unsigned long
print_context_stack_bp(struct task_struct *task,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data,
unsigned long *end, int *graph)
{
struct stack_frame *frame = (struct stack_frame *)bp;
unsigned long *retp = &frame->return_address;
while (valid_stack_ptr(task, retp, sizeof(*retp), end)) {
unsigned long addr = *retp;
unsigned long real_addr;
if (!__kernel_text_address(addr))
break;
real_addr = ftrace_graph_ret_addr(task, graph, addr, retp);
if (ops->address(data, real_addr, 1))
break;
frame = frame->next_frame;
retp = &frame->return_address;
}
return (unsigned long)frame;
}
unsigned long unwind_get_return_address(struct unwind_state *state)
{
if (unwind_done(state))
return 0;
return ftrace_graph_ret_addr(state->task, &state->graph_idx,
*state->sp, state->sp);
}
unsigned long
print_context_stack(struct task_struct *task,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data,
unsigned long *end, int *graph)
{
struct stack_frame *frame = (struct stack_frame *)bp;
/*
* If we overflowed the stack into a guard page, jump back to the
* bottom of the usable stack.
*/
if ((unsigned long)task_stack_page(task) - (unsigned long)stack <
PAGE_SIZE)
stack = (unsigned long *)task_stack_page(task);
while (valid_stack_ptr(task, stack, sizeof(*stack), end)) {
unsigned long addr = *stack;
if (__kernel_text_address(addr)) {
unsigned long real_addr;
int reliable = 0;
if ((unsigned long) stack == bp + sizeof(long)) {
reliable = 1;
frame = frame->next_frame;
bp = (unsigned long) frame;
}
/*
* When function graph tracing is enabled for a
* function, its return address on the stack is
* replaced with the address of an ftrace handler
* (return_to_handler). In that case, before printing
* the "real" address, we want to print the handler
* address as an "unreliable" hint that function graph
* tracing was involved.
*/
real_addr = ftrace_graph_ret_addr(task, graph, addr,
stack);
if (real_addr != addr)
ops->address(data, addr, 0);
ops->address(data, real_addr, reliable);
}
stack++;
}
return bp;
}
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;
if (state->regs && user_mode(state->regs))
return 0;
addr = READ_ONCE_TASK_STACK(state->task, *addr_p);
addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, addr,
addr_p);
return __kernel_text_address(addr) ? addr : 0;
}
static void notrace walk_stackframe(struct task_struct *task,
struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg)
{
unsigned long fp, sp, pc;
if (regs) {
fp = frame_pointer(regs);
sp = user_stack_pointer(regs);
pc = instruction_pointer(regs);
} else if (task == NULL || task == current) {
const register unsigned long current_sp __asm__ ("sp");
fp = (unsigned long)__builtin_frame_address(0);
sp = current_sp;
pc = (unsigned long)walk_stackframe;
} else {
/* task blocked in __switch_to */
fp = task->thread.s[0];
sp = task->thread.sp;
pc = task->thread.ra;
}
for (;;) {
unsigned long low, high;
struct stackframe *frame;
if (unlikely(!__kernel_text_address(pc) || fn(pc, arg)))
break;
/* Validate frame pointer */
low = sp + sizeof(struct stackframe);
high = ALIGN(sp, THREAD_SIZE);
if (unlikely(fp < low || fp > high || fp & 0x7))
break;
/* Unwind stack frame */
frame = (struct stackframe *)fp - 1;
sp = fp;
fp = frame->fp;
pc = ftrace_graph_ret_addr(current, NULL, frame->ra,
(unsigned long *)(fp - 8));
}
}
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;
if (state->regs && user_mode(state->regs))
return 0;
addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p,
addr_p);
if (!__kernel_text_address(addr)) {
printk_deferred_once(KERN_WARNING
"WARNING: unrecognized kernel stack return address %p at %p in %s:%d\n",
(void *)addr, addr_p, state->task->comm,
state->task->pid);
return 0;
}
return addr;
}
void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack, char *log_lvl)
{
struct unwind_state state;
struct stack_info stack_info = {0};
unsigned long visit_mask = 0;
int graph_idx = 0;
printk("%sCall Trace:\n", log_lvl);
unwind_start(&state, task, regs, stack);
stack = stack ? : get_stack_pointer(task, regs);
/*
* Iterate through the stacks, starting with the current stack pointer.
* Each stack has a pointer to the next one.
*
* x86-64 can have several stacks:
* - task stack
* - interrupt stack
* - HW exception stacks (double fault, nmi, debug, mce)
*
* x86-32 can have up to three stacks:
* - task stack
* - softirq stack
* - hardirq stack
*/
for (regs = NULL; stack; stack = stack_info.next_sp) {
const char *stack_name;
/*
* If we overflowed the task stack into a guard page, jump back
* to the bottom of the usable stack.
*/
if (task_stack_page(task) - (void *)stack < PAGE_SIZE)
stack = task_stack_page(task);
if (get_stack_info(stack, task, &stack_info, &visit_mask))
break;
stack_name = stack_type_name(stack_info.type);
if (stack_name)
printk("%s <%s>\n", log_lvl, stack_name);
/*
* Scan the stack, printing any text addresses we find. At the
* same time, follow proper stack frames with the unwinder.
*
* Addresses found during the scan which are not reported by
* the unwinder are considered to be additional clues which are
* sometimes useful for debugging and are prefixed with '?'.
* This also serves as a failsafe option in case the unwinder
* goes off in the weeds.
*/
for (; stack < stack_info.end; stack++) {
unsigned long real_addr;
int reliable = 0;
unsigned long addr = READ_ONCE_NOCHECK(*stack);
unsigned long *ret_addr_p =
unwind_get_return_address_ptr(&state);
if (!__kernel_text_address(addr))
continue;
/*
* Don't print regs->ip again if it was already printed
* by __show_regs() below.
*/
if (regs && stack == ®s->ip) {
unwind_next_frame(&state);
continue;
}
if (stack == ret_addr_p)
reliable = 1;
/*
* When function graph tracing is enabled for a
* function, its return address on the stack is
* replaced with the address of an ftrace handler
* (return_to_handler). In that case, before printing
* the "real" address, we want to print the handler
* address as an "unreliable" hint that function graph
* tracing was involved.
*/
real_addr = ftrace_graph_ret_addr(task, &graph_idx,
addr, stack);
if (real_addr != addr)
printk_stack_address(addr, 0, log_lvl);
printk_stack_address(real_addr, reliable, log_lvl);
if (!reliable)
continue;
/*
* Get the next frame from the unwinder. No need to
* check for an error: if anything goes wrong, the rest
* of the addresses will just be printed as unreliable.
*/
unwind_next_frame(&state);
/* if the frame has entry regs, print them */
regs = unwind_get_entry_regs(&state);
if (regs)
__show_regs(regs, 0);
}
if (stack_name)
printk("%s </%s>\n", log_lvl, stack_name);
}
}
static bool update_stack_state(struct unwind_state *state,
unsigned long *next_bp)
{
struct stack_info *info = &state->stack_info;
enum stack_type prev_type = info->type;
struct pt_regs *regs;
unsigned long *frame, *prev_frame_end, *addr_p, addr;
size_t len;
if (state->regs)
prev_frame_end = (void *)state->regs + regs_size(state->regs);
else
prev_frame_end = (void *)state->bp + FRAME_HEADER_SIZE;
/* Is the next frame pointer an encoded pointer to pt_regs? */
regs = decode_frame_pointer(next_bp);
if (regs) {
frame = (unsigned long *)regs;
len = regs_size(regs);
state->got_irq = true;
} else {
frame = next_bp;
len = FRAME_HEADER_SIZE;
}
/*
* If the next bp 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 the next bp
* could be on a subsequent stack.
*/
while (!on_stack(info, frame, len))
if (get_stack_info(info->next_sp, state->task, info,
&state->stack_mask))
return false;
/* Make sure it only unwinds up and doesn't overlap the prev frame: */
if (state->orig_sp && state->stack_info.type == prev_type &&
frame < prev_frame_end)
return false;
/* Move state to the next frame: */
if (regs) {
state->regs = regs;
state->bp = NULL;
} else {
state->bp = next_bp;
state->regs = NULL;
}
/* Save the return address: */
if (state->regs && user_mode(state->regs))
state->ip = 0;
else {
addr_p = unwind_get_return_address_ptr(state);
addr = READ_ONCE_TASK_STACK(state->task, *addr_p);
state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
addr, addr_p);
}
/* Save the original stack pointer for unwind_dump(): */
if (!state->orig_sp)
state->orig_sp = frame;
return true;
}
int
save_stack_trace_tsk_reliable(struct task_struct *tsk,
struct stack_trace *trace)
{
unsigned long sp;
unsigned long stack_page = (unsigned long)task_stack_page(tsk);
unsigned long stack_end;
int graph_idx = 0;
/*
* The last frame (unwinding first) may not yet have saved
* its LR onto the stack.
*/
int firstframe = 1;
if (tsk == current)
sp = current_stack_pointer();
else
sp = tsk->thread.ksp;
stack_end = stack_page + THREAD_SIZE;
if (!is_idle_task(tsk)) {
/*
* For user tasks, this is the SP value loaded on
* kernel entry, see "PACAKSAVE(r13)" in _switch() and
* system_call_common()/EXCEPTION_PROLOG_COMMON().
*
* Likewise for non-swapper kernel threads,
* this also happens to be the top of the stack
* as setup by copy_thread().
*
* Note that stack backlinks are not properly setup by
* copy_thread() and thus, a forked task() will have
* an unreliable stack trace until it's been
* _switch()'ed to for the first time.
*/
stack_end -= STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
} else {
/*
* idle tasks have a custom stack layout,
* c.f. cpu_idle_thread_init().
*/
stack_end -= STACK_FRAME_OVERHEAD;
}
if (sp < stack_page + sizeof(struct thread_struct) ||
sp > stack_end - STACK_FRAME_MIN_SIZE) {
return 1;
}
for (;;) {
unsigned long *stack = (unsigned long *) sp;
unsigned long newsp, ip;
/* sanity check: ABI requires SP to be aligned 16 bytes. */
if (sp & 0xF)
return 1;
/* Mark stacktraces with exception frames as unreliable. */
if (sp <= stack_end - STACK_INT_FRAME_SIZE &&
stack[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) {
return 1;
}
newsp = stack[0];
/* Stack grows downwards; unwinder may only go up. */
if (newsp <= sp)
return 1;
if (newsp != stack_end &&
newsp > stack_end - STACK_FRAME_MIN_SIZE) {
return 1; /* invalid backlink, too far up. */
}
/* Examine the saved LR: it must point into kernel code. */
ip = stack[STACK_FRAME_LR_SAVE];
if (!firstframe && !__kernel_text_address(ip))
return 1;
firstframe = 0;
/*
* FIXME: IMHO these tests do not belong in
* arch-dependent code, they are generic.
*/
ip = ftrace_graph_ret_addr(tsk, &graph_idx, ip, NULL);
#ifdef CONFIG_KPROBES
/*
* Mark stacktraces with kretprobed functions on them
* as unreliable.
*/
if (ip == (unsigned long)kretprobe_trampoline)
return 1;
#endif
if (!trace->skip)
trace->entries[trace->nr_entries++] = ip;
else
trace->skip--;
if (newsp == stack_end)
break;
if (trace->nr_entries >= trace->max_entries)
return -E2BIG;
sp = newsp;
}
return 0;
}
