stacktrace/x86: add function for detecting reliable stack traces
For live patching and possibly other use cases, a stack trace is only
useful if it can be assured that it's completely reliable. Add a new
save_stack_trace_tsk_reliable() function to achieve that.
Note that if the target task isn't the current task, and the target task
is allowed to run, then it could be writing the stack while the unwinder
is reading it, resulting in possible corruption. So the caller of
save_stack_trace_tsk_reliable() must ensure that the task is either
'current' or inactive.
save_stack_trace_tsk_reliable() relies on the x86 unwinder's detection
of pt_regs on the stack. If the pt_regs are not user-mode registers
from a syscall, then they indicate an in-kernel interrupt or exception
(e.g. preemption or a page fault), in which case the stack is considered
unreliable due to the nature of frame pointers.
It also relies on the x86 unwinder's detection of other issues, such as:
- corrupted stack data
- stack grows the wrong way
- stack walk doesn't reach the bottom
- user didn't provide a large enough entries array
Such issues are reported by checking unwind_error() and !unwind_done().
Also add CONFIG_HAVE_RELIABLE_STACKTRACE so arch-independent code can
determine at build time whether the function is implemented.
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Reviewed-by: Miroslav Benes <mbenes@suse.cz>
Acked-by: Ingo Molnar <mingo@kernel.org> # for the x86 changes
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
diff --git a/arch/Kconfig b/arch/Kconfig
index cd211a1..6ad00ad 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -713,6 +713,12 @@
Architecture supports the 'objtool check' host tool command, which
performs compile-time stack metadata validation.
+config HAVE_RELIABLE_STACKTRACE
+ bool
+ help
+ Architecture has a save_stack_trace_tsk_reliable() function which
+ only returns a stack trace if it can guarantee the trace is reliable.
+
config HAVE_ARCH_HASH
bool
default n
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cc98d5a..2a26852 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -160,6 +160,7 @@
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
select HAVE_REGS_AND_STACK_ACCESS_API
+ select HAVE_RELIABLE_STACKTRACE if X86_64 && FRAME_POINTER && STACK_VALIDATION
select HAVE_STACK_VALIDATION if X86_64
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_UNSTABLE_SCHED_CLOCK
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index 6fa75b1..137e9cc 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -11,6 +11,7 @@
unsigned long stack_mask;
struct task_struct *task;
int graph_idx;
+ bool error;
#ifdef CONFIG_FRAME_POINTER
unsigned long *bp, *orig_sp;
struct pt_regs *regs;
@@ -40,6 +41,11 @@
__unwind_start(state, task, regs, first_frame);
}
+static inline bool unwind_error(struct unwind_state *state)
+{
+ return state->error;
+}
+
#ifdef CONFIG_FRAME_POINTER
static inline
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 8e2b79b..8dabd7b 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -76,6 +76,101 @@
}
EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
+
+#define STACKTRACE_DUMP_ONCE(task) ({ \
+ static bool __section(.data.unlikely) __dumped; \
+ \
+ if (!__dumped) { \
+ __dumped = true; \
+ WARN_ON(1); \
+ show_stack(task, NULL); \
+ } \
+})
+
+static int __save_stack_trace_reliable(struct stack_trace *trace,
+ struct task_struct *task)
+{
+ struct unwind_state state;
+ struct pt_regs *regs;
+ unsigned long addr;
+
+ for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state);
+ unwind_next_frame(&state)) {
+
+ regs = unwind_get_entry_regs(&state);
+ if (regs) {
+ /*
+ * Kernel mode registers on the stack indicate an
+ * in-kernel interrupt or exception (e.g., preemption
+ * or a page fault), which can make frame pointers
+ * unreliable.
+ */
+ if (!user_mode(regs))
+ return -EINVAL;
+
+ /*
+ * The last frame contains the user mode syscall
+ * pt_regs. Skip it and finish the unwind.
+ */
+ unwind_next_frame(&state);
+ if (!unwind_done(&state)) {
+ STACKTRACE_DUMP_ONCE(task);
+ return -EINVAL;
+ }
+ break;
+ }
+
+ 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) {
+ STACKTRACE_DUMP_ONCE(task);
+ return -EINVAL;
+ }
+
+ if (save_stack_address(trace, addr, false))
+ return -EINVAL;
+ }
+
+ /* Check for stack corruption */
+ if (unwind_error(&state)) {
+ STACKTRACE_DUMP_ONCE(task);
+ return -EINVAL;
+ }
+
+ if (trace->nr_entries < trace->max_entries)
+ trace->entries[trace->nr_entries++] = ULONG_MAX;
+
+ return 0;
+}
+
+/*
+ * This function returns an error if it detects any unreliable features of the
+ * stack. Otherwise it guarantees that the stack trace is reliable.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is inactive.
+ */
+int save_stack_trace_tsk_reliable(struct task_struct *tsk,
+ struct stack_trace *trace)
+{
+ int ret;
+
+ if (!try_get_task_stack(tsk))
+ return -EINVAL;
+
+ ret = __save_stack_trace_reliable(trace, tsk);
+
+ put_task_stack(tsk);
+
+ return ret;
+}
+#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */
+
/* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
struct stack_frame_user {
@@ -138,4 +233,3 @@
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}
-
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 478d15d..5ed4391 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -225,6 +225,8 @@
return true;
bad_address:
+ state->error = true;
+
/*
* When unwinding a non-current task, the task might actually be
* running on another CPU, in which case it could be modifying its