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;
}
void __unwind_start(struct unwind_state *state, struct task_struct *task,
struct pt_regs *regs, unsigned long *first_frame)
{
unsigned long *bp;
memset(state, 0, sizeof(*state));
state->task = task;
state->got_irq = (regs);
/* Don't even attempt to start from user mode regs: */
if (regs && user_mode(regs)) {
state->stack_info.type = STACK_TYPE_UNKNOWN;
return;
}
bp = get_frame_pointer(task, regs);
/* Initialize stack info and make sure the frame data is accessible: */
get_stack_info(bp, state->task, &state->stack_info,
&state->stack_mask);
update_stack_state(state, bp);
/*
* 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);
}
unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
{
if (unwind_done(state))
return NULL;
return state->regs ? &state->regs->ip : state->bp + 1;
}
unsigned long unwind_get_return_address(struct unwind_state *state)
{
if (unwind_done(state))
return 0;
return __kernel_text_address(state->ip) ? state->ip : 0;
}
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 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;
}
bool unwind_next_frame(struct unwind_state *state)
{
struct stack_info *info = &state->stack_info;
if (unwind_done(state))
return false;
do {
for (state->sp++; state->sp < info->end; state->sp++)
if (__kernel_text_address(*state->sp))
return true;
state->sp = info->next_sp;
} while (!get_stack_info(state->sp, state->task, info,
&state->stack_mask));
return false;
}
void __unwind_start(struct unwind_state *state, struct task_struct *task,
struct pt_regs *regs, unsigned long *first_frame)
{
unsigned long *bp, *frame;
size_t len;
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 */
bp = get_frame_pointer(task, regs);
regs = decode_frame_pointer(bp);
if (regs) {
state->regs = regs;
frame = (unsigned long *)regs;
len = sizeof(*regs);
} else {
state->bp = bp;
frame = bp;
len = FRAME_HEADER_SIZE;
}
/* initialize stack info and make sure the frame data is accessible */
get_stack_info(frame, state->task, &state->stack_info,
&state->stack_mask);
update_stack_state(state, frame, len);
/*
* 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);
}
static void __save_stack_trace(struct stack_trace *trace,
struct task_struct *task, struct pt_regs *regs,
bool nosched)
{
struct unwind_state state;
unsigned long addr;
if (regs)
save_stack_address(trace, regs->ip, nosched);
for (unwind_start(&state, task, regs, NULL); !unwind_done(&state);
unwind_next_frame(&state)) {
addr = unwind_get_return_address(&state);
if (!addr || save_stack_address(trace, addr, nosched))
break;
}
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}
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;
state->sp = first_frame;
get_stack_info(first_frame, state->task, &state->stack_info,
&state->stack_mask);
/*
* 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.
*/
if (!unwind_done(state) &&
(!on_stack(&state->stack_info, first_frame, sizeof(long)) ||
!__kernel_text_address(*first_frame)))
unwind_next_frame(state);
}
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;
}
bool unwind_next_frame(struct unwind_state *state)
{
struct pt_regs *regs;
unsigned long *next_bp, *next_frame;
size_t next_len;
enum stack_type prev_type = state->stack_info.type;
if (unwind_done(state))
return false;
/* have we reached the end? */
if (state->regs && user_mode(state->regs))
goto the_end;
if (is_last_task_frame(state)) {
regs = task_pt_regs(state->task);
/*
* kthreads (other than the boot CPU's idle thread) have some
* partial regs at the end of their stack which were placed
* there by copy_thread_tls(). But the regs don't have any
* useful information, so we can skip them.
*
* This user_mode() check is slightly broader than a PF_KTHREAD
* check because it also catches the awkward situation where a
* newly forked kthread transitions into a user task by calling
* do_execve(), which eventually clears PF_KTHREAD.
*/
if (!user_mode(regs))
goto the_end;
/*
* We're almost at the end, but not quite: there's still the
* syscall regs frame. Entry code doesn't encode the regs
* pointer for syscalls, so we have to set it manually.
*/
state->regs = regs;
state->bp = NULL;
return true;
}
/* get the next frame pointer */
if (state->regs)
next_bp = (unsigned long *)state->regs->bp;
else
next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task,*state->bp);
/* is the next frame pointer an encoded pointer to pt_regs? */
regs = decode_frame_pointer(next_bp);
if (regs) {
next_frame = (unsigned long *)regs;
next_len = sizeof(*regs);
} else {
next_frame = next_bp;
next_len = FRAME_HEADER_SIZE;
}
/* make sure the next frame's data is accessible */
if (!update_stack_state(state, next_frame, next_len)) {
/*
* Don't warn on bad regs->bp. An interrupt in entry code
* might cause a false positive warning.
*/
if (state->regs)
goto the_end;
goto bad_address;
}
/* Make sure it only unwinds up and doesn't overlap the last frame: */
if (state->stack_info.type == prev_type) {
if (state->regs && (void *)next_frame < (void *)state->regs + regs_size(state->regs))
goto bad_address;
if (state->bp && (void *)next_frame < (void *)state->bp + FRAME_HEADER_SIZE)
goto bad_address;
}
/* move to the next frame */
if (regs) {
state->regs = regs;
state->bp = NULL;
} else {
state->bp = next_bp;
state->regs = NULL;
}
return true;
bad_address:
/*
* When unwinding a non-current task, the task might actually be
* running on another CPU, in which case it could be modifying its
* stack while we're reading it. This is generally not a problem and
* can be ignored as long as the caller understands that unwinding
* another task will not always succeed.
*/
if (state->task != current)
goto the_end;
if (state->regs) {
printk_deferred_once(KERN_WARNING
"WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n",
state->regs, state->task->comm,
state->task->pid, next_frame);
unwind_dump(state, (unsigned long *)state->regs);
} else {
printk_deferred_once(KERN_WARNING
"WARNING: kernel stack frame pointer at %p in %s:%d has bad value %p\n",
state->bp, state->task->comm,
state->task->pid, next_frame);
unwind_dump(state, state->bp);
}
the_end:
state->stack_info.type = STACK_TYPE_UNKNOWN;
return false;
}
bool unwind_next_frame(struct unwind_state *state)
{
struct pt_regs *regs;
unsigned long *next_bp;
if (unwind_done(state))
return false;
/* Have we reached the end? */
if (state->regs && user_mode(state->regs))
goto the_end;
if (is_last_task_frame(state)) {
regs = task_pt_regs(state->task);
/*
* kthreads (other than the boot CPU's idle thread) have some
* partial regs at the end of their stack which were placed
* there by copy_thread_tls(). But the regs don't have any
* useful information, so we can skip them.
*
* This user_mode() check is slightly broader than a PF_KTHREAD
* check because it also catches the awkward situation where a
* newly forked kthread transitions into a user task by calling
* do_execve(), which eventually clears PF_KTHREAD.
*/
if (!user_mode(regs))
goto the_end;
/*
* We're almost at the end, but not quite: there's still the
* syscall regs frame. Entry code doesn't encode the regs
* pointer for syscalls, so we have to set it manually.
*/
state->regs = regs;
state->bp = NULL;
state->ip = 0;
return true;
}
/* Get the next frame pointer: */
if (state->regs)
next_bp = (unsigned long *)state->regs->bp;
else
next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task, *state->bp);
/* Move to the next frame if it's safe: */
if (!update_stack_state(state, next_bp))
goto bad_address;
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
* stack while we're reading it. This is generally not a problem and
* can be ignored as long as the caller understands that unwinding
* another task will not always succeed.
*/
if (state->task != current)
goto the_end;
/*
* Don't warn if the unwinder got lost due to an interrupt in entry
* code or in the C handler before the first frame pointer got set up:
*/
if (state->got_irq && in_entry_code(state->ip))
goto the_end;
if (state->regs &&
state->regs->sp >= (unsigned long)last_aligned_frame(state) &&
state->regs->sp < (unsigned long)task_pt_regs(state->task))
goto the_end;
if (state->regs) {
printk_deferred_once(KERN_WARNING
"WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n",
state->regs, state->task->comm,
state->task->pid, next_bp);
unwind_dump(state);
} else {
printk_deferred_once(KERN_WARNING
"WARNING: kernel stack frame pointer at %p in %s:%d has bad value %p\n",
state->bp, state->task->comm,
state->task->pid, next_bp);
unwind_dump(state);
}
the_end:
state->stack_info.type = STACK_TYPE_UNKNOWN;
return false;
}
