[1/2] arm64: Implement arch_stack_walk_reliable

Commit Message

Song Liu March 8, 2025, 1:27 a.m. UTC

With proper exception boundary detection, it is possible to implment
arch_stack_walk_reliable without sframe.

Note that, arch_stack_walk_reliable does not guarantee getting reliable
stack in all scenarios. Instead, it can reliably detect when the stack
trace is not reliable, which is enough to provide reliable livepatching.

This version has been inspired by Weinan Liu's patch [1].

[1] https://lore.kernel.org/live-patching/[e-mail]/
Signed-off-by: Song Liu <[e-mail]>
---
 arch/arm64/Kconfig                         |  2 +-
 arch/arm64/include/asm/stacktrace/common.h |  1 +
 arch/arm64/kernel/stacktrace.c             | 44 +++++++++++++++++++++-
 3 files changed, 45 insertions(+), 2 deletions(-)

Patch

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 940343beb3d4..ed4f7bf4a879 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -275,6 +275,7 @@  config ARM64
 	select HAVE_SOFTIRQ_ON_OWN_STACK
 	select USER_STACKTRACE_SUPPORT
 	select VDSO_GETRANDOM
+	select HAVE_RELIABLE_STACKTRACE
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
@@ -2499,4 +2500,3 @@  endmenu # "CPU Power Management"
 source "drivers/acpi/Kconfig"
 
 source "arch/arm64/kvm/Kconfig"
-
diff --git a/arch/arm64/include/asm/stacktrace/common.h b/arch/arm64/include/asm/stacktrace/common.h
index 821a8fdd31af..072469fd91b7 100644
--- a/arch/arm64/include/asm/stacktrace/common.h
+++ b/arch/arm64/include/asm/stacktrace/common.h
@@ -33,6 +33,7 @@  struct unwind_state {
 	struct stack_info stack;
 	struct stack_info *stacks;
 	int nr_stacks;
+	bool unreliable;
 };
 
 static inline struct stack_info stackinfo_get_unknown(void)
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 1d9d51d7627f..69d0567a0c38 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -230,8 +230,14 @@  kunwind_next_frame_record(struct kunwind_state *state)
 	new_fp = READ_ONCE(record->fp);
 	new_pc = READ_ONCE(record->lr);
 
-	if (!new_fp && !new_pc)
+	if (!new_fp && !new_pc) {
+		/*
+		 * Searching across exception boundaries. The stack is now
+		 * unreliable.
+		 */
+		state->common.unreliable = true;
 		return kunwind_next_frame_record_meta(state);
+	}
 
 	unwind_consume_stack(&state->common, info, fp, sizeof(*record));
 
@@ -347,6 +353,7 @@  kunwind_stack_walk(kunwind_consume_fn consume_state,
 		.common = {
 			.stacks = stacks,
 			.nr_stacks = ARRAY_SIZE(stacks),
+			.unreliable = false,
 		},
 	};
 
@@ -387,6 +394,41 @@  noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry,
 	kunwind_stack_walk(arch_kunwind_consume_entry, &data, task, regs);
 }
 
+struct kunwind_reliable_consume_entry_data {
+	stack_trace_consume_fn consume_entry;
+	void *cookie;
+	bool unreliable;
+};
+
+static __always_inline bool
+arch_kunwind_reliable_consume_entry(const struct kunwind_state *state, void *cookie)
+{
+	struct kunwind_reliable_consume_entry_data *data = cookie;
+
+	if (state->common.unreliable) {
+		data->unreliable = true;
+		return false;
+	}
+	return data->consume_entry(data->cookie, state->common.pc);
+}
+
+noinline noinstr int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
+			void *cookie, struct task_struct *task)
+{
+	struct kunwind_reliable_consume_entry_data data = {
+		.consume_entry = consume_entry,
+		.cookie = cookie,
+		.unreliable = false,
+	};
+
+	kunwind_stack_walk(arch_kunwind_reliable_consume_entry, &data, task, NULL);
+
+	if (data.unreliable)
+		return -EINVAL;
+
+	return 0;
+}
+
 struct bpf_unwind_consume_entry_data {
 	bool (*consume_entry)(void *cookie, u64 ip, u64 sp, u64 fp);
 	void *cookie;