
valid_stack_ptr() is buggy: it assumes that all stacks are of size THREAD_SIZE, which is not true for exception stacks. So the walk_stack() callbacks will need to know the location of the beginning of the stack as well as the end. Another issue is that in general the various features of a stack (type, size, next stack pointer, description string) are scattered around in various places throughout the stack dump code. Encapsulate all that information in a single place with a new stack_info struct and a get_stack_info() interface. Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> 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/8164dd0db96b7e6a279fa17ae5e6dc375eecb4a9.1473905218.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
303 lines
6.6 KiB
C
303 lines
6.6 KiB
C
/*
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
* Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
|
|
*/
|
|
#include <linux/kallsyms.h>
|
|
#include <linux/kprobes.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/hardirq.h>
|
|
#include <linux/kdebug.h>
|
|
#include <linux/export.h>
|
|
#include <linux/ptrace.h>
|
|
#include <linux/kexec.h>
|
|
#include <linux/sysfs.h>
|
|
#include <linux/bug.h>
|
|
#include <linux/nmi.h>
|
|
|
|
#include <asm/stacktrace.h>
|
|
|
|
static char *exception_stack_names[N_EXCEPTION_STACKS] = {
|
|
[ DOUBLEFAULT_STACK-1 ] = "#DF",
|
|
[ NMI_STACK-1 ] = "NMI",
|
|
[ DEBUG_STACK-1 ] = "#DB",
|
|
[ MCE_STACK-1 ] = "#MC",
|
|
};
|
|
|
|
static unsigned long exception_stack_sizes[N_EXCEPTION_STACKS] = {
|
|
[0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ,
|
|
[DEBUG_STACK - 1] = DEBUG_STKSZ
|
|
};
|
|
|
|
void stack_type_str(enum stack_type type, const char **begin, const char **end)
|
|
{
|
|
BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
|
|
|
|
switch (type) {
|
|
case STACK_TYPE_IRQ:
|
|
*begin = "IRQ";
|
|
*end = "EOI";
|
|
break;
|
|
case STACK_TYPE_EXCEPTION ... STACK_TYPE_EXCEPTION_LAST:
|
|
*begin = exception_stack_names[type - STACK_TYPE_EXCEPTION];
|
|
*end = "EOE";
|
|
break;
|
|
default:
|
|
*begin = NULL;
|
|
*end = NULL;
|
|
}
|
|
}
|
|
|
|
static bool in_exception_stack(unsigned long *stack, struct stack_info *info,
|
|
unsigned long *visit_mask)
|
|
{
|
|
unsigned long *begin, *end;
|
|
struct pt_regs *regs;
|
|
unsigned k;
|
|
|
|
BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
|
|
|
|
for (k = 0; k < N_EXCEPTION_STACKS; k++) {
|
|
end = (unsigned long *)raw_cpu_ptr(&orig_ist)->ist[k];
|
|
begin = end - (exception_stack_sizes[k] / sizeof(long));
|
|
regs = (struct pt_regs *)end - 1;
|
|
|
|
if (stack < begin || stack >= end)
|
|
continue;
|
|
|
|
/*
|
|
* Make sure we don't iterate through an exception stack more
|
|
* than once. If it comes up a second time then there's
|
|
* something wrong going on - just break out and report an
|
|
* unknown stack type.
|
|
*/
|
|
if (*visit_mask & (1U << k))
|
|
break;
|
|
*visit_mask |= 1U << k;
|
|
|
|
info->type = STACK_TYPE_EXCEPTION + k;
|
|
info->begin = begin;
|
|
info->end = end;
|
|
info->next_sp = (unsigned long *)regs->sp;
|
|
|
|
return true;
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
static bool in_irq_stack(unsigned long *stack, struct stack_info *info)
|
|
{
|
|
unsigned long *end = (unsigned long *)this_cpu_read(irq_stack_ptr);
|
|
unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long));
|
|
|
|
if (stack < begin || stack >= end)
|
|
return false;
|
|
|
|
info->type = STACK_TYPE_IRQ;
|
|
info->begin = begin;
|
|
info->end = end;
|
|
|
|
/*
|
|
* The next stack pointer is the first thing pushed by the entry code
|
|
* after switching to the irq stack.
|
|
*/
|
|
info->next_sp = (unsigned long *)*(end - 1);
|
|
|
|
return true;
|
|
}
|
|
|
|
int get_stack_info(unsigned long *stack, struct task_struct *task,
|
|
struct stack_info *info, unsigned long *visit_mask)
|
|
{
|
|
if (!stack)
|
|
goto unknown;
|
|
|
|
task = task ? : current;
|
|
|
|
if (in_task_stack(stack, task, info))
|
|
return 0;
|
|
|
|
if (task != current)
|
|
goto unknown;
|
|
|
|
if (in_exception_stack(stack, info, visit_mask))
|
|
return 0;
|
|
|
|
if (in_irq_stack(stack, info))
|
|
return 0;
|
|
|
|
return 0;
|
|
|
|
unknown:
|
|
info->type = STACK_TYPE_UNKNOWN;
|
|
return -EINVAL;
|
|
}
|
|
|
|
/*
|
|
* x86-64 can have up to three kernel stacks:
|
|
* process stack
|
|
* interrupt stack
|
|
* severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
|
|
*/
|
|
|
|
void dump_trace(struct task_struct *task, struct pt_regs *regs,
|
|
unsigned long *stack, unsigned long bp,
|
|
const struct stacktrace_ops *ops, void *data)
|
|
{
|
|
unsigned long visit_mask = 0;
|
|
struct stack_info info;
|
|
int graph = 0;
|
|
int done = 0;
|
|
|
|
task = task ? : current;
|
|
stack = stack ? : get_stack_pointer(task, regs);
|
|
bp = bp ? : (unsigned long)get_frame_pointer(task, regs);
|
|
|
|
/*
|
|
* Print function call entries in all stacks, starting at the
|
|
* current stack address. If the stacks consist of nested
|
|
* exceptions
|
|
*/
|
|
while (!done) {
|
|
const char *begin_str, *end_str;
|
|
|
|
get_stack_info(stack, task, &info, &visit_mask);
|
|
|
|
/* Default finish unless specified to continue */
|
|
done = 1;
|
|
|
|
switch (info.type) {
|
|
|
|
/* Break out early if we are on the thread stack */
|
|
case STACK_TYPE_TASK:
|
|
break;
|
|
|
|
case STACK_TYPE_IRQ:
|
|
case STACK_TYPE_EXCEPTION ... STACK_TYPE_EXCEPTION_LAST:
|
|
|
|
stack_type_str(info.type, &begin_str, &end_str);
|
|
|
|
if (ops->stack(data, begin_str) < 0)
|
|
break;
|
|
|
|
bp = ops->walk_stack(task, stack, bp, ops,
|
|
data, &info, &graph);
|
|
|
|
ops->stack(data, end_str);
|
|
|
|
stack = info.next_sp;
|
|
done = 0;
|
|
break;
|
|
|
|
default:
|
|
ops->stack(data, "UNK");
|
|
break;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* This handles the process stack:
|
|
*/
|
|
bp = ops->walk_stack(task, stack, bp, ops, data, &info, &graph);
|
|
}
|
|
EXPORT_SYMBOL(dump_trace);
|
|
|
|
void
|
|
show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
|
|
unsigned long *sp, unsigned long bp, char *log_lvl)
|
|
{
|
|
unsigned long *irq_stack_end;
|
|
unsigned long *irq_stack;
|
|
unsigned long *stack;
|
|
int i;
|
|
|
|
irq_stack_end = (unsigned long *)this_cpu_read(irq_stack_ptr);
|
|
irq_stack = irq_stack_end - (IRQ_STACK_SIZE / sizeof(long));
|
|
|
|
sp = sp ? : get_stack_pointer(task, regs);
|
|
|
|
stack = sp;
|
|
for (i = 0; i < kstack_depth_to_print; i++) {
|
|
unsigned long word;
|
|
|
|
if (stack >= irq_stack && stack <= irq_stack_end) {
|
|
if (stack == irq_stack_end) {
|
|
stack = (unsigned long *) (irq_stack_end[-1]);
|
|
pr_cont(" <EOI> ");
|
|
}
|
|
} else {
|
|
if (kstack_end(stack))
|
|
break;
|
|
}
|
|
|
|
if (probe_kernel_address(stack, word))
|
|
break;
|
|
|
|
if ((i % STACKSLOTS_PER_LINE) == 0) {
|
|
if (i != 0)
|
|
pr_cont("\n");
|
|
printk("%s %016lx", log_lvl, word);
|
|
} else
|
|
pr_cont(" %016lx", word);
|
|
|
|
stack++;
|
|
touch_nmi_watchdog();
|
|
}
|
|
|
|
pr_cont("\n");
|
|
show_trace_log_lvl(task, regs, sp, bp, log_lvl);
|
|
}
|
|
|
|
void show_regs(struct pt_regs *regs)
|
|
{
|
|
int i;
|
|
|
|
show_regs_print_info(KERN_DEFAULT);
|
|
__show_regs(regs, 1);
|
|
|
|
/*
|
|
* When in-kernel, we also print out the stack and code at the
|
|
* time of the fault..
|
|
*/
|
|
if (!user_mode(regs)) {
|
|
unsigned int code_prologue = code_bytes * 43 / 64;
|
|
unsigned int code_len = code_bytes;
|
|
unsigned char c;
|
|
u8 *ip;
|
|
|
|
printk(KERN_DEFAULT "Stack:\n");
|
|
show_stack_log_lvl(NULL, regs, NULL, 0, KERN_DEFAULT);
|
|
|
|
printk(KERN_DEFAULT "Code: ");
|
|
|
|
ip = (u8 *)regs->ip - code_prologue;
|
|
if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
|
|
/* try starting at IP */
|
|
ip = (u8 *)regs->ip;
|
|
code_len = code_len - code_prologue + 1;
|
|
}
|
|
for (i = 0; i < code_len; i++, ip++) {
|
|
if (ip < (u8 *)PAGE_OFFSET ||
|
|
probe_kernel_address(ip, c)) {
|
|
pr_cont(" Bad RIP value.");
|
|
break;
|
|
}
|
|
if (ip == (u8 *)regs->ip)
|
|
pr_cont("<%02x> ", c);
|
|
else
|
|
pr_cont("%02x ", c);
|
|
}
|
|
}
|
|
pr_cont("\n");
|
|
}
|
|
|
|
int is_valid_bugaddr(unsigned long ip)
|
|
{
|
|
unsigned short ud2;
|
|
|
|
if (__copy_from_user(&ud2, (const void __user *) ip, sizeof(ud2)))
|
|
return 0;
|
|
|
|
return ud2 == 0x0b0f;
|
|
}
|