long)__irqentry_text_start,
+					(unsigned long)__irqentry_text_end);
+	return ret;
+}
+
+void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs)
+{
+	return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL);
+}
+
+void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
+				      struct pt_regs *regs)
+{
+	ri->ret_addr = (kprobe_opcode_t *)regs->ra;
+	ri->fp = NULL;
+	regs->ra = (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/riscv/kernel/probes/kprobes_trampoline.S b/arch/riscv/kernel/probes/kprobes_trampoline.S
new file mode 100644
index 000000000000..6e85d021e2a2
--- /dev/null
+++ b/arch/riscv/kernel/probes/kprobes_trampoline.S
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Author: Patrick Stählin <me@packi.ch>
+ */
+#include <linux/linkage.h>
+
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+
+	.text
+	.altmacro
+
+	.macro save_all_base_regs
+	REG_S x1,  PT_RA(sp)
+	REG_S x3,  PT_GP(sp)
+	REG_S x4,  PT_TP(sp)
+	REG_S x5,  PT_T0(sp)
+	REG_S x6,  PT_T1(sp)
+	REG_S x7,  PT_T2(sp)
+	REG_S x8,  PT_S0(sp)
+	REG_S x9,  PT_S1(sp)
+	REG_S x10, PT_A0(sp)
+	REG_S x11, PT_A1(sp)
+	REG_S x12, PT_A2(sp)
+	REG_S x13, PT_A3(sp)
+	REG_S x14, PT_A4(sp)
+	REG_S x15, PT_A5(sp)
+	REG_S x16, PT_A6(sp)
+	REG_S x17, PT_A7(sp)
+	REG_S x18, PT_S2(sp)
+	REG_S x19, PT_S3(sp)
+	REG_S x20, PT_S4(sp)
+	REG_S x21, PT_S5(sp)
+	REG_S x22, PT_S6(sp)
+	REG_S x23, PT_S7(sp)
+	REG_S x24, PT_S8(sp)
+	REG_S x25, PT_S9(sp)
+	REG_S x26, PT_S10(sp)
+	REG_S x27, PT_S11(sp)
+	REG_S x28, PT_T3(sp)
+	REG_S x29, PT_T4(sp)
+	REG_S x30, PT_T5(sp)
+	REG_S x31, PT_T6(sp)
+	.endm
+
+	.macro restore_all_base_regs
+	REG_L x3,  PT_GP(sp)
+	REG_L x4,  PT_TP(sp)
+	REG_L x5,  PT_T0(sp)
+	REG_L x6,  PT_T1(sp)
+	REG_L x7,  PT_T2(sp)
+	REG_L x8,  PT_S0(sp)
+	REG_L x9,  PT_S1(sp)
+	REG_L x10, PT_A0(sp)
+	REG_L x11, PT_A1(sp)
+	REG_L x12, PT_A2(sp)
+	REG_L x13, PT_A3(sp)
+	REG_L x14, PT_A4(sp)
+	REG_L x15, PT_A5(sp)
+	REG_L x16, PT_A6(sp)
+	REG_L x17, PT_A7(sp)
+	REG_L x18, PT_S2(sp)
+	REG_L x19, PT_S3(sp)
+	REG_L x20, PT_S4(sp)
+	REG_L x21, PT_S5(sp)
+	REG_L x22, PT_S6(sp)
+	REG_L x23, PT_S7(sp)
+	REG_L x24, PT_S8(sp)
+	REG_L x25, PT_S9(sp)
+	REG_L x26, PT_S10(sp)
+	REG_L x27, PT_S11(sp)
+	REG_L x28, PT_T3(sp)
+	REG_L x29, PT_T4(sp)
+	REG_L x30, PT_T5(sp)
+	REG_L x31, PT_T6(sp)
+	.endm
+
+ENTRY(kretprobe_trampoline)
+	addi sp, sp, -(PT_SIZE_ON_STACK)
+	save_all_base_regs
+
+	move a0, sp /* pt_regs */
+
+	call trampoline_probe_handler
+
+	/* use the result as the return-address */
+	move ra, a0
+
+	restore_all_base_regs
+	addi sp, sp, PT_SIZE_ON_STACK
+
+	ret
+ENDPROC(kretprobe_trampoline)
diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c
new file mode 100644
index 000000000000..2519ce26377d
--- /dev/null
+++ b/arch/riscv/kernel/probes/simulate-insn.c
@@ -0,0 +1,85 @@
+// 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 rv_insn_reg_get_val(struct pt_regs *regs, u32 index,
+				       unsigned long *ptr)
+{
+	if (index == 0)
+		*ptr = 0;
+	else if (index <= 31)
+		*ptr = *((unsigned long *)regs + index);
+	else
+		return false;
+
+	return true;
+}
+
+static inline bool rv_insn_reg_set_val(struct pt_regs *regs, u32 index,
+				       unsigned long val)
+{
+	if (index == 0)
+		return false;
+	else if (index <= 31)
+		*((unsigned long *)regs + index) = val;
+	else
+		return false;
+
+	return true;
+}
+
+bool __kprobes simulate_jal(u32 opcode, unsigned long addr, struct pt_regs *regs)
+{
+	/*
+	 *     31    30       21    20     19        12 11 7 6      0
+	 * imm [20] | imm[10:1] | imm[11] | imm[19:12] | rd | opcode
+	 *     1         10          1           8       5    JAL/J
+	 */
+	bool ret;
+	u32 imm;
+	u32 index = (opcode >> 7) & 0x1f;
+
+	ret = rv_insn_reg_set_val(regs, index, addr + 4);
+	if (!ret)
+		return ret;
+
+	imm  = ((opcode >> 21) & 0x3ff) << 1;
+	imm |= ((opcode >> 20) & 0x1)   << 11;
+	imm |= ((opcode >> 12) & 0xff)  << 12;
+	imm |= ((opcode >> 31) & 0x1)   << 20;
+
+	instruction_pointer_set(regs, addr + sign_extend32((imm), 20));
+
+	return ret;
+}
+
+bool __kprobes simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs)
+{
+	/*
+	 * 31          20 19 15 14 12 11 7 6      0
+	 *  offset[11:0] | rs1 | 010 | rd | opcode
+	 *      12         5      3    5    JALR/JR
+	 */
+	bool ret;
+	unsigned long base_addr;
+	u32 imm = (opcode >> 20) & 0xfff;
+	u32 rd_index = (opcode >> 7) & 0x1f;
+	u32 rs1_index = (opcode >> 15) & 0x1f;
+
+	ret = rv_insn_reg_set_val(regs, rd_index, addr + 4);
+	if (!ret)
+		return ret;
+
+	ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr);
+	if (!ret)
+		return ret;
+
+	instruction_pointer_set(regs, (base_addr + sign_extend32((imm), 11))&~1);
+
+	return ret;
+}
diff --git a/arch/riscv/kernel/probes/simulate-insn.h b/arch/riscv/kernel/probes/simulate-insn.h
new file mode 100644
index 000000000000..cb6ff7dccb92
--- /dev/null
+++ b/arch/riscv/kernel/probes/simulate-insn.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _RISCV_KERNEL_PROBES_SIMULATE_INSN_H
+#define _RISCV_KERNEL_PROBES_SIMULATE_INSN_H
+
+#define __RISCV_INSN_FUNCS(name, mask, val)				\
+static __always_inline bool riscv_insn_is_##name(probe_opcode_t code)	\
+{									\
+	BUILD_BUG_ON(~(mask) & (val));					\
+	return (code & (mask)) == (val);				\
+}									\
+bool simulate_##name(u32 opcode, unsigned long addr,			\
+		     struct pt_regs *regs)
+
+#define RISCV_INSN_REJECTED(name, code)					\
+	do {								\
+		if (riscv_insn_is_##name(code)) {			\
+			return INSN_REJECTED;				\
+		}							\
+	} while (0)
+
+__RISCV_INSN_FUNCS(system,	0x7f, 0x73);
+__RISCV_INSN_FUNCS(fence,	0x7f, 0x0f);
+
+#define RISCV_INSN_SET_SIMULATE(name, code)				\
+	do {								\
+		if (riscv_insn_is_##name(code)) {			\
+			api->handler = simulate_##name;			\
+			return INSN_GOOD_NO_SLOT;			\
+		}							\
+	} while (0)
+
+__RISCV_INSN_FUNCS(c_j,		0xe003, 0xa001);
+__RISCV_INSN_FUNCS(c_jr,	0xf007, 0x8002);
+__RISCV_INSN_FUNCS(c_jal,	0xe003, 0x2001);
+__RISCV_INSN_FUNCS(c_jalr,	0xf007, 0x9002);
+__RISCV_INSN_FUNCS(c_beqz,	0xe003, 0xc001);
+__RISCV_INSN_FUNCS(c_bnez,	0xe003, 0xe001);
+__RISCV_INSN_FUNCS(c_ebreak,	0xffff, 0x9002);
+
+__RISCV_INSN_FUNCS(auipc,	0x7f, 0x17);
+__RISCV_INSN_FUNCS(branch,	0x7f, 0x63);
+
+__RISCV_INSN_FUNCS(jal,		0x7f, 0x6f);
+__RISCV_INSN_FUNCS(jalr,	0x707f, 0x67);
+
+#endif /* _RISCV_KERNEL_PROBES_SIMULATE_INSN_H */
diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c
new file mode 100644
index 000000000000..7a057b5f0adc
--- /dev/null
+++ b/arch/riscv/kernel/probes/uprobes.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/highmem.h>
+#include <linux/ptrace.h>
+#include <linux/uprobes.h>
+
+#include "decode-insn.h"
+
+#define UPROBE_TRAP_NR	UINT_MAX
+
+bool is_swbp_insn(uprobe_opcode_t *insn)
+{
+#ifdef CONFIG_RISCV_ISA_C
+	return (*insn & 0xffff) == UPROBE_SWBP_INSN;
+#else
+	return *insn == UPROBE_SWBP_INSN;
+#endif
+}
+
+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 opcode;
+
+	opcode = *(probe_opcode_t *)(&auprobe->insn[0]);
+
+	auprobe->insn_size = GET_INSN_LENGTH(opcode);
+
+	switch (riscv_probe_decode_insn(&opcode, &auprobe->api)) {
+	case INSN_REJECTED:
+		return -EINVAL;
+
+	case INSN_GOOD_NO_SLOT:
+		auprobe->simulate = true;
+		break;
+
+	case INSN_GOOD:
+		auprobe->simulate = false;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	utask->autask.saved_cause = current->thread.bad_cause;
+	current->thread.bad_cause = UPROBE_TRAP_NR;
+
+	instruction_pointer_set(regs, utask->xol_vaddr);
+
+	regs->status &= ~SR_SPIE;
+
+	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.bad_cause != UPROBE_TRAP_NR);
+
+	instruction_pointer_set(regs, utask->vaddr + auprobe->insn_size);
+
+	regs->status |= SR_SPIE;
+
+	return 0;
+}
+
+bool arch_uprobe_xol_was_trapped(struct task_struct *t)
+{
+	if (t->thread.bad_cause != 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);
+
+	regs->status &= ~SR_SPIE;
+}
+
+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->sp <= ret->stack;
+	else
+		return regs->sp < ret->stack;
+}
+
+unsigned long
+arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr,
+				  struct pt_regs *regs)
+{
+	unsigned long ra;
+
+	ra = regs->ra;
+
+	regs->ra = trampoline_vaddr;
+
+	return ra;
+}
+
+int arch_uprobe_exception_notify(struct notifier_block *self,
+				 unsigned long val, void *data)
+{
+	return NOTIFY_DONE;
+}
+
+bool uprobe_breakpoint_handler(struct pt_regs *regs)
+{
+	if (uprobe_pre_sstep_notifier(regs))
+		return true;
+
+	return false;
+}
+
+bool uprobe_single_step_handler(struct pt_regs *regs)
+{
+	if (uprobe_post_sstep_notifier(regs))
+		return true;
+
+	return false;
+}
+
+void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
+			   void *src, unsigned long len)
+{
+	/* Initialize the slot */
+	void *kaddr = kmap_atomic(page);
+	void *dst = kaddr + (vaddr & ~PAGE_MASK);
+
+	memcpy(dst, src, len);
+
+	/* Add ebreak behind opcode to simulate singlestep */
+	if (vaddr) {
+		dst += GET_INSN_LENGTH(*(probe_opcode_t *)src);
+		*(uprobe_opcode_t *)dst = __BUG_INSN_32;
+	}
+
+	kunmap_atomic(kaddr);
+
+	/*
+	 * We probably need flush_icache_user_page() but it needs vma.
+	 * This should work on most of architectures by default. If
+	 * architecture needs to do something different it can define
+	 * its own version of the function.
+	 */
+	flush_dcache_page(page);
+}
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index dd5f985b1f40..19f4688f2f36 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -18,13 +18,14 @@
 #include <asm/unistd.h>
 #include <asm/processor.h>
 #include <asm/csr.h>
+#include <asm/stacktrace.h>
 #include <asm/string.h>
 #include <asm/switch_to.h>
 #include <asm/thread_info.h>
 
 register unsigned long gp_in_global __asm__("gp");
 
-#ifdef CONFIG_STACKPROTECTOR
+#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
 #include <linux/stackprotector.h>
 unsigned long __stack_chk_guard __read_mostly;
 EXPORT_SYMBOL(__stack_chk_guard);
@@ -39,11 +40,16 @@ void arch_cpu_idle(void)
 	raw_local_irq_enable();
 }
 
-void show_regs(struct pt_regs *regs)
+void __show_regs(struct pt_regs *regs)
 {
 	show_regs_print_info(KERN_DEFAULT);
 
-	pr_cont("epc: " REG_FMT " ra : " REG_FMT " sp : " REG_FMT "\n",
+	if (!user_mode(regs)) {
+		pr_cont("epc : %pS\n", (void *)regs->epc);
+		pr_cont(" ra : %pS\n", (void *)regs->ra);
+	}
+
+	pr_cont("epc : " REG_FMT " ra : " REG_FMT " sp : " REG_FMT "\n",
 		regs->epc, regs->ra, regs->sp);
 	pr_cont(" gp : " REG_FMT " tp : " REG_FMT " t0 : " REG_FMT "\n",
 		regs->gp, regs->tp, regs->t0);
@@ -69,6 +75,12 @@ void show_regs(struct pt_regs *regs)
 	pr_cont("status: " REG_FMT " badaddr: " REG_FMT " cause: " REG_FMT "\n",
 		regs->status, regs->badaddr, regs->cause);
 }
+void show_regs(struct pt_regs *regs)
+{
+	__show_regs(regs);
+	if (!user_mode(regs))
+		dump_backtrace(regs, NULL, KERN_DEFAULT);
+}
 
 void start_thread(struct pt_regs *regs, unsigned long pc,
 	unsigned long sp)
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 2d6395f5ad54..1a85305720e8 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -114,6 +114,105 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 	return &riscv_user_native_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(epc),
+	REG_OFFSET_NAME(ra),
+	REG_OFFSET_NAME(sp),
+	REG_OFFSET_NAME(gp),
+	REG_OFFSET_NAME(tp),
+	REG_OFFSET_NAME(t0),
+	REG_OFFSET_NAME(t1),
+	REG_OFFSET_NAME(t2),
+	REG_OFFSET_NAME(s0),
+	REG_OFFSET_NAME(s1),
+	REG_OFFSET_NAME(a0),
+	REG_OFFSET_NAME(a1),
+	REG_OFFSET_NAME(a2),
+	REG_OFFSET_NAME(a3),
+	REG_OFFSET_NAME(a4),
+	REG_OFFSET_NAME(a5),
+	REG_OFFSET_NAME(a6),
+	REG_OFFSET_NAME(a7),
+	REG_OFFSET_NAME(s2),
+	REG_OFFSET_NAME(s3),
+	REG_OFFSET_NAME(s4),
+	REG_OFFSET_NAME(s5),
+	REG_OFFSET_NAME(s6),
+	REG_OFFSET_NAME(s7),
+	REG_OFFSET_NAME(s8),
+	REG_OFFSET_NAME(s9),
+	REG_OFFSET_NAME(s10),
+	REG_OFFSET_NAME(s11),
+	REG_OFFSET_NAME(t3),
+	REG_OFFSET_NAME(t4),
+	REG_OFFSET_NAME(t5),
+	REG_OFFSET_NAME(t6),
+	REG_OFFSET_NAME(status),
+	REG_OFFSET_NAME(badaddr),
+	REG_OFFSET_NAME(cause),
+	REG_OFFSET_NAME(orig_a0),
+	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)
 {
 	clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
index 226ccce0f9e0..f4a7db3d309e 100644
--- a/arch/riscv/kernel/sbi.c
+++ b/arch/riscv/kernel/sbi.c
@@ -351,7 +351,7 @@ static int __sbi_rfence_v02(int fid, const unsigned long *hart_mask,
  * sbi_set_timer() - Program the timer for next timer event.
  * @stime_value: The value after which next timer event should fire.
  *
- * Return: None
+ * Return: None.
  */
 void sbi_set_timer(uint64_t stime_value)
 {
@@ -362,11 +362,11 @@ void sbi_set_timer(uint64_t stime_value)
  * sbi_send_ipi() - Send an IPI to any hart.
  * @hart_mask: A cpu mask containing all the target harts.
  *
- * Return: None
+ * Return: 0 on success, appropriate linux error code otherwise.
  */
-void sbi_send_ipi(const unsigned long *hart_mask)
+int sbi_send_ipi(const unsigned long *hart_mask)
 {
-	__sbi_send_ipi(hart_mask);
+	return __sbi_send_ipi(hart_mask);
 }
 EXPORT_SYMBOL(sbi_send_ipi);
 
@@ -374,12 +374,12 @@ EXPORT_SYMBOL(sbi_send_ipi);
  * sbi_remote_fence_i() - Execute FENCE.I instruction on given remote harts.
  * @hart_mask: A cpu mask containing all the target harts.
  *
- * Return: None
+ * Return: 0 on success, appropriate linux error code otherwise.
  */
-void sbi_remote_fence_i(const unsigned long *hart_mask)
+int sbi_remote_fence_i(const unsigned long *hart_mask)
 {
-	__sbi_rfence(SBI_EXT_RFENCE_REMOTE_FENCE_I,
-		     hart_mask, 0, 0, 0, 0);
+	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_FENCE_I,
+			    hart_mask, 0, 0, 0, 0);
 }
 EXPORT_SYMBOL(sbi_remote_fence_i);
 
@@ -390,14 +390,14 @@ EXPORT_SYMBOL(sbi_remote_fence_i);
  * @start: Start of the virtual address
  * @size: Total size of the virtual address range.
  *
- * Return: None
+ * Return: 0 on success, appropriate linux error code otherwise.
  */
-void sbi_remote_sfence_vma(const unsigned long *hart_mask,
+int sbi_remote_sfence_vma(const unsigned long *hart_mask,
 			   unsigned long start,
 			   unsigned long size)
 {
-	__sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
-		     hart_mask, start, size, 0, 0);
+	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
+			    hart_mask, start, size, 0, 0);
 }
 EXPORT_SYMBOL(sbi_remote_sfence_vma);
 
@@ -410,15 +410,15 @@ EXPORT_SYMBOL(sbi_remote_sfence_vma);
  * @size: Total size of the virtual address range.
  * @asid: The value of address space identifier (ASID).
  *
- * Return: None
+ * Return: 0 on success, appropriate linux error code otherwise.
  */
-void sbi_remote_sfence_vma_asid(const unsigned long *hart_mask,
+int sbi_remote_sfence_vma_asid(const unsigned long *hart_mask,
 				unsigned long start,
 				unsigned long size,
 				unsigned long asid)
 {
-	__sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
-		     hart_mask, start, size, asid, 0);
+	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
+			    hart_mask, start, size, asid, 0);
 }
 EXPORT_SYMBOL(sbi_remote_sfence_vma_asid);
 
@@ -560,7 +560,7 @@ static struct riscv_ipi_ops sbi_ipi_ops = {
 	.ipi_inject = sbi_send_cpumask_ipi
 };
 
-int __init sbi_init(void)
+void __init sbi_init(void)
 {
 	int ret;
 
@@ -600,6 +600,4 @@ int __init sbi_init(void)
 	}
 
 	riscv_set_ipi_ops(&sbi_ipi_ops);
-
-	return 0;
 }
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index c7c0655dd45b..e85bacff1b50 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -216,8 +216,15 @@ static void __init init_resources(void)
 static void __init parse_dtb(void)
 {
 	/* Early scan of device tree from init memory */
-	if (early_init_dt_scan(dtb_early_va))
+	if (early_init_dt_scan(dtb_early_va)) {
+		const char *name = of_flat_dt_get_machine_name();
+
+		if (name) {
+			pr_info("Machine model: %s\n", name);
+			dump_stack_set_arch_desc("%s (DT)", name);
+		}
 		return;
+	}
 
 	pr_err("No DTB passed to the kernel\n");
 #ifdef CONFIG_CMDLINE_FORCE
@@ -252,9 +259,9 @@ void __init setup_arch(char **cmdline_p)
 	else
 		pr_err("No DTB found in kernel mappings\n");
 #endif
+	misc_mem_init();
 
-	if (IS_ENABLED(CONFIG_RISCV_SBI))
-		sbi_init();
+	sbi_init();
 
 	if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
 		protect_kernel_text_data();
@@ -275,13 +282,19 @@ void __init setup_arch(char **cmdline_p)
 
 static int __init topology_init(void)
 {
-	int i;
+	int i, ret;
+
+	for_each_online_node(i)
+		register_one_node(i);
 
 	for_each_possible_cpu(i) {
 		struct cpu *cpu = &per_cpu(cpu_devices, i);
 
 		cpu->hotpluggable = cpu_has_hotplug(i);
-		register_cpu(cpu, i);
+		ret = register_cpu(cpu, i);
+		if (unlikely(ret))
+			pr_warn("Warning: %s: register_cpu %d failed (%d)\n",
+			       __func__, i, ret);
 	}
 
 	return 0;
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 469aef8ed922..65942b3748b4 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -309,6 +309,9 @@ static void do_signal(struct pt_regs *regs)
 asmlinkage __visible void do_notify_resume(struct pt_regs *regs,
 					   unsigned long thread_info_flags)
 {
+	if (thread_info_flags & _TIF_UPROBE)
+		uprobe_notify_resume(regs);
+
 	/* Handle pending signal delivery */
 	if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
 		do_signal(regs);
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 96167d55ed98..5e276c25646f 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -27,6 +27,7 @@
 #include <asm/cpu_ops.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
+#include <asm/numa.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
 #include <asm/sbi.h>
@@ -45,13 +46,18 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	int cpuid;
 	int ret;
+	unsigned int curr_cpuid;
+
+	curr_cpuid = smp_processor_id();
+	numa_store_cpu_info(curr_cpuid);
+	numa_add_cpu(curr_cpuid);
 
 	/* This covers non-smp usecase mandated by "nosmp" option */
 	if (max_cpus == 0)
 		return;
 
 	for_each_possible_cpu(cpuid) {
-		if (cpuid == smp_processor_id())
+		if (cpuid == curr_cpuid)
 			continue;
 		if (cpu_ops[cpuid]->cpu_prepare) {
 			ret = cpu_ops[cpuid]->cpu_prepare(cpuid);
@@ -59,6 +65,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 				continue;
 		}
 		set_cpu_present(cpuid, true);
+		numa_store_cpu_info(cpuid);
 	}
 }
 
@@ -79,6 +86,7 @@ void __init setup_smp(void)
 		if (hart == cpuid_to_hartid_map(0)) {
 			BUG_ON(found_boot_cpu);
 			found_boot_cpu = 1;
+			early_map_cpu_to_node(0, of_node_to_nid(dn));
 			continue;
 		}
 		if (cpuid >= NR_CPUS) {
@@ -88,6 +96,7 @@ void __init setup_smp(void)
 		}
 
 		cpuid_to_hartid_map(cpuid) = hart;
+		early_map_cpu_to_node(cpuid, of_node_to_nid(dn));
 		cpuid++;
 	}
 
@@ -153,6 +162,7 @@ asmlinkage __visible void smp_callin(void)
 	current->active_mm = mm;
 
 	notify_cpu_starting(curr_cpuid);
+	numa_add_cpu(curr_cpuid);
 	update_siblings_masks(curr_cpuid);
 	set_cpu_online(curr_cpuid, 1);
 
diff --git a/arch/riscv/kernel/soc.c b/arch/riscv/kernel/soc.c
index c7b0a73e382e..a0516172a33c 100644
--- a/arch/riscv/kernel/soc.c
+++ b/arch/riscv/kernel/soc.c
@@ -26,30 +26,3 @@ void __init soc_early_init(void)
 		}
 	}
 }
-
-static bool soc_builtin_dtb_match(unsigned long vendor_id,
-				unsigned long arch_id, unsigned long imp_id,
-				const struct soc_builtin_dtb *entry)
-{
-	return entry->vendor_id == vendor_id &&
-	       entry->arch_id == arch_id &&
-	       entry->imp_id == imp_id;
-}
-
-void * __init soc_lookup_builtin_dtb(void)
-{
-	unsigned long vendor_id, arch_id, imp_id;
-	const struct soc_builtin_dtb *s;
-
-	__asm__ ("csrr %0, mvendorid" : "=r"(vendor_id));
-	__asm__ ("csrr %0, marchid" : "=r"(arch_id));
-	__asm__ ("csrr %0, mimpid" : "=r"(imp_id));
-
-	for (s = (void *)&__soc_builtin_dtb_table_start;
-	     (void *)s < (void *)&__soc_builtin_dtb_table_end; s++) {
-		if (soc_builtin_dtb_match(vendor_id, arch_id, imp_id, s))
-			return s->dtb_func();
-	}
-
-	return NULL;
-}
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index df5d2da7c40b..3f893c9d9d85 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -53,9 +53,15 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 		/* Unwind stack frame */
 		frame = (struct stackframe *)fp - 1;
 		sp = fp;
-		fp = frame->fp;
-		pc = ftrace_graph_ret_addr(current, NULL, frame->ra,
-					   (unsigned long *)(fp - 8));
+		if (regs && (regs->epc == pc) && (frame->fp & 0x7)) {
+			fp = frame->ra;
+			pc = regs->ra;
+		} else {
+			fp = frame->fp;
+			pc = ftrace_graph_ret_addr(current, NULL, frame->ra,
+						   (unsigned long *)(fp - 8));
+		}
+
 	}
 }
 
@@ -100,10 +106,16 @@ static bool print_trace_address(void *arg, unsigned long pc)
 	return true;
 }
 
+void dump_backtrace(struct pt_regs *regs, struct task_struct *task,
+		    const char *loglvl)
+{
+	pr_cont("%sCall Trace:\n", loglvl);
+	walk_stackframe(task, regs, print_trace_address, (void *)loglvl);
+}
+
 void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl)
 {
-	pr_cont("Call Trace:\n");
-	walk_stackframe(task, NULL, print_trace_address, (void *)loglvl);
+	dump_backtrace(NULL, task, loglvl);
 }
 
 static bool save_wchan(void *arg, unsigned long pc)
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index ad14f4466d92..3ed2c23601a0 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -12,10 +12,12 @@
 #include <linux/signal.h>
 #include <linux/kdebug.h>
 #include <linux/uaccess.h>
+#include <linux/kprobes.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/irq.h>
 
+#include <asm/bug.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/csr.h>
@@ -66,7 +68,7 @@ void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr)
 			tsk->comm, task_pid_nr(tsk), signo, code, addr);
 		print_vma_addr(KERN_CONT " in ", instruction_pointer(regs));
 		pr_cont("\n");
-		show_regs(regs);
+		__show_regs(regs);
 	}
 
 	force_sig_fault(signo, code, (void __user *)addr);
@@ -75,6 +77,8 @@ void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr)
 static void do_trap_error(struct pt_regs *regs, int signo, int code,
 	unsigned long addr, const char *str)
 {
+	current->thread.bad_cause = regs->cause;
+
 	if (user_mode(regs)) {
 		do_trap(regs, signo, code, addr);
 	} else {
@@ -145,6 +149,22 @@ static inline unsigned long get_break_insn_length(unsigned long pc)
 
 asmlinkage __visible void do_trap_break(struct pt_regs *regs)
 {
+#ifdef CONFIG_KPROBES
+	if (kprobe_single_step_handler(regs))
+		return;
+
+	if (kprobe_breakpoint_handler(regs))
+		return;
+#endif
+#ifdef CONFIG_UPROBES
+	if (uprobe_single_step_handler(regs))
+		return;
+
+	if (uprobe_breakpoint_handler(regs))
+		return;
+#endif
+	current->thread.bad_cause = regs->cause;
+
 	if (user_mode(regs))
 		force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->epc);
 #ifdef CONFIG_KGDB
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 0cfd6da784f8..71a315e73cbe 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -32,9 +32,10 @@ CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
 # Disable -pg to prevent insert call site
 CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os
 
-# Disable gcov profiling for VDSO code
+# Disable profiling and instrumentation for VDSO code
 GCOV_PROFILE := n
 KCOV_INSTRUMENT := n
+KASAN_SANITIZE := n
 
 # Force dependency
 $(obj)/vdso.o: $(obj)/vdso.so