summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu/mce/intel.c
blob: 5627b1091b85639eb800a592d882832d81d1a941 (plain)
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
// SPDX-License-Identifier: GPL-2.0
/*
 * Intel specific MCE features.
 * Copyright 2004 Zwane Mwaikambo <zwane@linuxpower.ca>
 * Copyright (C) 2008, 2009 Intel Corporation
 * Author: Andi Kleen
 */

#include <linux/gfp.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/sched.h>
#include <linux/cpumask.h>
#include <asm/apic.h>
#include <asm/cpufeature.h>
#include <asm/intel-family.h>
#include <asm/processor.h>
#include <asm/msr.h>
#include <asm/mce.h>

#include "internal.h"

/*
 * Support for Intel Correct Machine Check Interrupts. This allows
 * the CPU to raise an interrupt when a corrected machine check happened.
 * Normally we pick those up using a regular polling timer.
 * Also supports reliable discovery of shared banks.
 */

/*
 * CMCI can be delivered to multiple cpus that share a machine check bank
 * so we need to designate a single cpu to process errors logged in each bank
 * in the interrupt handler (otherwise we would have many races and potential
 * double reporting of the same error).
 * Note that this can change when a cpu is offlined or brought online since
 * some MCA banks are shared across cpus. When a cpu is offlined, cmci_clear()
 * disables CMCI on all banks owned by the cpu and clears this bitfield. At
 * this point, cmci_rediscover() kicks in and a different cpu may end up
 * taking ownership of some of the shared MCA banks that were previously
 * owned by the offlined cpu.
 */
static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);

/*
 * CMCI storm detection backoff counter
 *
 * During storm, we reset this counter to INITIAL_CHECK_INTERVAL in case we've
 * encountered an error. If not, we decrement it by one. We signal the end of
 * the CMCI storm when it reaches 0.
 */
static DEFINE_PER_CPU(int, cmci_backoff_cnt);

/*
 * cmci_discover_lock protects against parallel discovery attempts
 * which could race against each other.
 */
static DEFINE_RAW_SPINLOCK(cmci_discover_lock);

#define CMCI_THRESHOLD		1
#define CMCI_POLL_INTERVAL	(30 * HZ)
#define CMCI_STORM_INTERVAL	(HZ)
#define CMCI_STORM_THRESHOLD	15

static DEFINE_PER_CPU(unsigned long, cmci_time_stamp);
static DEFINE_PER_CPU(unsigned int, cmci_storm_cnt);
static DEFINE_PER_CPU(unsigned int, cmci_storm_state);

enum {
	CMCI_STORM_NONE,
	CMCI_STORM_ACTIVE,
	CMCI_STORM_SUBSIDED,
};

static atomic_t cmci_storm_on_cpus;

static int cmci_supported(int *banks)
{
	u64 cap;

	if (mca_cfg.cmci_disabled || mca_cfg.ignore_ce)
		return 0;

	/*
	 * Vendor check is not strictly needed, but the initial
	 * initialization is vendor keyed and this
	 * makes sure none of the backdoors are entered otherwise.
	 */
	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
	    boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
		return 0;

	if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6)
		return 0;
	rdmsrl(MSR_IA32_MCG_CAP, cap);
	*banks = min_t(unsigned, MAX_NR_BANKS, cap & 0xff);
	return !!(cap & MCG_CMCI_P);
}

static bool lmce_supported(void)
{
	u64 tmp;

	if (mca_cfg.lmce_disabled)
		return false;

	rdmsrl(MSR_IA32_MCG_CAP, tmp);

	/*
	 * LMCE depends on recovery support in the processor. Hence both
	 * MCG_SER_P and MCG_LMCE_P should be present in MCG_CAP.
	 */
	if ((tmp & (MCG_SER_P | MCG_LMCE_P)) !=
		   (MCG_SER_P | MCG_LMCE_P))
		return false;

	/*
	 * BIOS should indicate support for LMCE by setting bit 20 in
	 * IA32_FEAT_CTL without which touching MCG_EXT_CTL will generate a #GP
	 * fault.  The MSR must also be locked for LMCE_ENABLED to take effect.
	 * WARN if the MSR isn't locked as init_ia32_feat_ctl() unconditionally
	 * locks the MSR in the event that it wasn't already locked by BIOS.
	 */
	rdmsrl(MSR_IA32_FEAT_CTL, tmp);
	if (WARN_ON_ONCE(!(tmp & FEAT_CTL_LOCKED)))
		return false;

	return tmp & FEAT_CTL_LMCE_ENABLED;
}

bool mce_intel_cmci_poll(void)
{
	if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
		return false;

	/*
	 * Reset the counter if we've logged an error in the last poll
	 * during the storm.
	 */
	if (machine_check_poll(0, this_cpu_ptr(&mce_banks_owned)))
		this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL);
	else
		this_cpu_dec(cmci_backoff_cnt);

	return true;
}

void mce_intel_hcpu_update(unsigned long cpu)
{
	if (per_cpu(cmci_storm_state, cpu) == CMCI_STORM_ACTIVE)
		atomic_dec(&cmci_storm_on_cpus);

	per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE;
}

static void cmci_toggle_interrupt_mode(bool on)
{
	unsigned long flags, *owned;
	int bank;
	u64 val;

	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
	owned = this_cpu_ptr(mce_banks_owned);
	for_each_set_bit(bank, owned, MAX_NR_BANKS) {
		rdmsrl(MSR_IA32_MCx_CTL2(bank), val);

		if (on)
			val |= MCI_CTL2_CMCI_EN;
		else
			val &= ~MCI_CTL2_CMCI_EN;

		wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
	}
	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
}

unsigned long cmci_intel_adjust_timer(unsigned long interval)
{
	if ((this_cpu_read(cmci_backoff_cnt) > 0) &&
	    (__this_cpu_read(cmci_storm_state) == CMCI_STORM_ACTIVE)) {
		mce_notify_irq();
		return CMCI_STORM_INTERVAL;
	}

	switch (__this_cpu_read(cmci_storm_state)) {
	case CMCI_STORM_ACTIVE:

		/*
		 * We switch back to interrupt mode once the poll timer has
		 * silenced itself. That means no events recorded and the timer
		 * interval is back to our poll interval.
		 */
		__this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED);
		if (!atomic_sub_return(1, &cmci_storm_on_cpus))
			pr_notice("CMCI storm subsided: switching to interrupt mode\n");

		/* FALLTHROUGH */

	case CMCI_STORM_SUBSIDED:
		/*
		 * We wait for all CPUs to go back to SUBSIDED state. When that
		 * happens we switch back to interrupt mode.
		 */
		if (!atomic_read(&cmci_storm_on_cpus)) {
			__this_cpu_write(cmci_storm_state, CMCI_STORM_NONE);
			cmci_toggle_interrupt_mode(true);
			cmci_recheck();
		}
		return CMCI_POLL_INTERVAL;
	default:

		/* We have shiny weather. Let the poll do whatever it thinks. */
		return interval;
	}
}

static bool cmci_storm_detect(void)
{
	unsigned int cnt = __this_cpu_read(cmci_storm_cnt);
	unsigned long ts = __this_cpu_read(cmci_time_stamp);
	unsigned long now = jiffies;
	int r;

	if (__this_cpu_read(cmci_storm_state) != CMCI_STORM_NONE)
		return true;

	if (time_before_eq(now, ts + CMCI_STORM_INTERVAL)) {
		cnt++;
	} else {
		cnt = 1;
		__this_cpu_write(cmci_time_stamp, now);
	}
	__this_cpu_write(cmci_storm_cnt, cnt);

	if (cnt <= CMCI_STORM_THRESHOLD)
		return false;

	cmci_toggle_interrupt_mode(false);
	__this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE);
	r = atomic_add_return(1, &cmci_storm_on_cpus);
	mce_timer_kick(CMCI_STORM_INTERVAL);
	this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL);

	if (r == 1)
		pr_notice("CMCI storm detected: switching to poll mode\n");
	return true;
}

/*
 * The interrupt handler. This is called on every event.
 * Just call the poller directly to log any events.
 * This could in theory increase the threshold under high load,
 * but doesn't for now.
 */
static void intel_threshold_interrupt(void)
{
	if (cmci_storm_detect())
		return;

	machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
}

/*
 * Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks
 * on this CPU. Use the algorithm recommended in the SDM to discover shared
 * banks.
 */
static void cmci_discover(int banks)
{
	unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned);
	unsigned long flags;
	int i;
	int bios_wrong_thresh = 0;

	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
	for (i = 0; i < banks; i++) {
		u64 val;
		int bios_zero_thresh = 0;

		if (test_bit(i, owned))
			continue;

		/* Skip banks in firmware first mode */
		if (test_bit(i, mce_banks_ce_disabled))
			continue;

		rdmsrl(MSR_IA32_MCx_CTL2(i), val);

		/* Already owned by someone else? */
		if (val & MCI_CTL2_CMCI_EN) {
			clear_bit(i, owned);
			__clear_bit(i, this_cpu_ptr(mce_poll_banks));
			continue;
		}

		if (!mca_cfg.bios_cmci_threshold) {
			val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK;
			val |= CMCI_THRESHOLD;
		} else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) {
			/*
			 * If bios_cmci_threshold boot option was specified
			 * but the threshold is zero, we'll try to initialize
			 * it to 1.
			 */
			bios_zero_thresh = 1;
			val |= CMCI_THRESHOLD;
		}

		val |= MCI_CTL2_CMCI_EN;
		wrmsrl(MSR_IA32_MCx_CTL2(i), val);
		rdmsrl(MSR_IA32_MCx_CTL2(i), val);

		/* Did the enable bit stick? -- the bank supports CMCI */
		if (val & MCI_CTL2_CMCI_EN) {
			set_bit(i, owned);
			__clear_bit(i, this_cpu_ptr(mce_poll_banks));
			/*
			 * We are able to set thresholds for some banks that
			 * had a threshold of 0. This means the BIOS has not
			 * set the thresholds properly or does not work with
			 * this boot option. Note down now and report later.
			 */
			if (mca_cfg.bios_cmci_threshold && bios_zero_thresh &&
					(val & MCI_CTL2_CMCI_THRESHOLD_MASK))
				bios_wrong_thresh = 1;
		} else {
			WARN_ON(!test_bit(i, this_cpu_ptr(mce_poll_banks)));
		}
	}
	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
	if (mca_cfg.bios_cmci_threshold && bios_wrong_thresh) {
		pr_info_once(
			"bios_cmci_threshold: Some banks do not have valid thresholds set\n");
		pr_info_once(
			"bios_cmci_threshold: Make sure your BIOS supports this boot option\n");
	}
}

/*
 * Just in case we missed an event during initialization check
 * all the CMCI owned banks.
 */
void cmci_recheck(void)
{
	unsigned long flags;
	int banks;

	if (!mce_available(raw_cpu_ptr(&cpu_info)) || !cmci_supported(&banks))
		return;

	local_irq_save(flags);
	machine_check_poll(0, this_cpu_ptr(&mce_banks_owned));
	local_irq_restore(flags);
}

/* Caller must hold the lock on cmci_discover_lock */
static void __cmci_disable_bank(int bank)
{
	u64 val;

	if (!test_bit(bank, this_cpu_ptr(mce_banks_owned)))
		return;
	rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
	val &= ~MCI_CTL2_CMCI_EN;
	wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
	__clear_bit(bank, this_cpu_ptr(mce_banks_owned));
}

/*
 * Disable CMCI on this CPU for all banks it owns when it goes down.
 * This allows other CPUs to claim the banks on rediscovery.
 */
void cmci_clear(void)
{
	unsigned long flags;
	int i;
	int banks;

	if (!cmci_supported(&banks))
		return;
	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
	for (i = 0; i < banks; i++)
		__cmci_disable_bank(i);
	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
}

static void cmci_rediscover_work_func(void *arg)
{
	int banks;

	/* Recheck banks in case CPUs don't all have the same */
	if (cmci_supported(&banks))
		cmci_discover(banks);
}

/* After a CPU went down cycle through all the others and rediscover */
void cmci_rediscover(void)
{
	int banks;

	if (!cmci_supported(&banks))
		return;

	on_each_cpu(cmci_rediscover_work_func, NULL, 1);
}

/*
 * Reenable CMCI on this CPU in case a CPU down failed.
 */
void cmci_reenable(void)
{
	int banks;
	if (cmci_supported(&banks))
		cmci_discover(banks);
}

void cmci_disable_bank(int bank)
{
	int banks;
	unsigned long flags;

	if (!cmci_supported(&banks))
		return;

	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
	__cmci_disable_bank(bank);
	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
}

void intel_init_cmci(void)
{
	int banks;

	if (!cmci_supported(&banks))
		return;

	mce_threshold_vector = intel_threshold_interrupt;
	cmci_discover(banks);
	/*
	 * For CPU #0 this runs with still disabled APIC, but that's
	 * ok because only the vector is set up. We still do another
	 * check for the banks later for CPU #0 just to make sure
	 * to not miss any events.
	 */
	apic_write(APIC_LVTCMCI, THRESHOLD_APIC_VECTOR|APIC_DM_FIXED);
	cmci_recheck();
}

void intel_init_lmce(void)
{
	u64 val;

	if (!lmce_supported())
		return;

	rdmsrl(MSR_IA32_MCG_EXT_CTL, val);

	if (!(val & MCG_EXT_CTL_LMCE_EN))
		wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
}

void intel_clear_lmce(void)
{
	u64 val;

	if (!lmce_supported())
		return;

	rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
	val &= ~MCG_EXT_CTL_LMCE_EN;
	wrmsrl(MSR_IA32_MCG_EXT_CTL, val);
}

static void intel_ppin_init(struct cpuinfo_x86 *c)
{
	unsigned long long val;

	/*
	 * Even if testing the presence of the MSR would be enough, we don't
	 * want to risk the situation where other models reuse this MSR for
	 * other purposes.
	 */
	switch (c->x86_model) {
	case INTEL_FAM6_IVYBRIDGE_X:
	case INTEL_FAM6_HASWELL_X:
	case INTEL_FAM6_BROADWELL_D:
	case INTEL_FAM6_BROADWELL_X:
	case INTEL_FAM6_SKYLAKE_X:
	case INTEL_FAM6_ICELAKE_X:
	case INTEL_FAM6_XEON_PHI_KNL:
	case INTEL_FAM6_XEON_PHI_KNM:

		if (rdmsrl_safe(MSR_PPIN_CTL, &val))
			return;

		if ((val & 3UL) == 1UL) {
			/* PPIN available but disabled: */
			return;
		}

		/* If PPIN is disabled, but not locked, try to enable: */
		if (!(val & 3UL)) {
			wrmsrl_safe(MSR_PPIN_CTL,  val | 2UL);
			rdmsrl_safe(MSR_PPIN_CTL, &val);
		}

		if ((val & 3UL) == 2UL)
			set_cpu_cap(c, X86_FEATURE_INTEL_PPIN);
	}
}

void mce_intel_feature_init(struct cpuinfo_x86 *c)
{
	intel_init_thermal(c);
	intel_init_cmci();
	intel_init_lmce();
	intel_ppin_init(c);
}

void mce_intel_feature_clear(struct cpuinfo_x86 *c)
{
	intel_clear_lmce();
}