summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/nmi.c
blob: c3e985d1751ced9dbab5ac0aa7c38f9623b449f4 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
/*
 *  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/nmi.h>
#include <linux/debugfs.h>
#include <linux/delay.h>
#include <linux/hardirq.h>
#include <linux/slab.h>
#include <linux/export.h>

#if defined(CONFIG_EDAC)
#include <linux/edac.h>
#endif

#include <linux/atomic.h>
#include <asm/traps.h>
#include <asm/mach_traps.h>
#include <asm/nmi.h>
#include <asm/x86_init.h>

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

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

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

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_max_handler(struct irq_work *w)
{
	struct nmiaction *a = container_of(w, struct nmiaction, irq_work);
	int remainder_ns, decimal_msecs;
	u64 whole_msecs = ACCESS_ONCE(a->max_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",
		a->handler, whole_msecs, decimal_msecs);
}

static int nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
{
	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);

		if (delta < nmi_longest_ns || delta < a->max_duration)
			continue;

		a->max_duration = delta;
		irq_work_queue(&a->irq_work);
	}

	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;

	init_irq_work(&action->irq_work, nmi_max_handler);

	spin_lock_irqsave(&desc->lock, flags);

	/*
	 * most handlers of type NMI_UNKNOWN never return because
	 * they just assume the NMI is theirs.  Just a sanity check
	 * to manage expectations
	 */
	WARN_ON_ONCE(type == NMI_UNKNOWN && !list_empty(&desc->head));
	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);
	
	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;

	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;
		}
	}

	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, false))
		return;

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

	/*
	 * On some machines, PCI SERR line is used to report memory
	 * errors. EDAC makes use of it.
	 */
#if defined(CONFIG_EDAC)
	if (edac_handler_set()) {
		edac_atomic_assert_error();
		return;
	}
#endif

	if (panic_on_unrecovered_nmi)
		panic("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, false))
		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)
		panic("NMI IOCK error: Not continuing");

	/* 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, false);
	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, smp_processor_id());

	pr_emerg("Do you have a strange power saving mode enabled?\n");
	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
		panic("NMI: Not continuing");

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

static DEFINE_PER_CPU(bool, swallow_nmi);
static DEFINE_PER_CPU(unsigned long, last_nmi_rip);

static void default_do_nmi(struct pt_regs *regs)
{
	unsigned char reason = 0;
	int handled;
	bool b2b = false;

	/*
	 * CPU-specific NMI must be processed before non-CPU-specific
	 * NMI, otherwise we may lose it, because the CPU-specific
	 * NMI can not be detected/processed on other CPUs.
	 */

	/*
	 * Back-to-back NMIs are interesting because they can either
	 * be two NMI or more than two NMIs (any thing over two is dropped
	 * due to NMI being edge-triggered).  If this is the second half
	 * of the back-to-back NMI, assume we dropped things and process
	 * more handlers.  Otherwise reset the 'swallow' NMI behaviour
	 */
	if (regs->ip == __this_cpu_read(last_nmi_rip))
		b2b = true;
	else
		__this_cpu_write(swallow_nmi, false);

	__this_cpu_write(last_nmi_rip, regs->ip);

	handled = nmi_handle(NMI_LOCAL, regs, b2b);
	__this_cpu_add(nmi_stats.normal, handled);
	if (handled) {
		/*
		 * There are cases when a NMI handler handles multiple
		 * events in the current NMI.  One of these events may
		 * be queued for in the next NMI.  Because the event is
		 * already handled, the next NMI will result in an unknown
		 * NMI.  Instead lets flag this for a potential NMI to
		 * swallow.
		 */
		if (handled > 1)
			__this_cpu_write(swallow_nmi, true);
		return;
	}

	/* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
	raw_spin_lock(&nmi_reason_lock);
	reason = x86_platform.get_nmi_reason();

	if (reason & NMI_REASON_MASK) {
		if (reason & NMI_REASON_SERR)
			pci_serr_error(reason, regs);
		else if (reason & NMI_REASON_IOCHK)
			io_check_error(reason, regs);
#ifdef CONFIG_X86_32
		/*
		 * Reassert NMI in case it became active
		 * meanwhile as it's edge-triggered:
		 */
		reassert_nmi();
#endif
		__this_cpu_add(nmi_stats.external, 1);
		raw_spin_unlock(&nmi_reason_lock);
		return;
	}
	raw_spin_unlock(&nmi_reason_lock);

	/*
	 * Only one NMI can be latched at a time.  To handle
	 * this we may process multiple nmi handlers at once to
	 * cover the case where an NMI is dropped.  The downside
	 * to this approach is we may process an NMI prematurely,
	 * while its real NMI is sitting latched.  This will cause
	 * an unknown NMI on the next run of the NMI processing.
	 *
	 * We tried to flag that condition above, by setting the
	 * swallow_nmi flag when we process more than one event.
	 * This condition is also only present on the second half
	 * of a back-to-back NMI, so we flag that condition too.
	 *
	 * If both are true, we assume we already processed this
	 * NMI previously and we swallow it.  Otherwise we reset
	 * the logic.
	 *
	 * There are scenarios where we may accidentally swallow
	 * a 'real' unknown NMI.  For example, while processing
	 * a perf NMI another perf NMI comes in along with a
	 * 'real' unknown NMI.  These two NMIs get combined into
	 * one (as descibed above).  When the next NMI gets
	 * processed, it will be flagged by perf as handled, but
	 * noone will know that there was a 'real' unknown NMI sent
	 * also.  As a result it gets swallowed.  Or if the first
	 * perf NMI returns two events handled then the second
	 * NMI will get eaten by the logic below, again losing a
	 * 'real' unknown NMI.  But this is the best we can do
	 * for now.
	 */
	if (b2b && __this_cpu_read(swallow_nmi))
		__this_cpu_add(nmi_stats.swallow, 1);
	else
		unknown_nmi_error(reason, regs);
}
NOKPROBE_SYMBOL(default_do_nmi);

/*
 * NMIs can hit breakpoints which will cause it to lose its
 * NMI context with the CPU when the breakpoint does an iret.
 */
#ifdef CONFIG_X86_32
/*
 * For i386, NMIs use the same stack as the kernel, and we can
 * add a workaround to the iret problem in C (preventing nested
 * NMIs if an NMI takes a trap). Simply have 3 states the NMI
 * can be in:
 *
 *  1) not running
 *  2) executing
 *  3) latched
 *
 * When no NMI is in progress, it is in the "not running" state.
 * When an NMI comes in, it goes into the "executing" state.
 * Normally, if another NMI is triggered, it does not interrupt
 * the running NMI and the HW will simply latch it so that when
 * the first NMI finishes, it will restart the second NMI.
 * (Note, the latch is binary, thus multiple NMIs triggering,
 *  when one is running, are ignored. Only one NMI is restarted.)
 *
 * If an NMI hits a breakpoint that executes an iret, another
 * NMI can preempt it. We do not want to allow this new NMI
 * to run, but we want to execute it when the first one finishes.
 * We set the state to "latched", and the exit of the first NMI will
 * perform a dec_return, if the result is zero (NOT_RUNNING), then
 * it will simply exit the NMI handler. If not, the dec_return
 * would have set the state to NMI_EXECUTING (what we want it to
 * be when we are running). In this case, we simply jump back
 * to rerun the NMI handler again, and restart the 'latched' NMI.
 *
 * No trap (breakpoint or page fault) should be hit before nmi_restart,
 * thus there is no race between the first check of state for NOT_RUNNING
 * and setting it to NMI_EXECUTING. The HW will prevent nested NMIs
 * at this point.
 *
 * In case the NMI takes a page fault, we need to save off the CR2
 * because the NMI could have preempted another page fault and corrupt
 * the CR2 that is about to be read. As nested NMIs must be restarted
 * and they can not take breakpoints or page faults, the update of the
 * CR2 must be done before converting the nmi state back to NOT_RUNNING.
 * Otherwise, there would be a race of another nested NMI coming in
 * after setting state to NOT_RUNNING but before updating the nmi_cr2.
 */
enum nmi_states {
	NMI_NOT_RUNNING = 0,
	NMI_EXECUTING,
	NMI_LATCHED,
};
static DEFINE_PER_CPU(enum nmi_states, nmi_state);
static DEFINE_PER_CPU(unsigned long, nmi_cr2);

#define nmi_nesting_preprocess(regs)					\
	do {								\
		if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {	\
			this_cpu_write(nmi_state, NMI_LATCHED);		\
			return;						\
		}							\
		this_cpu_write(nmi_state, NMI_EXECUTING);		\
		this_cpu_write(nmi_cr2, read_cr2());			\
	} while (0);							\
	nmi_restart:

#define nmi_nesting_postprocess()					\
	do {								\
		if (unlikely(this_cpu_read(nmi_cr2) != read_cr2()))	\
			write_cr2(this_cpu_read(nmi_cr2));		\
		if (this_cpu_dec_return(nmi_state))			\
			goto nmi_restart;				\
	} while (0)
#else /* x86_64 */
/*
 * In x86_64 things are a bit more difficult. This has the same problem
 * where an NMI hitting a breakpoint that calls iret will remove the
 * NMI context, allowing a nested NMI to enter. What makes this more
 * difficult is that both NMIs and breakpoints have their own stack.
 * When a new NMI or breakpoint is executed, the stack is set to a fixed
 * point. If an NMI is nested, it will have its stack set at that same
 * fixed address that the first NMI had, and will start corrupting the
 * stack. This is handled in entry_64.S, but the same problem exists with
 * the breakpoint stack.
 *
 * If a breakpoint is being processed, and the debug stack is being used,
 * if an NMI comes in and also hits a breakpoint, the stack pointer
 * will be set to the same fixed address as the breakpoint that was
 * interrupted, causing that stack to be corrupted. To handle this case,
 * check if the stack that was interrupted is the debug stack, and if
 * so, change the IDT so that new breakpoints will use the current stack
 * and not switch to the fixed address. On return of the NMI, switch back
 * to the original IDT.
 */
static DEFINE_PER_CPU(int, update_debug_stack);

static inline void nmi_nesting_preprocess(struct pt_regs *regs)
{
	/*
	 * If we interrupted a breakpoint, it is possible that
	 * the nmi handler will have breakpoints too. We need to
	 * change the IDT such that breakpoints that happen here
	 * continue to use the NMI stack.
	 */
	if (unlikely(is_debug_stack(regs->sp))) {
		debug_stack_set_zero();
		this_cpu_write(update_debug_stack, 1);
	}
}

static inline void nmi_nesting_postprocess(void)
{
	if (unlikely(this_cpu_read(update_debug_stack))) {
		debug_stack_reset();
		this_cpu_write(update_debug_stack, 0);
	}
}
#endif

dotraplinkage notrace void
do_nmi(struct pt_regs *regs, long error_code)
{
	nmi_nesting_preprocess(regs);

	nmi_enter();

	inc_irq_stat(__nmi_count);

	if (!ignore_nmis)
		default_do_nmi(regs);

	nmi_exit();

	/* On i386, may loop back to preprocess */
	nmi_nesting_postprocess();
}
NOKPROBE_SYMBOL(do_nmi);

void stop_nmi(void)
{
	ignore_nmis++;
}

void restart_nmi(void)
{
	ignore_nmis--;
}

/* reset the back-to-back NMI logic */
void local_touch_nmi(void)
{
	__this_cpu_write(last_nmi_rip, 0);
}
EXPORT_SYMBOL_GPL(local_touch_nmi);