summaryrefslogtreecommitdiff
path: root/drivers/thermal/intel/intel_hfi.c
blob: 730fd121df6ec3582499d94503f0ec89dc89cb1c (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Hardware Feedback Interface Driver
 *
 * Copyright (c) 2021, Intel Corporation.
 *
 * Authors: Aubrey Li <aubrey.li@linux.intel.com>
 *          Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
 *
 *
 * The Hardware Feedback Interface provides a performance and energy efficiency
 * capability information for each CPU in the system. Depending on the processor
 * model, hardware may periodically update these capabilities as a result of
 * changes in the operating conditions (e.g., power limits or thermal
 * constraints). On other processor models, there is a single HFI update
 * at boot.
 *
 * This file provides functionality to process HFI updates and relay these
 * updates to userspace.
 */

#define pr_fmt(fmt)  "intel-hfi: " fmt

#include <linux/bitops.h>
#include <linux/cpufeature.h>
#include <linux/cpumask.h>
#include <linux/gfp.h>
#include <linux/io.h>
#include <linux/kernel.h>
#include <linux/math.h>
#include <linux/mutex.h>
#include <linux/percpu-defs.h>
#include <linux/printk.h>
#include <linux/processor.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/topology.h>
#include <linux/workqueue.h>

#include <asm/msr.h>

#include "../thermal_core.h"
#include "intel_hfi.h"

#define THERM_STATUS_CLEAR_PKG_MASK (BIT(1) | BIT(3) | BIT(5) | BIT(7) | \
				     BIT(9) | BIT(11) | BIT(26))

/* Hardware Feedback Interface MSR configuration bits */
#define HW_FEEDBACK_PTR_VALID_BIT		BIT(0)
#define HW_FEEDBACK_CONFIG_HFI_ENABLE_BIT	BIT(0)

/* CPUID detection and enumeration definitions for HFI */

#define CPUID_HFI_LEAF 6

union hfi_capabilities {
	struct {
		u8	performance:1;
		u8	energy_efficiency:1;
		u8	__reserved:6;
	} split;
	u8 bits;
};

union cpuid6_edx {
	struct {
		union hfi_capabilities	capabilities;
		u32			table_pages:4;
		u32			__reserved:4;
		s32			index:16;
	} split;
	u32 full;
};

/**
 * struct hfi_cpu_data - HFI capabilities per CPU
 * @perf_cap:		Performance capability
 * @ee_cap:		Energy efficiency capability
 *
 * Capabilities of a logical processor in the HFI table. These capabilities are
 * unitless.
 */
struct hfi_cpu_data {
	u8	perf_cap;
	u8	ee_cap;
} __packed;

/**
 * struct hfi_hdr - Header of the HFI table
 * @perf_updated:	Hardware updated performance capabilities
 * @ee_updated:		Hardware updated energy efficiency capabilities
 *
 * Properties of the data in an HFI table.
 */
struct hfi_hdr {
	u8	perf_updated;
	u8	ee_updated;
} __packed;

/**
 * struct hfi_instance - Representation of an HFI instance (i.e., a table)
 * @local_table:	Base of the local copy of the HFI table
 * @timestamp:		Timestamp of the last update of the local table.
 *			Located at the base of the local table.
 * @hdr:		Base address of the header of the local table
 * @data:		Base address of the data of the local table
 * @cpus:		CPUs represented in this HFI table instance
 * @hw_table:		Pointer to the HFI table of this instance
 * @update_work:	Delayed work to process HFI updates
 * @table_lock:		Lock to protect acceses to the table of this instance
 * @event_lock:		Lock to process HFI interrupts
 *
 * A set of parameters to parse and navigate a specific HFI table.
 */
struct hfi_instance {
	union {
		void			*local_table;
		u64			*timestamp;
	};
	void			*hdr;
	void			*data;
	cpumask_var_t		cpus;
	void			*hw_table;
	struct delayed_work	update_work;
	raw_spinlock_t		table_lock;
	raw_spinlock_t		event_lock;
};

/**
 * struct hfi_features - Supported HFI features
 * @nr_table_pages:	Size of the HFI table in 4KB pages
 * @cpu_stride:		Stride size to locate the capability data of a logical
 *			processor within the table (i.e., row stride)
 * @hdr_size:		Size of the table header
 *
 * Parameters and supported features that are common to all HFI instances
 */
struct hfi_features {
	unsigned int	nr_table_pages;
	unsigned int	cpu_stride;
	unsigned int	hdr_size;
};

/**
 * struct hfi_cpu_info - Per-CPU attributes to consume HFI data
 * @index:		Row of this CPU in its HFI table
 * @hfi_instance:	Attributes of the HFI table to which this CPU belongs
 *
 * Parameters to link a logical processor to an HFI table and a row within it.
 */
struct hfi_cpu_info {
	s16			index;
	struct hfi_instance	*hfi_instance;
};

static DEFINE_PER_CPU(struct hfi_cpu_info, hfi_cpu_info) = { .index = -1 };

static int max_hfi_instances;
static struct hfi_instance *hfi_instances;

static struct hfi_features hfi_features;
static DEFINE_MUTEX(hfi_instance_lock);

static struct workqueue_struct *hfi_updates_wq;
#define HFI_UPDATE_INTERVAL		HZ
#define HFI_MAX_THERM_NOTIFY_COUNT	16

static void get_hfi_caps(struct hfi_instance *hfi_instance,
			 struct thermal_genl_cpu_caps *cpu_caps)
{
	int cpu, i = 0;

	raw_spin_lock_irq(&hfi_instance->table_lock);
	for_each_cpu(cpu, hfi_instance->cpus) {
		struct hfi_cpu_data *caps;
		s16 index;

		index = per_cpu(hfi_cpu_info, cpu).index;
		caps = hfi_instance->data + index * hfi_features.cpu_stride;
		cpu_caps[i].cpu = cpu;

		/*
		 * Scale performance and energy efficiency to
		 * the [0, 1023] interval that thermal netlink uses.
		 */
		cpu_caps[i].performance = caps->perf_cap << 2;
		cpu_caps[i].efficiency = caps->ee_cap << 2;

		++i;
	}
	raw_spin_unlock_irq(&hfi_instance->table_lock);
}

/*
 * Call update_capabilities() when there are changes in the HFI table.
 */
static void update_capabilities(struct hfi_instance *hfi_instance)
{
	struct thermal_genl_cpu_caps *cpu_caps;
	int i = 0, cpu_count;

	/* CPUs may come online/offline while processing an HFI update. */
	mutex_lock(&hfi_instance_lock);

	cpu_count = cpumask_weight(hfi_instance->cpus);

	/* No CPUs to report in this hfi_instance. */
	if (!cpu_count)
		goto out;

	cpu_caps = kcalloc(cpu_count, sizeof(*cpu_caps), GFP_KERNEL);
	if (!cpu_caps)
		goto out;

	get_hfi_caps(hfi_instance, cpu_caps);

	if (cpu_count < HFI_MAX_THERM_NOTIFY_COUNT)
		goto last_cmd;

	/* Process complete chunks of HFI_MAX_THERM_NOTIFY_COUNT capabilities. */
	for (i = 0;
	     (i + HFI_MAX_THERM_NOTIFY_COUNT) <= cpu_count;
	     i += HFI_MAX_THERM_NOTIFY_COUNT)
		thermal_genl_cpu_capability_event(HFI_MAX_THERM_NOTIFY_COUNT,
						  &cpu_caps[i]);

	cpu_count = cpu_count - i;

last_cmd:
	/* Process the remaining capabilities if any. */
	if (cpu_count)
		thermal_genl_cpu_capability_event(cpu_count, &cpu_caps[i]);

	kfree(cpu_caps);
out:
	mutex_unlock(&hfi_instance_lock);
}

static void hfi_update_work_fn(struct work_struct *work)
{
	struct hfi_instance *hfi_instance;

	hfi_instance = container_of(to_delayed_work(work), struct hfi_instance,
				    update_work);
	if (!hfi_instance)
		return;

	update_capabilities(hfi_instance);
}

void intel_hfi_process_event(__u64 pkg_therm_status_msr_val)
{
	struct hfi_instance *hfi_instance;
	int cpu = smp_processor_id();
	struct hfi_cpu_info *info;
	u64 new_timestamp;

	if (!pkg_therm_status_msr_val)
		return;

	info = &per_cpu(hfi_cpu_info, cpu);
	if (!info)
		return;

	/*
	 * A CPU is linked to its HFI instance before the thermal vector in the
	 * local APIC is unmasked. Hence, info->hfi_instance cannot be NULL
	 * when receiving an HFI event.
	 */
	hfi_instance = info->hfi_instance;
	if (unlikely(!hfi_instance)) {
		pr_debug("Received event on CPU %d but instance was null", cpu);
		return;
	}

	/*
	 * On most systems, all CPUs in the package receive a package-level
	 * thermal interrupt when there is an HFI update. It is sufficient to
	 * let a single CPU to acknowledge the update and queue work to
	 * process it. The remaining CPUs can resume their work.
	 */
	if (!raw_spin_trylock(&hfi_instance->event_lock))
		return;

	/* Skip duplicated updates. */
	new_timestamp = *(u64 *)hfi_instance->hw_table;
	if (*hfi_instance->timestamp == new_timestamp) {
		raw_spin_unlock(&hfi_instance->event_lock);
		return;
	}

	raw_spin_lock(&hfi_instance->table_lock);

	/*
	 * Copy the updated table into our local copy. This includes the new
	 * timestamp.
	 */
	memcpy(hfi_instance->local_table, hfi_instance->hw_table,
	       hfi_features.nr_table_pages << PAGE_SHIFT);

	raw_spin_unlock(&hfi_instance->table_lock);
	raw_spin_unlock(&hfi_instance->event_lock);

	/*
	 * Let hardware know that we are done reading the HFI table and it is
	 * free to update it again.
	 */
	pkg_therm_status_msr_val &= THERM_STATUS_CLEAR_PKG_MASK &
				    ~PACKAGE_THERM_STATUS_HFI_UPDATED;
	wrmsrl(MSR_IA32_PACKAGE_THERM_STATUS, pkg_therm_status_msr_val);

	queue_delayed_work(hfi_updates_wq, &hfi_instance->update_work,
			   HFI_UPDATE_INTERVAL);
}

static void init_hfi_cpu_index(struct hfi_cpu_info *info)
{
	union cpuid6_edx edx;

	/* Do not re-read @cpu's index if it has already been initialized. */
	if (info->index > -1)
		return;

	edx.full = cpuid_edx(CPUID_HFI_LEAF);
	info->index = edx.split.index;
}

/*
 * The format of the HFI table depends on the number of capabilities that the
 * hardware supports. Keep a data structure to navigate the table.
 */
static void init_hfi_instance(struct hfi_instance *hfi_instance)
{
	/* The HFI header is below the time-stamp. */
	hfi_instance->hdr = hfi_instance->local_table +
			    sizeof(*hfi_instance->timestamp);

	/* The HFI data starts below the header. */
	hfi_instance->data = hfi_instance->hdr + hfi_features.hdr_size;
}

/**
 * intel_hfi_online() - Enable HFI on @cpu
 * @cpu:	CPU in which the HFI will be enabled
 *
 * Enable the HFI to be used in @cpu. The HFI is enabled at the die/package
 * level. The first CPU in the die/package to come online does the full HFI
 * initialization. Subsequent CPUs will just link themselves to the HFI
 * instance of their die/package.
 *
 * This function is called before enabling the thermal vector in the local APIC
 * in order to ensure that @cpu has an associated HFI instance when it receives
 * an HFI event.
 */
void intel_hfi_online(unsigned int cpu)
{
	struct hfi_instance *hfi_instance;
	struct hfi_cpu_info *info;
	phys_addr_t hw_table_pa;
	u64 msr_val;
	u16 die_id;

	/* Nothing to do if hfi_instances are missing. */
	if (!hfi_instances)
		return;

	/*
	 * Link @cpu to the HFI instance of its package/die. It does not
	 * matter whether the instance has been initialized.
	 */
	info = &per_cpu(hfi_cpu_info, cpu);
	die_id = topology_logical_die_id(cpu);
	hfi_instance = info->hfi_instance;
	if (!hfi_instance) {
		if (die_id < 0 || die_id >= max_hfi_instances)
			return;

		hfi_instance = &hfi_instances[die_id];
		info->hfi_instance = hfi_instance;
	}

	init_hfi_cpu_index(info);

	/*
	 * Now check if the HFI instance of the package/die of @cpu has been
	 * initialized (by checking its header). In such case, all we have to
	 * do is to add @cpu to this instance's cpumask.
	 */
	mutex_lock(&hfi_instance_lock);
	if (hfi_instance->hdr) {
		cpumask_set_cpu(cpu, hfi_instance->cpus);
		goto unlock;
	}

	/*
	 * Hardware is programmed with the physical address of the first page
	 * frame of the table. Hence, the allocated memory must be page-aligned.
	 */
	hfi_instance->hw_table = alloc_pages_exact(hfi_features.nr_table_pages,
						   GFP_KERNEL | __GFP_ZERO);
	if (!hfi_instance->hw_table)
		goto unlock;

	hw_table_pa = virt_to_phys(hfi_instance->hw_table);

	/*
	 * Allocate memory to keep a local copy of the table that
	 * hardware generates.
	 */
	hfi_instance->local_table = kzalloc(hfi_features.nr_table_pages << PAGE_SHIFT,
					    GFP_KERNEL);
	if (!hfi_instance->local_table)
		goto free_hw_table;

	/*
	 * Program the address of the feedback table of this die/package. On
	 * some processors, hardware remembers the old address of the HFI table
	 * even after having been reprogrammed and re-enabled. Thus, do not free
	 * the pages allocated for the table or reprogram the hardware with a
	 * new base address. Namely, program the hardware only once.
	 */
	msr_val = hw_table_pa | HW_FEEDBACK_PTR_VALID_BIT;
	wrmsrl(MSR_IA32_HW_FEEDBACK_PTR, msr_val);

	init_hfi_instance(hfi_instance);

	INIT_DELAYED_WORK(&hfi_instance->update_work, hfi_update_work_fn);
	raw_spin_lock_init(&hfi_instance->table_lock);
	raw_spin_lock_init(&hfi_instance->event_lock);

	cpumask_set_cpu(cpu, hfi_instance->cpus);

	/*
	 * Enable the hardware feedback interface and never disable it. See
	 * comment on programming the address of the table.
	 */
	rdmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val);
	msr_val |= HW_FEEDBACK_CONFIG_HFI_ENABLE_BIT;
	wrmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val);

unlock:
	mutex_unlock(&hfi_instance_lock);
	return;

free_hw_table:
	free_pages_exact(hfi_instance->hw_table, hfi_features.nr_table_pages);
	goto unlock;
}

/**
 * intel_hfi_offline() - Disable HFI on @cpu
 * @cpu:	CPU in which the HFI will be disabled
 *
 * Remove @cpu from those covered by its HFI instance.
 *
 * On some processors, hardware remembers previous programming settings even
 * after being reprogrammed. Thus, keep HFI enabled even if all CPUs in the
 * die/package of @cpu are offline. See note in intel_hfi_online().
 */
void intel_hfi_offline(unsigned int cpu)
{
	struct hfi_cpu_info *info = &per_cpu(hfi_cpu_info, cpu);
	struct hfi_instance *hfi_instance;

	/*
	 * Check if @cpu as an associated, initialized (i.e., with a non-NULL
	 * header). Also, HFI instances are only initialized if X86_FEATURE_HFI
	 * is present.
	 */
	hfi_instance = info->hfi_instance;
	if (!hfi_instance)
		return;

	if (!hfi_instance->hdr)
		return;

	mutex_lock(&hfi_instance_lock);
	cpumask_clear_cpu(cpu, hfi_instance->cpus);
	mutex_unlock(&hfi_instance_lock);
}

static __init int hfi_parse_features(void)
{
	unsigned int nr_capabilities;
	union cpuid6_edx edx;

	if (!boot_cpu_has(X86_FEATURE_HFI))
		return -ENODEV;

	/*
	 * If we are here we know that CPUID_HFI_LEAF exists. Parse the
	 * supported capabilities and the size of the HFI table.
	 */
	edx.full = cpuid_edx(CPUID_HFI_LEAF);

	if (!edx.split.capabilities.split.performance) {
		pr_debug("Performance reporting not supported! Not using HFI\n");
		return -ENODEV;
	}

	/*
	 * The number of supported capabilities determines the number of
	 * columns in the HFI table. Exclude the reserved bits.
	 */
	edx.split.capabilities.split.__reserved = 0;
	nr_capabilities = hweight8(edx.split.capabilities.bits);

	/* The number of 4KB pages required by the table */
	hfi_features.nr_table_pages = edx.split.table_pages + 1;

	/*
	 * The header contains change indications for each supported feature.
	 * The size of the table header is rounded up to be a multiple of 8
	 * bytes.
	 */
	hfi_features.hdr_size = DIV_ROUND_UP(nr_capabilities, 8) * 8;

	/*
	 * Data of each logical processor is also rounded up to be a multiple
	 * of 8 bytes.
	 */
	hfi_features.cpu_stride = DIV_ROUND_UP(nr_capabilities, 8) * 8;

	return 0;
}

void __init intel_hfi_init(void)
{
	struct hfi_instance *hfi_instance;
	int i, j;

	if (hfi_parse_features())
		return;

	/* There is one HFI instance per die/package. */
	max_hfi_instances = topology_max_packages() *
			    topology_max_die_per_package();

	/*
	 * This allocation may fail. CPU hotplug callbacks must check
	 * for a null pointer.
	 */
	hfi_instances = kcalloc(max_hfi_instances, sizeof(*hfi_instances),
				GFP_KERNEL);
	if (!hfi_instances)
		return;

	for (i = 0; i < max_hfi_instances; i++) {
		hfi_instance = &hfi_instances[i];
		if (!zalloc_cpumask_var(&hfi_instance->cpus, GFP_KERNEL))
			goto err_nomem;
	}

	hfi_updates_wq = create_singlethread_workqueue("hfi-updates");
	if (!hfi_updates_wq)
		goto err_nomem;

	return;

err_nomem:
	for (j = 0; j < i; ++j) {
		hfi_instance = &hfi_instances[j];
		free_cpumask_var(hfi_instance->cpus);
	}

	kfree(hfi_instances);
	hfi_instances = NULL;
}