summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
blob: 1c48917da3cf3712b39eb72aaf1511fc3936845c (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
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
/*
 * Copyright 2015 Advanced Micro Devices, Inc.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWI/*
 * arch/sh/oprofile/op_model_sh7750.c
 *
 * OProfile support for SH7750/SH7750S Performance Counters
 *
 * Copyright (C) 2003, 2004  Paul Mundt
 *
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 */
#include <linux/kernel.h>
#include <linux/oprofile.h>
#include <linux/profile.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/fs.h>
#include <asm/uaccess.h>
#include <asm/io.h>

#define PM_CR_BASE	0xff000084	/* 16-bit */
#define PM_CTR_BASE	0xff100004	/* 32-bit */

#define PMCR1		(PM_CR_BASE  + 0x00)
#define PMCR2		(PM_CR_BASE  + 0x04)
#define PMCTR1H		(PM_CTR_BASE + 0x00)
#define PMCTR1L		(PM_CTR_BASE + 0x04)
#define PMCTR2H		(PM_CTR_BASE + 0x08)
#define PMCTR2L		(PM_CTR_BASE + 0x0c)

#define PMCR_PMM_MASK	0x0000003f

#define PMCR_CLKF	0x00000100
#define PMCR_PMCLR	0x00002000
#define PMCR_PMST	0x00004000
#define PMCR_PMEN	0x00008000

#define PMCR_ENABLE	(PMCR_PMST | PMCR_PMEN)

/*
 * SH7750/SH7750S have 2 perf counters
 */
#define NR_CNTRS	2

struct op_counter_config {
	unsigned long enabled;
	unsigned long event;
	unsigned long count;

	/* Dummy values for userspace tool compliance */
	unsigned long kernel;
	unsigned long user;
	unsigned long unit_mask;
};

static struct op_counter_config ctr[NR_CNTRS];

/*
 * There are a number of events supported by each counter (33 in total).
 * Since we have 2 counters, each counter will take the event code as it
 * corresponds to the PMCR PMM setting. Each counter can be configured
 * independently.
 *
 *	Event Code	Description
 *	----------	-----------
 *
 *	0x01		Operand read access
 *	0x02		Operand write access
 *	0x03		UTLB miss
 *	0x04		Operand cache read miss
 *	0x05		Operand cache write miss
 *	0x06		Instruction fetch (w/ cache)
 *	0x07		Instruction TLB miss
 *	0x08		Instruction cache miss
 *	0x09		All operand accesses
 *	0x0a		All instruction accesses
 *	0x0b		OC RAM operand access
 *	0x0d		On-chip I/O space access
 *	0x0e		Operand access (r/w)
 *	0x0f		Operand cache miss (r/w)
 *	0x10		Branch instruction
 *	0x11		Branch taken
 *	0x12		BSR/BSRF/JSR
 *	0x13		Instruction execution
 *	0x14		Instruction execution in parallel
 *	0x15		FPU Instruction execution
 *	0x16		Interrupt
 *	0x17		NMI
 *	0x18		trapa instruction execution
 *	0x19		UBCA match
 *	0x1a		UBCB match
 *	0x21		Instruction cache fill
 *	0x22		Operand cache fill
 *	0x23		Elapsed time
 *	0x24		Pipeline freeze by I-cache miss
 *	0x25		Pipeline freeze by D-cache miss
 *	0x27		Pipeline freeze by branch instruction
 *	0x28		Pipeline freeze by CPU register
 *	0x29		Pipeline freeze by FPU
 *
 * Unfortunately we don't have a native exception or interrupt for counter
 * overflow (although since these counters can run for 16.3 days without
 * overflowing, it's not really necessary).
 *
 * OProfile on the other hand likes to have samples taken periodically, so
 * for now we just piggyback the timer interrupt to get the expected
 * behavior.
 */

static int sh7750_timer_notify(struct pt_regs *regs)
{
	oprofile_add_sample(regs, 0);
	return 0;
}

static u64 sh7750_read_counter(int counter)
{
	u32 hi, lo;

	hi = (counter == 0) ? ctrl_inl(PMCTR1H) : ctrl_inl(PMCTR2H);
	lo = (counter == 0) ? ctrl_inl(PMCTR1L) : ctrl_inl(PMCTR2L);

	return (u64)((u64)(hi & 0xffff) << 32) | lo;
}

/*
 * Files will be in a path like:
 *
 *  /<oprofilefs mount point>/<counter number>/<file>
 *
 * So when dealing with <file>, we look to the parent dentry for the counter
 * number.
 */
static inline int to_counter(struct file *file)
{
	const unsigned char *name = file->f_path.dentry->d_parent->d_name.name;

	return (int)simple_strtol(name, NULL, 10);
}

/*
 * XXX: We have 48-bit counters, so we're probably going to want something
 * more along the lines of oprofilefs_ullong_to_user().. Truncating to
 * unsigned long works fine for now though, as long as we don't attempt to
 * profile for too horribly long.
 */
static ssize_t sh7750_read_count(struct file *file, char __user *buf,
				 size_t count, loff_t *ppos)
{
	int counter = to_counter(file);
	u64 val = sh7750_read_counter(counter);

	return oprofilefs_ulong_to_user((unsigned long)val, buf, count, ppos);
}

static ssize_t sh7750_write_count(struct file *file, const char __user *buf,
				  size_t count, loff_t *ppos)
{
	int counter = to_counter(file);
	unsigned long val;

	if (oprofilefs_ulong_from_user(&val, buf, count))
		return -EFAULT;

	/*
	 * Any write will clear the counter, although only 0 should be
	 * written for this purpose, as we do not support setting the
	 * counter to an arbitrary value.
	 */
	WARN_ON(val != 0);

	if (counter == 0) {
		ctrl_outw(ctrl_inw(PMCR1) | PMCR_PMCLR, PMCR1);
	} else {
		ctrl_outw(ctrl_inw(PMCR2) | PMCR_PMCLR, PMCR2);
	}

	return count;
}

static const struct file_operations count_fops = {
	.read		= sh7750_read_count,
	.write		= sh7750_write_count,
};

static int sh7750_perf_counter_create_files(struct super_block *sb, struct dentry *root)
{
	int i;

	for (i = 0; i < NR_CNTRS; i++) {
		struct dentry *dir;
		char buf[4];

		snprintf(buf, sizeof(buf), "%d", i);
		dir = oprofilefs_mkdir(sb, root, buf);

		oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
		oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
		oprofilefs_create_file(sb, dir, "count", &count_fops);

		/* Dummy entries */
		oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
		oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
		oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
	}

	return 0;
}

static int sh7750_perf_counter_start(void)
{
	u16 pmcr;

	/* Enable counter 1 */
	if (ctr[0].enabled) {
		pmcr = ctrl_inw(PMCR1);
		WARN_ON(pmcr & PMCR_PMEN);

		pmcr &= ~PMCR_PMM_MASK;
		pmcr |= ctr[0].event;
		ctrl_outw(pmcr | PMCR_ENABLE, PMCR1);
	}

	/* Enable counter 2 */
	if (ctr[1].enabled) {
		pmcr = ctrl_inw(PMCR2);
		WARN_ON(pmcr & PMCR_PMEN);

		pmcr &= ~PMCR_PMM_MASK;
		pmcr |= ctr[1].event;
		ctrl_outw(pmcr | PMCR_ENABLE, PMCR2);
	}

	return register_timer_hook(sh7750_timer_notify);
}

static void sh7750_perf_counter_stop(void)
{
	ctrl_outw(ctrl_inw(PMCR1) & ~PMCR_PMEN, PMCR1);
	ctrl_outw(ctrl_inw(PMCR2) & ~PMCR_PMEN, PMCR2);

	unregister_timer_hook(sh7750_timer_notify);
}

static struct oprofile_operations sh7750_perf_counter_ops = {
	.create_files	= sh7750_perf_counter_create_files,
	.start		= sh7750_perf_counter_start,
	.stop		= sh7750_perf_counter_stop,
};

int __init oprofile_arch_init(struct oprofile_operations *ops)
{
	if (!(current_cpu_data.flags & CPU_HAS_PERF_COUNTER))
		return -ENODEV;

	ops = &sh7750_perf_counter_ops;
	ops->cpu_type = (char *)get_cpu_subtype(&current_cpu_data);

	printk(KERN_INFO "oprofile: using SH-4 (%s) performance monitoring.\n",
	       sh7750_perf_counter_ops.cpu_type);

	/* Clear the counters */
	ctrl_outw(ctrl_inw(PMCR1) | PMCR_PMCLR, PMCR1);
	ctrl_outw(ctrl_inw(PMCR2) | PMCR_PMCLR, PMCR2);

	return 0;
}

void oprofile_arch_exit(void)
{
}

lass="hl opt">; PP_ASSERT_WITH_CODE((NULL != vol_table), "Voltage Table empty.", return -EINVAL); table = kzalloc(sizeof(struct pp_atomctrl_voltage_table), GFP_KERNEL); if (NULL == table) return -EINVAL; table->mask_low = vol_table->mask_low; table->phase_delay = vol_table->phase_delay; for (i = 0; i < vol_table->count; i++) { vvalue = vol_table->entries[i].value; found = false; for (j = 0; j < table->count; j++) { if (vvalue == table->entries[j].value) { found = true; break; } } if (!found) { table->entries[table->count].value = vvalue; table->entries[table->count].smio_low = vol_table->entries[i].smio_low; table->count++; } } memcpy(vol_table, table, sizeof(struct pp_atomctrl_voltage_table)); kfree(table); return 0; } int phm_get_svi2_mvdd_voltage_table(struct pp_atomctrl_voltage_table *vol_table, phm_ppt_v1_clock_voltage_dependency_table *dep_table) { uint32_t i; int result; PP_ASSERT_WITH_CODE((0 != dep_table->count), "Voltage Dependency Table empty.", return -EINVAL); PP_ASSERT_WITH_CODE((NULL != vol_table), "vol_table empty.", return -EINVAL); vol_table->mask_low = 0; vol_table->phase_delay = 0; vol_table->count = dep_table->count; for (i = 0; i < dep_table->count; i++) { vol_table->entries[i].value = dep_table->entries[i].mvdd; vol_table->entries[i].smio_low = 0; } result = phm_trim_voltage_table(vol_table); PP_ASSERT_WITH_CODE((0 == result), "Failed to trim MVDD table.", return result); return 0; } int phm_get_svi2_vddci_voltage_table(struct pp_atomctrl_voltage_table *vol_table, phm_ppt_v1_clock_voltage_dependency_table *dep_table) { uint32_t i; int result; PP_ASSERT_WITH_CODE((0 != dep_table->count), "Voltage Dependency Table empty.", return -EINVAL); PP_ASSERT_WITH_CODE((NULL != vol_table), "vol_table empty.", return -EINVAL); vol_table->mask_low = 0; vol_table->phase_delay = 0; vol_table->count = dep_table->count; for (i = 0; i < dep_table->count; i++) { vol_table->entries[i].value = dep_table->entries[i].vddci; vol_table->entries[i].smio_low = 0; } result = phm_trim_voltage_table(vol_table); PP_ASSERT_WITH_CODE((0 == result), "Failed to trim VDDCI table.", return result); return 0; } int phm_get_svi2_vdd_voltage_table(struct pp_atomctrl_voltage_table *vol_table, phm_ppt_v1_voltage_lookup_table *lookup_table) { int i = 0; PP_ASSERT_WITH_CODE((0 != lookup_table->count), "Voltage Lookup Table empty.", return -EINVAL); PP_ASSERT_WITH_CODE((NULL != vol_table), "vol_table empty.", return -EINVAL); vol_table->mask_low = 0; vol_table->phase_delay = 0; vol_table->count = lookup_table->count; for (i = 0; i < vol_table->count; i++) { vol_table->entries[i].value = lookup_table->entries[i].us_vdd; vol_table->entries[i].smio_low = 0; } return 0; } void phm_trim_voltage_table_to_fit_state_table(uint32_t max_vol_steps, struct pp_atomctrl_voltage_table *vol_table) { unsigned int i, diff; if (vol_table->count <= max_vol_steps) return; diff = vol_table->count - max_vol_steps; for (i = 0; i < max_vol_steps; i++) vol_table->entries[i] = vol_table->entries[i + diff]; vol_table->count = max_vol_steps; return; } int phm_reset_single_dpm_table(void *table, uint32_t count, int max) { int i; struct vi_dpm_table *dpm_table = (struct vi_dpm_table *)table; PP_ASSERT_WITH_CODE(count <= max, "Fatal error, can not set up single DPM table entries to exceed max number!", ); dpm_table->count = count; for (i = 0; i < max; i++) dpm_table->dpm_level[i].enabled = false; return 0; } void phm_setup_pcie_table_entry( void *table, uint32_t index, uint32_t pcie_gen, uint32_t pcie_lanes) { struct vi_dpm_table *dpm_table = (struct vi_dpm_table *)table; dpm_table->dpm_level[index].value = pcie_gen; dpm_table->dpm_level[index].param1 = pcie_lanes; dpm_table->dpm_level[index].enabled = 1; } int32_t phm_get_dpm_level_enable_mask_value(void *table) { int32_t i; int32_t mask = 0; struct vi_dpm_table *dpm_table = (struct vi_dpm_table *)table; for (i = dpm_table->count; i > 0; i--) { mask = mask << 1; if (dpm_table->dpm_level[i - 1].enabled) mask |= 0x1; else mask &= 0xFFFFFFFE; } return mask; } uint8_t phm_get_voltage_index( struct phm_ppt_v1_voltage_lookup_table *lookup_table, uint16_t voltage) { uint8_t count = (uint8_t) (lookup_table->count); uint8_t i; PP_ASSERT_WITH_CODE((NULL != lookup_table), "Lookup Table empty.", return 0); PP_ASSERT_WITH_CODE((0 != count), "Lookup Table empty.", return 0); for (i = 0; i < lookup_table->count; i++) { /* find first voltage equal or bigger than requested */ if (lookup_table->entries[i].us_vdd >= voltage) return i; } /* voltage is bigger than max voltage in the table */ return i - 1; } uint16_t phm_find_closest_vddci(struct pp_atomctrl_voltage_table *vddci_table, uint16_t vddci) { uint32_t i; for (i = 0; i < vddci_table->count; i++) { if (vddci_table->entries[i].value >= vddci) return vddci_table->entries[i].value; } PP_ASSERT_WITH_CODE(false, "VDDCI is larger than max VDDCI in VDDCI Voltage Table!", return vddci_table->entries[i].value); } int phm_find_boot_level(void *table, uint32_t value, uint32_t *boot_level) { int result = -EINVAL; uint32_t i; struct vi_dpm_table *dpm_table = (struct vi_dpm_table *)table; for (i = 0; i < dpm_table->count; i++) { if (value == dpm_table->dpm_level[i].value) { *boot_level = i; result = 0; } } return result; } int phm_get_sclk_for_voltage_evv(struct pp_hwmgr *hwmgr, phm_ppt_v1_voltage_lookup_table *lookup_table, uint16_t virtual_voltage_id, int32_t *sclk) { uint8_t entryId; uint8_t voltageId; struct phm_ppt_v1_information *table_info = (struct phm_ppt_v1_information *)(hwmgr->pptable); PP_ASSERT_WITH_CODE(lookup_table->count != 0, "Lookup table is empty", return -EINVAL); /* search for leakage voltage ID 0xff01 ~ 0xff08 and sckl */ for (entryId = 0; entryId < table_info->vdd_dep_on_sclk->count; entryId++) { voltageId = table_info->vdd_dep_on_sclk->entries[entryId].vddInd; if (lookup_table->entries[voltageId].us_vdd == virtual_voltage_id) break; } PP_ASSERT_WITH_CODE(entryId < table_info->vdd_dep_on_sclk->count, "Can't find requested voltage id in vdd_dep_on_sclk table!", return -EINVAL; ); *sclk = table_info->vdd_dep_on_sclk->entries[entryId].clk; return 0; } /** * Initialize Dynamic State Adjustment Rule Settings * * @param hwmgr the address of the powerplay hardware manager. */ int phm_initializa_dynamic_state_adjustment_rule_settings(struct pp_hwmgr *hwmgr) { uint32_t table_size; struct phm_clock_voltage_dependency_table *table_clk_vlt; struct phm_ppt_v1_information *pptable_info = (struct phm_ppt_v1_information *)(hwmgr->pptable); /* initialize vddc_dep_on_dal_pwrl table */ table_size = sizeof(uint32_t) + 4 * sizeof(struct phm_clock_voltage_dependency_record); table_clk_vlt = (struct phm_clock_voltage_dependency_table *)kzalloc(table_size, GFP_KERNEL); if (NULL == table_clk_vlt) { printk(KERN_ERR "[ powerplay ] Can not allocate space for vddc_dep_on_dal_pwrl! \n"); return -ENOMEM; } else { table_clk_vlt->count = 4; table_clk_vlt->entries[0].clk = PP_DAL_POWERLEVEL_ULTRALOW; table_clk_vlt->entries[0].v = 0; table_clk_vlt->entries[1].clk = PP_DAL_POWERLEVEL_LOW; table_clk_vlt->entries[1].v = 720; table_clk_vlt->entries[2].clk = PP_DAL_POWERLEVEL_NOMINAL; table_clk_vlt->entries[2].v = 810; table_clk_vlt->entries[3].clk = PP_DAL_POWERLEVEL_PERFORMANCE; table_clk_vlt->entries[3].v = 900; pptable_info->vddc_dep_on_dal_pwrl = table_clk_vlt; hwmgr->dyn_state.vddc_dep_on_dal_pwrl = table_clk_vlt; } return 0; } int phm_hwmgr_backend_fini(struct pp_hwmgr *hwmgr) { if (NULL != hwmgr->dyn_state.vddc_dep_on_dal_pwrl) { kfree(hwmgr->dyn_state.vddc_dep_on_dal_pwrl); hwmgr->dyn_state.vddc_dep_on_dal_pwrl = NULL; } if (NULL != hwmgr->backend) { kfree(hwmgr->backend); hwmgr->backend = NULL; } return 0; } uint32_t phm_get_lowest_enabled_level(struct pp_hwmgr *hwmgr, uint32_t mask) { uint32_t level = 0; while (0 == (mask & (1 << level))) level++; return level; } void phm_apply_dal_min_voltage_request(struct pp_hwmgr *hwmgr) { struct phm_ppt_v1_information *table_info = (struct phm_ppt_v1_information *)hwmgr->pptable; struct phm_clock_voltage_dependency_table *table = table_info->vddc_dep_on_dal_pwrl; struct phm_ppt_v1_clock_voltage_dependency_table *vddc_table; enum PP_DAL_POWERLEVEL dal_power_level = hwmgr->dal_power_level; uint32_t req_vddc = 0, req_volt, i; if (!table || table->count <= 0 || dal_power_level < PP_DAL_POWERLEVEL_ULTRALOW || dal_power_level > PP_DAL_POWERLEVEL_PERFORMANCE) return; for (i = 0; i < table->count; i++) { if (dal_power_level == table->entries[i].clk) { req_vddc = table->entries[i].v; break; } } vddc_table = table_info->vdd_dep_on_sclk; for (i = 0; i < vddc_table->count; i++) { if (req_vddc <= vddc_table->entries[i].vddc) { req_volt = (((uint32_t)vddc_table->entries[i].vddc) * VOLTAGE_SCALE); smum_send_msg_to_smc_with_parameter(hwmgr->smumgr, PPSMC_MSG_VddC_Request, req_volt); return; } } printk(KERN_ERR "DAL requested level can not" " found a available voltage in VDDC DPM Table \n"); }