[PW_SID:1101637] riscv: Add reliable stack unwinding for livepatch

arch/riscv/Kconfig

@@ -185,6 +185,7 @@ config RISCV
 	select HAVE_KRETPROBES
 	# https://github.com/ClangBuiltLinux/linux/issues/1881
 	select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if !LD_IS_LLD
+	select HAVE_LIVEPATCH if FRAME_POINTER && 64BIT
 	select HAVE_MOVE_PMD
 	select HAVE_MOVE_PUD
 	select HAVE_PAGE_SIZE_4KB
@@ -195,6 +196,7 @@ config RISCV
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select HAVE_PREEMPT_DYNAMIC_KEY
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_RELIABLE_STACKTRACE if FRAME_POINTER && 64BIT
 	select HAVE_RETHOOK
 	select HAVE_RSEQ
 	select HAVE_RUST if RUSTC_SUPPORTS_RISCV && CC_IS_CLANG
@@ -1394,3 +1396,5 @@ endmenu # "CPU Power Management"
 source "arch/riscv/kvm/Kconfig"
 
 source "drivers/acpi/Kconfig"
+
+source "kernel/livepatch/Kconfig"

arch/riscv/include/asm/ptrace.h

@@ -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

arch/riscv/include/asm/stacktrace.h

@@ -3,8 +3,13 @@
 #ifndef _ASM_RISCV_STACKTRACE_H
 #define _ASM_RISCV_STACKTRACE_H
 
+#include <linux/percpu.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/irq_stack.h>
 #include <asm/ptrace.h>
+#include <asm/stacktrace/common.h>
 
 struct stackframe {
 	unsigned long fp;
@@ -16,14 +21,70 @@ extern void notrace walk_stackframe(struct task_struct *task, struct pt_regs *re
 extern void dump_backtrace(struct pt_regs *regs, struct task_struct *task,
 			   const char *loglvl);
 
-static inline bool on_thread_stack(void)
+/*
+ * IRQ stack accessors
+ */
+static inline struct stack_info stackinfo_get_irq(void)
+{
+	unsigned long low = (unsigned long)raw_cpu_read(irq_stack_ptr);
+	unsigned long high = low + IRQ_STACK_SIZE;
+
+	return (struct stack_info) {
+		.low = low,
+		.high = high,
+	};
+}
+
+static inline bool on_irq_stack(unsigned long sp, unsigned long size)
+{
+	struct stack_info info = stackinfo_get_irq();
+
+	return stackinfo_on_stack(&info, sp, size);
+}
+
+/*
+ * Task stack accessors
+ */
+static inline struct stack_info stackinfo_get_task(const struct task_struct *tsk)
 {
-	return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1));
+	unsigned long low = (unsigned long)task_stack_page(tsk);
+	unsigned long high = low + THREAD_SIZE;
+
+	return (struct stack_info) {
+		.low = low,
+		.high = high,
+	};
+}
+
+static inline bool on_task_stack(const struct task_struct *tsk,
+				 unsigned long sp, unsigned long size)
+{
+	struct stack_info info = stackinfo_get_task(tsk);
+
+	return stackinfo_on_stack(&info, sp, size);
 }
 
+/*
+ * Cast is necessary since current->stack is an opaque ptr.
+ */
+#define on_thread_stack()	(on_task_stack(current, current_stack_pointer, 1))
 
+/*
+ * Overflow stack accessors
+ */
 #ifdef CONFIG_VMAP_STACK
 DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
+
+static inline struct stack_info stackinfo_get_overflow(void)
+{
+	unsigned long low = (unsigned long)raw_cpu_ptr(overflow_stack);
+	unsigned long high = low + OVERFLOW_STACK_SIZE;
+
+	return (struct stack_info) {
+		.low = low,
+		.high = high,
+	};
+}
 #endif /* CONFIG_VMAP_STACK */
 
 #endif /* _ASM_RISCV_STACKTRACE_H */

arch/riscv/include/asm/stacktrace/common.h

@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * RISC-V common stack unwinder types and helpers.
+ *
+ * See: arch/arm64/include/asm/stacktrace/common.h for the reference
+ * implementation.
+ *
+ * Copyright (C) 2024
+ */
+#ifndef __ASM_RISCV_STACKTRACE_COMMON_H
+#define __ASM_RISCV_STACKTRACE_COMMON_H
+
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+
+#include <asm/stacktrace/frame.h>
+
+/**
+ * struct stack_info - describes the bounds of a stack.
+ *
+ * @low:  The lowest valid address on the stack.
+ * @high: The highest valid address on the stack.
+ */
+struct stack_info {
+	unsigned long low;
+	unsigned long high;
+};
+
+/**
+ * struct unwind_state - state used for robust unwinding.
+ *
+ * @fp:        The fp value in the frame record (or the real fp).
+ * @pc:        The ra value in the frame record (or the real ra).
+ *
+ * @stack:     The stack currently being unwound.
+ * @stacks:    An array of stacks which can be unwound.
+ * @nr_stacks: The number of stacks in @stacks.
+ */
+struct unwind_state {
+	unsigned long fp;
+	unsigned long pc;
+
+	struct stack_info stack;
+	struct stack_info *stacks;
+	int nr_stacks;
+};
+
+/**
+ * stackinfo_get_unknown() - Get an unknown stack_info.
+ *
+ * Return: a stack_info with low and high set to 0.
+ */
+static inline struct stack_info stackinfo_get_unknown(void)
+{
+	return (struct stack_info) {
+		.low = 0,
+		.high = 0,
+	};
+}
+
+/**
+ * stackinfo_on_stack() - Check whether an object is fully within a stack.
+ *
+ * @info: The stack to check against.
+ * @sp:   The base address of the object.
+ * @size: The size of the object.
+ *
+ * Return: true if the object is fully contained within the stack.
+ */
+static inline bool stackinfo_on_stack(const struct stack_info *info,
+				      unsigned long sp, unsigned long size)
+{
+	if (!info->low)
+		return false;
+
+	if (sp < info->low || sp + size < sp || sp + size > info->high)
+		return false;
+
+	return true;
+}
+
+/**
+ * unwind_init_common() - Initialize the common parts of the unwind state.
+ *
+ * @state: the unwind state to initialize.
+ */
+static inline void unwind_init_common(struct unwind_state *state)
+{
+	state->stack = stackinfo_get_unknown();
+}
+
+/**
+ * unwind_find_stack() - Find the accessible stack which entirely contains an
+ * object.
+ *
+ * @state: the current unwind state.
+ * @sp:    the base address of the object.
+ * @size:  the size of the object.
+ *
+ * Return: a pointer to the relevant stack_info if found; NULL otherwise.
+ */
+static inline struct stack_info *unwind_find_stack(struct unwind_state *state,
+						   unsigned long sp,
+						   unsigned long size)
+{
+	struct stack_info *info = &state->stack;
+
+	if (stackinfo_on_stack(info, sp, size))
+		return info;
+
+	for (int i = 0; i < state->nr_stacks; i++) {
+		info = &state->stacks[i];
+		if (stackinfo_on_stack(info, sp, size))
+			return info;
+	}
+
+	return NULL;
+}
+
+/**
+ * unwind_consume_stack() - Update stack boundaries so that future unwind steps
+ * cannot consume this object again.
+ *
+ * @state: the current unwind state.
+ * @info:  the stack_info of the stack containing the object.
+ * @sp:    the base address of the object.
+ * @size:  the size of the object.
+ *
+ * Stack transitions are strictly one-way, and once we've
+ * transitioned from one stack to another, it's never valid to
+ * unwind back to the old stack.
+ *
+ * Note that stacks can nest in several valid orders, e.g.
+ *
+ *   TASK -> IRQ -> OVERFLOW
+ *
+ * ... so we do not check the specific order of stack
+ * transitions.
+ */
+static inline void unwind_consume_stack(struct unwind_state *state,
+					struct stack_info *info,
+					unsigned long sp,
+					unsigned long size)
+{
+	struct stack_info tmp;
+
+	tmp = *info;
+	*info = stackinfo_get_unknown();
+	state->stack = tmp;
+
+	/*
+	 * Future unwind steps can only consume stack above this frame record.
+	 * Update the current stack to start immediately above it.
+	 */
+	state->stack.low = sp + size;
+}
+
+#endif /* __ASM_RISCV_STACKTRACE_COMMON_H */

arch/riscv/include/asm/stacktrace/frame.h

@@ -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 */

arch/riscv/kernel/Makefile

@@ -44,6 +44,11 @@ CFLAGS_REMOVE_return_address.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_sbi_ecall.o = $(CC_FLAGS_FTRACE)
 endif
 
+# When KASAN is enabled, a stack trace is recorded for every alloc/free, which
+# can significantly impact performance. Avoid instrumenting the stack trace
+# collection code to minimize this impact.
+KASAN_SANITIZE_stacktrace.o := n
+
 always-$(KBUILD_BUILTIN) += vmlinux.lds
 
 obj-y	+= head.o

arch/riscv/kernel/asm-offsets.c

@@ -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