path: root/arch/x86/kernel/nmi.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
 *  Copyright (C) 2011	Don Zickus Red Hat, Inc.
 *
 *  Pentium III FXSR, SSE support
 *	Gareth Hughes <gareth@valinux.com>, May 2000
 */

/*
 * Handle hardware traps and faults.
 */
#include <linux/spinlock.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/sched/debug.h>
#include <linux/nmi.h>
#include <linux/debugfs.h>
#include <linux/delay.h>
#include <linux/hardirq.h>
#include <linux/ratelimit.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/atomic.h>
#include <linux/sched/clock.h>

#include <asm/cpu_entry_area.h>
#include <asm/traps.h>
#include <asm/mach_traps.h>
#include <asm/nmi.h>
#include <asm/x86_init.h>
#include <asm/reboot.h>
#include <asm/cache.h>
#include <asm/nospec-branch.h>

#define CREATE_TRACE_POINTS
#include <trace/events/nmi.h>

struct nmi_desc {
	raw_spinlock_t lock;
	struct list_head head;
};

static struct nmi_desc nmi_desc[NMI_MAX] = 
{
	{
		.lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[0].lock),
		.head = LIST_HEAD_INIT(nmi_desc[0].head),
	},
	{
		.lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock),
		.head = LIST_HEAD_INIT(nmi_desc[1].head),
	},
	{
		.lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[2].lock),
		.head = LIST_HEAD_INIT(nmi_desc[2].head),
	},
	{
		.lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[3].lock),
		.head = LIST_HEAD_INIT(nmi_desc[3].head),
	},

};

struct nmi_stats {
	unsigned int normal;
	unsigned int unknown;
	unsigned int external;
	unsigned int swallow;
};

static DEFINE_PER_CPU(struct nmi_stats, nmi_stats);

static int ignore_nmis __read_mostly;

int unknown_nmi_panic;
/*
 * Prevent NMI reason port (0x61) being accessed simultaneously, can
 * only be used in NMI handler.
 */
static DEFINE_RAW_SPINLOCK(nmi_reason_lock);

static int __init setup_unknown_nmi_panic(char *str)
{
	unknown_nmi_panic = 1;
	return 1;
}
__setup("unknown_nmi_panic", setup_unknown_nmi_panic);

#define nmi_to_desc(type) (&nmi_desc[type])

static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC;

static int __init nmi_warning_debugfs(void)
{
	debugfs_create_u64("nmi_longest_ns", 0644,
			arch_debugfs_dir, &nmi_longest_ns);
	return 0;
}
fs_initcall(nmi_warning_debugfs);

static void nmi_check_duration(struct nmiaction *action, u64 duration)
{
	u64 whole_msecs = READ_ONCE(action->max_duration);
	int remainder_ns, decimal_msecs;

	if (duration < nmi_longest_ns || duration < action->max_duration)
		return;

	action->max_duration = duration;

	remainder_ns = do_div(whole_msecs, (1000 * 1000));
	decimal_msecs = remainder_ns / 1000;

	printk_ratelimited(KERN_INFO
		"INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n",
		action->handler, whole_msecs, decimal_msecs);
}

static int nmi_handle(unsigned int type, struct pt_regs *regs)
{
	struct nmi_desc *desc = nmi_to_desc(type);
	struct nmiaction *a;
	int handled=0;

	rcu_read_lock();

	/*
	 * NMIs are edge-triggered, which means if you have enough
	 * of them concurrently, you can lose some because only one
	 * can be latched at any given time.  Walk the whole list
	 * to handle those situations.
	 */
	list_for_each_entry_rcu(a, &desc->head, list) {
		int thishandled;
		u64 delta;

		delta = sched_clock();
		thishandled = a->handler(type, regs);
		handled += thishandled;
		delta = sched_clock() - delta;
		trace_nmi_handler(a->handler, (int)delta, thishandled);

		nmi_check_duration(a, delta);
	}

	rcu_read_unlock();

	/* return total number of NMI events handled */
	return handled;
}
NOKPROBE_SYMBOL(nmi_handle);

int __register_nmi_handler(unsigned int type, struct nmiaction *action)
{
	struct nmi_desc *desc = nmi_to_desc(type);
	unsigned long flags;

	if (!action->handler)
		return -EINVAL;

	raw_spin_lock_irqsave(&desc->lock, flags);

	/*
	 * Indicate if there are multiple registrations on the
	 * internal NMI handler call chains (SERR and IO_CHECK).
	 */
	WARN_ON_ONCE(type == NMI_SERR && !list_empty(&desc->head));
	WARN_ON_ONCE(type == NMI_IO_CHECK && !list_empty(&desc->head));

	/*
	 * some handlers need to be executed first otherwise a fake
	 * event confuses some handlers (kdump uses this flag)
	 */
	if (action->flags & NMI_FLAG_FIRST)
		list_add_rcu(&action->list, &desc->head);
	else
		list_add_tail_rcu(&action->list, &desc->head);
	
	raw_spin_unlock_irqrestore(&desc->lock, flags);
	return 0;
}
EXPORT_SYMBOL(__register_nmi_handler);

void unregister_nmi_handler(unsigned int type, const char *name)
{
	struct nmi_desc *desc = nmi_to_desc(type);
	struct nmiaction *n;
	unsigned long flags;

	raw_spin_lock_irqsave(&desc->lock, flags);

	list_for_each_entry_rcu(n, &desc->head, list) {
		/*
		 * the name passed in to describe the nmi handler
		 * is used as the lookup key
		 */
		if (!strcmp(n->name, name)) {
			WARN(in_nmi(),
				"Trying to free NMI (%s) from NMI context!\n", n->name);
			list_del_rcu(&n->list);
			break;
		}
	}

	raw_spin_unlock_irqrestore(&desc->lock, flags);
	synchronize_rcu();
}
EXPORT_SYMBOL_GPL(unregister_nmi_handler);

static void
pci_serr_error(unsigned char reason, struct pt_regs *regs)
{
	/* check to see if anyone registered against these types of errors */
	if (nmi_handle(NMI_SERR, regs))
		return;

	pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
		 reason, smp_processor_id());

	if (panic_on_unrecovered_nmi)
		nmi_panic(regs, "NMI: Not continuing");

	pr_emerg("Dazed and confused, but trying to continue\n");

	/* Clear and disable the PCI SERR error line. */
	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR;
	outb(reason, NMI_REASON_PORT);
}
NOKPROBE_SYMBOL(pci_serr_error);

static void
io_check_error(unsigned char reason, struct pt_regs *regs)
{
	unsigned long i;

	/* check to see if anyone registered against these types of errors */
	if (nmi_handle(NMI_IO_CHECK, regs))
		return;

	pr_emerg(
	"NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n",
		 reason, smp_processor_id());
	show_regs(regs);

	if (panic_on_io_nmi) {
		nmi_panic(regs, "NMI IOCK error: Not continuing");

		/*
		 * If we end up here, it means we have received an NMI while
		 * processing panic(). Simply return without delaying and
		 * re-enabling NMIs.
		 */
		return;
	}

	/* Re-enable the IOCK line, wait for a few seconds */
	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
	outb(reason, NMI_REASON_PORT);

	i = 20000;
	while (--i) {
		touch_nmi_watchdog();
		udelay(100);
	}

	reason &= ~NMI_REASON_CLEAR_IOCHK;
	outb(reason, NMI_REASON_PORT);
}
NOKPROBE_SYMBOL(io_check_error);

static void
unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
{
	int handled;

	/*
	 * Use 'false' as back-to-back NMIs are dealt with one level up.
	 * Of course this makes having multiple 'unknown' handlers useless
	 * as only the first one is ever run (unless it can actually determine
	 * if it caused the NMI)
	 */
	handled = nmi_handle(NMI_UNKNOWN, regs);
	if (handled) {
		__this_cpu_add(nmi_stats.unknown, handled);
		return;
	}

	__this_cpu_add(nmi_stats.unknown, 1);

	pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
		 reason