@@ -8,6 +8,7 @@
 
 #include <uapi/asm/ptrace.h>
 #include <asm/csr.h>
+#include <asm/stacktrace/frame.h>
 #include <linux/compiler.h>
 
 #ifndef __ASSEMBLER__

@@ -53,6 +54,14 @@ struct pt_regs {
 	unsigned long cause;
 	/* a0 value before the syscall */
 	unsigned long orig_a0;
+
+	/*
+	 * This frame record is entirely zeroed on exception entry, allowing the
+	 * unwinder to identify exception boundaries. The type field encodes
+	 * whether the exception was taken from user (FINAL) or kernel (PT_REGS)
+	 * mode.
+	 */
+	struct frame_record_meta stackframe;
 };
 
 #define PTRACE_SYSEMU			0x1f

@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_RISCV_STACKTRACE_FRAME_H
+#define __ASM_RISCV_STACKTRACE_FRAME_H
+
+/*
+ * See: arch/arm64/include/asm/stacktrace/frame.h for the reference
+ * implementation.
+ */
+
+/*
+ * - FRAME_META_TYPE_NONE
+ *
+ *   This value is reserved.
+ *
+ * - FRAME_META_TYPE_FINAL
+ *
+ *   The record is the last entry on the stack.
+ *   Unwinding should terminate successfully.
+ *
+ * - FRAME_META_TYPE_PT_REGS
+ *
+ *   The record is embedded within a struct pt_regs, recording the registers at
+ *   an arbitrary point in time.
+ *   Unwinding should consume pt_regs::epc, followed by pt_regs::ra.
+ *
+ * Note: all other values are reserved and should result in unwinding
+ * terminating with an error.
+ */
+#define FRAME_META_TYPE_NONE		0
+#define FRAME_META_TYPE_FINAL		1
+#define FRAME_META_TYPE_PT_REGS		2
+
+#ifndef __ASSEMBLER__
+/*
+ * A standard RISC-V frame record.
+ */
+struct frame_record {
+	unsigned long fp;
+	unsigned long ra;
+};
+
+/*
+ * A metadata frame record indicating a special unwind.
+ * The record::{fp,ra} fields must be zero to indicate the presence of
+ * metadata.
+ */
+struct frame_record_meta {
+	struct frame_record record;
+	unsigned long type;
+};
+#endif /* __ASSEMBLER__ */
+
+#endif /* __ASM_RISCV_STACKTRACE_FRAME_H */

@@ -131,6 +131,9 @@ void asm_offsets(void)
 	OFFSET(PT_BADADDR, pt_regs, badaddr);
 	OFFSET(PT_CAUSE, pt_regs, cause);
 
+	DEFINE(S_STACKFRAME,		offsetof(struct pt_regs, stackframe));
+	DEFINE(S_STACKFRAME_TYPE,	offsetof(struct pt_regs, stackframe.type));
+
 	OFFSET(SUSPEND_CONTEXT_REGS, suspend_context, regs);
 
 	OFFSET(HIBERN_PBE_ADDR, pbe, address);

@@ -501,6 +504,7 @@ void asm_offsets(void)
 	OFFSET(SBI_HART_BOOT_STACK_PTR_OFFSET, sbi_hart_boot_data, stack_ptr);
 
 	DEFINE(STACKFRAME_SIZE_ON_STACK, ALIGN(sizeof(struct stackframe), STACK_ALIGN));
+	DEFINE(STACKFRAME_RECORD_SIZE, sizeof(struct stackframe));
 	OFFSET(STACKFRAME_FP, stackframe, fp);
 	OFFSET(STACKFRAME_RA, stackframe, ra);
 #ifdef CONFIG_FUNCTION_TRACER

@@ -11,6 +11,7 @@
 #include <asm/asm.h>
 #include <asm/csr.h>
 #include <asm/scs.h>
+#include <asm/stacktrace/frame.h>
 #include <asm/unistd.h>
 #include <asm/page.h>
 #include <asm/thread_info.h>

@@ -193,6 +194,27 @@ SYM_CODE_START(handle_exception)
 	REG_S s4, PT_CAUSE(sp)
 	REG_S s5, PT_TP(sp)
 
+	/*
+	 * Create a metadata frame record. The unwinder will use this to
+	 * identify and unwind exception boundaries.
+	 */
+	REG_S zero, (S_STACKFRAME + STACKFRAME_FP)(sp) /* stackframe.record.fp = 0 */
+	REG_S zero, (S_STACKFRAME + STACKFRAME_RA)(sp) /* stackframe.record.ra = 0 */
+#ifdef CONFIG_RISCV_M_MODE
+	li t0, SR_MPP
+	and t0, s1, t0
+#else
+	andi t0, s1, SR_SPP
+#endif
+	bnez t0, 1f
+	li t0, FRAME_META_TYPE_FINAL
+	j 2f
+1:
+	li t0, FRAME_META_TYPE_PT_REGS
+2:
+	REG_S t0, S_STACKFRAME_TYPE(sp)
+	addi s0, sp, S_STACKFRAME + STACKFRAME_RECORD_SIZE
+
 	/*
 	 * Set the scratch register to 0, so that if a recursive exception
 	 * occurs, the exception vector knows it came from the kernel

@@ -357,8 +379,8 @@ ASM_NOKPROBE(handle_kernel_stack_overflow)
 
 SYM_CODE_START(ret_from_fork_kernel_asm)
 	call schedule_tail
-	move a0, s1 /* fn_arg */
-	move a1, s0 /* fn */
+	move a0, s3 /* fn_arg */
+	move a1, s2 /* fn */
 	move a2, sp /* pt_regs */
 	call ret_from_fork_kernel
 	j ret_from_exception

@@ -383,7 +405,7 @@ SYM_FUNC_START(call_on_irq_stack)
 	addi	sp, sp, -STACKFRAME_SIZE_ON_STACK
 	REG_S	ra, STACKFRAME_RA(sp)
 	REG_S	s0, STACKFRAME_FP(sp)
-	addi	s0, sp, STACKFRAME_SIZE_ON_STACK
+	addi	s0, sp, STACKFRAME_RECORD_SIZE
 
 	/* Switch to the per-CPU shadow call stack */
 	scs_save_current

@@ -399,7 +421,7 @@ SYM_FUNC_START(call_on_irq_stack)
 	scs_load_current
 
 	/* Switch back to the thread stack and restore ra and s0 */
-	addi	sp, s0, -STACKFRAME_SIZE_ON_STACK
+	addi	sp, s0, -STACKFRAME_RECORD_SIZE
 	REG_L	ra, STACKFRAME_RA(sp)
 	REG_L	s0, STACKFRAME_FP(sp)
 	addi	sp, sp, STACKFRAME_SIZE_ON_STACK

@@ -14,6 +14,7 @@
 #include <asm/hwcap.h>
 #include <asm/image.h>
 #include <asm/scs.h>
+#include <asm/stacktrace/frame.h>
 #include <asm/usercfi.h>
 #include "efi-header.S"
 

@@ -177,6 +178,14 @@ secondary_start_sbi:
 	REG_S a0, (a1)
 1:
 #endif
+
+	/*
+	 * Set up the frame pointer for the secondary idle task so reliable
+	 * stack unwinding terminates at the metadata frame in task_pt_regs().
+	 * Without this, the first frame records can inherit an undefined caller
+	 * fp and unwind past smp_callin() into .Lsecondary_park.
+	 */
+	addi s0, sp, S_STACKFRAME + STACKFRAME_RECORD_SIZE
 	scs_load_current
 	call smp_callin
 #endif /* CONFIG_SMP */

@@ -305,6 +314,20 @@ SYM_CODE_START(_start_kernel)
 	la tp, init_task
 	la sp, init_thread_union + THREAD_SIZE
 	addi sp, sp, -PT_SIZE_ON_STACK
+
+	/*
+	 * Set up a metadata frame record for the init task so that
+	 * the unwinder can identify the outermost frame by its
+	 * {fp, ra} = {0, 0} sentinel at the bottom of pt_regs.
+	 * fp/s0 points above the metadata record (RISC-V
+	 * convention).
+	 */
+	REG_S zero, (S_STACKFRAME + STACKFRAME_FP)(sp)
+	REG_S zero, (S_STACKFRAME + STACKFRAME_RA)(sp)
+	li t0, FRAME_META_TYPE_FINAL
+	REG_S t0, S_STACKFRAME_TYPE(sp)
+	addi s0, sp, S_STACKFRAME + STACKFRAME_RECORD_SIZE
+
 #if defined(CONFIG_RISCV_SBI) && defined(CONFIG_RISCV_USER_CFI)
 	li a7, SBI_EXT_FWFT
 	li a6, SBI_EXT_FWFT_SET

@@ -258,8 +258,23 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		/* Supervisor/Machine, irqs on: */
 		childregs->status = SR_PP | SR_PIE;
 
-		p->thread.s[0] = (unsigned long)args->fn;
-		p->thread.s[1] = (unsigned long)args->fn_arg;
+		/*
+		 * Set up a metadata frame record at the bottom of the
+		 * stack for the unwinder. Use FRAME_META_TYPE_FINAL
+		 * since this is the outermost kernel entry for the new
+		 * task. The frame_record::{fp,ra} are already zero from
+		 * memset().
+		 *
+		 * fp/s0 points above the metadata record (RISC-V
+		 * convention). fn and fn_arg are passed via s2/s3,
+		 * keeping s0 available for the frame pointer chain.
+		 */
+		childregs->stackframe.type = FRAME_META_TYPE_FINAL;
+
+		p->thread.s[0] = (unsigned long)(&childregs->stackframe)
+				+ sizeof(struct frame_record);
+		p->thread.s[2] = (unsigned long)args->fn;
+		p->thread.s[3] = (unsigned long)args->fn_arg;
 		p->thread.ra = (unsigned long)ret_from_fork_kernel_asm;
 	} else {
 		/* allocate new shadow stack if needed. In case of CLONE_VM we have to */

@@ -278,6 +293,18 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		if (clone_flags & CLONE_SETTLS)
 			childregs->tp = tls;
 		childregs->a0 = 0; /* Return value of fork() */
+
+		/*
+		 * Set up the unwind boundary: ensure the metadata
+		 * frame record has its {fp,ra} sentinel zeroed and
+		 * point fp/s0 above the metadata record. The type
+		 * field is inherited from the parent's pt_regs.
+		 */
+		childregs->stackframe.record.fp = 0;
+		childregs->stackframe.record.ra = 0;
+		p->thread.s[0] = (unsigned long)(&childregs->stackframe)
+				+ sizeof(struct frame_record);
+
 		p->thread.ra = (unsigned long)ret_from_fork_user_asm;
 	}
 	p->thread.riscv_v_flags = 0;