summaryrefslogtreecommitdiffstats
path: root/drivers/hwmon/coretemp.c
blob: 30a19d711f8985fb7aa22cf160af8a6483fbc9e3 (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
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
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
// SPDX-License-Identifier: GPL-2.0-only
/*
 * coretemp.c - Linux kernel module for hardware monitoring
 *
 * Copyright (C) 2007 Rudolf Marek <r.marek@assembler.cz>
 *
 * Inspired from many hwmon drivers
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/module.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/jiffies.h>
#include <linux/hwmon.h>
#include <linux/sysfs.h>
#include <linux/hwmon-sysfs.h>
#include <linux/err.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/platform_device.h>
#include <linux/cpu.h>
#include <linux/smp.h>
#include <linux/moduleparam.h>
#include <linux/pci.h>
#include <asm/msr.h>
#include <asm/processor.h>
#include <asm/cpu_device_id.h>

#define DRVNAME	"coretemp"

/*
 * force_tjmax only matters when TjMax can't be read from the CPU itself.
 * When set, it replaces the driver's suboptimal heuristic.
 */
static int force_tjmax;
module_param_named(tjmax, force_tjmax, int, 0444);
MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");

#define PKG_SYSFS_ATTR_NO	1	/* Sysfs attribute for package temp */
#define BASE_SYSFS_ATTR_NO	2	/* Sysfs Base attr no for coretemp */
#define NUM_REAL_CORES		128	/* Number of Real cores per cpu */
#define CORETEMP_NAME_LENGTH	19	/* String Length of attrs */
#define MAX_CORE_ATTRS		4	/* Maximum no of basic attrs */
#define TOTAL_ATTRS		(MAX_CORE_ATTRS + 1)
#define MAX_CORE_DATA		(NUM_REAL_CORES + BASE_SYSFS_ATTR_NO)

#ifdef CONFIG_SMP
#define for_each_sibling(i, cpu) \
	for_each_cpu(i, topology_sibling_cpumask(cpu))
#else
#define for_each_sibling(i, cpu)	for (i = 0; false; )
#endif

/*
 * Per-Core Temperature Data
 * @last_updated: The time when the current temperature value was updated
 *		earlier (in jiffies).
 * @cpu_core_id: The CPU Core from which temperature values should be read
 *		This value is passed as "id" field to rdmsr/wrmsr functions.
 * @status_reg: One of IA32_THERM_STATUS or IA32_PACKAGE_THERM_STATUS,
 *		from where the temperature values should be read.
 * @attr_size:  Total number of pre-core attrs displayed in the sysfs.
 * @is_pkg_data: If this is 1, the temp_data holds pkgtemp data.
 *		Otherwise, temp_data holds coretemp data.
 * @valid: If this is 1, the current temperature is valid.
 */
struct temp_data {
	int temp;
	int ttarget;
	int tjmax;
	unsigned long last_updated;
	unsigned int cpu;
	u32 cpu_core_id;
	u32 status_reg;
	int attr_size;
	bool is_pkg_data;
	bool valid;
	struct sensor_device_attribute sd_attrs[TOTAL_ATTRS];
	char attr_name[TOTAL_ATTRS][CORETEMP_NAME_LENGTH];
	struct attribute *attrs[TOTAL_ATTRS + 1];
	struct attribute_group attr_group;
	struct mutex update_lock;
};

/* Platform Data per Physical CPU */
struct platform_data {
	struct device		*hwmon_dev;
	u16			pkg_id;
	u16			cpu_map[NUM_REAL_CORES];
	struct ida		ida;
	struct cpumask		cpumask;
	struct temp_data	*core_data[MAX_CORE_DATA];
	struct device_attribute name_attr;
};

/* Keep track of how many zone pointers we allocated in init() */
static int max_zones __read_mostly;
/* Array of zone pointers. Serialized by cpu hotplug lock */
static struct platform_device **zone_devices;

static ssize_t show_label(struct device *dev,
				struct device_attribute *devattr, char *buf)
{
	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
	struct platform_data *pdata = dev_get_drvdata(dev);
	struct temp_data *tdata = pdata->core_data[attr->index];

	if (tdata->is_pkg_data)
		return sprintf(buf, "Package id %u\n", pdata->pkg_id);

	return sprintf(buf, "Core %u\n", tdata->cpu_core_id);
}

static ssize_t show_crit_alarm(struct device *dev,
				struct device_attribute *devattr, char *buf)
{
	u32 eax, edx;
	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
	struct platform_data *pdata = dev_get_drvdata(dev);
	struct temp_data *tdata = pdata->core_data[attr->index];

	mutex_lock(&tdata->update_lock);
	rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
	mutex_unlock(&tdata->update_lock);

	return sprintf(buf, "%d\n", (eax >> 5) & 1);
}

static ssize_t show_tjmax(struct device *dev,
			struct device_attribute *devattr, char *buf)
{
	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
	struct platform_data *pdata = dev_get_drvdata(dev);

	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->tjmax);
}

static ssize_t show_ttarget(struct device *dev,
				struct device_attribute *devattr, char *buf)
{
	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
	struct platform_data *pdata = dev_get_drvdata(dev);

	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->ttarget);
}

static ssize_t show_temp(struct device *dev,
			struct device_attribute *devattr, char *buf)
{
	u32 eax, edx;
	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
	struct platform_data *pdata = dev_get_drvdata(dev);
	struct temp_data *tdata = pdata->core_data[attr->index];

	mutex_lock(&tdata->update_lock);

	/* Check whether the time interval has elapsed */
	if (!tdata->valid || time_after(jiffies, tdata->last_updated + HZ)) {
		rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
		/*
		 * Ignore the valid bit. In all observed cases the register
		 * value is either low or zero if the valid bit is 0.
		 * Return it instead of reporting an error which doesn't
		 * really help at all.
		 */
		tdata->temp = tdata->tjmax - ((eax >> 16) & 0x7f) * 1000;
		tdata->valid = true;
		tdata->last_updated = jiffies;
	}

	mutex_unlock(&tdata->update_lock);
	return sprintf(buf, "%d\n", tdata->temp);
}

struct tjmax_pci {
	unsigned int device;
	int tjmax;
};

static const struct tjmax_pci tjmax_pci_table[] = {
	{ 0x0708, 110000 },	/* CE41x0 (Sodaville ) */
	{ 0x0c72, 102000 },	/* Atom S1240 (Centerton) */
	{ 0x0c73, 95000 },	/* Atom S1220 (Centerton) */
	{ 0x0c75, 95000 },	/* Atom S1260 (Centerton) */
};

struct tjmax {
	char const *id;
	int tjmax;
};

static const struct tjmax tjmax_table[] = {
	{ "CPU  230", 100000 },		/* Model 0x1c, stepping 2	*/
	{ "CPU  330", 125000 },		/* Model 0x1c, stepping 2	*/
};

struct tjmax_model {
	u8 model;
	u8 mask;
	int tjmax;
};

#define ANY 0xff

static const struct tjmax_model tjmax_model_table[] = {
	{ 0x1c, 10, 100000 },	/* D4xx, K4xx, N4xx, D5xx, K5xx, N5xx */
	{ 0x1c, ANY, 90000 },	/* Z5xx, N2xx, possibly others
				 * Note: Also matches 230 and 330,
				 * which are covered by tjmax_table
				 */
	{ 0x26, ANY, 90000 },	/* Atom Tunnel Creek (Exx), Lincroft (Z6xx)
				 * Note: TjMax for E6xxT is 110C, but CPU type
				 * is undetectable by software
				 */
	{ 0x27, ANY, 90000 },	/* Atom Medfield (Z2460) */
	{ 0x35, ANY, 90000 },	/* Atom Clover Trail/Cloverview (Z27x0) */
	{ 0x36, ANY, 100000 },	/* Atom Cedar Trail/Cedarview (N2xxx, D2xxx)
				 * Also matches S12x0 (stepping 9), covered by
				 * PCI table
				 */
};

static int adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
{
	/* The 100C is default for both mobile and non mobile CPUs */

	int tjmax = 100000;
	int tjmax_ee = 85000;
	int usemsr_ee = 1;
	int err;
	u32 eax, edx;
	int i;
	u16 devfn = PCI_DEVFN(0, 0);
	struct pci_dev *host_bridge = pci_get_domain_bus_and_slot(0, 0, devfn);

	/*
	 * Explicit tjmax table entries override heuristics.
	 * First try PCI host bridge IDs, followed by model ID strings
	 * and model/stepping information.
	 */
	if (host_bridge && host_bridge->vendor == PCI_VENDOR_ID_INTEL) {
		for (i = 0; i < ARRAY_SIZE(tjmax_pci_table); i++) {
			if (host_bridge->device == tjmax_pci_table[i].device)
				return tjmax_pci_table[i].tjmax;
		}
	}

	for (i = 0; i < ARRAY_SIZE(tjmax_table); i++) {
		if (strstr(c->x86_model_id, tjmax_table[i].id))
			return tjmax_table[i].tjmax;
	}

	for (i = 0; i < ARRAY_SIZE(tjmax_model_table); i++) {
		const struct tjmax_model *tm = &tjmax_model_table[i];
		if (c->x86_model == tm->model &&
		    (tm->mask == ANY || c->x86_stepping == tm->mask))
			return tm->tjmax;
	}

	/* Early chips have no MSR for TjMax */

	if (c->x86_model == 0xf && c->x86_stepping < 4)
		usemsr_ee = 0;

	if (c->x86_model > 0xe && usemsr_ee) {
		u8 platform_id;

		/*
		 * Now we can detect the mobile CPU using Intel provided table
		 * http://softwarecommunity.intel.com/Wiki/Mobility/720.htm
		 * For Core2 cores, check MSR 0x17, bit 28 1 = Mobile CPU
		 */
		err = rdmsr_safe_on_cpu(id, 0x17, &eax, &edx);
		if (err) {
			dev_warn(dev,
				 "Unable to access MSR 0x17, assuming desktop"
				 " CPU\n");
			usemsr_ee = 0;
		} else if (c->x86_model < 0x17 && !(eax & 0x10000000)) {
			/*
			 * Trust bit 28 up to Penryn, I could not find any
			 * documentation on that; if you happen to know
			 * someone at Intel please ask
			 */
			usemsr_ee = 0;
		} else {
			/* Platform ID bits 52:50 (EDX starts at bit 32) */
			platform_id = (edx >> 18) & 0x7;

			/*
			 * Mobile Penryn CPU seems to be platform ID 7 or 5
			 * (guesswork)
			 */
			if (c->x86_model == 0x17 &&
			    (platform_id == 5 || platform_id == 7)) {
				/*
				 * If MSR EE bit is set, set it to 90 degrees C,
				 * otherwise 105 degrees C
				 */
				tjmax_ee = 90000;
				tjmax = 105000;
			}
		}
	}

	if (usemsr_ee) {
		err = rdmsr_safe_on_cpu(id, 0xee, &eax, &edx);
		if (err) {
			dev_warn(dev,
				 "Unable to access MSR 0xEE, for Tjmax, left"
				 " at default\n");
		} else if (eax & 0x40000000) {
			tjmax = tjmax_ee;
		}
	} else if (tjmax == 100000) {
		/*
		 * If we don't use msr EE it means we are desktop CPU
		 * (with exeception of Atom)
		 */
		dev_warn(dev, "Using relative temperature scale!\n");
	}

	return tjmax;
}

static bool cpu_has_tjmax(struct cpuinfo_x86 *c)
{
	u8 model = c->x86_model;

	return model > 0xe &&
	       model != 0x1c &&
	       model != 0x26 &&
	       model != 0x27 &&
	       model != 0x35 &&
	       model != 0x36;
}

static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
{
	int err;
	u32 eax, edx;
	u32 val;

	/*
	 * A new feature of current Intel(R) processors, the
	 * IA32_TEMPERATURE_TARGET contains the TjMax value
	 */
	err = rdmsr_safe_on_cpu(id, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
	if (err) {
		if (cpu_has_tjmax(c))
			dev_warn(dev, "Unable to read TjMax from CPU %u\n", id);
	} else {
		val = (eax >> 16) & 0xff;
		/*
		 * If the TjMax is not plausible, an assumption
		 * will be used
		 */
		if (val) {
			dev_dbg(dev, "TjMax is %d degrees C\n", val);
			return val * 1000;
		}
	}

	if (force_tjmax) {
		dev_notice(dev, "TjMax forced to %d degrees C by user\n",
			   force_tjmax);
		return force_tjmax * 1000;
	}

	/*
	 * An assumption is made for early CPUs and unreadable MSR.
	 * NOTE: the calculated value may not be correct.
	 */
	return adjust_tjmax(c, id, dev);
}

static int create_core_attrs(struct temp_data *tdata, struct device *dev,
			     int attr_no)
{
	int i;
	static ssize_t (*const rd_ptr[TOTAL_ATTRS]) (struct device *dev,
			struct device_attribute *devattr, char *buf) = {
			show_label, show_crit_alarm, show_temp, show_tjmax,
			show_ttarget };
	static const char *const suffixes[TOTAL_ATTRS] = {
		"label", "crit_alarm", "input", "crit", "max"
	};

	for (i = 0; i < tdata->attr_size; i++) {
		snprintf(tdata->attr_name[i], CORETEMP_NAME_LENGTH,
			 "temp%d_%s", attr_no, suffixes[i]);
		sysfs_attr_init(&tdata->sd_attrs[i].dev_attr.attr);
		tdata->sd_attrs[i].dev_attr.attr.name = tdata->attr_name[i];
		tdata->sd_attrs[i].dev_attr.attr.mode = 0444;
		tdata->sd_attrs[i].dev_attr.show = rd_ptr[i];
		tdata->sd_attrs[i].index = attr_no;
		tdata->attrs[i] = &tdata->sd_attrs[i].dev_attr.attr;
	}
	tdata->attr_group.attrs = tdata->attrs;
	return sysfs_create_group(&dev->kobj, &tdata->attr_group);
}


static int chk_ucode_version(unsigned int cpu)
{
	struct cpuinfo_x86 *c = &cpu_data(cpu);

	/*
	 * Check if we have problem with errata AE18 of Core processors:
	 * Readings might stop update when processor visited too deep sleep,
	 * fixed for stepping D0 (6EC).
	 */
	if (c->x86_model == 0xe && c->x86_stepping < 0xc && c->microcode < 0x39) {
		pr_err("Errata AE18 not fixed, update BIOS or microcode of the CPU!\n");
		return -ENODEV;
	}
	return 0;
}

static struct platform_device *coretemp_get_pdev(unsigned int cpu)
{
	int id = topology_logical_die_id(cpu);

	if (id >= 0 && id < max_zones)
		return zone_devices[id];
	return NULL;
}

static struct temp_data *init_temp_data(unsigned int cpu, int pkg_flag)
{
	struct temp_data *tdata;

	tdata = kzalloc(sizeof(struct temp_data), GFP_KERNEL);
	if (!tdata)
		return NULL;

	tdata->status_reg = pkg_flag ? MSR_IA32_PACKAGE_THERM_STATUS :
							MSR_IA32_THERM_STATUS;
	tdata->is_pkg_data = pkg_flag;
	tdata->cpu = cpu;
	tdata->cpu_core_id = topology_core_id(cpu);
	tdata->attr_size = MAX_CORE_ATTRS;
	mutex_init(&tdata->update_lock);
	return tdata;
}

static int create_core_data(struct platform_device *pdev, unsigned int cpu,
			    int pkg_flag)
{
	struct temp_data *tdata;
	struct platform_data *pdata = platform_get_drvdata(pdev);
	struct cpuinfo_x86 *c = &cpu_data(cpu);
	u32 eax, edx;
	int err, index, attr_no;

	/*
	 * Find attr number for sysfs:
	 * We map the attr number to core id of the CPU
	 * The attr number is always core id + 2
	 * The Pkgtemp will always show up as temp1_*, if available
	 */
	if (pkg_flag) {
		attr_no = PKG_SYSFS_ATTR_NO;
	} else {
		index = ida_alloc(&pdata->ida, GFP_KERNEL);
		if (index < 0)
			return index;
		pdata->cpu_map[index] = topology_core_id(cpu);
		attr_no = index + BASE_SYSFS_ATTR_NO;
	}

	if (attr_no > MAX_CORE_DATA - 1) {
		err = -ERANGE;
		goto ida_free;
	}

	tdata = init_temp_data(cpu, pkg_flag);
	if (!tdata) {
		err = -ENOMEM;
		goto ida_free;
	}

	/* Test if we can access the status register */
	err = rdmsr_safe_on_cpu(cpu, tdata->status_reg, &eax, &edx);
	if (err)
		goto exit_free;

	/* We can access status register. Get Critical Temperature */
	tdata->tjmax = get_tjmax(c, cpu, &pdev->dev);

	/*
	 * Read the still undocumented bits 8:15 of IA32_TEMPERATURE_TARGET.
	 * The target temperature is available on older CPUs but not in this
	 * register. Atoms don't have the register at all.
	 */
	if (c->x86_model > 0xe && c->x86_model != 0x1c) {
		err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET,
					&eax, &edx);
		if (!err) {
			tdata->ttarget
			  = tdata->tjmax - ((eax >> 8) & 0xff) * 1000;
			tdata->attr_size++;
		}
	}

	pdata->core_data[attr_no] = tdata;

	/* Create sysfs interfaces */
	err = create_core_attrs(tdata, pdata->hwmon_dev, attr_no);
	if (err)
		goto exit_free;

	return 0;
exit_free:
	pdata->core_data[attr_no] = NULL;
	kfree(tdata);
ida_free:
	if (!pkg_flag)
		ida_free(&pdata->ida, index);
	return err;
}

static void
coretemp_add_core(struct platform_device *pdev, unsigned int cpu, int pkg_flag)
{
	if (create_core_data(pdev, cpu, pkg_flag))
		dev_err(&pdev->dev, "Adding Core %u failed\n", cpu);
}

static void coretemp_remove_core(struct platform_data *pdata, int indx)
{
	struct temp_data *tdata = pdata->core_data[indx];

	/* if we errored on add then this is already gone */
	if (!tdata)
		return;

	/* Remove the sysfs attributes */
	sysfs_remove_group(&pdata->hwmon_dev->kobj, &tdata->attr_group);

	kfree(pdata->core_data[indx]);
	pdata->core_data[indx] = NULL;

	if (indx >= BASE_SYSFS_ATTR_NO)
		ida_free(&pdata->ida, indx - BASE_SYSFS_ATTR_NO);
}

static int coretemp_probe(struct platform_device *pdev)
{
	struct device *dev = &pdev->dev;
	struct platform_data *pdata;

	/* Initialize the per-zone data structures */
	pdata = devm_kzalloc(dev, sizeof(struct platform_data), GFP_KERNEL);
	if (!pdata)
		return -ENOMEM;

	pdata->pkg_id = pdev->id;
	ida_init(&pdata->ida);
	platform_set_drvdata(pdev, pdata);

	pdata->hwmon_dev = devm_hwmon_device_register_with_groups(dev, DRVNAME,
								  pdata, NULL);
	return PTR_ERR_OR_ZERO(pdata->hwmon_dev);
}

static int coretemp_remove(struct platform_device *pdev)
{
	struct platform_data *pdata = platform_get_drvdata(pdev);
	int i;

	for (i = MAX_CORE_DATA - 1; i >= 0; --i)
		if (pdata->core_data[i])
			coretemp_remove_core(pdata, i);

	ida_destroy(&pdata->ida);
	return 0;
}

static struct platform_driver coretemp_driver = {
	.driver = {
		.name = DRVNAME,
	},
	.probe = coretemp_probe,
	.remove = coretemp_remove,
};

static struct platform_device *coretemp_device_add(unsigned int cpu)
{
	int err, zoneid = topology_logical_die_id(cpu);
	struct platform_device *pdev;

	if (zoneid < 0)
		return ERR_PTR(-ENOMEM);

	pdev = platform_device_alloc(DRVNAME, zoneid);
	if (!pdev)
		return ERR_PTR(-ENOMEM);

	err = platform_device_add(pdev);
	if (err) {
		platform_device_put(pdev);
		return ERR_PTR(err);
	}

	zone_devices[zoneid] = pdev;
	return pdev;
}

static int coretemp_cpu_online(unsigned int cpu)
{
	struct platform_device *pdev = coretemp_get_pdev(cpu);
	struct cpuinfo_x86 *c = &cpu_data(cpu);
	struct platform_data *pdata;

	/*
	 * Don't execute this on resume as the offline callback did
	 * not get executed on suspend.
	 */
	if (cpuhp_tasks_frozen)
		return 0;

	/*
	 * CPUID.06H.EAX[0] indicates whether the CPU has thermal
	 * sensors. We check this bit only, all the early CPUs
	 * without thermal sensors will be filtered out.
	 */
	if (!cpu_has(c, X86_FEATURE_DTHERM))
		return -ENODEV;

	if (!pdev) {
		/* Check the microcode version of the CPU */
		if (chk_ucode_version(cpu))
			return -EINVAL;

		/*
		 * Alright, we have DTS support.
		 * We are bringing the _first_ core in this pkg
		 * online. So, initialize per-pkg data structures and
		 * then bring this core online.
		 */
		pdev = coretemp_device_add(cpu);
		if (IS_ERR(pdev))
			return PTR_ERR(pdev);

		/*
		 * Check whether pkgtemp support is available.
		 * If so, add interfaces for pkgtemp.
		 */
		if (cpu_has(c, X86_FEATURE_PTS))
			coretemp_add_core(pdev, cpu, 1);
	}

	pdata = platform_get_drvdata(pdev);
	/*
	 * Check whether a thread sibling is already online. If not add the
	 * interface for this CPU core.
	 */
	if (!cpumask_intersects(&pdata->cpumask, topology_sibling_cpumask(cpu)))
		coretemp_add_core(pdev, cpu, 0);

	cpumask_set_cpu(cpu, &pdata->cpumask);
	return 0;
}

static int coretemp_cpu_offline(unsigned int cpu)
{
	struct platform_device *pdev = coretemp_get_pdev(cpu);
	struct platform_data *pd;
	struct temp_data *tdata;
	int i, indx = -1, target;

	/*
	 * Don't execute this on suspend as the device remove locks
	 * up the machine.
	 */
	if (cpuhp_tasks_frozen)
		return 0;

	/* If the physical CPU device does not exist, just return */
	if (!pdev)
		return 0;

	pd = platform_get_drvdata(pdev);

	for (i = 0; i < NUM_REAL_CORES; i++) {
		if (pd->cpu_map[i] == topology_core_id(cpu)) {
			indx = i + BASE_SYSFS_ATTR_NO;
			break;
		}
	}

	/* Too many cores and this core is not populated, just return */
	if (indx < 0)
		return 0;

	tdata = pd->core_data[indx];

	cpumask_clear_cpu(cpu, &pd->cpumask);

	/*
	 * If this is the last thread sibling, remove the CPU core
	 * interface, If there is still a sibling online, transfer the
	 * target cpu of that core interface to it.
	 */
	target = cpumask_any_and(&pd->cpumask, topology_sibling_cpumask(cpu));
	if (target >= nr_cpu_ids) {
		coretemp_remove_core(pd, indx);
	} else if (tdata && tdata->cpu == cpu) {
		mutex_lock(&tdata->update_lock);
		tdata->cpu = target;
		mutex_unlock(&tdata->update_lock);
	}

	/*
	 * If all cores in this pkg are offline, remove the device. This
	 * will invoke the platform driver remove function, which cleans up
	 * the rest.
	 */
	if (cpumask_empty(&pd->cpumask)) {
		zone_devices[topology_logical_die_id(cpu)] = NULL;
		platform_device_unregister(pdev);
		return 0;
	}

	/*
	 * Check whether this core is the target for the package
	 * interface. We need to assign it to some other cpu.
	 */
	tdata = pd->core_data[PKG_SYSFS_ATTR_NO];
	if (tdata && tdata->cpu == cpu) {
		target = cpumask_first(&pd->cpumask);
		mutex_lock(&tdata->update_lock);
		tdata->cpu = target;
		mutex_unlock(&tdata->update_lock);
	}
	return 0;
}
static const struct x86_cpu_id __initconst coretemp_ids[] = {
	X86_MATCH_VENDOR_FEATURE(INTEL, X86_FEATURE_DTHERM, NULL),
	{}
};
MODULE_DEVICE_TABLE(x86cpu, coretemp_ids);

static enum cpuhp_state coretemp_hp_online;

static int __init coretemp_init(void)
{
	int err;

	/*
	 * CPUID.06H.EAX[0] indicates whether the CPU has thermal
	 * sensors. We check this bit only, all the early CPUs
	 * without thermal sensors will be filtered out.
	 */
	if (!x86_match_cpu(coretemp_ids))
		return -ENODEV;

	max_zones = topology_max_packages() * topology_max_die_per_package();
	zone_devices = kcalloc(max_zones, sizeof(struct platform_device *),
			      GFP_KERNEL);
	if (!zone_devices)
		return -ENOMEM;

	err = platform_driver_register(&coretemp_driver);
	if (err)
		goto outzone;

	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "hwmon/coretemp:online",
				coretemp_cpu_online, coretemp_cpu_offline);
	if (err < 0)
		goto outdrv;
	coretemp_hp_online = err;
	return 0;

outdrv:
	platform_driver_unregister(&coretemp_driver);
outzone:
	kfree(zone_devices);
	return err;
}
module_init(coretemp_init)

static void __exit coretemp_exit(void)
{
	cpuhp_remove_state(coretemp_hp_online);
	platform_driver_unregister(&coretemp_driver);
	kfree(zone_devices);
}
module_exit(coretemp_exit)

MODULE_AUTHOR("Rudolf Marek <r.marek@assembler.cz>");
MODULE_DESCRIPTION("Intel Core temperature monitor");
MODULE_LICENSE("GPL");