Linux内核之BUG_ON()和WARN_ON()

@Linux内核之BUG_ON()和WARN_ON()

1. BUG_ON()

内核中有许多地方调用类似BUG_ON()的语句，它非常像一个内核运行时的断言，意味着本来不该执行到BUG_ON()这条语句，一旦执行即抛出Oops，导致栈的回溯和错误信息的打印。为什么这些声明会导致 oops跟硬件的体系结构是相关的。大部分体系结构把BUG()和BUG_ON()定义成某种非法操作，这样自然会产生需要的oops。你可以把这些调用当作断言使用，想要断言某种情况不该发生。
BUG_ON()的定义为：

/*include/asm-generic/bug.h*/
/*
 * Don't use BUG() or BUG_ON() unless there's really no way out; one
 * example might be detecting data structure corruption in the middle
 * of an operation that can't be backed out of.  If the (sub)system
 * can somehow continue operating, perhaps with reduced functionality,
 * it's probably not BUG-worthy.
 *
 * If you're tempted to BUG(), think again:  is completely giving up
 * really the *only* solution?  There are usually better options, where
 * users don't need to reboot ASAP and can mostly shut down cleanly.
 */
#ifndef HAVE_ARCH_BUG
#define BUG() do { \
	printk("BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); \
	barrier_before_unreachable(); \
	panic("BUG!"); \
} while (0)
#endif

#ifndef HAVE_ARCH_BUG_ON
#define BUG_ON(condition) do { if (unlikely(condition)) BUG(); } while (0)
#endif

其中panic()定义在kernel/panic.c中，会导致内核崩溃，并打印Oops。

/**
 *	panic - halt the system
 *	@fmt: The text string to print
 *
 *	Display a message, then perform cleanups.
 *
 *	This function never returns.
 */
void panic(const char *fmt, ...)
{
	static char buf[1024];
	va_list args;
	long i, i_next = 0, len;
	int state = 0;
	int old_cpu, this_cpu;
	bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers;

	if (panic_on_warn) {
		/*
		 * This thread may hit another WARN() in the panic path.
		 * Resetting this prevents additional WARN() from panicking the
		 * system on this thread.  Other threads are blocked by the
		 * panic_mutex in panic().
		 */
		panic_on_warn = 0;
	}

	/*
	 * Disable local interrupts. This will prevent panic_smp_self_stop
	 * from deadlocking the first cpu that invokes the panic, since
	 * there is nothing to prevent an interrupt handler (that runs
	 * after setting panic_cpu) from invoking panic() again.
	 */
	local_irq_disable();
	preempt_disable_notrace();

	/*
	 * It's possible to come here directly from a panic-assertion and
	 * not have preempt disabled. Some functions called from here want
	 * preempt to be disabled. No point enabling it later though...
	 *
	 * Only one CPU is allowed to execute the panic code from here. For
	 * multiple parallel invocations of panic, all other CPUs either
	 * stop themself or will wait until they are stopped by the 1st CPU
	 * with smp_send_stop().
	 *
	 * `old_cpu == PANIC_CPU_INVALID' means this is the 1st CPU which
	 * comes here, so go ahead.
	 * `old_cpu == this_cpu' means we came from nmi_panic() which sets
	 * panic_cpu to this CPU.  In this case, this is also the 1st CPU.
	 */
	this_cpu = raw_smp_processor_id();
	old_cpu  = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);

	if (old_cpu != PANIC_CPU_INVALID && old_cpu != this_cpu)
		panic_smp_self_stop();

	console_verbose();
	bust_spinlocks(1);
	va_start(args, fmt);
	len = vscnprintf(buf, sizeof(buf), fmt, args);
	va_end(args);

	if (len && buf[len - 1] == '\n')
		buf[len - 1] = '\0';

	pr_emerg("Kernel panic - not syncing: %s\n", buf);
#ifdef CONFIG_DEBUG_BUGVERBOSE
	/*
	 * Avoid nested stack-dumping if a panic occurs during oops processing
	 */
	if (!test_taint(TAINT_DIE) && oops_in_progress <= 1)
		dump_stack();
#endif

	/*
	 * If kgdb is enabled, give it a chance to run before we stop all
	 * the other CPUs or else we won't be able to debug processes left
	 * running on them.
	 */
	kgdb_panic(buf);

	/*
	 * If we have crashed and we have a crash kernel loaded let it handle
	 * everything else.
	 * If we want to run this after calling panic_notifiers, pass
	 * the "crash_kexec_post_notifiers" option to the kernel.
	 *
	 * Bypass the panic_cpu check and call __crash_kexec directly.
	 */
	if (!_crash_kexec_post_notifiers) {
		__crash_kexec(NULL);

		/*
		 * Note smp_send_stop is the usual smp shutdown function, which
		 * unfortunately means it may not be hardened to work in a
		 * panic situation.
		 */
		smp_send_stop();
	} else {
		/*
		 * If we want to do crash dump after notifier calls and
		 * kmsg_dump, we will need architecture dependent extra
		 * works in addition to stopping other CPUs.
		 */
		crash_smp_send_stop();
	}

	/*
	 * Run any panic handlers, including those that might need to
	 * add information to the kmsg dump output.
	 */
	atomic_notifier_call_chain(&panic_notifier_list, 0, buf);

	panic_print_sys_info(false);

	kmsg_dump(KMSG_DUMP_PANIC);

	/*
	 * If you doubt kdump always works fine in any situation,
	 * "crash_kexec_post_notifiers" offers you a chance to run
	 * panic_notifiers and dumping kmsg before kdump.
	 * Note: since some panic_notifiers can make crashed kernel
	 * more unstable, it can increase risks of the kdump failure too.
	 *
	 * Bypass the panic_cpu check and call __crash_kexec directly.
	 */
	if (_crash_kexec_post_notifiers)
		__crash_kexec(NULL);

#ifdef CONFIG_VT
	unblank_screen();
#endif
	console_unblank();

	/*
	 * We may have ended up stopping the CPU holding the lock (in
	 * smp_send_stop()) while still having some valuable data in the console
	 * buffer.  Try to acquire the lock then release it regardless of the
	 * result.  The release will also print the buffers out.  Locks debug
	 * should be disabled to avoid reporting bad unlock balance when
	 * panic() is not being callled from OOPS.
	 */
	debug_locks_off();
	console_flush_on_panic(CONSOLE_FLUSH_PENDING);

	panic_print_sys_info(true);

	if (!panic_blink)
		panic_blink = no_blink;

	if (panic_timeout > 0) {
		/*
		 * Delay timeout seconds before rebooting the machine.
		 * We can't use the "normal" timers since we just panicked.
		 */
		pr_emerg("Rebooting in %d seconds..\n", panic_timeout);

		for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
			touch_nmi_watchdog();
			if (i >= i_next) {
				i += panic_blink(state ^= 1);
				i_next = i + 3600 / PANIC_BLINK_SPD;
			}
			mdelay(PANIC_TIMER_STEP);
		}
	}
	if (panic_timeout != 0) {
		/*
		 * This will not be a clean reboot, with everything
		 * shutting down.  But if there is a chance of
		 * rebooting the system it will be rebooted.
		 */
		if (panic_reboot_mode != REBOOT_UNDEFINED)
			reboot_mode = panic_reboot_mode;
		emergency_restart();
	}
#ifdef __sparc__
	{
		extern int stop_a_enabled;
		/* Make sure the user can actually press Stop-A (L1-A) */
		stop_a_enabled = 1;
		pr_emerg("Press Stop-A (L1-A) from sun keyboard or send break\n"
			 "twice on console to return to the boot prom\n");
	}
#endif
#if defined(CONFIG_S390)
	disabled_wait();
#endif
	pr_emerg("---[ end Kernel panic - not syncing: %s ]---\n", buf);

	/* Do not scroll important messages printed above */
	suppress_printk = 1;
	local_irq_enable();
	for (i = 0; ; i += PANIC_TIMER_STEP) {
		touch_softlockup_watchdog();
		if (i >= i_next) {
			i += panic_blink(state ^= 1);
			i_next = i + 3600 / PANIC_BLINK_SPD;
		}
		mdelay(PANIC_TIMER_STEP);
	}
}

EXPORT_SYMBOL(panic);

调用panic()不但会打印错误消息(Oops)而且还会挂起整个系统。显然，你只应该在极端恶劣的情况下使用它。
但是对于BUG_ON()，只有当括号内的条件成立时，才抛出Oops。

2. WARN_ON()

除了BUG_ON()外，内核有个稍微弱一些WARN_ON()，在括号中的条件成立时，内核会抛出栈回溯，但是不会panic()，这通常用于内核抛出一个警告，暗示某种不太合理的事情发生了。

而WARN_ON则是调用dump_stack，打印堆栈信息，不会OOPS,具体的调用情况与中断有关，可以通过linux中断机制来学习。

有时，WARN_ON()也可以作为一个调试技巧。比如，进到内核某个函数后，不知道这个函数是怎么一级一级被调用进来的，可以在该函数中加入一个WARN_ON(1)。

/*
 * Don't use BUG() or BUG_ON() unless there's really no way out; one
 * example might be detecting data structure corruption in the middle
 * of an operation that can't be backed out of.  If the (sub)system
 * can somehow continue operating, perhaps with reduced functionality,
 * it's probably not BUG-worthy.
 *
 * If you're tempted to BUG(), think again:  is completely giving up
 * really the *only* solution?  There are usually better options, where
 * users don't need to reboot ASAP and can mostly shut down cleanly.
 */
#ifndef HAVE_ARCH_BUG
#define BUG() do { \
	printk("BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); \
	barrier_before_unreachable(); \
	panic("BUG!"); \
} while (0)
#endif

#ifndef HAVE_ARCH_BUG_ON
#define BUG_ON(condition) do { if (unlikely(condition)) BUG(); } while (0)
#endif

/*
 * WARN(), WARN_ON(), WARN_ON_ONCE, and so on can be used to report
 * significant kernel issues that need prompt attention if they should ever
 * appear at runtime.
 *
 * Do not use these macros when checking for invalid external inputs
 * (e.g. invalid system call arguments, or invalid data coming from
 * network/devices), and on transient conditions like ENOMEM or EAGAIN.
 * These macros should be used for recoverable kernel issues only.
 * For invalid external inputs, transient conditions, etc use
 * pr_err[_once/_ratelimited]() followed by dump_stack(), if necessary.
 * Do not include "BUG"/"WARNING" in format strings manually to make these
 * conditions distinguishable from kernel issues.
 *
 * Use the versions with printk format strings to provide better diagnostics.
 */
#ifndef __WARN_FLAGS
extern __printf(4, 5)
void warn_slowpath_fmt(const char *file, const int line, unsigned taint,
		       const char *fmt, ...);
#define __WARN()		__WARN_printf(TAINT_WARN, NULL)
#define __WARN_printf(taint, arg...) do {				\
		instrumentation_begin();				\
		warn_slowpath_fmt(__FILE__, __LINE__, taint, arg);	\
		instrumentation_end();					\
	} while (0)
#else
extern __printf(1, 2) void __warn_printk(const char *fmt, ...);
#define __WARN()		__WARN_FLAGS(BUGFLAG_TAINT(TAINT_WARN))
#define __WARN_printf(taint, arg...) do {				\
		instrumentation_begin();				\
		__warn_printk(arg);					\
		__WARN_FLAGS(BUGFLAG_NO_CUT_HERE | BUGFLAG_TAINT(taint));\
		instrumentation_end();					\
	} while (0)
#define WARN_ON_ONCE(condition) ({				\
	int __ret_warn_on = !!(condition);			\
	if (unlikely(__ret_warn_on))				\
		__WARN_FLAGS(BUGFLAG_ONCE |			\
			     BUGFLAG_TAINT(TAINT_WARN));	\
	unlikely(__ret_warn_on);				\
})
#endif

/* used internally by panic.c */

#ifndef WARN_ON
#define WARN_ON(condition) ({						\
	int __ret_warn_on = !!(condition);				\
	if (unlikely(__ret_warn_on))					\
		__WARN();						\
	unlikely(__ret_warn_on);					\
})
#endif

#ifndef WARN
#define WARN(condition, format...) ({					\
	int __ret_warn_on = !!(condition);				\
	if (unlikely(__ret_warn_on))					\
		__WARN_printf(TAINT_WARN, format);			\
	unlikely(__ret_warn_on);					\
})
#endif

#define WARN_TAINT(condition, taint, format...) ({			\
	int __ret_warn_on = !!(condition);				\
	if (unlikely(__ret_warn_on))					\
		__WARN_printf(taint, format);				\
	unlikely(__ret_warn_on);					\
})

#ifndef WARN_ON_ONCE
#define WARN_ON_ONCE(condition)					\
	DO_ONCE_LITE_IF(condition, WARN_ON, 1)
#endif

#define WARN_ONCE(condition, format...)				\
	DO_ONCE_LITE_IF(condition, WARN, 1, format)

#define WARN_TAINT_ONCE(condition, taint, format...)		\
	DO_ONCE_LITE_IF(condition, WARN_TAINT, 1, taint, format)

#ifndef __WARN_FLAGS
void warn_slowpath_fmt(const char *file, int line, unsigned taint,
		       const char *fmt, ...)
{
	struct warn_args args;

	pr_warn(CUT_HERE);

	if (!fmt) {
		__warn(file, line, __builtin_return_address(0), taint,
		       NULL, NULL);
		return;
	}

	args.fmt = fmt;
	va_start(args.args, fmt);
	__warn(file, line, __builtin_return_address(0), taint, NULL, &args);
	va_end(args.args);
}
EXPORT_SYMBOL(warn_slowpath_fmt);

void __warn(const char *file, int line, void *caller, unsigned taint,
	    struct pt_regs *regs, struct warn_args *args)
{
	disable_trace_on_warning();

	if (file)
		pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n",
			raw_smp_processor_id(), current->pid, file, line,
			caller);
	else
		pr_warn("WARNING: CPU: %d PID: %d at %pS\n",
			raw_smp_processor_id(), current->pid, caller);

	if (args)
		vprintk(args->fmt, args->args);

	print_modules();

	if (regs)
		show_regs(regs);

	if (panic_on_warn)
		panic("panic_on_warn set ...\n");

	if (!regs)
		dump_stack();

	print_irqtrace_events(current);

	print_oops_end_marker();
	trace_error_report_end(ERROR_DETECTOR_WARN, (unsigned long)caller);

	/* Just a warning, don't kill lockdep. */
	add_taint(taint, LOCKDEP_STILL_OK);
}