From e8aff71ca93026209dd0eab9b285e6808cd87d05 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Mon, 11 Mar 2024 22:23:46 +0800
Subject: objtool/LoongArch: Enable objtool to be built

Add the minimal changes to enable objtool build on LoongArch,
most of the functions are stubs to only fix the build errors
when make -C tools/objtool.

This is similar with commit e52ec98c5ab1 ("objtool/powerpc:
Enable objtool to be built on ppc").

Co-developed-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Jinyang He <hejinyang@loongson.cn>
Co-developed-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 tools/objtool/arch/loongarch/Build                 |  2 +
 tools/objtool/arch/loongarch/decode.c              | 71 ++++++++++++++++++++++
 .../objtool/arch/loongarch/include/arch/cfi_regs.h | 22 +++++++
 tools/objtool/arch/loongarch/include/arch/elf.h    | 30 +++++++++
 .../objtool/arch/loongarch/include/arch/special.h  | 33 ++++++++++
 tools/objtool/arch/loongarch/special.c             | 15 +++++
 6 files changed, 173 insertions(+)
 create mode 100644 tools/objtool/arch/loongarch/Build
 create mode 100644 tools/objtool/arch/loongarch/decode.c
 create mode 100644 tools/objtool/arch/loongarch/include/arch/cfi_regs.h
 create mode 100644 tools/objtool/arch/loongarch/include/arch/elf.h
 create mode 100644 tools/objtool/arch/loongarch/include/arch/special.h
 create mode 100644 tools/objtool/arch/loongarch/special.c

diff --git a/tools/objtool/arch/loongarch/Build b/tools/objtool/arch/loongarch/Build
new file mode 100644
index 00000000000000..d24d5636a5b843
--- /dev/null
+++ b/tools/objtool/arch/loongarch/Build
@@ -0,0 +1,2 @@
+objtool-y += decode.o
+objtool-y += special.o
diff --git a/tools/objtool/arch/loongarch/decode.c b/tools/objtool/arch/loongarch/decode.c
new file mode 100644
index 00000000000000..cc74ba4e0f5407
--- /dev/null
+++ b/tools/objtool/arch/loongarch/decode.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <string.h>
+#include <objtool/check.h>
+
+int arch_ftrace_match(char *name)
+{
+	return !strcmp(name, "_mcount");
+}
+
+unsigned long arch_jump_destination(struct instruction *insn)
+{
+	return insn->offset + (insn->immediate << 2);
+}
+
+unsigned long arch_dest_reloc_offset(int addend)
+{
+	return addend;
+}
+
+bool arch_pc_relative_reloc(struct reloc *reloc)
+{
+	return false;
+}
+
+bool arch_callee_saved_reg(unsigned char reg)
+{
+	switch (reg) {
+	case CFI_RA:
+	case CFI_FP:
+	case CFI_S0 ... CFI_S8:
+		return true;
+	default:
+		return false;
+	}
+}
+
+int arch_decode_hint_reg(u8 sp_reg, int *base)
+{
+	return 0;
+}
+
+int arch_decode_instruction(struct objtool_file *file, const struct section *sec,
+			    unsigned long offset, unsigned int maxlen,
+			    struct instruction *insn)
+{
+	return 0;
+}
+
+const char *arch_nop_insn(int len)
+{
+	return NULL;
+}
+
+const char *arch_ret_insn(int len)
+{
+	return NULL;
+}
+
+void arch_initial_func_cfi_state(struct cfi_init_state *state)
+{
+	int i;
+
+	for (i = 0; i < CFI_NUM_REGS; i++) {
+		state->regs[i].base = CFI_UNDEFINED;
+		state->regs[i].offset = 0;
+	}
+
+	/* initial CFA (call frame address) */
+	state->cfa.base = CFI_SP;
+	state->cfa.offset = 0;
+}
diff --git a/tools/objtool/arch/loongarch/include/arch/cfi_regs.h b/tools/objtool/arch/loongarch/include/arch/cfi_regs.h
new file mode 100644
index 00000000000000..d183cc8f43bf3a
--- /dev/null
+++ b/tools/objtool/arch/loongarch/include/arch/cfi_regs.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _OBJTOOL_ARCH_CFI_REGS_H
+#define _OBJTOOL_ARCH_CFI_REGS_H
+
+#define CFI_RA		1
+#define CFI_SP		3
+#define CFI_A0		4
+#define CFI_FP		22
+#define CFI_S0		23
+#define CFI_S1		24
+#define CFI_S2		25
+#define CFI_S3		26
+#define CFI_S4		27
+#define CFI_S5		28
+#define CFI_S6		29
+#define CFI_S7		30
+#define CFI_S8		31
+#define CFI_NUM_REGS	32
+
+#define CFI_BP		CFI_FP
+
+#endif /* _OBJTOOL_ARCH_CFI_REGS_H */
diff --git a/tools/objtool/arch/loongarch/include/arch/elf.h b/tools/objtool/arch/loongarch/include/arch/elf.h
new file mode 100644
index 00000000000000..9623d663220eff
--- /dev/null
+++ b/tools/objtool/arch/loongarch/include/arch/elf.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _OBJTOOL_ARCH_ELF_H
+#define _OBJTOOL_ARCH_ELF_H
+
+/*
+ * See the following link for more info about ELF Relocation types:
+ * https://loongson.github.io/LoongArch-Documentation/LoongArch-ELF-ABI-EN.html#_relocations
+ */
+#ifndef R_LARCH_NONE
+#define R_LARCH_NONE		0
+#endif
+#ifndef R_LARCH_32
+#define R_LARCH_32		1
+#endif
+#ifndef R_LARCH_64
+#define R_LARCH_64		2
+#endif
+#ifndef R_LARCH_32_PCREL
+#define R_LARCH_32_PCREL	99
+#endif
+
+#define R_NONE			R_LARCH_NONE
+#define R_ABS32			R_LARCH_32
+#define R_ABS64			R_LARCH_64
+#define R_DATA32		R_LARCH_32_PCREL
+#define R_DATA64		R_LARCH_32_PCREL
+#define R_TEXT32		R_LARCH_32_PCREL
+#define R_TEXT64		R_LARCH_32_PCREL
+
+#endif /* _OBJTOOL_ARCH_ELF_H */
diff --git a/tools/objtool/arch/loongarch/include/arch/special.h b/tools/objtool/arch/loongarch/include/arch/special.h
new file mode 100644
index 00000000000000..35fc979b550ab5
--- /dev/null
+++ b/tools/objtool/arch/loongarch/include/arch/special.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _OBJTOOL_ARCH_SPECIAL_H
+#define _OBJTOOL_ARCH_SPECIAL_H
+
+/*
+ * See more info about struct exception_table_entry
+ * in arch/loongarch/include/asm/extable.h
+ */
+#define EX_ENTRY_SIZE		12
+#define EX_ORIG_OFFSET		0
+#define EX_NEW_OFFSET		4
+
+/*
+ * See more info about struct jump_entry
+ * in include/linux/jump_label.h
+ */
+#define JUMP_ENTRY_SIZE		16
+#define JUMP_ORIG_OFFSET	0
+#define JUMP_NEW_OFFSET		4
+#define JUMP_KEY_OFFSET		8
+
+/*
+ * See more info about struct alt_instr
+ * in arch/loongarch/include/asm/alternative.h
+ */
+#define ALT_ENTRY_SIZE		12
+#define ALT_ORIG_OFFSET		0
+#define ALT_NEW_OFFSET		4
+#define ALT_FEATURE_OFFSET	8
+#define ALT_ORIG_LEN_OFFSET	10
+#define ALT_NEW_LEN_OFFSET	11
+
+#endif /* _OBJTOOL_ARCH_SPECIAL_H */
diff --git a/tools/objtool/arch/loongarch/special.c b/tools/objtool/arch/loongarch/special.c
new file mode 100644
index 00000000000000..9bba1e9318e0ba
--- /dev/null
+++ b/tools/objtool/arch/loongarch/special.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <objtool/special.h>
+
+bool arch_support_alt_relocation(struct special_alt *special_alt,
+				 struct instruction *insn,
+				 struct reloc *reloc)
+{
+	return false;
+}
+
+struct reloc *arch_find_switch_table(struct objtool_file *file,
+				     struct instruction *insn)
+{
+	return NULL;
+}
-- 
cgit 1.2.3-korg


From b2d23158e6c881326321c2351b92568be4e57030 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Mon, 11 Mar 2024 22:23:47 +0800
Subject: objtool/LoongArch: Implement instruction decoder

Only copy the minimal definitions of instruction opcodes and formats
in inst.h from arch/loongarch to tools/arch/loongarch, and also copy
the definition of sign_extend64() to tools/include/linux/bitops.h to
decode the following kinds of instructions:

(1) stack pointer related instructions
addi.d, ld.d, st.d, ldptr.d and stptr.d

(2) branch and jump related instructions
beq, bne, blt, bge, bltu, bgeu, beqz, bnez, bceqz, bcnez, b, bl and jirl

(3) other instructions
break, nop and ertn

See more info about instructions in LoongArch Reference Manual:
https://loongson.github.io/LoongArch-Documentation/LoongArch-Vol1-EN.html

Co-developed-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Jinyang He <hejinyang@loongson.cn>
Co-developed-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 tools/arch/loongarch/include/asm/inst.h | 161 +++++++++++++++++++
 tools/include/linux/bitops.h            |  11 ++
 tools/objtool/arch/loongarch/decode.c   | 273 +++++++++++++++++++++++++++++++-
 3 files changed, 443 insertions(+), 2 deletions(-)
 create mode 100644 tools/arch/loongarch/include/asm/inst.h

diff --git a/tools/arch/loongarch/include/asm/inst.h b/tools/arch/loongarch/include/asm/inst.h
new file mode 100644
index 00000000000000..c25b5853181dba
--- /dev/null
+++ b/tools/arch/loongarch/include/asm/inst.h
@@ -0,0 +1,161 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#ifndef _ASM_INST_H
+#define _ASM_INST_H
+
+#include <linux/bitops.h>
+
+#define LOONGARCH_INSN_NOP		0x03400000
+
+enum reg0i15_op {
+	break_op	= 0x54,
+};
+
+enum reg0i26_op {
+	b_op		= 0x14,
+	bl_op		= 0x15,
+};
+
+enum reg1i21_op {
+	beqz_op		= 0x10,
+	bnez_op		= 0x11,
+	bceqz_op	= 0x12, /* bits[9:8] = 0x00 */
+	bcnez_op	= 0x12, /* bits[9:8] = 0x01 */
+};
+
+enum reg2_op {
+	ertn_op		= 0x1920e,
+};
+
+enum reg2i12_op {
+	addid_op	= 0x0b,
+	andi_op		= 0x0d,
+	ldd_op		= 0xa3,
+	std_op		= 0xa7,
+};
+
+enum reg2i14_op {
+	ldptrd_op	= 0x26,
+	stptrd_op	= 0x27,
+};
+
+enum reg2i16_op {
+	jirl_op		= 0x13,
+	beq_op		= 0x16,
+	bne_op		= 0x17,
+	blt_op		= 0x18,
+	bge_op		= 0x19,
+	bltu_op		= 0x1a,
+	bgeu_op		= 0x1b,
+};
+
+struct reg0i15_format {
+	unsigned int immediate : 15;
+	unsigned int opcode : 17;
+};
+
+struct reg0i26_format {
+	unsigned int immediate_h : 10;
+	unsigned int immediate_l : 16;
+	unsigned int opcode : 6;
+};
+
+struct reg1i21_format {
+	unsigned int immediate_h  : 5;
+	unsigned int rj : 5;
+	unsigned int immediate_l : 16;
+	unsigned int opcode : 6;
+};
+
+struct reg2_format {
+	unsigned int rd : 5;
+	unsigned int rj : 5;
+	unsigned int opcode : 22;
+};
+
+struct reg2i12_format {
+	unsigned int rd : 5;
+	unsigned int rj : 5;
+	unsigned int immediate : 12;
+	unsigned int opcode : 10;
+};
+
+struct reg2i14_format {
+	unsigned int rd : 5;
+	unsigned int rj : 5;
+	unsigned int immediate : 14;
+	unsigned int opcode : 8;
+};
+
+struct reg2i16_format {
+	unsigned int rd : 5;
+	unsigned int rj : 5;
+	unsigned int immediate : 16;
+	unsigned int opcode : 6;
+};
+
+union loongarch_instruction {
+	unsigned int word;
+	struct reg0i15_format	reg0i15_format;
+	struct reg0i26_format	reg0i26_format;
+	struct reg1i21_format	reg1i21_format;
+	struct reg2_format	reg2_format;
+	struct reg2i12_format	reg2i12_format;
+	struct reg2i14_format	reg2i14_format;
+	struct reg2i16_format	reg2i16_format;
+};
+
+#define LOONGARCH_INSN_SIZE	sizeof(union loongarch_instruction)
+
+enum loongarch_gpr {
+	LOONGARCH_GPR_ZERO = 0,
+	LOONGARCH_GPR_RA = 1,
+	LOONGARCH_GPR_TP = 2,
+	LOONGARCH_GPR_SP = 3,
+	LOONGARCH_GPR_A0 = 4,	/* Reused as V0 for return value */
+	LOONGARCH_GPR_A1,	/* Reused as V1 for return value */
+	LOONGARCH_GPR_A2,
+	LOONGARCH_GPR_A3,
+	LOONGARCH_GPR_A4,
+	LOONGARCH_GPR_A5,
+	LOONGARCH_GPR_A6,
+	LOONGARCH_GPR_A7,
+	LOONGARCH_GPR_T0 = 12,
+	LOONGARCH_GPR_T1,
+	LOONGARCH_GPR_T2,
+	LOONGARCH_GPR_T3,
+	LOONGARCH_GPR_T4,
+	LOONGARCH_GPR_T5,
+	LOONGARCH_GPR_T6,
+	LOONGARCH_GPR_T7,
+	LOONGARCH_GPR_T8,
+	LOONGARCH_GPR_FP = 22,
+	LOONGARCH_GPR_S0 = 23,
+	LOONGARCH_GPR_S1,
+	LOONGARCH_GPR_S2,
+	LOONGARCH_GPR_S3,
+	LOONGARCH_GPR_S4,
+	LOONGARCH_GPR_S5,
+	LOONGARCH_GPR_S6,
+	LOONGARCH_GPR_S7,
+	LOONGARCH_GPR_S8,
+	LOONGARCH_GPR_MAX
+};
+
+#define DEF_EMIT_REG2I16_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rj,			\
+			       enum loongarch_gpr rd,			\
+			       int offset)				\
+{									\
+	insn->reg2i16_format.opcode = OP;				\
+	insn->reg2i16_format.immediate = offset;			\
+	insn->reg2i16_format.rj = rj;					\
+	insn->reg2i16_format.rd = rd;					\
+}
+
+DEF_EMIT_REG2I16_FORMAT(jirl, jirl_op)
+
+#endif /* _ASM_INST_H */
diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
index f18683b95ea673..7319f6ced10860 100644
--- a/tools/include/linux/bitops.h
+++ b/tools/include/linux/bitops.h
@@ -87,4 +87,15 @@ static inline __u32 rol32(__u32 word, unsigned int shift)
 	return (word << shift) | (word >> ((-shift) & 31));
 }
 
+/**
+ * sign_extend64 - sign extend a 64-bit value using specified bit as sign-bit
+ * @value: value to sign extend
+ * @index: 0 based bit index (0<=index<64) to sign bit
+ */
+static __always_inline __s64 sign_extend64(__u64 value, int index)
+{
+	__u8 shift = 63 - index;
+	return (__s64)(value << shift) >> shift;
+}
+
 #endif
diff --git a/tools/objtool/arch/loongarch/decode.c b/tools/objtool/arch/loongarch/decode.c
index cc74ba4e0f5407..ff0b53144d1267 100644
--- a/tools/objtool/arch/loongarch/decode.c
+++ b/tools/objtool/arch/loongarch/decode.c
@@ -1,6 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 #include <string.h>
 #include <objtool/check.h>
+#include <objtool/warn.h>
+#include <asm/inst.h>
+
+#ifndef EM_LOONGARCH
+#define EM_LOONGARCH	258
+#endif
 
 int arch_ftrace_match(char *name)
 {
@@ -39,21 +45,284 @@ int arch_decode_hint_reg(u8 sp_reg, int *base)
 	return 0;
 }
 
+static bool is_loongarch(const struct elf *elf)
+{
+	if (elf->ehdr.e_machine == EM_LOONGARCH)
+		return true;
+
+	WARN("unexpected ELF machine type %d", elf->ehdr.e_machine);
+	return false;
+}
+
+#define ADD_OP(op) \
+	if (!(op = calloc(1, sizeof(*op)))) \
+		return -1; \
+	else for (*ops_list = op, ops_list = &op->next; op; op = NULL)
+
+static bool decode_insn_reg0i26_fomat(union loongarch_instruction inst,
+				      struct instruction *insn)
+{
+	switch (inst.reg0i26_format.opcode) {
+	case b_op:
+		insn->type = INSN_JUMP_UNCONDITIONAL;
+		insn->immediate = sign_extend64(inst.reg0i26_format.immediate_h << 16 |
+						inst.reg0i26_format.immediate_l, 25);
+		break;
+	case bl_op:
+		insn->type = INSN_CALL;
+		insn->immediate = sign_extend64(inst.reg0i26_format.immediate_h << 16 |
+						inst.reg0i26_format.immediate_l, 25);
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+static bool decode_insn_reg1i21_fomat(union loongarch_instruction inst,
+				      struct instruction *insn)
+{
+	switch (inst.reg1i21_format.opcode) {
+	case beqz_op:
+	case bnez_op:
+	case bceqz_op:
+		insn->type = INSN_JUMP_CONDITIONAL;
+		insn->immediate = sign_extend64(inst.reg1i21_format.immediate_h << 16 |
+						inst.reg1i21_format.immediate_l, 20);
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+static bool decode_insn_reg2i12_fomat(union loongarch_instruction inst,
+				      struct instruction *insn,
+				      struct stack_op **ops_list,
+				      struct stack_op *op)
+{
+	switch (inst.reg2i12_format.opcode) {
+	case addid_op:
+		if ((inst.reg2i12_format.rd == CFI_SP) || (inst.reg2i12_format.rj == CFI_SP)) {
+			/* addi.d sp,sp,si12 or addi.d fp,sp,si12 */
+			insn->immediate = sign_extend64(inst.reg2i12_format.immediate, 11);
+			ADD_OP(op) {
+				op->src.type = OP_SRC_ADD;
+				op->src.reg = inst.reg2i12_format.rj;
+				op->src.offset = insn->immediate;
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = inst.reg2i12_format.rd;
+			}
+		}
+		break;
+	case ldd_op:
+		if (inst.reg2i12_format.rj == CFI_SP) {
+			/* ld.d rd,sp,si12 */
+			insn->immediate = sign_extend64(inst.reg2i12_format.immediate, 11);
+			ADD_OP(op) {
+				op->src.type = OP_SRC_REG_INDIRECT;
+				op->src.reg = CFI_SP;
+				op->src.offset = insn->immediate;
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = inst.reg2i12_format.rd;
+			}
+		}
+		break;
+	case std_op:
+		if (inst.reg2i12_format.rj == CFI_SP) {
+			/* st.d rd,sp,si12 */
+			insn->immediate = sign_extend64(inst.reg2i12_format.immediate, 11);
+			ADD_OP(op) {
+				op->src.type = OP_SRC_REG;
+				op->src.reg = inst.reg2i12_format.rd;
+				op->dest.type = OP_DEST_REG_INDIRECT;
+				op->dest.reg = CFI_SP;
+				op->dest.offset = insn->immediate;
+			}
+		}
+		break;
+	case andi_op:
+		if (inst.reg2i12_format.rd == 0 &&
+		    inst.reg2i12_format.rj == 0 &&
+		    inst.reg2i12_format.immediate == 0)
+			/* andi r0,r0,0 */
+			insn->type = INSN_NOP;
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+static bool decode_insn_reg2i14_fomat(union loongarch_instruction inst,
+				      struct instruction *insn,
+				      struct stack_op **ops_list,
+				      struct stack_op *op)
+{
+	switch (inst.reg2i14_format.opcode) {
+	case ldptrd_op:
+		if (inst.reg2i14_format.rj == CFI_SP) {
+			/* ldptr.d rd,sp,si14 */
+			insn->immediate = sign_extend64(inst.reg2i14_format.immediate, 13);
+			ADD_OP(op) {
+				op->src.type = OP_SRC_REG_INDIRECT;
+				op->src.reg = CFI_SP;
+				op->src.offset = insn->immediate;
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = inst.reg2i14_format.rd;
+			}
+		}
+		break;
+	case stptrd_op:
+		if (inst.reg2i14_format.rj == CFI_SP) {
+			/* stptr.d ra,sp,0 */
+			if (inst.reg2i14_format.rd == LOONGARCH_GPR_RA &&
+			    inst.reg2i14_format.immediate == 0)
+				break;
+
+			/* stptr.d rd,sp,si14 */
+			insn->immediate = sign_extend64(inst.reg2i14_format.immediate, 13);
+			ADD_OP(op) {
+				op->src.type = OP_SRC_REG;
+				op->src.reg = inst.reg2i14_format.rd;
+				op->dest.type = OP_DEST_REG_INDIRECT;
+				op->dest.reg = CFI_SP;
+				op->dest.offset = insn->immediate;
+			}
+		}
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+static bool decode_insn_reg2i16_fomat(union loongarch_instruction inst,
+				      struct instruction *insn)
+{
+	switch (inst.reg2i16_format.opcode) {
+	case jirl_op:
+		if (inst.reg2i16_format.rd == 0 &&
+		    inst.reg2i16_format.rj == CFI_RA &&
+		    inst.reg2i16_format.immediate == 0) {
+			/* jirl r0,ra,0 */
+			insn->type = INSN_RETURN;
+		} else if (inst.reg2i16_format.rd == CFI_RA) {
+			/* jirl ra,rj,offs16 */
+			insn->type = INSN_CALL_DYNAMIC;
+		} else if (inst.reg2i16_format.rd == CFI_A0 &&
+			   inst.reg2i16_format.immediate == 0) {
+			/*
+			 * jirl a0,t0,0
+			 * this is a special case in loongarch_suspend_enter,
+			 * just treat it as a call instruction.
+			 */
+			insn->type = INSN_CALL_DYNAMIC;
+		} else if (inst.reg2i16_format.rd == 0 &&
+			   inst.reg2i16_format.immediate == 0) {
+			/* jirl r0,rj,0 */
+			insn->type = INSN_JUMP_DYNAMIC;
+		} else if (inst.reg2i16_format.rd == 0 &&
+			   inst.reg2i16_format.immediate != 0) {
+			/*
+			 * jirl r0,t0,12
+			 * this is a rare case in JUMP_VIRT_ADDR,
+			 * just ignore it due to it is harmless for tracing.
+			 */
+			break;
+		} else {
+			/* jirl rd,rj,offs16 */
+			insn->type = INSN_JUMP_UNCONDITIONAL;
+			insn->immediate = sign_extend64(inst.reg2i16_format.immediate, 15);
+		}
+		break;
+	case beq_op:
+	case bne_op:
+	case blt_op:
+	case bge_op:
+	case bltu_op:
+	case bgeu_op:
+		insn->type = INSN_JUMP_CONDITIONAL;
+		insn->immediate = sign_extend64(inst.reg2i16_format.immediate, 15);
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
 int arch_decode_instruction(struct objtool_file *file, const struct section *sec,
 			    unsigned long offset, unsigned int maxlen,
 			    struct instruction *insn)
 {
+	struct stack_op **ops_list = &insn->stack_ops;
+	const struct elf *elf = file->elf;
+	struct stack_op *op = NULL;
+	union loongarch_instruction inst;
+
+	if (!is_loongarch(elf))
+		return -1;
+
+	if (maxlen < LOONGARCH_INSN_SIZE)
+		return 0;
+
+	insn->len = LOONGARCH_INSN_SIZE;
+	insn->type = INSN_OTHER;
+	insn->immediate = 0;
+
+	inst = *(union loongarch_instruction *)(sec->data->d_buf + offset);
+
+	if (decode_insn_reg0i26_fomat(inst, insn))
+		return 0;
+	if (decode_insn_reg1i21_fomat(inst, insn))
+		return 0;
+	if (decode_insn_reg2i12_fomat(inst, insn, ops_list, op))
+		return 0;
+	if (decode_insn_reg2i14_fomat(inst, insn, ops_list, op))
+		return 0;
+	if (decode_insn_reg2i16_fomat(inst, insn))
+		return 0;
+
+	if (inst.word == 0)
+		insn->type = INSN_NOP;
+	else if (inst.reg0i15_format.opcode == break_op) {
+		/* break */
+		insn->type = INSN_BUG;
+	} else if (inst.reg2_format.opcode == ertn_op) {
+		/* ertn */
+		insn->type = INSN_RETURN;
+	}
+
 	return 0;
 }
 
 const char *arch_nop_insn(int len)
 {
-	return NULL;
+	static u32 nop;
+
+	if (len != LOONGARCH_INSN_SIZE)
+		WARN("invalid NOP size: %d\n", len);
+
+	nop = LOONGARCH_INSN_NOP;
+
+	return (const char *)&nop;
 }
 
 const char *arch_ret_insn(int len)
 {
-	return NULL;
+	static u32 ret;
+
+	if (len != LOONGARCH_INSN_SIZE)
+		WARN("invalid RET size: %d\n", len);
+
+	emit_jirl((union loongarch_instruction *)&ret, LOONGARCH_GPR_RA, LOONGARCH_GPR_ZERO, 0);
+
+	return (const char *)&ret;
 }
 
 void arch_initial_func_cfi_state(struct cfi_init_state *state)
-- 
cgit 1.2.3-korg


From b8e85e6f3a09fc56b0ff574887798962ef8a8f80 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Mon, 11 Mar 2024 22:23:47 +0800
Subject: objtool/x86: Separate arch-specific and generic parts

Move init_orc_entry(), write_orc_entry(), reg_name(), orc_type_name()
and print_reg() from generic orc_gen.c and orc_dump.c to arch-specific
orc.c, then introduce a new function orc_print_dump() to print info.

This is preparation for later patch, no functionality change.

Co-developed-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Jinyang He <hejinyang@loongson.cn>
Co-developed-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 tools/objtool/arch/x86/Build        |   1 +
 tools/objtool/arch/x86/orc.c        | 188 ++++++++++++++++++++++++++++++++++++
 tools/objtool/include/objtool/orc.h |  14 +++
 tools/objtool/orc_dump.c            |  69 +------------
 tools/objtool/orc_gen.c             | 113 +---------------------
 5 files changed, 206 insertions(+), 179 deletions(-)
 create mode 100644 tools/objtool/arch/x86/orc.c
 create mode 100644 tools/objtool/include/objtool/orc.h

diff --git a/tools/objtool/arch/x86/Build b/tools/objtool/arch/x86/Build
index 9f7869b5c5e0ca..3dedb2fd8f3a0c 100644
--- a/tools/objtool/arch/x86/Build
+++ b/tools/objtool/arch/x86/Build
@@ -1,5 +1,6 @@
 objtool-y += special.o
 objtool-y += decode.o
+objtool-y += orc.o
 
 inat_tables_script = ../arch/x86/tools/gen-insn-attr-x86.awk
 inat_tables_maps = ../arch/x86/lib/x86-opcode-map.txt
diff --git a/tools/objtool/arch/x86/orc.c b/tools/objtool/arch/x86/orc.c
new file mode 100644
index 00000000000000..b6cd943e87f936
--- /dev/null
+++ b/tools/objtool/arch/x86/orc.c
@@ -0,0 +1,188 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/objtool_types.h>
+#include <asm/orc_types.h>
+
+#include <objtool/check.h>
+#include <objtool/orc.h>
+#include <objtool/warn.h>
+#include <objtool/endianness.h>
+
+int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, struct instruction *insn)
+{
+	struct cfi_reg *bp = &cfi->regs[CFI_BP];
+
+	memset(orc, 0, sizeof(*orc));
+
+	if (!cfi) {
+		/*
+		 * This is usually either unreachable nops/traps (which don't
+		 * trigger unreachable instruction warnings), or
+		 * STACK_FRAME_NON_STANDARD functions.
+		 */
+		orc->type = ORC_TYPE_UNDEFINED;
+		return 0;
+	}
+
+	switch (cfi->type) {
+	case UNWIND_HINT_TYPE_UNDEFINED:
+		orc->type = ORC_TYPE_UNDEFINED;
+		return 0;
+	case UNWIND_HINT_TYPE_END_OF_STACK:
+		orc->type = ORC_TYPE_END_OF_STACK;
+		return 0;
+	case UNWIND_HINT_TYPE_CALL:
+		orc->type = ORC_TYPE_CALL;
+		break;
+	case UNWIND_HINT_TYPE_REGS:
+		orc->type = ORC_TYPE_REGS;
+		break;
+	case UNWIND_HINT_TYPE_REGS_PARTIAL:
+		orc->type = ORC_TYPE_REGS_PARTIAL;
+		break;
+	default:
+		WARN_INSN(insn, "unknown unwind hint type %d", cfi->type);
+		return -1;
+	}
+
+	orc->signal = cfi->signal;
+
+	switch (cfi->cfa.base) {
+	case CFI_SP:
+		orc->sp_reg = ORC_REG_SP;
+		break;
+	case CFI_SP_INDIRECT:
+		orc->sp_reg = ORC_REG_SP_INDIRECT;
+		break;
+	case CFI_BP:
+		orc->sp_reg = ORC_REG_BP;
+		break;
+	case CFI_BP_INDIRECT:
+		orc->sp_reg = ORC_REG_BP_INDIRECT;
+		break;
+	case CFI_R10:
+		orc->sp_reg = ORC_REG_R10;
+		break;
+	case CFI_R13:
+		orc->sp_reg = ORC_REG_R13;
+		break;
+	case CFI_DI:
+		orc->sp_reg = ORC_REG_DI;
+		break;
+	case CFI_DX:
+		orc->sp_reg = ORC_REG_DX;
+		break;
+	default:
+		WARN_INSN(insn, "unknown CFA base reg %d", cfi->cfa.base);
+		return -1;
+	}
+
+	switch (bp->base) {
+	case CFI_UNDEFINED:
+		orc->bp_reg = ORC_REG_UNDEFINED;
+		break;
+	case CFI_CFA:
+		orc->bp_reg = ORC_REG_PREV_SP;
+		break;
+	case CFI_BP:
+		orc->bp_reg = ORC_REG_BP;
+		break;
+	default:
+		WARN_INSN(insn, "unknown BP base reg %d", bp->base);
+		return -1;
+	}
+
+	orc->sp_offset = cfi->cfa.offset;
+	orc->bp_offset = bp->offset;
+
+	return 0;
+}
+
+int write_orc_entry(struct elf *elf, struct section *orc_sec,
+		    struct section *ip_sec, unsigned int idx,
+		    struct section *insn_sec, unsigned long insn_off,
+		    struct orc_entry *o)
+{
+	struct orc_entry *orc;
+
+	/* populate ORC data */
+	orc = (struct orc_entry *)orc_sec->data->d_buf + idx;
+	memcpy(orc, o, sizeof(*orc));
+	orc->sp_offset = bswap_if_needed(elf, orc->sp_offset);
+	orc->bp_offset = bswap_if_needed(elf, orc->bp_offset);
+
+	/* populate reloc for ip */
+	if (!elf_init_reloc_text_sym(elf, ip_sec, idx * sizeof(int), idx,
+				     insn_sec, insn_off))
+		return -1;
+
+	return 0;
+}
+
+static const char *reg_name(unsigned int reg)
+{
+	switch (reg) {
+	case ORC_REG_PREV_SP:
+		return "prevsp";
+	case ORC_REG_DX:
+		return "dx";
+	case ORC_REG_DI:
+		return "di";
+	case ORC_REG_BP:
+		return "bp";
+	case ORC_REG_SP:
+		return "sp";
+	case ORC_REG_R10:
+		return "r10";
+	case ORC_REG_R13:
+		return "r13";
+	case ORC_REG_BP_INDIRECT:
+		return "bp(ind)";
+	case ORC_REG_SP_INDIRECT:
+		return "sp(ind)";
+	default:
+		return "?";
+	}
+}
+
+static const char *orc_type_name(unsigned int type)
+{
+	switch (type) {
+	case ORC_TYPE_UNDEFINED:
+		return "(und)";
+	case ORC_TYPE_END_OF_STACK:
+		return "end";
+	case ORC_TYPE_CALL:
+		return "call";
+	case ORC_TYPE_REGS:
+		return "regs";
+	case ORC_TYPE_REGS_PARTIAL:
+		return "regs (partial)";
+	default:
+		return "?";
+	}
+}
+
+static void print_reg(unsigned int reg, int offset)
+{
+	if (reg == ORC_REG_BP_INDIRECT)
+		printf("(bp%+d)", offset);
+	else if (reg == ORC_REG_SP_INDIRECT)
+		printf("(sp)%+d", offset);
+	else if (reg == ORC_REG_UNDEFINED)
+		printf("(und)");
+	else
+		printf("%s%+d", reg_name(reg), offset);
+}
+
+void orc_print_dump(struct elf *dummy_elf, struct orc_entry *orc, int i)
+{
+	printf("type:%s", orc_type_name(orc[i].type));
+
+	printf(" sp:");
+	print_reg(orc[i].sp_reg, bswap_if_needed(dummy_elf, orc[i].sp_offset));
+
+	printf(" bp:");
+	print_reg(orc[i].bp_reg, bswap_if_needed(dummy_elf, orc[i].bp_offset));
+
+	printf(" signal:%d\n", orc[i].signal);
+}
diff --git a/tools/objtool/include/objtool/orc.h b/tools/objtool/include/objtool/orc.h
new file mode 100644
index 00000000000000..15a32def1071d0
--- /dev/null
+++ b/tools/objtool/include/objtool/orc.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _OBJTOOL_ORC_H
+#define _OBJTOOL_ORC_H
+
+#include <objtool/check.h>
+
+int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, struct instruction *insn);
+void orc_print_dump(struct elf *dummy_elf, struct orc_entry *orc, int i);
+int write_orc_entry(struct elf *elf, struct section *orc_sec,
+		    struct section *ip_sec, unsigned int idx,
+		    struct section *insn_sec, unsigned long insn_off,
+		    struct orc_entry *o);
+
+#endif /* _OBJTOOL_ORC_H */
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index 0e183bb1c72051..a62247efb64f2e 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -6,65 +6,10 @@
 #include <unistd.h>
 #include <asm/orc_types.h>
 #include <objtool/objtool.h>
+#include <objtool/orc.h>
 #include <objtool/warn.h>
 #include <objtool/endianness.h>
 
-static const char *reg_name(unsigned int reg)
-{
-	switch (reg) {
-	case ORC_REG_PREV_SP:
-		return "prevsp";
-	case ORC_REG_DX:
-		return "dx";
-	case ORC_REG_DI:
-		return "di";
-	case ORC_REG_BP:
-		return "bp";
-	case ORC_REG_SP:
-		return "sp";
-	case ORC_REG_R10:
-		return "r10";
-	case ORC_REG_R13:
-		return "r13";
-	case ORC_REG_BP_INDIRECT:
-		return "bp(ind)";
-	case ORC_REG_SP_INDIRECT:
-		return "sp(ind)";
-	default:
-		return "?";
-	}
-}
-
-static const char *orc_type_name(unsigned int type)
-{
-	switch (type) {
-	case ORC_TYPE_UNDEFINED:
-		return "(und)";
-	case ORC_TYPE_END_OF_STACK:
-		return "end";
-	case ORC_TYPE_CALL:
-		return "call";
-	case ORC_TYPE_REGS:
-		return "regs";
-	case ORC_TYPE_REGS_PARTIAL:
-		return "regs (partial)";
-	default:
-		return "?";
-	}
-}
-
-static void print_reg(unsigned int reg, int offset)
-{
-	if (reg == ORC_REG_BP_INDIRECT)
-		printf("(bp%+d)", offset);
-	else if (reg == ORC_REG_SP_INDIRECT)
-		printf("(sp)%+d", offset);
-	else if (reg == ORC_REG_UNDEFINED)
-		printf("(und)");
-	else
-		printf("%s%+d", reg_name(reg), offset);
-}
-
 int orc_dump(const char *_objname)
 {
 	int fd, nr_entries, i, *orc_ip = NULL, orc_size = 0;
@@ -205,17 +150,7 @@ int orc_dump(const char *_objname)
 			printf("%llx:", (unsigned long long)(orc_ip_addr + (i * sizeof(int)) + orc_ip[i]));
 		}
 
-		printf("type:%s", orc_type_name(orc[i].type));
-
-		printf(" sp:");
-
-		print_reg(orc[i].sp_reg, bswap_if_needed(&dummy_elf, orc[i].sp_offset));
-
-		printf(" bp:");
-
-		print_reg(orc[i].bp_reg, bswap_if_needed(&dummy_elf, orc[i].bp_offset));
-
-		printf(" signal:%d\n", orc[i].signal);
+		orc_print_dump(&dummy_elf, orc, i);
 	}
 
 	elf_end(elf);
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index bae34390886710..922e6aac7cea7c 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -10,121 +10,10 @@
 #include <asm/orc_types.h>
 
 #include <objtool/check.h>
+#include <objtool/orc.h>
 #include <objtool/warn.h>
 #include <objtool/endianness.h>
 
-static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi,
-			  struct instruction *insn)
-{
-	struct cfi_reg *bp = &cfi->regs[CFI_BP];
-
-	memset(orc, 0, sizeof(*orc));
-
-	if (!cfi) {
-		/*
-		 * This is usually either unreachable nops/traps (which don't
-		 * trigger unreachable instruction warnings), or
-		 * STACK_FRAME_NON_STANDARD functions.
-		 */
-		orc->type = ORC_TYPE_UNDEFINED;
-		return 0;
-	}
-
-	switch (cfi->type) {
-	case UNWIND_HINT_TYPE_UNDEFINED:
-		orc->type = ORC_TYPE_UNDEFINED;
-		return 0;
-	case UNWIND_HINT_TYPE_END_OF_STACK:
-		orc->type = ORC_TYPE_END_OF_STACK;
-		return 0;
-	case UNWIND_HINT_TYPE_CALL:
-		orc->type = ORC_TYPE_CALL;
-		break;
-	case UNWIND_HINT_TYPE_REGS:
-		orc->type = ORC_TYPE_REGS;
-		break;
-	case UNWIND_HINT_TYPE_REGS_PARTIAL:
-		orc->type = ORC_TYPE_REGS_PARTIAL;
-		break;
-	default:
-		WARN_INSN(insn, "unknown unwind hint type %d", cfi->type);
-		return -1;
-	}
-
-	orc->signal = cfi->signal;
-
-	switch (cfi->cfa.base) {
-	case CFI_SP:
-		orc->sp_reg = ORC_REG_SP;
-		break;
-	case CFI_SP_INDIRECT:
-		orc->sp_reg = ORC_REG_SP_INDIRECT;
-		break;
-	case CFI_BP:
-		orc->sp_reg = ORC_REG_BP;
-		break;
-	case CFI_BP_INDIRECT:
-		orc->sp_reg = ORC_REG_BP_INDIRECT;
-		break;
-	case CFI_R10:
-		orc->sp_reg = ORC_REG_R10;
-		break;
-	case CFI_R13:
-		orc->sp_reg = ORC_REG_R13;
-		break;
-	case CFI_DI:
-		orc->sp_reg = ORC_REG_DI;
-		break;
-	case CFI_DX:
-		orc->sp_reg = ORC_REG_DX;
-		break;
-	default:
-		WARN_INSN(insn, "unknown CFA base reg %d", cfi->cfa.base);
-		return -1;
-	}
-
-	switch (bp->base) {
-	case CFI_UNDEFINED:
-		orc->bp_reg = ORC_REG_UNDEFINED;
-		break;
-	case CFI_CFA:
-		orc->bp_reg = ORC_REG_PREV_SP;
-		break;
-	case CFI_BP:
-		orc->bp_reg = ORC_REG_BP;
-		break;
-	default:
-		WARN_INSN(insn, "unknown BP base reg %d", bp->base);
-		return -1;
-	}
-
-	orc->sp_offset = cfi->cfa.offset;
-	orc->bp_offset = bp->offset;
-
-	return 0;
-}
-
-static int write_orc_entry(struct elf *elf, struct section *orc_sec,
-			   struct section *ip_sec, unsigned int idx,
-			   struct section *insn_sec, unsigned long insn_off,
-			   struct orc_entry *o)
-{
-	struct orc_entry *orc;
-
-	/* populate ORC data */
-	orc = (struct orc_entry *)orc_sec->data->d_buf + idx;
-	memcpy(orc, o, sizeof(*orc));
-	orc->sp_offset = bswap_if_needed(elf, orc->sp_offset);
-	orc->bp_offset = bswap_if_needed(elf, orc->bp_offset);
-
-	/* populate reloc for ip */
-	if (!elf_init_reloc_text_sym(elf, ip_sec, idx * sizeof(int), idx,
-				     insn_sec, insn_off))
-		return -1;
-
-	return 0;
-}
-
 struct orc_list_entry {
 	struct list_head list;
 	struct orc_entry orc;
-- 
cgit 1.2.3-korg


From 3c7266cd7bc5e7843b631fea73cb0e82111e3158 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Mon, 11 Mar 2024 22:23:47 +0800
Subject: objtool/LoongArch: Enable orc to be built

Implement arch-specific init_orc_entry(), write_orc_entry(), reg_name(),
orc_type_name(), print_reg() and orc_print_dump(), then set BUILD_ORC as
y to build the orc related files.

Co-developed-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Jinyang He <hejinyang@loongson.cn>
Co-developed-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 tools/arch/loongarch/include/asm/orc_types.h |  58 +++++++++
 tools/objtool/Makefile                       |   4 +
 tools/objtool/arch/loongarch/Build           |   1 +
 tools/objtool/arch/loongarch/decode.c        |  16 +++
 tools/objtool/arch/loongarch/orc.c           | 171 +++++++++++++++++++++++++++
 5 files changed, 250 insertions(+)
 create mode 100644 tools/arch/loongarch/include/asm/orc_types.h
 create mode 100644 tools/objtool/arch/loongarch/orc.c

diff --git a/tools/arch/loongarch/include/asm/orc_types.h b/tools/arch/loongarch/include/asm/orc_types.h
new file mode 100644
index 00000000000000..caf1f71a1057b6
--- /dev/null
+++ b/tools/arch/loongarch/include/asm/orc_types.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ORC_TYPES_H
+#define _ORC_TYPES_H
+
+#include <linux/types.h>
+
+/*
+ * The ORC_REG_* registers are base registers which are used to find other
+ * registers on the stack.
+ *
+ * ORC_REG_PREV_SP, also known as DWARF Call Frame Address (CFA), is the
+ * address of the previous frame: the caller's SP before it called the current
+ * function.
+ *
+ * ORC_REG_UNDEFINED means the corresponding register's value didn't change in
+ * the current frame.
+ *
+ * The most commonly used base registers are SP and FP -- which the previous SP
+ * is usually based on -- and PREV_SP and UNDEFINED -- which the previous FP is
+ * usually based on.
+ *
+ * The rest of the base registers are needed for special cases like entry code
+ * and GCC realigned stacks.
+ */
+#define ORC_REG_UNDEFINED		0
+#define ORC_REG_PREV_SP			1
+#define ORC_REG_SP			2
+#define ORC_REG_FP			3
+#define ORC_REG_MAX			4
+
+#define ORC_TYPE_UNDEFINED		0
+#define ORC_TYPE_END_OF_STACK		1
+#define ORC_TYPE_CALL			2
+#define ORC_TYPE_REGS			3
+#define ORC_TYPE_REGS_PARTIAL		4
+
+#ifndef __ASSEMBLY__
+/*
+ * This struct is more or less a vastly simplified version of the DWARF Call
+ * Frame Information standard.  It contains only the necessary parts of DWARF
+ * CFI, simplified for ease of access by the in-kernel unwinder.  It tells the
+ * unwinder how to find the previous SP and FP (and sometimes entry regs) on
+ * the stack for a given code address.  Each instance of the struct corresponds
+ * to one or more code locations.
+ */
+struct orc_entry {
+	s16		sp_offset;
+	s16		fp_offset;
+	s16		ra_offset;
+	unsigned int	sp_reg:4;
+	unsigned int	fp_reg:4;
+	unsigned int	ra_reg:4;
+	unsigned int	type:3;
+	unsigned int	signal:1;
+};
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ORC_TYPES_H */
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 83b100c1e7f684..bf7f7f84ac6259 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -57,6 +57,10 @@ ifeq ($(SRCARCH),x86)
 	BUILD_ORC := y
 endif
 
+ifeq ($(SRCARCH),loongarch)
+	BUILD_ORC := y
+endif
+
 export BUILD_ORC
 export srctree OUTPUT CFLAGS SRCARCH AWK
 include $(srctree)/tools/build/Makefile.include
diff --git a/tools/objtool/arch/loongarch/Build b/tools/objtool/arch/loongarch/Build
index d24d5636a5b843..1d4b784b6887ab 100644
--- a/tools/objtool/arch/loongarch/Build
+++ b/tools/objtool/arch/loongarch/Build
@@ -1,2 +1,3 @@
 objtool-y += decode.o
 objtool-y += special.o
+objtool-y += orc.o
diff --git a/tools/objtool/arch/loongarch/decode.c b/tools/objtool/arch/loongarch/decode.c
index ff0b53144d1267..aee479d2191c21 100644
--- a/tools/objtool/arch/loongarch/decode.c
+++ b/tools/objtool/arch/loongarch/decode.c
@@ -3,6 +3,8 @@
 #include <objtool/check.h>
 #include <objtool/warn.h>
 #include <asm/inst.h>
+#include <asm/orc_types.h>
+#include <linux/objtool_types.h>
 
 #ifndef EM_LOONGARCH
 #define EM_LOONGARCH	258
@@ -42,6 +44,20 @@ bool arch_callee_saved_reg(unsigned char reg)
 
 int arch_decode_hint_reg(u8 sp_reg, int *base)
 {
+	switch (sp_reg) {
+	case ORC_REG_UNDEFINED:
+		*base = CFI_UNDEFINED;
+		break;
+	case ORC_REG_SP:
+		*base = CFI_SP;
+		break;
+	case ORC_REG_FP:
+		*base = CFI_FP;
+		break;
+	default:
+		return -1;
+	}
+
 	return 0;
 }
 
diff --git a/tools/objtool/arch/loongarch/orc.c b/tools/objtool/arch/loongarch/orc.c
new file mode 100644
index 00000000000000..873536d009d91d
--- /dev/null
+++ b/tools/objtool/arch/loongarch/orc.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/objtool_types.h>
+#include <asm/orc_types.h>
+
+#include <objtool/check.h>
+#include <objtool/orc.h>
+#include <objtool/warn.h>
+#include <objtool/endianness.h>
+
+int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, struct instruction *insn)
+{
+	struct cfi_reg *fp = &cfi->regs[CFI_FP];
+	struct cfi_reg *ra = &cfi->regs[CFI_RA];
+
+	memset(orc, 0, sizeof(*orc));
+
+	if (!cfi) {
+		/*
+		 * This is usually either unreachable nops/traps (which don't
+		 * trigger unreachable instruction warnings), or
+		 * STACK_FRAME_NON_STANDARD functions.
+		 */
+		orc->type = ORC_TYPE_UNDEFINED;
+		return 0;
+	}
+
+	switch (cfi->type) {
+	case UNWIND_HINT_TYPE_UNDEFINED:
+		orc->type = ORC_TYPE_UNDEFINED;
+		return 0;
+	case UNWIND_HINT_TYPE_END_OF_STACK:
+		orc->type = ORC_TYPE_END_OF_STACK;
+		return 0;
+	case UNWIND_HINT_TYPE_CALL:
+		orc->type = ORC_TYPE_CALL;
+		break;
+	case UNWIND_HINT_TYPE_REGS:
+		orc->type = ORC_TYPE_REGS;
+		break;
+	case UNWIND_HINT_TYPE_REGS_PARTIAL:
+		orc->type = ORC_TYPE_REGS_PARTIAL;
+		break;
+	default:
+		WARN_INSN(insn, "unknown unwind hint type %d", cfi->type);
+		return -1;
+	}
+
+	orc->signal = cfi->signal;
+
+	switch (cfi->cfa.base) {
+	case CFI_SP:
+		orc->sp_reg = ORC_REG_SP;
+		break;
+	case CFI_FP:
+		orc->sp_reg = ORC_REG_FP;
+		break;
+	default:
+		WARN_INSN(insn, "unknown CFA base reg %d", cfi->cfa.base);
+		return -1;
+	}
+
+	switch (fp->base) {
+	case CFI_UNDEFINED:
+		orc->fp_reg = ORC_REG_UNDEFINED;
+		orc->fp_offset = 0;
+		break;
+	case CFI_CFA:
+		orc->fp_reg = ORC_REG_PREV_SP;
+		orc->fp_offset = fp->offset;
+		break;
+	case CFI_FP:
+		orc->fp_reg = ORC_REG_FP;
+		break;
+	default:
+		WARN_INSN(insn, "unknown FP base reg %d", fp->base);
+		return -1;
+	}
+
+	switch (ra->base) {
+	case CFI_UNDEFINED:
+		orc->ra_reg = ORC_REG_UNDEFINED;
+		orc->ra_offset = 0;
+		break;
+	case CFI_CFA:
+		orc->ra_reg = ORC_REG_PREV_SP;
+		orc->ra_offset = ra->offset;
+		break;
+	case CFI_FP:
+		orc->ra_reg = ORC_REG_FP;
+		break;
+	default:
+		WARN_INSN(insn, "unknown RA base reg %d", ra->base);
+		return -1;
+	}
+
+	orc->sp_offset = cfi->cfa.offset;
+
+	return 0;
+}
+
+int write_orc_entry(struct elf *elf, struct section *orc_sec,
+		    struct section *ip_sec, unsigned int idx,
+		    struct section *insn_sec, unsigned long insn_off,
+		    struct orc_entry *o)
+{
+	struct orc_entry *orc;
+
+	/* populate ORC data */
+	orc = (struct orc_entry *)orc_sec->data->d_buf + idx;
+	memcpy(orc, o, sizeof(*orc));
+
+	/* populate reloc for ip */
+	if (!elf_init_reloc_text_sym(elf, ip_sec, idx * sizeof(int), idx,
+				     insn_sec, insn_off))
+		return -1;
+
+	return 0;
+}
+
+static const char *reg_name(unsigned int reg)
+{
+	switch (reg) {
+	case ORC_REG_SP:
+		return "sp";
+	case ORC_REG_FP:
+		return "fp";
+	case ORC_REG_PREV_SP:
+		return "prevsp";
+	default:
+		return "?";
+	}
+}
+
+static const char *orc_type_name(unsigned int type)
+{
+	switch (type) {
+	case UNWIND_HINT_TYPE_CALL:
+		return "call";
+	case UNWIND_HINT_TYPE_REGS:
+		return "regs";
+	case UNWIND_HINT_TYPE_REGS_PARTIAL:
+		return "regs (partial)";
+	default:
+		return "?";
+	}
+}
+
+static void print_reg(unsigned int reg, int offset)
+{
+	if (reg == ORC_REG_UNDEFINED)
+		printf(" (und) ");
+	else
+		printf("%s + %3d", reg_name(reg), offset);
+
+}
+
+void orc_print_dump(struct elf *dummy_elf, struct orc_entry *orc, int i)
+{
+	printf("type:%s", orc_type_name(orc[i].type));
+
+	printf(" sp:");
+	print_reg(orc[i].sp_reg, orc[i].sp_offset);
+
+	printf(" fp:");
+	print_reg(orc[i].fp_reg, orc[i].fp_offset);
+
+	printf(" ra:");
+	print_reg(orc[i].ra_reg, orc[i].ra_offset);
+
+	printf(" signal:%d\n", orc[i].signal);
+}
-- 
cgit 1.2.3-korg


From d5ab2bc36c6b0ce2f3409f934ff9cdf6d6768fa2 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Mon, 11 Mar 2024 22:23:47 +0800
Subject: objtool: Check local label in add_dead_ends()

When update the latest upstream gcc and binutils, it generates more
objtool warnings on LoongArch, like this:

  init/main.o: warning: objtool: unexpected relocation symbol type in .rela.discard.unreachable

We can see that the reloc sym name is local label instead of section in
relocation section '.rela.discard.unreachable', in this case, the reloc
sym type is STT_NOTYPE instead of STT_SECTION.

As suggested by Peter Zijlstra, we add a "local_label" member in struct
symbol, then set it as true if symbol type is STT_NOTYPE and symbol name
starts with ".L" string in classify_symbols().

Let's check reloc->sym->local_label to not return -1 in add_dead_ends(),
and also use reloc->sym->offset instead of reloc addend which is 0 to
find the corresponding instruction. At the same time, let's replace the
variable "addend" with "offset" to reflect the reality.

Here are some detailed info:
[fedora@linux 6.8.test]$ gcc --version
gcc (GCC) 14.0.1 20240129 (experimental)
[fedora@linux 6.8.test]$ as --version
GNU assembler (GNU Binutils) 2.42.50.20240129
[fedora@linux 6.8.test]$ readelf -r init/main.o | grep -A 2 "rela.discard.unreachable"
Relocation section '.rela.discard.unreachable' at offset 0x6028 contains 1 entry:
  Offset          Info           Type           Sym. Value    Sym. Name + Addend
000000000000  00d900000063 R_LARCH_32_PCREL  00000000000002c4 .L500^B1 + 0

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 tools/objtool/check.c               | 40 +++++++++++++++++++++----------------
 tools/objtool/include/objtool/elf.h |  1 +
 2 files changed, 24 insertions(+), 17 deletions(-)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 548ec3cd7c00ca..d0e82c729dd995 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -20,6 +20,7 @@
 #include <linux/hashtable.h>
 #include <linux/kernel.h>
 #include <linux/static_call_types.h>
+#include <linux/string.h>
 
 struct alternative {
 	struct alternative *next;
@@ -584,7 +585,7 @@ static int add_dead_ends(struct objtool_file *file)
 	struct section *rsec;
 	struct reloc *reloc;
 	struct instruction *insn;
-	s64 addend;
+	unsigned long offset;
 
 	/*
 	 * Check for manually annotated dead ends.
@@ -594,27 +595,28 @@ static int add_dead_ends(struct objtool_file *file)
 		goto reachable;
 
 	for_each_reloc(rsec, reloc) {
-
-		if (reloc->sym->type != STT_SECTION) {
+		if (reloc->sym->type == STT_SECTION) {
+			offset = reloc_addend(reloc);
+		} else if (reloc->sym->local_label) {
+			offset = reloc->sym->offset;
+		} else {
 			WARN("unexpected relocation symbol type in %s", rsec->name);
 			return -1;
 		}
 
-		addend = reloc_addend(reloc);
-
-		insn = find_insn(file, reloc->sym->sec, addend);
+		insn = find_insn(file, reloc->sym->sec, offset);
 		if (insn)
 			insn = prev_insn_same_sec(file, insn);
-		else if (addend == reloc->sym->sec->sh.sh_size) {
+		else if (offset == reloc->sym->sec->sh.sh_size) {
 			insn = find_last_insn(file, reloc->sym->sec);
 			if (!insn) {
 				WARN("can't find unreachable insn at %s+0x%" PRIx64,
-				     reloc->sym->sec->name, addend);
+				     reloc->sym->sec->name, offset);
 				return -1;
 			}
 		} else {
 			WARN("can't find unreachable insn at %s+0x%" PRIx64,
-			     reloc->sym->sec->name, addend);
+			     reloc->sym->sec->name, offset);
 			return -1;
 		}
 
@@ -633,27 +635,28 @@ reachable:
 		return 0;
 
 	for_each_reloc(rsec, reloc) {
-
-		if (reloc->sym->type != STT_SECTION) {
+		if (reloc->sym->type == STT_SECTION) {
+			offset = reloc_addend(reloc);
+		} else if (reloc->sym->local_label) {
+			offset = reloc->sym->offset;
+		} else {
 			WARN("unexpected relocation symbol type in %s", rsec->name);
 			return -1;
 		}
 
-		addend = reloc_addend(reloc);
-
-		insn = find_insn(file, reloc->sym->sec, addend);
+		insn = find_insn(file, reloc->sym->sec, offset);
 		if (insn)
 			insn = prev_insn_same_sec(file, insn);
-		else if (addend == reloc->sym->sec->sh.sh_size) {
+		else if (offset == reloc->sym->sec->sh.sh_size) {
 			insn = find_last_insn(file, reloc->sym->sec);
 			if (!insn) {
 				WARN("can't find reachable insn at %s+0x%" PRIx64,
-				     reloc->sym->sec->name, addend);
+				     reloc->sym->sec->name, offset);
 				return -1;
 			}
 		} else {
 			WARN("can't find reachable insn at %s+0x%" PRIx64,
-			     reloc->sym->sec->name, addend);
+			     reloc->sym->sec->name, offset);
 			return -1;
 		}
 
@@ -2522,6 +2525,9 @@ static int classify_symbols(struct objtool_file *file)
 	struct symbol *func;
 
 	for_each_sym(file, func) {
+		if (func->type == STT_NOTYPE && strstarts(func->name, ".L"))
+			func->local_label = true;
+
 		if (func->bind != STB_GLOBAL)
 			continue;
 
diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h
index 9f71e988eca45f..2b8a69de4db871 100644
--- a/tools/objtool/include/objtool/elf.h
+++ b/tools/objtool/include/objtool/elf.h
@@ -67,6 +67,7 @@ struct symbol {
 	u8 profiling_func    : 1;
 	u8 warned	     : 1;
 	u8 embedded_insn     : 1;
+	u8 local_label       : 1;
 	struct list_head pv_target;
 	struct reloc *relocs;
 };
-- 
cgit 1.2.3-korg


From e91c5e4c21b0339376ee124cda5c9b27d41f2cbc Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Mon, 11 Mar 2024 22:23:47 +0800
Subject: objtool: Check local label in read_unwind_hints()

When update the latest upstream gcc and binutils, it generates some
objtool warnings on LoongArch, like this:

  arch/loongarch/kernel/entry.o: warning: objtool: ret_from_fork+0x0: unreachable instruction

We can see that the reloc sym name is local label instead of section
in relocation section '.rela.discard.unwind_hints', in this case, the
reloc sym type is STT_NOTYPE instead of STT_SECTION. Let us check it
to not return -1, then use reloc->sym->offset instead of reloc addend
which is 0 to find the corresponding instruction.

Here are some detailed info:
[fedora@linux 6.8.test]$ gcc --version
gcc (GCC) 14.0.1 20240129 (experimental)
[fedora@linux 6.8.test]$ as --version
GNU assembler (GNU Binutils) 2.42.50.20240129
[fedora@linux 6.8.test]$ readelf -r arch/loongarch/kernel/entry.o | grep -A 3 "rela.discard.unwind_hints"
Relocation section '.rela.discard.unwind_hints' at offset 0x3a8 contains 7 entries:
  Offset          Info           Type           Sym. Value    Sym. Name + Addend
000000000000  000a00000063 R_LARCH_32_PCREL  0000000000000000 .Lhere_1 + 0
00000000000c  000b00000063 R_LARCH_32_PCREL  00000000000000a8 .Lhere_50 + 0

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 tools/objtool/check.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index d0e82c729dd995..1009d144f756ad 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -2227,6 +2227,7 @@ static int read_unwind_hints(struct objtool_file *file)
 	struct unwind_hint *hint;
 	struct instruction *insn;
 	struct reloc *reloc;
+	unsigned long offset;
 	int i;
 
 	sec = find_section_by_name(file->elf, ".discard.unwind_hints");
@@ -2254,7 +2255,16 @@ static int read_unwind_hints(struct objtool_file *file)
 			return -1;
 		}
 
-		insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc));
+		if (reloc->sym->type == STT_SECTION) {
+			offset = reloc_addend(reloc);
+		} else if (reloc->sym->local_label) {
+			offset = reloc->sym->offset;
+		} else {
+			WARN("unexpected relocation symbol type in %s", sec->rsec->name);
+			return -1;
+		}
+
+		insn = find_insn(file, reloc->sym->sec, offset);
 		if (!insn) {
 			WARN("can't find insn for unwind_hints[%d]", i);
 			return -1;
-- 
cgit 1.2.3-korg


From cb8a2ef0848ca80d67d6d56e2df757cfdf6b3355 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Mon, 11 Mar 2024 22:23:47 +0800
Subject: LoongArch: Add ORC stack unwinder support

The kernel CONFIG_UNWINDER_ORC option enables the ORC unwinder, which is
similar in concept to a DWARF unwinder. The difference is that the format
of the ORC data is much simpler than DWARF, which in turn allows the ORC
unwinder to be much simpler and faster.

The ORC data consists of unwind tables which are generated by objtool.
After analyzing all the code paths of a .o file, it determines information
about the stack state at each instruction address in the file and outputs
that information to the .orc_unwind and .orc_unwind_ip sections.

The per-object ORC sections are combined at link time and are sorted and
post-processed at boot time. The unwinder uses the resulting data to
correlate instruction addresses with their stack states at run time.

Most of the logic are similar with x86, in order to get ra info before ra
is saved into stack, add ra_reg and ra_offset into orc_entry. At the same
time, modify some arch-specific code to silence the objtool warnings.

Co-developed-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Jinyang He <hejinyang@loongson.cn>
Co-developed-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Kconfig                     |   2 +
 arch/loongarch/Kconfig.debug               |  11 +
 arch/loongarch/Makefile                    |  23 +-
 arch/loongarch/include/asm/Kbuild          |   2 +
 arch/loongarch/include/asm/bug.h           |   1 +
 arch/loongarch/include/asm/exception.h     |   2 +
 arch/loongarch/include/asm/module.h        |   7 +
 arch/loongarch/include/asm/orc_header.h    |  18 +
 arch/loongarch/include/asm/orc_lookup.h    |  31 ++
 arch/loongarch/include/asm/orc_types.h     |  58 ++++
 arch/loongarch/include/asm/stackframe.h    |   3 +
 arch/loongarch/include/asm/unwind.h        |  20 +-
 arch/loongarch/include/asm/unwind_hints.h  |  28 ++
 arch/loongarch/kernel/Makefile             |   4 +
 arch/loongarch/kernel/entry.S              |   5 +
 arch/loongarch/kernel/fpu.S                |   7 +
 arch/loongarch/kernel/genex.S              |   6 +
 arch/loongarch/kernel/lbt.S                |   3 +
 arch/loongarch/kernel/mcount_dyn.S         |   6 +
 arch/loongarch/kernel/module.c             |  22 +-
 arch/loongarch/kernel/relocate_kernel.S    |   7 +-
 arch/loongarch/kernel/rethook_trampoline.S |   1 +
 arch/loongarch/kernel/setup.c              |   2 +
 arch/loongarch/kernel/stacktrace.c         |   1 +
 arch/loongarch/kernel/traps.c              |  42 ++-
 arch/loongarch/kernel/unwind_orc.c         | 528 +++++++++++++++++++++++++++++
 arch/loongarch/kernel/vmlinux.lds.S        |   3 +
 arch/loongarch/kvm/switch.S                |   9 +-
 arch/loongarch/lib/clear_user.S            |   3 +
 arch/loongarch/lib/copy_user.S             |   3 +
 arch/loongarch/lib/memcpy.S                |   3 +
 arch/loongarch/lib/memset.S                |   3 +
 arch/loongarch/mm/tlb.c                    |  27 +-
 arch/loongarch/mm/tlbex.S                  |   9 +
 arch/loongarch/vdso/Makefile               |   1 +
 include/linux/compiler.h                   |   9 +
 scripts/Makefile                           |   7 +-
 37 files changed, 875 insertions(+), 42 deletions(-)
 create mode 100644 arch/loongarch/include/asm/orc_header.h
 create mode 100644 arch/loongarch/include/asm/orc_lookup.h
 create mode 100644 arch/loongarch/include/asm/orc_types.h
 create mode 100644 arch/loongarch/include/asm/unwind_hints.h
 create mode 100644 arch/loongarch/kernel/unwind_orc.c

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 929f68926b3432..8d6725115ac6bd 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -136,6 +136,7 @@ config LOONGARCH
 	select HAVE_KVM
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
+	select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -148,6 +149,7 @@ config LOONGARCH
 	select HAVE_SAMPLE_FTRACE_DIRECT
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	select HAVE_SETUP_PER_CPU_AREA if NUMA
+	select HAVE_STACK_VALIDATION if HAVE_OBJTOOL
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_TIF_NOHZ
diff --git a/arch/loongarch/Kconfig.debug b/arch/loongarch/Kconfig.debug
index 8d36aab530083b..98d60630c3d4b4 100644
--- a/arch/loongarch/Kconfig.debug
+++ b/arch/loongarch/Kconfig.debug
@@ -26,4 +26,15 @@ config UNWINDER_PROLOGUE
 	  Some of the addresses it reports may be incorrect (but better than the
 	  Guess unwinder).
 
+config UNWINDER_ORC
+	bool "ORC unwinder"
+	select OBJTOOL
+	help
+	  This option enables the ORC (Oops Rewind Capability) unwinder for
+	  unwinding kernel stack traces.  It uses a custom data format which is
+	  a simplified version of the DWARF Call Frame Information standard.
+
+	  Enabling this option will increase the kernel's runtime memory usage
+	  by roughly 2-4MB, depending on your kernel config.
+
 endchoice
diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index 983aa2b1629a69..e3bc02fb7fdcce 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -26,6 +26,18 @@ endif
 32bit-emul		= elf32loongarch
 64bit-emul		= elf64loongarch
 
+ifdef CONFIG_UNWINDER_ORC
+orc_hash_h := arch/$(SRCARCH)/include/generated/asm/orc_hash.h
+orc_hash_sh := $(srctree)/scripts/orc_hash.sh
+targets += $(orc_hash_h)
+quiet_cmd_orc_hash = GEN     $@
+      cmd_orc_hash = mkdir -p $(dir $@); \
+		     $(CONFIG_SHELL) $(orc_hash_sh) < $< > $@
+$(orc_hash_h): $(srctree)/arch/loongarch/include/asm/orc_types.h $(orc_hash_sh) FORCE
+	$(call if_changed,orc_hash)
+archprepare: $(orc_hash_h)
+endif
+
 ifdef CONFIG_DYNAMIC_FTRACE
 KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
 CC_FLAGS_FTRACE := -fpatchable-function-entry=2
@@ -72,8 +84,6 @@ KBUILD_CFLAGS_KERNEL		+= $(call cc-option,-mdirect-extern-access)
 KBUILD_CFLAGS_KERNEL		+= $(call cc-option,-fdirect-access-external-data)
 KBUILD_AFLAGS_MODULE		+= $(call cc-option,-fno-direct-access-external-data)
 KBUILD_CFLAGS_MODULE		+= $(call cc-option,-fno-direct-access-external-data)
-KBUILD_AFLAGS_MODULE		+= $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax)
-KBUILD_CFLAGS_MODULE		+= $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax)
 else
 cflags-y			+= $(call cc-option,-mno-explicit-relocs)
 KBUILD_AFLAGS_KERNEL		+= -Wa,-mla-global-with-pcrel
@@ -82,6 +92,15 @@ KBUILD_AFLAGS_MODULE		+= -Wa,-mla-global-with-abs
 KBUILD_CFLAGS_MODULE		+= -fplt -Wa,-mla-global-with-abs,-mla-local-with-abs
 endif
 
+KBUILD_AFLAGS			+= $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax)
+KBUILD_CFLAGS			+= $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax)
+KBUILD_AFLAGS			+= $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma)-mthin-add-sub)
+KBUILD_CFLAGS			+= $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma)-mthin-add-sub)
+
+ifdef CONFIG_OBJTOOL
+KBUILD_CFLAGS			+= -fno-jump-tables
+endif
+
 KBUILD_RUSTFLAGS_MODULE		+= -Crelocation-model=pic
 
 ifeq ($(CONFIG_RELOCATABLE),y)
diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild
index 93783fa24f6e9b..a97c0edbb866a6 100644
--- a/arch/loongarch/include/asm/Kbuild
+++ b/arch/loongarch/include/asm/Kbuild
@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
+generated-y += orc_hash.h
+
 generic-y += dma-contiguous.h
 generic-y += mcs_spinlock.h
 generic-y += parport.h
diff --git a/arch/loongarch/include/asm/bug.h b/arch/loongarch/include/asm/bug.h
index d4ca3ba2541885..08388876ade4ce 100644
--- a/arch/loongarch/include/asm/bug.h
+++ b/arch/loongarch/include/asm/bug.h
@@ -44,6 +44,7 @@
 do {								\
 	instrumentation_begin();				\
 	__BUG_FLAGS(BUGFLAG_WARNING|(flags));			\
+	annotate_reachable();					\
 	instrumentation_end();					\
 } while (0)
 
diff --git a/arch/loongarch/include/asm/exception.h b/arch/loongarch/include/asm/exception.h
index af74a3fdcad179..c6d20736fd9270 100644
--- a/arch/loongarch/include/asm/exception.h
+++ b/arch/loongarch/include/asm/exception.h
@@ -6,6 +6,8 @@
 #include <asm/ptrace.h>
 #include <linux/kprobes.h>
 
+extern void *exception_table[];
+
 void show_registers(struct pt_regs *regs);
 
 asmlinkage void cache_parity_error(void);
diff --git a/arch/loongarch/include/asm/module.h b/arch/loongarch/include/asm/module.h
index 2ecd82bb64e132..f33f3fd32ecc2c 100644
--- a/arch/loongarch/include/asm/module.h
+++ b/arch/loongarch/include/asm/module.h
@@ -6,6 +6,7 @@
 #define _ASM_MODULE_H
 
 #include <asm/inst.h>
+#include <asm/orc_types.h>
 #include <asm-generic/module.h>
 
 #define RELA_STACK_DEPTH 16
@@ -21,6 +22,12 @@ struct mod_arch_specific {
 	struct mod_section plt;
 	struct mod_section plt_idx;
 
+#ifdef CONFIG_UNWINDER_ORC
+	unsigned int num_orcs;
+	int *orc_unwind_ip;
+	struct orc_entry *orc_unwind;
+#endif
+
 	/* For CONFIG_DYNAMIC_FTRACE */
 	struct plt_entry *ftrace_trampolines;
 };
diff --git a/arch/loongarch/include/asm/orc_header.h b/arch/loongarch/include/asm/orc_header.h
new file mode 100644
index 00000000000000..f9d509c3fd7048
--- /dev/null
+++ b/arch/loongarch/include/asm/orc_header.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _ORC_HEADER_H
+#define _ORC_HEADER_H
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <asm/orc_hash.h>
+
+/*
+ * The header is currently a 20-byte hash of the ORC entry definition; see
+ * scripts/orc_hash.sh.
+ */
+#define ORC_HEADER					\
+	__used __section(".orc_header") __aligned(4)	\
+	static const u8 orc_header[] = { ORC_HASH }
+
+#endif /* _ORC_HEADER_H */
diff --git a/arch/loongarch/include/asm/orc_lookup.h b/arch/loongarch/include/asm/orc_lookup.h
new file mode 100644
index 00000000000000..b02e6357def484
--- /dev/null
+++ b/arch/loongarch/include/asm/orc_lookup.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ORC_LOOKUP_H
+#define _ORC_LOOKUP_H
+
+/*
+ * This is a lookup table for speeding up access to the .orc_unwind table.
+ * Given an input address offset, the corresponding lookup table entry
+ * specifies a subset of the .orc_unwind table to search.
+ *
+ * Each block represents the end of the previous range and the start of the
+ * next range.  An extra block is added to give the last range an end.
+ *
+ * The block size should be a power of 2 to avoid a costly 'div' instruction.
+ *
+ * A block size of 256 was chosen because it roughly doubles unwinder
+ * performance while only adding ~5% to the ORC data footprint.
+ */
+#define LOOKUP_BLOCK_ORDER	8
+#define LOOKUP_BLOCK_SIZE	(1 << LOOKUP_BLOCK_ORDER)
+
+#ifndef LINKER_SCRIPT
+
+extern unsigned int orc_lookup[];
+extern unsigned int orc_lookup_end[];
+
+#define LOOKUP_START_IP		(unsigned long)_stext
+#define LOOKUP_STOP_IP		(unsigned long)_etext
+
+#endif /* LINKER_SCRIPT */
+
+#endif /* _ORC_LOOKUP_H */
diff --git a/arch/loongarch/include/asm/orc_types.h b/arch/loongarch/include/asm/orc_types.h
new file mode 100644
index 00000000000000..caf1f71a1057b6
--- /dev/null
+++ b/arch/loongarch/include/asm/orc_types.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ORC_TYPES_H
+#define _ORC_TYPES_H
+
+#include <linux/types.h>
+
+/*
+ * The ORC_REG_* registers are base registers which are used to find other
+ * registers on the stack.
+ *
+ * ORC_REG_PREV_SP, also known as DWARF Call Frame Address (CFA), is the
+ * address of the previous frame: the caller's SP before it called the current
+ * function.
+ *
+ * ORC_REG_UNDEFINED means the corresponding register's value didn't change in
+ * the current frame.
+ *
+ * The most commonly used base registers are SP and FP -- which the previous SP
+ * is usually based on -- and PREV_SP and UNDEFINED -- which the previous FP is
+ * usually based on.
+ *
+ * The rest of the base registers are needed for special cases like entry code
+ * and GCC realigned stacks.
+ */
+#define ORC_REG_UNDEFINED		0
+#define ORC_REG_PREV_SP			1
+#define ORC_REG_SP			2
+#define ORC_REG_FP			3
+#define ORC_REG_MAX			4
+
+#define ORC_TYPE_UNDEFINED		0
+#define ORC_TYPE_END_OF_STACK		1
+#define ORC_TYPE_CALL			2
+#define ORC_TYPE_REGS			3
+#define ORC_TYPE_REGS_PARTIAL		4
+
+#ifndef __ASSEMBLY__
+/*
+ * This struct is more or less a vastly simplified version of the DWARF Call
+ * Frame Information standard.  It contains only the necessary parts of DWARF
+ * CFI, simplified for ease of access by the in-kernel unwinder.  It tells the
+ * unwinder how to find the previous SP and FP (and sometimes entry regs) on
+ * the stack for a given code address.  Each instance of the struct corresponds
+ * to one or more code locations.
+ */
+struct orc_entry {
+	s16		sp_offset;
+	s16		fp_offset;
+	s16		ra_offset;
+	unsigned int	sp_reg:4;
+	unsigned int	fp_reg:4;
+	unsigned int	ra_reg:4;
+	unsigned int	type:3;
+	unsigned int	signal:1;
+};
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ORC_TYPES_H */
diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h
index 4fb1e6408b982a..45b507a7b06fca 100644
--- a/arch/loongarch/include/asm/stackframe.h
+++ b/arch/loongarch/include/asm/stackframe.h
@@ -13,6 +13,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/loongarch.h>
 #include <asm/thread_info.h>
+#include <asm/unwind_hints.h>
 
 /* Make the addition of cfi info a little easier. */
 	.macro cfi_rel_offset reg offset=0 docfi=0
@@ -162,6 +163,7 @@
 	li.w	t0, CSR_CRMD_WE
 	csrxchg	t0, t0, LOONGARCH_CSR_CRMD
 #endif
+	UNWIND_HINT_REGS
 	.endm
 
 	.macro	SAVE_ALL docfi=0
@@ -219,6 +221,7 @@
 
 	.macro	RESTORE_SP_AND_RET docfi=0
 	cfi_ld	sp, PT_R3, \docfi
+	UNWIND_HINT_FUNC
 	ertn
 	.endm
 
diff --git a/arch/loongarch/include/asm/unwind.h b/arch/loongarch/include/asm/unwind.h
index b9dce87afd2e05..40a6763c5aecd5 100644
--- a/arch/loongarch/include/asm/unwind.h
+++ b/arch/loongarch/include/asm/unwind.h
@@ -16,6 +16,7 @@
 enum unwinder_type {
 	UNWINDER_GUESS,
 	UNWINDER_PROLOGUE,
+	UNWINDER_ORC,
 };
 
 struct unwind_state {
@@ -24,7 +25,7 @@ struct unwind_state {
 	struct task_struct *task;
 	bool first, error, reset;
 	int graph_idx;
-	unsigned long sp, pc, ra;
+	unsigned long sp, fp, pc, ra;
 };
 
 bool default_next_frame(struct unwind_state *state);
@@ -61,14 +62,17 @@ static __always_inline void __unwind_start(struct unwind_state *state,
 		state->sp = regs->regs[3];
 		state->pc = regs->csr_era;
 		state->ra = regs->regs[1];
+		state->fp = regs->regs[22];
 	} else if (task && task != current) {
 		state->sp = thread_saved_fp(task);
 		state->pc = thread_saved_ra(task);
 		state->ra = 0;
+		state->fp = 0;
 	} else {
 		state->sp = (unsigned long)__builtin_frame_address(0);
 		state->pc = (unsigned long)__builtin_return_address(0);
 		state->ra = 0;
+		state->fp = 0;
 	}
 	state->task = task;
 	get_stack_info(state->sp, state->task, &state->stack_info);
@@ -77,6 +81,18 @@ static __always_inline void __unwind_start(struct unwind_state *state,
 
 static __always_inline unsigned long __unwind_get_return_address(struct unwind_state *state)
 {
-	return unwind_done(state) ? 0 : state->pc;
+	if (unwind_done(state))
+		return 0;
+
+	return __kernel_text_address(state->pc) ? state->pc : 0;
 }
+
+#ifdef CONFIG_UNWINDER_ORC
+void unwind_init(void);
+void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size);
+#else
+static inline void unwind_init(void) {}
+static inline void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size) {}
+#endif
+
 #endif /* _ASM_UNWIND_H */
diff --git a/arch/loongarch/include/asm/unwind_hints.h b/arch/loongarch/include/asm/unwind_hints.h
new file mode 100644
index 00000000000000..a01086ad9ddea4
--- /dev/null
+++ b/arch/loongarch/include/asm/unwind_hints.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_LOONGARCH_UNWIND_HINTS_H
+#define _ASM_LOONGARCH_UNWIND_HINTS_H
+
+#include <linux/objtool.h>
+#include <asm/orc_types.h>
+
+#ifdef __ASSEMBLY__
+
+.macro UNWIND_HINT_UNDEFINED
+	UNWIND_HINT type=UNWIND_HINT_TYPE_UNDEFINED
+.endm
+
+.macro UNWIND_HINT_END_OF_STACK
+	UNWIND_HINT type=UNWIND_HINT_TYPE_END_OF_STACK
+.endm
+
+.macro UNWIND_HINT_REGS
+	UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_REGS
+.endm
+
+.macro UNWIND_HINT_FUNC
+	UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_CALL
+.endm
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_LOONGARCH_UNWIND_HINTS_H */
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 3c808c6803703c..3a7620b66bc6c0 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -3,6 +3,8 @@
 # Makefile for the Linux/LoongArch kernel.
 #
 
+OBJECT_FILES_NON_STANDARD_head.o := y
+
 extra-y		:= vmlinux.lds
 
 obj-y		+= head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \
@@ -21,6 +23,7 @@ obj-$(CONFIG_ARCH_STRICT_ALIGN)	+= unaligned.o
 
 CFLAGS_module.o		+= $(call cc-option,-Wno-override-init,)
 CFLAGS_syscall.o	+= $(call cc-option,-Wno-override-init,)
+CFLAGS_traps.o		+= $(call cc-option,-Wno-override-init,)
 CFLAGS_perf_event.o	+= $(call cc-option,-Wno-override-init,)
 
 ifdef CONFIG_FUNCTION_TRACER
@@ -62,6 +65,7 @@ obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 
 obj-$(CONFIG_UNWINDER_GUESS)	+= unwind_guess.o
 obj-$(CONFIG_UNWINDER_PROLOGUE) += unwind_prologue.o
+obj-$(CONFIG_UNWINDER_ORC)	+= unwind_orc.o
 
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_regs.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S
index 1ec8e4c4cc2bd8..48e7e34e355e83 100644
--- a/arch/loongarch/kernel/entry.S
+++ b/arch/loongarch/kernel/entry.S
@@ -14,11 +14,13 @@
 #include <asm/regdef.h>
 #include <asm/stackframe.h>
 #include <asm/thread_info.h>
+#include <asm/unwind_hints.h>
 
 	.text
 	.cfi_sections	.debug_frame
 	.align	5
 SYM_CODE_START(handle_syscall)
+	UNWIND_HINT_UNDEFINED
 	csrrd		t0, PERCPU_BASE_KS
 	la.pcrel	t1, kernelsp
 	add.d		t1, t1, t0
@@ -57,6 +59,7 @@ SYM_CODE_START(handle_syscall)
 	cfi_st		fp, PT_R22
 
 	SAVE_STATIC
+	UNWIND_HINT_REGS
 
 #ifdef CONFIG_KGDB
 	li.w		t1, CSR_CRMD_WE
@@ -75,6 +78,7 @@ SYM_CODE_END(handle_syscall)
 _ASM_NOKPROBE(handle_syscall)
 
 SYM_CODE_START(ret_from_fork)
+	UNWIND_HINT_REGS
 	bl		schedule_tail		# a0 = struct task_struct *prev
 	move		a0, sp
 	bl 		syscall_exit_to_user_mode
@@ -84,6 +88,7 @@ SYM_CODE_START(ret_from_fork)
 SYM_CODE_END(ret_from_fork)
 
 SYM_CODE_START(ret_from_kernel_thread)
+	UNWIND_HINT_REGS
 	bl		schedule_tail		# a0 = struct task_struct *prev
 	move		a0, s1
 	jirl		ra, s0, 0
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index 4382e36ae3d444..69a85f2479fba1 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -15,6 +15,7 @@
 #include <asm/fpregdef.h>
 #include <asm/loongarch.h>
 #include <asm/regdef.h>
+#include <asm/unwind_hints.h>
 
 #define FPU_REG_WIDTH		8
 #define LSX_REG_WIDTH		16
@@ -526,3 +527,9 @@ SYM_FUNC_END(_restore_lasx_context)
 .L_fpu_fault:
 	li.w	a0, -EFAULT				# failure
 	jr	ra
+
+#ifdef CONFIG_CPU_HAS_LBT
+STACK_FRAME_NON_STANDARD _restore_fp
+STACK_FRAME_NON_STANDARD _restore_lsx
+STACK_FRAME_NON_STANDARD _restore_lasx
+#endif
diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S
index 2bb3aa2dcfcb2e..86d5d90ebefe5b 100644
--- a/arch/loongarch/kernel/genex.S
+++ b/arch/loongarch/kernel/genex.S
@@ -32,6 +32,7 @@ SYM_FUNC_START(__arch_cpu_idle)
 SYM_FUNC_END(__arch_cpu_idle)
 
 SYM_CODE_START(handle_vint)
+	UNWIND_HINT_UNDEFINED
 	BACKUP_T0T1
 	SAVE_ALL
 	la_abs	t1, __arch_cpu_idle
@@ -49,6 +50,7 @@ SYM_CODE_START(handle_vint)
 SYM_CODE_END(handle_vint)
 
 SYM_CODE_START(except_vec_cex)
+	UNWIND_HINT_UNDEFINED
 	b	cache_parity_error
 SYM_CODE_END(except_vec_cex)
 
@@ -67,6 +69,7 @@ SYM_CODE_END(except_vec_cex)
 	.macro	BUILD_HANDLER exception handler prep
 	.align	5
 	SYM_CODE_START(handle_\exception)
+	UNWIND_HINT_UNDEFINED
 	666:
 	BACKUP_T0T1
 	SAVE_ALL
@@ -77,7 +80,9 @@ SYM_CODE_END(except_vec_cex)
 	668:
 	RESTORE_ALL_AND_RET
 	SYM_CODE_END(handle_\exception)
+	.pushsection	".data", "aw", %progbits
 	SYM_DATA(unwind_hint_\exception, .word 668b - 666b)
+	.popsection
 	.endm
 
 	BUILD_HANDLER ade ade badv
@@ -94,6 +99,7 @@ SYM_CODE_END(except_vec_cex)
 	BUILD_HANDLER reserved reserved none	/* others */
 
 SYM_CODE_START(handle_sys)
+	UNWIND_HINT_UNDEFINED
 	la_abs	t0, handle_syscall
 	jr	t0
 SYM_CODE_END(handle_sys)
diff --git a/arch/loongarch/kernel/lbt.S b/arch/loongarch/kernel/lbt.S
index 9c75120a26d836..001f061d226ab5 100644
--- a/arch/loongarch/kernel/lbt.S
+++ b/arch/loongarch/kernel/lbt.S
@@ -11,6 +11,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/errno.h>
 #include <asm/regdef.h>
+#include <asm/unwind_hints.h>
 
 #define SCR_REG_WIDTH 8
 
@@ -153,3 +154,5 @@ SYM_FUNC_END(_restore_ftop_context)
 .L_lbt_fault:
 	li.w		a0, -EFAULT		# failure
 	jr		ra
+
+STACK_FRAME_NON_STANDARD _restore_ftop_context
diff --git a/arch/loongarch/kernel/mcount_dyn.S b/arch/loongarch/kernel/mcount_dyn.S
index 482aa553aa2d5e..0c65cf09110cd4 100644
--- a/arch/loongarch/kernel/mcount_dyn.S
+++ b/arch/loongarch/kernel/mcount_dyn.S
@@ -73,6 +73,7 @@ SYM_FUNC_START(ftrace_stub)
 SYM_FUNC_END(ftrace_stub)
 
 SYM_CODE_START(ftrace_common)
+	UNWIND_HINT_UNDEFINED
 	PTR_ADDI	a0, ra, -8	/* arg0: ip */
 	move		a1, t0		/* arg1: parent_ip */
 	la.pcrel	t1, function_trace_op
@@ -113,12 +114,14 @@ ftrace_common_return:
 SYM_CODE_END(ftrace_common)
 
 SYM_CODE_START(ftrace_caller)
+	UNWIND_HINT_UNDEFINED
 	ftrace_regs_entry allregs=0
 	b		ftrace_common
 SYM_CODE_END(ftrace_caller)
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 SYM_CODE_START(ftrace_regs_caller)
+	UNWIND_HINT_UNDEFINED
 	ftrace_regs_entry allregs=1
 	b		ftrace_common
 SYM_CODE_END(ftrace_regs_caller)
@@ -126,6 +129,7 @@ SYM_CODE_END(ftrace_regs_caller)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 SYM_CODE_START(ftrace_graph_caller)
+	UNWIND_HINT_UNDEFINED
 	PTR_L		a0, sp, PT_ERA
 	PTR_ADDI	a0, a0, -8	/* arg0: self_addr */
 	PTR_ADDI	a1, sp, PT_R1	/* arg1: parent */
@@ -134,6 +138,7 @@ SYM_CODE_START(ftrace_graph_caller)
 SYM_CODE_END(ftrace_graph_caller)
 
 SYM_CODE_START(return_to_handler)
+	UNWIND_HINT_UNDEFINED
 	/* Save return value regs */
 	PTR_ADDI	sp, sp, -FGRET_REGS_SIZE
 	PTR_S		a0, sp, FGRET_REGS_A0
@@ -155,6 +160,7 @@ SYM_CODE_END(return_to_handler)
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 SYM_CODE_START(ftrace_stub_direct_tramp)
+	UNWIND_HINT_UNDEFINED
 	jr		t0
 SYM_CODE_END(ftrace_stub_direct_tramp)
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
diff --git a/arch/loongarch/kernel/module.c b/arch/loongarch/kernel/module.c
index b13b2858fe3923..c7d0338d12c15b 100644
--- a/arch/loongarch/kernel/module.c
+++ b/arch/loongarch/kernel/module.c
@@ -20,6 +20,7 @@
 #include <linux/kernel.h>
 #include <asm/alternative.h>
 #include <asm/inst.h>
+#include <asm/unwind.h>
 
 static int rela_stack_push(s64 stack_value, s64 *rela_stack, size_t *rela_stack_top)
 {
@@ -515,15 +516,28 @@ static void module_init_ftrace_plt(const Elf_Ehdr *hdr,
 int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs, struct module *mod)
 {
-	const Elf_Shdr *s, *se;
 	const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+	const Elf_Shdr *s, *alt = NULL, *orc = NULL, *orc_ip = NULL, *ftrace = NULL;
 
-	for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
+	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
 		if (!strcmp(".altinstructions", secstrs + s->sh_name))
-			apply_alternatives((void *)s->sh_addr, (void *)s->sh_addr + s->sh_size);
+			alt = s;
+		if (!strcmp(".orc_unwind", secstrs + s->sh_name))
+			orc = s;
+		if (!strcmp(".orc_unwind_ip", secstrs + s->sh_name))
+			orc_ip = s;
 		if (!strcmp(".ftrace_trampoline", secstrs + s->sh_name))
-			module_init_ftrace_plt(hdr, s, mod);
+			ftrace = s;
 	}
 
+	if (alt)
+		apply_alternatives((void *)alt->sh_addr, (void *)alt->sh_addr + alt->sh_size);
+
+	if (orc && orc_ip)
+		unwind_module_init(mod, (void *)orc_ip->sh_addr, orc_ip->sh_size, (void *)orc->sh_addr, orc->sh_size);
+
+	if (ftrace)
+		module_init_ftrace_plt(hdr, ftrace, mod);
+
 	return 0;
 }
diff --git a/arch/loongarch/kernel/relocate_kernel.S b/arch/loongarch/kernel/relocate_kernel.S
index f49f6b053763d1..84e6de2fd97354 100644
--- a/arch/loongarch/kernel/relocate_kernel.S
+++ b/arch/loongarch/kernel/relocate_kernel.S
@@ -15,6 +15,7 @@
 #include <asm/addrspace.h>
 
 SYM_CODE_START(relocate_new_kernel)
+	UNWIND_HINT_UNDEFINED
 	/*
 	 * a0: EFI boot flag for the new kernel
 	 * a1: Command line pointer for the new kernel
@@ -90,6 +91,7 @@ SYM_CODE_END(relocate_new_kernel)
  * then start at the entry point from LOONGARCH_IOCSR_MBUF0.
  */
 SYM_CODE_START(kexec_smp_wait)
+	UNWIND_HINT_UNDEFINED
 1:	li.w		t0, 0x100			/* wait for init loop */
 2:	addi.w		t0, t0, -1			/* limit mailbox access */
 	bnez		t0, 2b
@@ -106,6 +108,5 @@ SYM_CODE_END(kexec_smp_wait)
 
 relocate_new_kernel_end:
 
-SYM_DATA_START(relocate_new_kernel_size)
-	PTR		relocate_new_kernel_end - relocate_new_kernel
-SYM_DATA_END(relocate_new_kernel_size)
+	.section ".data"
+SYM_DATA(relocate_new_kernel_size, .long relocate_new_kernel_end - relocate_new_kernel)
diff --git a/arch/loongarch/kernel/rethook_trampoline.S b/arch/loongarch/kernel/rethook_trampoline.S
index bd5772c963382f..d4ceb2fa2a5ce4 100644
--- a/arch/loongarch/kernel/rethook_trampoline.S
+++ b/arch/loongarch/kernel/rethook_trampoline.S
@@ -76,6 +76,7 @@
 	.endm
 
 SYM_CODE_START(arch_rethook_trampoline)
+	UNWIND_HINT_UNDEFINED
 	addi.d	sp, sp, -PT_SIZE
 	save_all_base_regs
 
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 634ef17fd38bf1..7bf9afaeea006b 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -47,6 +47,7 @@
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/time.h>
+#include <asm/unwind.h>
 
 #define SMBIOS_BIOSSIZE_OFFSET		0x09
 #define SMBIOS_BIOSEXTERN_OFFSET	0x13
@@ -587,6 +588,7 @@ static void __init prefill_possible_map(void)
 void __init setup_arch(char **cmdline_p)
 {
 	cpu_probe();
+	unwind_init();
 
 	init_environ();
 	efi_init();
diff --git a/arch/loongarch/kernel/stacktrace.c b/arch/loongarch/kernel/stacktrace.c
index f623feb2129f12..eaec82e02c92ab 100644
--- a/arch/loongarch/kernel/stacktrace.c
+++ b/arch/loongarch/kernel/stacktrace.c
@@ -29,6 +29,7 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
 			regs->csr_era = thread_saved_ra(task);
 		}
 		regs->regs[1] = 0;
+		regs->regs[22] = 0;
 	}
 
 	for (unwind_start(&state, task, regs);
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index aebfc3733a7607..f9f4eb00c92ef5 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -53,6 +53,32 @@
 
 #include "access-helper.h"
 
+void *exception_table[EXCCODE_INT_START] = {
+	[0 ... EXCCODE_INT_START - 1] = handle_reserved,
+
+	[EXCCODE_TLBI]		= handle_tlb_load,
+	[EXCCODE_TLBL]		= handle_tlb_load,
+	[EXCCODE_TLBS]		= handle_tlb_store,
+	[EXCCODE_TLBM]		= handle_tlb_modify,
+	[EXCCODE_TLBNR]		= handle_tlb_protect,
+	[EXCCODE_TLBNX]		= handle_tlb_protect,
+	[EXCCODE_TLBPE]		= handle_tlb_protect,
+	[EXCCODE_ADE]		= handle_ade,
+	[EXCCODE_ALE]		= handle_ale,
+	[EXCCODE_BCE]		= handle_bce,
+	[EXCCODE_SYS]		= handle_sys,
+	[EXCCODE_BP]		= handle_bp,
+	[EXCCODE_INE]		= handle_ri,
+	[EXCCODE_IPE]		= handle_ri,
+	[EXCCODE_FPDIS]		= handle_fpu,
+	[EXCCODE_LSXDIS]	= handle_lsx,
+	[EXCCODE_LASXDIS]	= handle_lasx,
+	[EXCCODE_FPE]		= handle_fpe,
+	[EXCCODE_WATCH]		= handle_watch,
+	[EXCCODE_BTDIS]		= handle_lbt,
+};
+EXPORT_SYMBOL_GPL(exception_table);
+
 static void show_backtrace(struct task_struct *task, const struct pt_regs *regs,
 			   const char *loglvl, bool user)
 {
@@ -1150,19 +1176,9 @@ void __init trap_init(void)
 	for (i = EXCCODE_INT_START; i <= EXCCODE_INT_END; i++)
 		set_handler(i * VECSIZE, handle_vint, VECSIZE);
 
-	set_handler(EXCCODE_ADE * VECSIZE, handle_ade, VECSIZE);
-	set_handler(EXCCODE_ALE * VECSIZE, handle_ale, VECSIZE);
-	set_handler(EXCCODE_BCE * VECSIZE, handle_bce, VECSIZE);
-	set_handler(EXCCODE_SYS * VECSIZE, handle_sys, VECSIZE);
-	set_handler(EXCCODE_BP * VECSIZE, handle_bp, VECSIZE);
-	set_handler(EXCCODE_INE * VECSIZE, handle_ri, VECSIZE);
-	set_handler(EXCCODE_IPE * VECSIZE, handle_ri, VECSIZE);
-	set_handler(EXCCODE_FPDIS * VECSIZE, handle_fpu, VECSIZE);
-	set_handler(EXCCODE_LSXDIS * VECSIZE, handle_lsx, VECSIZE);
-	set_handler(EXCCODE_LASXDIS * VECSIZE, handle_lasx, VECSIZE);
-	set_handler(EXCCODE_FPE * VECSIZE, handle_fpe, VECSIZE);
-	set_handler(EXCCODE_BTDIS * VECSIZE, handle_lbt, VECSIZE);
-	set_handler(EXCCODE_WATCH * VECSIZE, handle_watch, VECSIZE);
+	/* Set exception vector handler */
+	for (i = EXCCODE_ADE; i <= EXCCODE_BTDIS; i++)
+		set_handler(i * VECSIZE, exception_table[i], VECSIZE);
 
 	cache_error_setup();
 
diff --git a/arch/loongarch/kernel/unwind_orc.c b/arch/loongarch/kernel/unwind_orc.c
new file mode 100644
index 00000000000000..b2572287633179
--- /dev/null
+++ b/arch/loongarch/kernel/unwind_orc.c
@@ -0,0 +1,528 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/objtool.h>
+#include <linux/module.h>
+#include <linux/sort.h>
+#include <asm/exception.h>
+#include <asm/orc_header.h>
+#include <asm/orc_lookup.h>
+#include <asm/orc_types.h>
+#include <asm/ptrace.h>
+#include <asm/setup.h>
+#include <asm/stacktrace.h>
+#include <asm/tlb.h>
+#include <asm/unwind.h>
+
+ORC_HEADER;
+
+#define orc_warn(fmt, ...) \
+	printk_deferred_once(KERN_WARNING "WARNING: " fmt, ##__VA_ARGS__)
+
+extern int __start_orc_unwind_ip[];
+extern int __stop_orc_unwind_ip[];
+extern struct orc_entry __start_orc_unwind[];
+extern struct orc_entry __stop_orc_unwind[];
+
+static bool orc_init __ro_after_init;
+static unsigned int lookup_num_blocks __ro_after_init;
+
+/* Fake frame pointer entry -- used as a fallback for generated code */
+static struct orc_entry orc_fp_entry = {
+	.sp_reg		= ORC_REG_FP,
+	.sp_offset	= 16,
+	.fp_reg		= ORC_REG_PREV_SP,
+	.fp_offset	= -16,
+	.ra_reg		= ORC_REG_PREV_SP,
+	.ra_offset	= -8,
+	.type		= ORC_TYPE_CALL
+};
+
+/*
+ * If we crash with IP==0, the last successfully executed instruction
+ * was probably an indirect function call with a NULL function pointer,
+ * and we don't have unwind information for NULL.
+ * This hardcoded ORC entry for IP==0 allows us to unwind from a NULL function
+ * pointer into its parent and then continue normally from there.
+ */
+static struct orc_entry orc_null_entry = {
+	.sp_reg		= ORC_REG_SP,
+	.sp_offset	= sizeof(long),
+	.fp_reg		= ORC_REG_UNDEFINED,
+	.type		= ORC_TYPE_CALL
+};
+
+static inline unsigned long orc_ip(const int *ip)
+{
+	return (unsigned long)ip + *ip;
+}
+
+static struct orc_entry *__orc_find(int *ip_table, struct orc_entry *u_table,
+				    unsigned int num_entries, unsigned long ip)
+{
+	int *first = ip_table;
+	int *mid = first, *found = first;
+	int *last = ip_table + num_entries - 1;
+
+	if (!num_entries)
+		return NULL;
+
+	/*
+	 * Do a binary range search to find the rightmost duplicate of a given
+	 * starting address.  Some entries are section terminators which are
+	 * "weak" entries for ensuring there are no gaps.  They should be
+	 * ignored when they conflict with a real entry.
+	 */
+	while (first <= last) {
+		mid = first + ((last - first) / 2);
+
+		if (orc_ip(mid) <= ip) {
+			found = mid;
+			first = mid + 1;
+		} else
+			last = mid - 1;
+	}
+
+	return u_table + (found - ip_table);
+}
+
+#ifdef CONFIG_MODULES
+static struct orc_entry *orc_module_find(unsigned long ip)
+{
+	struct module *mod;
+
+	mod = __module_address(ip);
+	if (!mod || !mod->arch.orc_unwind || !mod->arch.orc_unwind_ip)
+		return NULL;
+
+	return __orc_find(mod->arch.orc_unwind_ip, mod->arch.orc_unwind, mod->arch.num_orcs, ip);
+}
+#else
+static struct orc_entry *orc_module_find(unsigned long ip)
+{
+	return NULL;
+}
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+static struct orc_entry *orc_find(unsigned long ip);
+
+/*
+ * Ftrace dynamic trampolines do not have orc entries of their own.
+ * But they are copies of the ftrace entries that are static and
+ * defined in ftrace_*.S, which do have orc entries.
+ *
+ * If the unwinder comes across a ftrace trampoline, then find the
+ * ftrace function that was used to create it, and use that ftrace
+ * function's orc entry, as the placement of the return code in
+ * the stack will be identical.
+ */
+static struct orc_entry *orc_ftrace_find(unsigned long ip)
+{
+	struct ftrace_ops *ops;
+	unsigned long tramp_addr, offset;
+
+	ops = ftrace_ops_trampoline(ip);
+	if (!ops)
+		return NULL;
+
+	/* Set tramp_addr to the start of the code copied by the trampoline */
+	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+		tramp_addr = (unsigned long)ftrace_regs_caller;
+	else
+		tramp_addr = (unsigned long)ftrace_caller;
+
+	/* Now place tramp_addr to the location within the trampoline ip is at */
+	offset = ip - ops->trampoline;
+	tramp_addr += offset;
+
+	/* Prevent unlikely recursion */
+	if (ip == tramp_addr)
+		return NULL;
+
+	return orc_find(tramp_addr);
+}
+#else
+static struct orc_entry *orc_ftrace_find(unsigned long ip)
+{
+	return NULL;
+}
+#endif
+
+static struct orc_entry *orc_find(unsigned long ip)
+{
+	static struct orc_entry *orc;
+
+	if (ip == 0)
+		return &orc_null_entry;
+
+	/* For non-init vmlinux addresses, use the fast lookup table: */
+	if (ip >= LOOKUP_START_IP && ip < LOOKUP_STOP_IP) {
+		unsigned int idx, start, stop;
+
+		idx = (ip - LOOKUP_START_IP) / LOOKUP_BLOCK_SIZE;
+
+		if (unlikely((idx >= lookup_num_blocks-1))) {
+			orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%pB\n",
+				 idx, lookup_num_blocks, (void *)ip);
+			return NULL;
+		}
+
+		start = orc_lookup[idx];
+		stop = orc_lookup[idx + 1] + 1;
+
+		if (unlikely((__start_orc_unwind + start >= __stop_orc_unwind) ||
+			     (__start_orc_unwind + stop > __stop_orc_unwind))) {
+			orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%pB\n",
+				 idx, lookup_num_blocks, start, stop, (void *)ip);
+			return NULL;
+		}
+
+		return __orc_find(__start_orc_unwind_ip + start,
+				  __start_orc_unwind + start, stop - start, ip);
+	}
+
+	/* vmlinux .init slow lookup: */
+	if (is_kernel_inittext(ip))
+		return __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
+				  __stop_orc_unwind_ip - __start_orc_unwind_ip, ip);
+
+	/* Module lookup: */
+	orc = orc_module_find(ip);
+	if (orc)
+		return orc;
+
+	return orc_ftrace_find(ip);
+}
+
+#ifdef CONFIG_MODULES
+
+static DEFINE_MUTEX(sort_mutex);
+static int *cur_orc_ip_table = __start_orc_unwind_ip;
+static struct orc_entry *cur_orc_table = __start_orc_unwind;
+
+static void orc_sort_swap(void *_a, void *_b, int size)
+{
+	int delta = _b - _a;
+	int *a = _a, *b = _b, tmp;
+	struct orc_entry *orc_a, *orc_b;
+
+	/* Swap the .orc_unwind_ip entries: */
+	tmp = *a;
+	*a = *b + delta;
+	*b = tmp - delta;
+
+	/* Swap the corresponding .orc_unwind entries: */
+	orc_a = cur_orc_table + (a - cur_orc_ip_table);
+	orc_b = cur_orc_table + (b - cur_orc_ip_table);
+	swap(*orc_a, *orc_b);
+}
+
+static int orc_sort_cmp(const void *_a, const void *_b)
+{
+	const int *a = _a, *b = _b;
+	unsigned long a_val = orc_ip(a);
+	unsigned long b_val = orc_ip(b);
+	struct orc_entry *orc_a;
+
+	if (a_val > b_val)
+		return 1;
+	if (a_val < b_val)
+		return -1;
+
+	/*
+	 * The "weak" section terminator entries need to always be first
+	 * to ensure the lookup code skips them in favor of real entries.
+	 * These terminator entries exist to handle any gaps created by
+	 * whitelisted .o files which didn't get objtool generation.
+	 */
+	orc_a = cur_orc_table + (a - cur_orc_ip_table);
+
+	return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1;
+}
+
+void unwind_module_init(struct module *mod, void *_orc_ip, size_t orc_ip_size,
+			void *_orc, size_t orc_size)
+{
+	int *orc_ip = _orc_ip;
+	struct orc_entry *orc = _orc;
+	unsigned int num_entries = orc_ip_size / sizeof(int);
+
+	WARN_ON_ONCE(orc_ip_size % sizeof(int) != 0 ||
+		     orc_size % sizeof(*orc) != 0 ||
+		     num_entries != orc_size / sizeof(*orc));
+
+	/*
+	 * The 'cur_orc_*' globals allow the orc_sort_swap() callback to
+	 * associate an .orc_unwind_ip table entry with its corresponding
+	 * .orc_unwind entry so they can both be swapped.
+	 */
+	mutex_lock(&sort_mutex);
+	cur_orc_ip_table = orc_ip;
+	cur_orc_table = orc;
+	sort(orc_ip, num_entries, sizeof(int), orc_sort_cmp, orc_sort_swap);
+	mutex_unlock(&sort_mutex);
+
+	mod->arch.orc_unwind_ip = orc_ip;
+	mod->arch.orc_unwind = orc;
+	mod->arch.num_orcs = num_entries;
+}
+#endif
+
+void __init unwind_init(void)
+{
+	int i;
+	size_t orc_size = (void *)__stop_orc_unwind - (void *)__start_orc_unwind;
+	size_t orc_ip_size = (void *)__stop_orc_unwind_ip - (void *)__start_orc_unwind_ip;
+	size_t num_entries = orc_ip_size / sizeof(int);
+	struct orc_entry *orc;
+
+	if (!num_entries || orc_ip_size % sizeof(int) != 0 ||
+	    orc_size % sizeof(struct orc_entry) != 0 ||
+	    num_entries != orc_size / sizeof(struct orc_entry)) {
+		orc_warn("WARNING: Bad or missing .orc_unwind table.  Disabling unwinder.\n");
+		return;
+	}
+
+	/*
+	 * Note, the orc_unwind and orc_unwind_ip tables were already
+	 * sorted at build time via the 'sorttable' tool.
+	 * It's ready for binary search straight away, no need to sort it.
+	 */
+
+	/* Initialize the fast lookup table: */
+	lookup_num_blocks = orc_lookup_end - orc_lookup;
+	for (i = 0; i < lookup_num_blocks-1; i++) {
+		orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
+				 num_entries, LOOKUP_START_IP + (LOOKUP_BLOCK_SIZE * i));
+		if (!orc) {
+			orc_warn("WARNING: Corrupt .orc_unwind table.  Disabling unwinder.\n");
+			return;
+		}
+
+		orc_lookup[i] = orc - __start_orc_unwind;
+	}
+
+	/* Initialize the ending block: */
+	orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind, num_entries, LOOKUP_STOP_IP);
+	if (!orc) {
+		orc_warn("WARNING: Corrupt .orc_unwind table.  Disabling unwinder.\n");
+		return;
+	}
+	orc_lookup[lookup_num_blocks-1] = orc - __start_orc_unwind;
+
+	orc_init = true;
+}
+
+static inline bool on_stack(struct stack_info *info, unsigned long addr, size_t len)
+{
+	unsigned long begin = info->begin;
+	unsigned long end   = info->end;
+
+	return (info->type != STACK_TYPE_UNKNOWN &&
+		addr >= begin && addr < end && addr + len > begin && addr + len <= end);
+}
+
+static bool stack_access_ok(struct unwind_state *state, unsigned long addr, size_t len)
+{
+	struct stack_info *info = &state->stack_info;
+
+	if (on_stack(info, addr, len))
+		return true;
+
+	return !get_stack_info(addr, state->task, info) && on_stack(info, addr, len);
+}
+
+unsigned long unwind_get_return_address(struct unwind_state *state)
+{
+	return __unwind_get_return_address(state);
+}
+EXPORT_SYMBOL_GPL(unwind_get_return_address);
+
+void unwind_start(struct unwind_state *state, struct task_struct *task,
+		    struct pt_regs *regs)
+{
+	__unwind_start(state, task, regs);
+	state->type = UNWINDER_ORC;
+	if (!unwind_done(state) && !__kernel_text_address(state->pc))
+		unwind_next_frame(state);
+}
+EXPORT_SYMBOL_GPL(unwind_start);
+
+static bool is_entry_func(unsigned long addr)
+{
+	extern u32 kernel_entry;
+	extern u32 kernel_entry_end;
+
+	return addr >= (unsigned long)&kernel_entry && addr < (unsigned long)&kernel_entry_end;
+}
+
+static inline unsigned long bt_address(unsigned long ra)
+{
+	extern unsigned long eentry;
+
+	if (__kernel_text_address(ra))
+		return ra;
+
+	if (__module_text_address(ra))
+		return ra;
+
+	if (ra >= eentry && ra < eentry +  EXCCODE_INT_END * VECSIZE) {
+		unsigned long func;
+		unsigned long type = (ra - eentry) / VECSIZE;
+		unsigned long offset = (ra - eentry) % VECSIZE;
+
+		switch (type) {
+		case 0 ... EXCCODE_INT_START - 1:
+			func = (unsigned long)exception_table[type];
+			break;
+		case EXCCODE_INT_START ... EXCCODE_INT_END:
+			func = (unsigned long)handle_vint;
+			break;
+		default:
+			func = (unsigned long)handle_reserved;
+			break;
+		}
+
+		return func + offset;
+	}
+
+	return ra;
+}
+
+bool unwind_next_frame(struct unwind_state *state)
+{
+	unsigned long *p, pc;
+	struct pt_regs *regs;
+	struct orc_entry *orc;
+	struct stack_info *info = &state->stack_info;
+
+	if (unwind_done(state))
+		return false;
+
+	/* Don't let modules unload while we're reading their ORC data. */
+	preempt_disable();
+
+	if (is_entry_func(state->pc))
+		goto end;
+
+	orc = orc_find(state->pc);
+	if (!orc) {
+		/*
+		 * As a fallback, try to assume this code uses a frame pointer.
+		 * This is useful for generated code, like BPF, which ORC
+		 * doesn't know about.  This is just a guess, so the rest of
+		 * the unwind is no longer considered reliable.
+		 */
+		orc = &orc_fp_entry;
+		state->error = true;
+	} else {
+		if (orc->type == ORC_TYPE_UNDEFINED)
+			goto err;
+
+		if (orc->type == ORC_TYPE_END_OF_STACK)
+			goto end;
+	}
+
+	switch (orc->sp_reg) {
+	case ORC_REG_SP:
+		if (info->type == STACK_TYPE_IRQ && state->sp == info->end)
+			orc->type = ORC_TYPE_REGS;
+		else
+			state->sp = state->sp + orc->sp_offset;
+		break;
+	case ORC_REG_FP:
+		state->sp = state->fp;
+		break;
+	default:
+		orc_warn("unknown SP base reg %d at %pB\n", orc->sp_reg, (void *)state->pc);
+		goto err;
+	}
+
+	switch (orc->fp_reg) {
+	case ORC_REG_PREV_SP:
+		p = (unsigned long *)(state->sp + orc->fp_offset);
+		if (!stack_access_ok(state, (unsigned long)p, sizeof(unsigned long)))
+			goto err;
+
+		state->fp = *p;
+		break;
+	case ORC_REG_UNDEFINED:
+		/* Nothing. */
+		break;
+	default:
+		orc_warn("unknown FP base reg %d at %pB\n", orc->fp_reg, (void *)state->pc);
+		goto err;
+	}
+
+	switch (orc->type) {
+	case ORC_TYPE_CALL:
+		if (orc->ra_reg == ORC_REG_PREV_SP) {
+			p = (unsigned long *)(state->sp + orc->ra_offset);
+			if (!stack_access_ok(state, (unsigned long)p, sizeof(unsigned long)))
+				goto err;
+
+			pc = unwind_graph_addr(state, *p, state->sp);
+			pc -= LOONGARCH_INSN_SIZE;
+		} else if (orc->ra_reg == ORC_REG_UNDEFINED) {
+			if (!state->ra || state->ra == state->pc)
+				goto err;
+
+			pc = unwind_graph_addr(state, state->ra, state->sp);
+			pc -=  LOONGARCH_INSN_SIZE;
+			state->ra = 0;
+		} else {
+			orc_warn("unknown ra base reg %d at %pB\n", orc->ra_reg, (void *)state->pc);
+			goto err;
+		}
+		break;
+	case ORC_TYPE_REGS:
+		if (info->type == STACK_TYPE_IRQ && state->sp == info->end)
+			regs = (struct pt_regs *)info->next_sp;
+		else
+			regs = (struct pt_regs *)state->sp;
+
+		if (!stack_access_ok(state, (unsigned long)regs, sizeof(*regs)))
+			goto err;
+
+		if ((info->end == (unsigned long)regs + sizeof(*regs)) &&
+		    !regs->regs[3] && !regs->regs[1])
+			goto end;
+
+		if (user_mode(regs))
+			goto end;
+
+		pc = regs->csr_era;
+		if (!__kernel_text_address(pc))
+			goto err;
+
+		state->sp = regs->regs[3];
+		state->ra = regs->regs[1];
+		state->fp = regs->regs[22];
+		get_stack_info(state->sp, state->task, info);
+
+		break;
+	default:
+		orc_warn("unknown .orc_unwind entry type %d at %pB\n", orc->type, (void *)state->pc);
+		goto err;
+	}
+
+	state->pc = bt_address(pc);
+	if (!state->pc) {
+		pr_err("cannot find unwind pc at %pK\n", (void *)pc);
+		goto err;
+	}
+
+	if (!__kernel_text_address(state->pc))
+		goto err;
+
+	preempt_enable();
+	return true;
+
+err:
+	state->error = true;
+
+end:
+	preempt_enable();
+	state->stack_info.type = STACK_TYPE_UNKNOWN;
+	return false;
+}
+EXPORT_SYMBOL_GPL(unwind_next_frame);
diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S
index a5d0cd2035da04..e8e97dbf9ca40f 100644
--- a/arch/loongarch/kernel/vmlinux.lds.S
+++ b/arch/loongarch/kernel/vmlinux.lds.S
@@ -2,6 +2,7 @@
 #include <linux/sizes.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
+#include <asm/orc_lookup.h>
 
 #define PAGE_SIZE _PAGE_SIZE
 #define RO_EXCEPTION_TABLE_ALIGN	4
@@ -122,6 +123,8 @@ SECTIONS
 	}
 #endif
 
+	ORC_UNWIND_TABLE
+
 	.sdata : {
 		*(.sdata)
 	}
diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S
index ba976509bfe819..1fcc4b7eda32ae 100644
--- a/arch/loongarch/kvm/switch.S
+++ b/arch/loongarch/kvm/switch.S
@@ -8,7 +8,7 @@
 #include <asm/asmmacro.h>
 #include <asm/loongarch.h>
 #include <asm/regdef.h>
-#include <asm/stackframe.h>
+#include <asm/unwind_hints.h>
 
 #define HGPR_OFFSET(x)		(PT_R0 + 8*x)
 #define GGPR_OFFSET(x)		(KVM_ARCH_GGPR + 8*x)
@@ -112,6 +112,7 @@
 	.text
 	.cfi_sections	.debug_frame
 SYM_CODE_START(kvm_exc_entry)
+	UNWIND_HINT_UNDEFINED
 	csrwr	a2,   KVM_TEMP_KS
 	csrrd	a2,   KVM_VCPU_KS
 	addi.d	a2,   a2, KVM_VCPU_ARCH
@@ -279,3 +280,9 @@ SYM_FUNC_END(kvm_restore_lasx)
 	.section ".rodata"
 SYM_DATA(kvm_exception_size, .quad kvm_exc_entry_end - kvm_exc_entry)
 SYM_DATA(kvm_enter_guest_size, .quad kvm_enter_guest_end - kvm_enter_guest)
+
+#ifdef CONFIG_CPU_HAS_LBT
+STACK_FRAME_NON_STANDARD kvm_restore_fpu
+STACK_FRAME_NON_STANDARD kvm_restore_lsx
+STACK_FRAME_NON_STANDARD kvm_restore_lasx
+#endif
diff --git a/arch/loongarch/lib/clear_user.S b/arch/loongarch/lib/clear_user.S
index be741544e62bf6..7a0db643b2866c 100644
--- a/arch/loongarch/lib/clear_user.S
+++ b/arch/loongarch/lib/clear_user.S
@@ -10,6 +10,7 @@
 #include <asm/asm-extable.h>
 #include <asm/cpu.h>
 #include <asm/regdef.h>
+#include <asm/unwind_hints.h>
 
 SYM_FUNC_START(__clear_user)
 	/*
@@ -204,3 +205,5 @@ SYM_FUNC_START(__clear_user_fast)
 	_asm_extable 28b, .Lsmall_fixup
 	_asm_extable 29b, .Lexit
 SYM_FUNC_END(__clear_user_fast)
+
+STACK_FRAME_NON_STANDARD __clear_user_fast
diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S
index feec3d3628032f..095ce9181c6c04 100644
--- a/arch/loongarch/lib/copy_user.S
+++ b/arch/loongarch/lib/copy_user.S
@@ -10,6 +10,7 @@
 #include <asm/asm-extable.h>
 #include <asm/cpu.h>
 #include <asm/regdef.h>
+#include <asm/unwind_hints.h>
 
 SYM_FUNC_START(__copy_user)
 	/*
@@ -278,3 +279,5 @@ SYM_FUNC_START(__copy_user_fast)
 	_asm_extable 58b, .Lexit
 	_asm_extable 59b, .Lexit
 SYM_FUNC_END(__copy_user_fast)
+
+STACK_FRAME_NON_STANDARD __copy_user_fast
diff --git a/arch/loongarch/lib/memcpy.S b/arch/loongarch/lib/memcpy.S
index fa1148878d2b9d..9517a2f961af3d 100644
--- a/arch/loongarch/lib/memcpy.S
+++ b/arch/loongarch/lib/memcpy.S
@@ -9,6 +9,7 @@
 #include <asm/asmmacro.h>
 #include <asm/cpu.h>
 #include <asm/regdef.h>
+#include <asm/unwind_hints.h>
 
 .section .noinstr.text, "ax"
 
@@ -197,3 +198,5 @@ SYM_FUNC_START(__memcpy_fast)
 	jr	ra
 SYM_FUNC_END(__memcpy_fast)
 _ASM_NOKPROBE(__memcpy_fast)
+
+STACK_FRAME_NON_STANDARD __memcpy_small
diff --git a/arch/loongarch/lib/memset.S b/arch/loongarch/lib/memset.S
index 06d3ca54cbfe7d..df38466205531d 100644
--- a/arch/loongarch/lib/memset.S
+++ b/arch/loongarch/lib/memset.S
@@ -9,6 +9,7 @@
 #include <asm/asmmacro.h>
 #include <asm/cpu.h>
 #include <asm/regdef.h>
+#include <asm/unwind_hints.h>
 
 .macro fill_to_64 r0
 	bstrins.d \r0, \r0, 15, 8
@@ -166,3 +167,5 @@ SYM_FUNC_START(__memset_fast)
 	jr	ra
 SYM_FUNC_END(__memset_fast)
 _ASM_NOKPROBE(__memset_fast)
+
+STACK_FRAME_NON_STANDARD __memset_fast
diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c
index 0b95d32b30c947..5ac9beb5f0935e 100644
--- a/arch/loongarch/mm/tlb.c
+++ b/arch/loongarch/mm/tlb.c
@@ -9,8 +9,9 @@
 #include <linux/hugetlb.h>
 #include <linux/export.h>
 
-#include <asm/cpu.h>
 #include <asm/bootinfo.h>
+#include <asm/cpu.h>
+#include <asm/exception.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/tlb.h>
@@ -266,24 +267,20 @@ static void setup_tlb_handler(int cpu)
 	setup_ptwalker();
 	local_flush_tlb_all();
 
+	if (cpu_has_ptw) {
+		exception_table[EXCCODE_TLBI] = handle_tlb_load_ptw;
+		exception_table[EXCCODE_TLBL] = handle_tlb_load_ptw;
+		exception_table[EXCCODE_TLBS] = handle_tlb_store_ptw;
+		exception_table[EXCCODE_TLBM] = handle_tlb_modify_ptw;
+	}
+
 	/* The tlb handlers are generated only once */
 	if (cpu == 0) {
 		memcpy((void *)tlbrentry, handle_tlb_refill, 0x80);
 		local_flush_icache_range(tlbrentry, tlbrentry + 0x80);
-		if (!cpu_has_ptw) {
-			set_handler(EXCCODE_TLBI * VECSIZE, handle_tlb_load, VECSIZE);
-			set_handler(EXCCODE_TLBL * VECSIZE, handle_tlb_load, VECSIZE);
-			set_handler(EXCCODE_TLBS * VECSIZE, handle_tlb_store, VECSIZE);
-			set_handler(EXCCODE_TLBM * VECSIZE, handle_tlb_modify, VECSIZE);
-		} else {
-			set_handler(EXCCODE_TLBI * VECSIZE, handle_tlb_load_ptw, VECSIZE);
-			set_handler(EXCCODE_TLBL * VECSIZE, handle_tlb_load_ptw, VECSIZE);
-			set_handler(EXCCODE_TLBS * VECSIZE, handle_tlb_store_ptw, VECSIZE);
-			set_handler(EXCCODE_TLBM * VECSIZE, handle_tlb_modify_ptw, VECSIZE);
-		}
-		set_handler(EXCCODE_TLBNR * VECSIZE, handle_tlb_protect, VECSIZE);
-		set_handler(EXCCODE_TLBNX * VECSIZE, handle_tlb_protect, VECSIZE);
-		set_handler(EXCCODE_TLBPE * VECSIZE, handle_tlb_protect, VECSIZE);
+
+		for (int i = EXCCODE_TLBL; i <= EXCCODE_TLBPE; i++)
+			set_handler(i * VECSIZE, exception_table[i], VECSIZE);
 	} else {
 		int vec_sz __maybe_unused;
 		void *addr __maybe_unused;
diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S
index d5d682f3d29f3a..a44387b838af61 100644
--- a/arch/loongarch/mm/tlbex.S
+++ b/arch/loongarch/mm/tlbex.S
@@ -18,6 +18,7 @@
 
 	.macro tlb_do_page_fault, write
 	SYM_CODE_START(tlb_do_page_fault_\write)
+	UNWIND_HINT_UNDEFINED
 	SAVE_ALL
 	csrrd		a2, LOONGARCH_CSR_BADV
 	move		a0, sp
@@ -32,6 +33,7 @@
 	tlb_do_page_fault 1
 
 SYM_CODE_START(handle_tlb_protect)
+	UNWIND_HINT_UNDEFINED
 	BACKUP_T0T1
 	SAVE_ALL
 	move		a0, sp
@@ -44,6 +46,7 @@ SYM_CODE_START(handle_tlb_protect)
 SYM_CODE_END(handle_tlb_protect)
 
 SYM_CODE_START(handle_tlb_load)
+	UNWIND_HINT_UNDEFINED
 	csrwr		t0, EXCEPTION_KS0
 	csrwr		t1, EXCEPTION_KS1
 	csrwr		ra, EXCEPTION_KS2
@@ -190,6 +193,7 @@ nopage_tlb_load:
 SYM_CODE_END(handle_tlb_load)
 
 SYM_CODE_START(handle_tlb_load_ptw)
+	UNWIND_HINT_UNDEFINED
 	csrwr		t0, LOONGARCH_CSR_KS0
 	csrwr		t1, LOONGARCH_CSR_KS1
 	la_abs		t0, tlb_do_page_fault_0
@@ -197,6 +201,7 @@ SYM_CODE_START(handle_tlb_load_ptw)
 SYM_CODE_END(handle_tlb_load_ptw)
 
 SYM_CODE_START(handle_tlb_store)
+	UNWIND_HINT_UNDEFINED
 	csrwr		t0, EXCEPTION_KS0
 	csrwr		t1, EXCEPTION_KS1
 	csrwr		ra, EXCEPTION_KS2
@@ -346,6 +351,7 @@ nopage_tlb_store:
 SYM_CODE_END(handle_tlb_store)
 
 SYM_CODE_START(handle_tlb_store_ptw)
+	UNWIND_HINT_UNDEFINED
 	csrwr		t0, LOONGARCH_CSR_KS0
 	csrwr		t1, LOONGARCH_CSR_KS1
 	la_abs		t0, tlb_do_page_fault_1
@@ -353,6 +359,7 @@ SYM_CODE_START(handle_tlb_store_ptw)
 SYM_CODE_END(handle_tlb_store_ptw)
 
 SYM_CODE_START(handle_tlb_modify)
+	UNWIND_HINT_UNDEFINED
 	csrwr		t0, EXCEPTION_KS0
 	csrwr		t1, EXCEPTION_KS1
 	csrwr		ra, EXCEPTION_KS2
@@ -500,6 +507,7 @@ nopage_tlb_modify:
 SYM_CODE_END(handle_tlb_modify)
 
 SYM_CODE_START(handle_tlb_modify_ptw)
+	UNWIND_HINT_UNDEFINED
 	csrwr		t0, LOONGARCH_CSR_KS0
 	csrwr		t1, LOONGARCH_CSR_KS1
 	la_abs		t0, tlb_do_page_fault_1
@@ -507,6 +515,7 @@ SYM_CODE_START(handle_tlb_modify_ptw)
 SYM_CODE_END(handle_tlb_modify_ptw)
 
 SYM_CODE_START(handle_tlb_refill)
+	UNWIND_HINT_UNDEFINED
 	csrwr		t0, LOONGARCH_CSR_TLBRSAVE
 	csrrd		t0, LOONGARCH_CSR_PGD
 	lddir		t0, t0, 3
diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
index f597cd08a96be0..75c6726382c34f 100644
--- a/arch/loongarch/vdso/Makefile
+++ b/arch/loongarch/vdso/Makefile
@@ -4,6 +4,7 @@
 KASAN_SANITIZE := n
 UBSAN_SANITIZE := n
 KCOV_INSTRUMENT := n
+OBJECT_FILES_NON_STANDARD := y
 
 # Include the generic Makefile to check the built vdso.
 include $(srctree)/lib/vdso/Makefile
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index bb1339c7057b49..39f2d4a05208db 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -116,6 +116,14 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
  */
 #define __stringify_label(n) #n
 
+#define __annotate_reachable(c) ({					\
+	asm volatile(__stringify_label(c) ":\n\t"			\
+			".pushsection .discard.reachable\n\t"		\
+			".long " __stringify_label(c) "b - .\n\t"	\
+			".popsection\n\t");				\
+})
+#define annotate_reachable() __annotate_reachable(__COUNTER__)
+
 #define __annotate_unreachable(c) ({					\
 	asm volatile(__stringify_label(c) ":\n\t"			\
 		     ".pushsection .discard.unreachable\n\t"		\
@@ -128,6 +136,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 #define __annotate_jump_table __section(".rodata..c_jump_table")
 
 #else /* !CONFIG_OBJTOOL */
+#define annotate_reachable()
 #define annotate_unreachable()
 #define __annotate_jump_table
 #endif /* CONFIG_OBJTOOL */
diff --git a/scripts/Makefile b/scripts/Makefile
index 576cf64be6677c..e4cca53d22858b 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -31,9 +31,12 @@ HOSTLDLIBS_sign-file = $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null |
 
 ifdef CONFIG_UNWINDER_ORC
 ifeq ($(ARCH),x86_64)
-ARCH := x86
+SRCARCH := x86
 endif
-HOSTCFLAGS_sorttable.o += -I$(srctree)/tools/arch/x86/include
+ifeq ($(ARCH),loongarch)
+SRCARCH := loongarch
+endif
+HOSTCFLAGS_sorttable.o += -I$(srctree)/tools/arch/$(SRCARCH)/include
 HOSTCFLAGS_sorttable.o += -DUNWINDER_ORC_ENABLED
 endif
 
-- 
cgit 1.2.3-korg


From 199cc14cb4f1cb8668be45f67af41755ed5f0175 Mon Sep 17 00:00:00 2001
From: Jinyang He <hejinyang@loongson.cn>
Date: Mon, 11 Mar 2024 22:23:47 +0800
Subject: LoongArch: Add kernel livepatching support

The arch-specified function ftrace_regs_set_instruction_pointer() has
been implemented in arch/loongarch/include/asm/ftrace.h, so here only
implement arch_stack_walk_reliable() function.

Here are the test logs:

[root@linux fedora]# cat /proc/cmdline
BOOT_IMAGE=/vmlinuz-6.8.0-rc2 root=/dev/sda3

[root@linux fedora]# modprobe livepatch-sample
[root@linux fedora]# cat /proc/cmdline
this has been live patched

[root@linux fedora]# echo 0 > /sys/kernel/livepatch/livepatch_sample/enabled
[root@linux fedora]# rmmod livepatch_sample
[root@linux fedora]# cat /proc/cmdline
BOOT_IMAGE=/vmlinuz-6.8.0-rc2 root=/dev/sda3

[root@linux fedora]# dmesg -t | tail -5
livepatch: enabling patch 'livepatch_sample'
livepatch: 'livepatch_sample': starting patching transition
livepatch: 'livepatch_sample': patching complete
livepatch: 'livepatch_sample': starting unpatching transition
livepatch: 'livepatch_sample': unpatching complete

Signed-off-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Kconfig                   |  4 ++++
 arch/loongarch/include/asm/thread_info.h |  2 ++
 arch/loongarch/kernel/stacktrace.c       | 40 ++++++++++++++++++++++++++++++++
 3 files changed, 46 insertions(+)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 8d6725115ac6bd..99a0a15ce5f7c0 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -134,6 +134,7 @@ config LOONGARCH
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_KRETPROBES
 	select HAVE_KVM
+	select HAVE_LIVEPATCH
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
 	select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS
@@ -143,6 +144,7 @@ config LOONGARCH
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_PREEMPT_DYNAMIC_KEY
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_RELIABLE_STACKTRACE if UNWINDER_ORC
 	select HAVE_RETHOOK
 	select HAVE_RSEQ
 	select HAVE_RUST
@@ -636,6 +638,8 @@ config RANDOMIZE_BASE_MAX_OFFSET
 
 	  This is limited by the size of the lower address memory, 256MB.
 
+source "kernel/livepatch/Kconfig"
+
 endmenu
 
 config ARCH_SELECT_MEMORY_MODEL
diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h
index 8cb653d49a5434..8bf0e6f5154668 100644
--- a/arch/loongarch/include/asm/thread_info.h
+++ b/arch/loongarch/include/asm/thread_info.h
@@ -86,6 +86,7 @@ register unsigned long current_stack_pointer __asm__("$sp");
 #define TIF_LASX_CTX_LIVE	18	/* LASX context must be preserved */
 #define TIF_USEDLBT		19	/* LBT was used by this task this quantum (SMP) */
 #define TIF_LBT_CTX_LIVE	20	/* LBT context must be preserved */
+#define TIF_PATCH_PENDING	21	/* pending live patching update */
 
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
@@ -105,6 +106,7 @@ register unsigned long current_stack_pointer __asm__("$sp");
 #define _TIF_LASX_CTX_LIVE	(1<<TIF_LASX_CTX_LIVE)
 #define _TIF_USEDLBT		(1<<TIF_USEDLBT)
 #define _TIF_LBT_CTX_LIVE	(1<<TIF_LBT_CTX_LIVE)
+#define _TIF_PATCH_PENDING	(1<<TIF_PATCH_PENDING)
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/loongarch/kernel/stacktrace.c b/arch/loongarch/kernel/stacktrace.c
index eaec82e02c92ab..9a038d1070d73b 100644
--- a/arch/loongarch/kernel/stacktrace.c
+++ b/arch/loongarch/kernel/stacktrace.c
@@ -40,6 +40,46 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
 	}
 }
 
+int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
+			     void *cookie, struct task_struct *task)
+{
+	unsigned long addr;
+	struct pt_regs dummyregs;
+	struct pt_regs *regs = &dummyregs;
+	struct unwind_state state;
+
+	if (task == current) {
+		regs->regs[3] = (unsigned long)__builtin_frame_address(0);
+		regs->csr_era = (unsigned long)__builtin_return_address(0);
+	} else {
+		regs->regs[3] = thread_saved_fp(task);
+		regs->csr_era = thread_saved_ra(task);
+	}
+	regs->regs[1] = 0;
+	regs->regs[22] = 0;
+
+	for (unwind_start(&state, task, regs);
+	     !unwind_done(&state) && !unwind_error(&state); unwind_next_frame(&state)) {
+		addr = unwind_get_return_address(&state);
+
+		/*
+		 * A NULL or invalid return address probably means there's some
+		 * generated code which __kernel_text_address() doesn't know about.
+		 */
+		if (!addr)
+			return -EINVAL;
+
+		if (!consume_entry(cookie, addr))
+			return -EINVAL;
+	}
+
+	/* Check for stack corruption */
+	if (unwind_error(&state))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int
 copy_stack_frame(unsigned long fp, struct stack_frame *frame)
 {
-- 
cgit 1.2.3-korg


From 8b5db5e5337ecb0a7954c39020861867a85b6206 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 19 Mar 2024 15:50:27 +0800
Subject: LoongArch: Select ARCH_HAS_CURRENT_STACK_POINTER in Kconfig

LoongArch has implemented the current_stack_pointer macro, so select
ARCH_HAS_CURRENT_STACK_POINTER in Kconfig. This will let it be used in
non-arch places (like HARDENED_USERCOPY).

Reviewed-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 99a0a15ce5f7c0..6df2b421895a14 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -15,6 +15,7 @@ config LOONGARCH
 	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
 	select ARCH_HAS_CPU_FINALIZE_INIT
+	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
-- 
cgit 1.2.3-korg


From f48ad26e5e57016b447461f22ecf7c3ed8337353 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 19 Mar 2024 15:50:34 +0800
Subject: LoongArch: Select HAVE_ARCH_USERFAULTFD_MINOR in Kconfig

This allocates the VM flag needed to support the userfaultfd minor fault
functionality. See commit 7677f7fd8be7665 ("userfaultfd: add minor fault
registration mode") for more information.

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 6df2b421895a14..526a88598fbfc5 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -105,6 +105,7 @@ config LOONGARCH
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select HAVE_ARCH_USERFAULTFD_MINOR if USERFAULTFD
 	select HAVE_ASM_MODVERSIONS
 	select HAVE_CONTEXT_TRACKING_USER
 	select HAVE_C_RECORDMCOUNT
-- 
cgit 1.2.3-korg


From c87e12e0e8c1241410e758e181ca6bf23efa5b5b Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 19 Mar 2024 15:50:34 +0800
Subject: LoongArch: Change __my_cpu_offset definition to avoid
 mis-optimization

From GCC commit 3f13154553f8546a ("df-scan: remove ad-hoc handling of
global regs in asms"), global registers will no longer be forced to add
to the def-use chain. Then current_thread_info(), current_stack_pointer
and __my_cpu_offset may be lifted out of the loop because they are no
longer treated as "volatile variables".

This optimization is still correct for the current_thread_info() and
current_stack_pointer usages because they are associated to a thread.
However it is wrong for __my_cpu_offset because it is associated to a
CPU rather than a thread: if the thread migrates to a different CPU in
the loop, __my_cpu_offset should be changed.

Change __my_cpu_offset definition to treat it as a "volatile variable",
in order to avoid such a mis-optimization.

Cc: stable@vger.kernel.org
Reported-by: Xiaotian Wu <wuxiaotian@loongson.cn>
Reported-by: Miao Wang <shankerwangmiao@gmail.com>
Signed-off-by: Xing Li <lixing@loongson.cn>
Signed-off-by: Hongchen Zhang <zhanghongchen@loongson.cn>
Signed-off-by: Rui Wang <wangrui@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/percpu.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h
index 9b36ac003f8907..8f290e5546cf72 100644
--- a/arch/loongarch/include/asm/percpu.h
+++ b/arch/loongarch/include/asm/percpu.h
@@ -29,7 +29,12 @@ static inline void set_my_cpu_offset(unsigned long off)
 	__my_cpu_offset = off;
 	csr_write64(off, PERCPU_BASE_KS);
 }
-#define __my_cpu_offset __my_cpu_offset
+
+#define __my_cpu_offset					\
+({							\
+	__asm__ __volatile__("":"+r"(__my_cpu_offset));	\
+	__my_cpu_offset;				\
+})
 
 #define PERCPU_OP(op, asm_op, c_op)					\
 static __always_inline unsigned long __percpu_##op(void *ptr,		\
-- 
cgit 1.2.3-korg


From d42ab9af605ee406ec339e5e80a1c3a708637fd6 Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Tue, 19 Mar 2024 15:50:34 +0800
Subject: LoongArch: Move {dmw,tlb}_virt_to_page() definition to page.h

These two functions are implemented in pgtable.c, and they are needed
only by the virt_to_page() macro in page.h. Having the prototypes in
pgtable.h causes a circular dependency between page.h and pgtable.h,
because the virt_to_page() macro in page.h needs pgtable.h for these
two functions, while pgtable.h needs various definitions from page.h
(e.g. pte_t and pgt_t).

Let's avoid this circular dependency by moving the function prototypes
to page.h.

Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/page.h    | 3 +++
 arch/loongarch/include/asm/pgtable.h | 3 ---
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h
index 63f137ce82a41f..2391fcd189087a 100644
--- a/arch/loongarch/include/asm/page.h
+++ b/arch/loongarch/include/asm/page.h
@@ -83,6 +83,9 @@ typedef struct { unsigned long pgprot; } pgprot_t;
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
 #define sym_to_pfn(x)		__phys_to_pfn(__pa_symbol(x))
 
+struct page *dmw_virt_to_page(unsigned long kaddr);
+struct page *tlb_virt_to_page(unsigned long kaddr);
+
 #define virt_to_pfn(kaddr)	PFN_DOWN(PHYSADDR(kaddr))
 
 #define virt_to_page(kaddr)								\
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 8b5df1bbf9e9c2..af3acdf3481a6a 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -363,9 +363,6 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
 extern pgd_t swapper_pg_dir[];
 extern pgd_t invalid_pg_dir[];
 
-struct page *dmw_virt_to_page(unsigned long kaddr);
-struct page *tlb_virt_to_page(unsigned long kaddr);
-
 /*
  * The following only work if pte_present() is true.
  * Undefined behaviour if not..
-- 
cgit 1.2.3-korg


From 82bf60a6fed806d57e284a1fb40dbc1ad5097611 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 19 Mar 2024 15:50:34 +0800
Subject: LoongArch: Remove superfluous flush_dcache_page() definition

LoongArch doesn't have cache aliases, so flush_dcache_page() is a no-op.
There is a generic implementation for this case in include/asm-generic/
cacheflush.h. So remove the superfluous flush_dcache_page() definition,
which also silences such build warnings:

   In file included from crypto/scompress.c:12:
   include/crypto/scatterwalk.h: In function 'scatterwalk_pagedone':
   include/crypto/scatterwalk.h:76:30: warning: variable 'page' set but not used [-Wunused-but-set-variable]
      76 |                 struct page *page;
         |                              ^~~~
   crypto/scompress.c: In function 'scomp_acomp_comp_decomp':
>> crypto/scompress.c:174:38: warning: unused variable 'dst_page' [-Wunused-variable]
     174 |                         struct page *dst_page = sg_page(req->dst);
         |

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202403091614.NeUw5zcv-lkp@intel.com/
Suggested-by: Barry Song <baohua@kernel.org>
Acked-by: Barry Song <baohua@kernel.org>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/cacheflush.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/arch/loongarch/include/asm/cacheflush.h b/arch/loongarch/include/asm/cacheflush.h
index 80bd74106985a9..f8754d08a31ab0 100644
--- a/arch/loongarch/include/asm/cacheflush.h
+++ b/arch/loongarch/include/asm/cacheflush.h
@@ -37,8 +37,6 @@ void local_flush_icache_range(unsigned long start, unsigned long end);
 #define flush_icache_range	local_flush_icache_range
 #define flush_icache_user_range	local_flush_icache_range
 
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-
 #define flush_cache_all()				do { } while (0)
 #define flush_cache_mm(mm)				do { } while (0)
 #define flush_cache_dup_mm(mm)				do { } while (0)
@@ -47,7 +45,6 @@ void local_flush_icache_range(unsigned long start, unsigned long end);
 #define flush_cache_vmap(start, end)			do { } while (0)
 #define flush_cache_vunmap(start, end)			do { } while (0)
 #define flush_icache_user_page(vma, page, addr, len)	do { } while (0)
-#define flush_dcache_page(page)				do { } while (0)
 #define flush_dcache_mmap_lock(mapping)			do { } while (0)
 #define flush_dcache_mmap_unlock(mapping)		do { } while (0)
 
-- 
cgit 1.2.3-korg


From 9c68ece8b2a5c5ff9b2fcaea923dd73efeb174cd Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 19 Mar 2024 15:50:34 +0800
Subject: LoongArch: Define the __io_aw() hook as mmiowb()

Commit fb24ea52f78e0d595852e ("drivers: Remove explicit invocations of
mmiowb()") remove all mmiowb() in drivers, but it says:

"NOTE: mmiowb() has only ever guaranteed ordering in conjunction with
spin_unlock(). However, pairing each mmiowb() removal in this patch with
the corresponding call to spin_unlock() is not at all trivial, so there
is a small chance that this change may regress any drivers incorrectly
relying on mmiowb() to order MMIO writes between CPUs using lock-free
synchronisation."

The mmio in radeon_ring_commit() is protected by a mutex rather than a
spinlock, but in the mutex fastpath it behaves similar to spinlock. We
can add mmiowb() calls in the radeon driver but the maintainer says he
doesn't like such a workaround, and radeon is not the only example of
mutex protected mmio.

So we should extend the mmiowb tracking system from spinlock to mutex,
and maybe other locking primitives. This is not easy and error prone, so
we solve it in the architectural code, by simply defining the __io_aw()
hook as mmiowb(). And we no longer need to override queued_spin_unlock()
so use the generic definition.

Without this, we get such an error when run 'glxgears' on weak ordering
architectures such as LoongArch:

radeon 0000:04:00.0: ring 0 stalled for more than 10324msec
radeon 0000:04:00.0: ring 3 stalled for more than 10240msec
radeon 0000:04:00.0: GPU lockup (current fence id 0x000000000001f412 last fence id 0x000000000001f414 on ring 3)
radeon 0000:04:00.0: GPU lockup (current fence id 0x000000000000f940 last fence id 0x000000000000f941 on ring 0)
radeon 0000:04:00.0: scheduling IB failed (-35).
[drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35)
radeon 0000:04:00.0: scheduling IB failed (-35).
[drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35)
radeon 0000:04:00.0: scheduling IB failed (-35).
[drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35)
radeon 0000:04:00.0: scheduling IB failed (-35).
[drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35)
radeon 0000:04:00.0: scheduling IB failed (-35).
[drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35)
radeon 0000:04:00.0: scheduling IB failed (-35).
[drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35)
radeon 0000:04:00.0: scheduling IB failed (-35).
[drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35)

Link: https://lore.kernel.org/dri-devel/29df7e26-d7a8-4f67-b988-44353c4270ac@amd.com/T/#t
Link: https://lore.kernel.org/linux-arch/20240301130532.3953167-1-chenhuacai@loongson.cn/T/#t
Cc: stable@vger.kernel.org
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/Kbuild      |  1 +
 arch/loongarch/include/asm/io.h        |  2 ++
 arch/loongarch/include/asm/qspinlock.h | 18 ------------------
 3 files changed, 3 insertions(+), 18 deletions(-)
 delete mode 100644 arch/loongarch/include/asm/qspinlock.h

diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild
index a97c0edbb866a6..2dbec7853ae864 100644
--- a/arch/loongarch/include/asm/Kbuild
+++ b/arch/loongarch/include/asm/Kbuild
@@ -6,6 +6,7 @@ generic-y += mcs_spinlock.h
 generic-y += parport.h
 generic-y += early_ioremap.h
 generic-y += qrwlock.h
+generic-y += qspinlock.h
 generic-y += rwsem.h
 generic-y += segment.h
 generic-y += user.h
diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h
index c486c2341b6623..4a8adcca329b81 100644
--- a/arch/loongarch/include/asm/io.h
+++ b/arch/loongarch/include/asm/io.h
@@ -71,6 +71,8 @@ extern void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t
 #define memcpy_fromio(a, c, l) __memcpy_fromio((a), (c), (l))
 #define memcpy_toio(c, a, l)   __memcpy_toio((c), (a), (l))
 
+#define __io_aw() mmiowb()
+
 #include <asm-generic/io.h>
 
 #define ARCH_HAS_VALID_PHYS_ADDR_RANGE
diff --git a/arch/loongarch/include/asm/qspinlock.h b/arch/loongarch/include/asm/qspinlock.h
deleted file mode 100644
index 34f43f8ad5912b..00000000000000
--- a/arch/loongarch/include/asm/qspinlock.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_QSPINLOCK_H
-#define _ASM_QSPINLOCK_H
-
-#include <asm-generic/qspinlock_types.h>
-
-#define queued_spin_unlock queued_spin_unlock
-
-static inline void queued_spin_unlock(struct qspinlock *lock)
-{
-	compiletime_assert_atomic_type(lock->locked);
-	c_sync();
-	WRITE_ONCE(lock->locked, 0);
-}
-
-#include <asm-generic/qspinlock.h>
-
-#endif /* _ASM_QSPINLOCK_H */
-- 
cgit 1.2.3-korg


From fea1c949f6ca5059e12de00d0483645debc5b206 Mon Sep 17 00:00:00 2001
From: Yuli Wang <wangyuli@uniontech.com>
Date: Tue, 19 Mar 2024 15:50:34 +0800
Subject: LoongArch/crypto: Clean up useless assignment operations

The LoongArch CRC32 hw acceleration is based on arch/mips/crypto/
crc32-mips.c. While the MIPS code supports both MIPS32 and MIPS64,
but LoongArch32 lacks the CRC instruction. As a result, the line
"len -= sizeof(u32)" is unnecessary.

Removing it can make context code style more unified and improve
code readability.

Cc: stable@vger.kernel.org
Reviewed-by: WANG Xuerui <git@xen0n.name>
Suggested-by: Wentao Guan <guanwentao@uniontech.com>
Signed-off-by: Yuli Wang <wangyuli@uniontech.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/crypto/crc32-loongarch.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/loongarch/crypto/crc32-loongarch.c b/arch/loongarch/crypto/crc32-loongarch.c
index a49e507af38c0e..3eebea3a7b478d 100644
--- a/arch/loongarch/crypto/crc32-loongarch.c
+++ b/arch/loongarch/crypto/crc32-loongarch.c
@@ -44,7 +44,6 @@ static u32 crc32_loongarch_hw(u32 crc_, const u8 *p, unsigned int len)
 
 		CRC32(crc, value, w);
 		p += sizeof(u32);
-		len -= sizeof(u32);
 	}
 
 	if (len & sizeof(u16)) {
@@ -80,7 +79,6 @@ static u32 crc32c_loongarch_hw(u32 crc_, const u8 *p, unsigned int len)
 
 		CRC32C(crc, value, w);
 		p += sizeof(u32);
-		len -= sizeof(u32);
 	}
 
 	if (len & sizeof(u16)) {
-- 
cgit 1.2.3-korg