![Josh Poimboeuf](/assets/img/avatar_default.png)
The x86 stack dump code is a bit of a mess. dump_trace() uses callbacks, and each user of it seems to have slightly different requirements, so there are several slightly different callbacks floating around. Also there are some upcoming features which will need more changes to the stack dump code, including the printing of stack pt_regs, reliable stack detection for live patching, and a DWARF unwinder. Each of those features would at least need more callbacks and/or callback interfaces, resulting in a much bigger mess than what we have today. Before doing all that, we should try to clean things up and replace dump_trace() with something cleaner and more flexible. The new unwinder is a simple state machine which was heavily inspired by a suggestion from Andy Lutomirski: https://lkml.kernel.org/r/CALCETrUbNTqaM2LRyXGRx=kVLRPeY5A3Pc6k4TtQxF320rUT=w@mail.gmail.com It's also similar to the libunwind API: http://www.nongnu.org/libunwind/man/libunwind(3).html Some if its advantages: - Simplicity: no more callback sprawl and less code duplication. - Flexibility: it allows the caller to stop and inspect the stack state at each step in the unwinding process. - Modularity: the unwinder code, console stack dump code, and stack metadata analysis code are all better separated so that changing one of them shouldn't have much of an impact on any of the others. Two implementations are added which conform to the new unwind interface: - The frame pointer unwinder which is used for CONFIG_FRAME_POINTER=y. - The "guess" unwinder which is used for CONFIG_FRAME_POINTER=n. This isn't an "unwinder" per se. All it does is scan the stack for kernel text addresses. But with no frame pointers, guesses are better than nothing in most cases. Suggested-by: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Byungchul Park <byungchul.park@lge.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nilay Vaish <nilayvaish@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/6dc2f909c47533d213d0505f0a113e64585bec82.1474045023.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
94 lines
2.5 KiB
C
94 lines
2.5 KiB
C
#include <linux/sched.h>
|
|
#include <asm/ptrace.h>
|
|
#include <asm/bitops.h>
|
|
#include <asm/stacktrace.h>
|
|
#include <asm/unwind.h>
|
|
|
|
#define FRAME_HEADER_SIZE (sizeof(long) * 2)
|
|
|
|
unsigned long unwind_get_return_address(struct unwind_state *state)
|
|
{
|
|
unsigned long addr;
|
|
unsigned long *addr_p = unwind_get_return_address_ptr(state);
|
|
|
|
if (unwind_done(state))
|
|
return 0;
|
|
|
|
addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p,
|
|
addr_p);
|
|
|
|
return __kernel_text_address(addr) ? addr : 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(unwind_get_return_address);
|
|
|
|
static bool update_stack_state(struct unwind_state *state, void *addr,
|
|
size_t len)
|
|
{
|
|
struct stack_info *info = &state->stack_info;
|
|
|
|
/*
|
|
* If addr isn't on the current stack, switch to the next one.
|
|
*
|
|
* We may have to traverse multiple stacks to deal with the possibility
|
|
* that 'info->next_sp' could point to an empty stack and 'addr' could
|
|
* be on a subsequent stack.
|
|
*/
|
|
while (!on_stack(info, addr, len))
|
|
if (get_stack_info(info->next_sp, state->task, info,
|
|
&state->stack_mask))
|
|
return false;
|
|
|
|
return true;
|
|
}
|
|
|
|
bool unwind_next_frame(struct unwind_state *state)
|
|
{
|
|
unsigned long *next_bp;
|
|
|
|
if (unwind_done(state))
|
|
return false;
|
|
|
|
next_bp = (unsigned long *)*state->bp;
|
|
|
|
/* make sure the next frame's data is accessible */
|
|
if (!update_stack_state(state, next_bp, FRAME_HEADER_SIZE))
|
|
return false;
|
|
|
|
/* move to the next frame */
|
|
state->bp = next_bp;
|
|
return true;
|
|
}
|
|
EXPORT_SYMBOL_GPL(unwind_next_frame);
|
|
|
|
void __unwind_start(struct unwind_state *state, struct task_struct *task,
|
|
struct pt_regs *regs, unsigned long *first_frame)
|
|
{
|
|
memset(state, 0, sizeof(*state));
|
|
state->task = task;
|
|
|
|
/* don't even attempt to start from user mode regs */
|
|
if (regs && user_mode(regs)) {
|
|
state->stack_info.type = STACK_TYPE_UNKNOWN;
|
|
return;
|
|
}
|
|
|
|
/* set up the starting stack frame */
|
|
state->bp = get_frame_pointer(task, regs);
|
|
|
|
/* initialize stack info and make sure the frame data is accessible */
|
|
get_stack_info(state->bp, state->task, &state->stack_info,
|
|
&state->stack_mask);
|
|
update_stack_state(state, state->bp, FRAME_HEADER_SIZE);
|
|
|
|
/*
|
|
* The caller can provide the address of the first frame directly
|
|
* (first_frame) or indirectly (regs->sp) to indicate which stack frame
|
|
* to start unwinding at. Skip ahead until we reach it.
|
|
*/
|
|
while (!unwind_done(state) &&
|
|
(!on_stack(&state->stack_info, first_frame, sizeof(long)) ||
|
|
state->bp < first_frame))
|
|
unwind_next_frame(state);
|
|
}
|
|
EXPORT_SYMBOL_GPL(__unwind_start);
|