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

@@ -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

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

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)

arch/loongarch/include/asm/Kbuild

 # 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

arch/loongarch/include/asm/bug.h

@@ -44,6 +44,7 @@
 do {								\
 	instrumentation_begin();				\
 	__BUG_FLAGS(BUGFLAG_WARNING|(flags));			\
+	annotate_reachable();					\
 	instrumentation_end();					\
 } while (0)
 

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);

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;
 };

arch/loongarch/include/asm/orc_header.h

+/* 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 */

arch/loongarch/include/asm/orc_lookup.h

+/* 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 */

arch/loongarch/include/asm/orc_types.h

+/* 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 */

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
 

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 */

arch/loongarch/include/asm/unwind_hints.h

+/* 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 */

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

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

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

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)

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

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 */

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;
 }

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)

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
 

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();

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);

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();
 

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)
 	}

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

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

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

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

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

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;

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

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

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 */

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