/*
* Called from fs/proc with a reference on @p to find the function
* which called into schedule(). This needs to be done carefully
* because the task might wake up and we might look at a stack
* changing under us.
*/
unsigned long get_wchan(struct task_struct *p)
{
unsigned long start, bottom, top, sp, fp, ip, ret = 0;
int count = 0;
if (!p || p == current || p->state == TASK_RUNNING)
return 0;
if (!try_get_task_stack(p))
return 0;
start = (unsigned long)task_stack_page(p);
if (!start)
goto out;
/*
* Layout of the stack page:
*
* ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long)
* PADDING
* ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING
* stack
* ----------- bottom = start
*
* The tasks stack pointer points at the location where the
* framepointer is stored. The data on the stack is:
* ... IP FP ... IP FP
*
* We need to read FP and IP, so we need to adjust the upper
* bound by another unsigned long.
*/
top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;
top -= 2 * sizeof(unsigned long);
bottom = start;
sp = READ_ONCE(p->thread.sp);
if (sp < bottom || sp > top)
goto out;
fp = READ_ONCE_NOCHECK(((struct inactive_task_frame *)sp)->bp);
do {
if (fp < bottom || fp > top)
goto out;
ip = READ_ONCE_NOCHECK(*(unsigned long *)(fp + sizeof(unsigned long)));
if (!in_sched_functions(ip)) {
ret = ip;
goto out;
}
fp = READ_ONCE_NOCHECK(*(unsigned long *)fp);
} while (count++ < 16 && p->state != TASK_RUNNING);
out:
put_task_stack(p);
return ret;
}
static void unwind_dump(struct unwind_state *state, unsigned long *sp)
{
static bool dumped_before = false;
bool prev_zero, zero = false;
unsigned long word;
if (dumped_before)
return;
dumped_before = true;
printk_deferred("unwind stack type:%d next_sp:%p mask:%lx graph_idx:%d\n",
state->stack_info.type, state->stack_info.next_sp,
state->stack_mask, state->graph_idx);
for (sp = state->orig_sp; sp < state->stack_info.end; sp++) {
word = READ_ONCE_NOCHECK(*sp);
prev_zero = zero;
zero = word == 0;
if (zero) {
if (!prev_zero)
printk_deferred("%p: %016x ...\n", sp, 0);
continue;
}
printk_deferred("%p: %016lx (%pB)\n", sp, word, (void *)word);
}
}
static void unwind_dump(struct unwind_state *state)
{
static bool dumped_before = false;
bool prev_zero, zero = false;
unsigned long word, *sp;
struct stack_info stack_info = {0};
unsigned long visit_mask = 0;
if (dumped_before)
return;
dumped_before = true;
printk_deferred("unwind stack type:%d next_sp:%p mask:0x%lx graph_idx:%d\n",
state->stack_info.type, state->stack_info.next_sp,
state->stack_mask, state->graph_idx);
for (sp = state->orig_sp; sp; sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
if (get_stack_info(sp, state->task, &stack_info, &visit_mask))
break;
for (; sp < stack_info.end; sp++) {
word = READ_ONCE_NOCHECK(*sp);
prev_zero = zero;
zero = word == 0;
if (zero) {
if (!prev_zero)
printk_deferred("%p: %0*x ...\n",
sp, BITS_PER_LONG/4, 0);
continue;
}
printk_deferred("%p: %0*lx (%pB)\n",
sp, BITS_PER_LONG/4, word, (void *)word);
}
}
}
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);
}
}
/*
* Return saved PC of a blocked thread.
* What is this good for? it will be always the scheduler or ret_from_fork.
*/
unsigned long thread_saved_pc(struct task_struct *tsk)
{
struct inactive_task_frame *frame =
(struct inactive_task_frame *) READ_ONCE(tsk->thread.sp);
return READ_ONCE_NOCHECK(frame->ret_addr);
}
/*
* AArch64 PCS assigns the frame pointer to x29.
*
* A simple function prologue looks like this:
* sub sp, sp, #0x10
* stp x29, x30, [sp]
* mov x29, sp
*
* A simple function epilogue looks like this:
* mov sp, x29
* ldp x29, x30, [sp]
* add sp, sp, #0x10
*/
int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
{
unsigned long high, low;
unsigned long fp = frame->fp;
unsigned long irq_stack_ptr;
/*
* Switching between stacks is valid when tracing current and in
* non-preemptible context.
*/
if (tsk == current && !preemptible())
irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id());
else
irq_stack_ptr = 0;
low = frame->sp;
/* irq stacks are not THREAD_SIZE aligned */
if (on_irq_stack(frame->sp, raw_smp_processor_id()))
high = irq_stack_ptr;
else
high = ALIGN(low, THREAD_SIZE) - 0x20;
if (fp < low || fp > high || fp & 0xf)
return -EINVAL;
frame->sp = fp + 0x10;
frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
if (tsk && tsk->ret_stack &&
(frame->pc == (unsigned long)return_to_handler)) {
/*
* This is a case where function graph tracer has
* modified a return address (LR) in a stack frame
* to hook a function return.
* So replace it to an original value.
*/
frame->pc = tsk->ret_stack[frame->graph--].ret;
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
/*
* Check whether we are going to walk through from interrupt stack
* to task stack.
* If we reach the end of the stack - and its an interrupt stack,
* unpack the dummy frame to find the original elr.
*
* Check the frame->fp we read from the bottom of the irq_stack,
* and the original task stack pointer are both in current->stack.
*/
if (frame->sp == irq_stack_ptr) {
struct pt_regs *irq_args;
unsigned long orig_sp = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr);
if (object_starts_on_stack((void *)orig_sp) &&
object_starts_on_stack((void *)frame->fp)) {
frame->sp = orig_sp;
/* orig_sp is the saved pt_regs, find the elr */
irq_args = (struct pt_regs *)orig_sp;
frame->pc = irq_args->pc;
} else {
/*
* This frame has a non-standard format, and we
* didn't fix it, because the data looked wrong.
* Refuse to output this frame.
*/
return -EINVAL;
}
}
return 0;
}
