forked from ~ljy/RK356X_SDK_RELEASE
blame | history | patch | commit | commitdiff
hc
2024-01-05 071106ecf68c401173c58808b1cf5f68cc50d390 
 kernel/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
....@@ -27,11 +27,290 @@
2727 #include "df/df_3_6_offset.h"
2828 #include "df/df_3_6_sh_mask.h"
2929 
30
+#define DF_3_6_SMN_REG_INST_DIST        0x8
31
+#define DF_3_6_INST_CNT                 8
32
+
3033 static u32 df_v3_6_channel_number[] = {1, 2, 0, 4, 0, 8, 0,
3134 				       16, 32, 0, 0, 0, 2, 4, 8};
3235 
33
-static void df_v3_6_init(struct amdgpu_device *adev)
36
+/* init df format attrs */
37
+AMDGPU_PMU_ATTR(event,		"config:0-7");
38
+AMDGPU_PMU_ATTR(instance,	"config:8-15");
39
+AMDGPU_PMU_ATTR(umask,		"config:16-23");
40
+
41
+/* df format attributes  */
42
+static struct attribute *df_v3_6_format_attrs[] = {
43
+	&pmu_attr_event.attr,
44
+	&pmu_attr_instance.attr,
45
+	&pmu_attr_umask.attr,
46
+	NULL
47
+};
48
+
49
+/* df format attribute group */
50
+static struct attribute_group df_v3_6_format_attr_group = {
51
+	.name = "format",
52
+	.attrs = df_v3_6_format_attrs,
53
+};
54
+
55
+/* df event attrs */
56
+AMDGPU_PMU_ATTR(cake0_pcsout_txdata,
57
+		      "event=0x7,instance=0x46,umask=0x2");
58
+AMDGPU_PMU_ATTR(cake1_pcsout_txdata,
59
+		      "event=0x7,instance=0x47,umask=0x2");
60
+AMDGPU_PMU_ATTR(cake0_pcsout_txmeta,
61
+		      "event=0x7,instance=0x46,umask=0x4");
62
+AMDGPU_PMU_ATTR(cake1_pcsout_txmeta,
63
+		      "event=0x7,instance=0x47,umask=0x4");
64
+AMDGPU_PMU_ATTR(cake0_ftiinstat_reqalloc,
65
+		      "event=0xb,instance=0x46,umask=0x4");
66
+AMDGPU_PMU_ATTR(cake1_ftiinstat_reqalloc,
67
+		      "event=0xb,instance=0x47,umask=0x4");
68
+AMDGPU_PMU_ATTR(cake0_ftiinstat_rspalloc,
69
+		      "event=0xb,instance=0x46,umask=0x8");
70
+AMDGPU_PMU_ATTR(cake1_ftiinstat_rspalloc,
71
+		      "event=0xb,instance=0x47,umask=0x8");
72
+
73
+/* df event attributes  */
74
+static struct attribute *df_v3_6_event_attrs[] = {
75
+	&pmu_attr_cake0_pcsout_txdata.attr,
76
+	&pmu_attr_cake1_pcsout_txdata.attr,
77
+	&pmu_attr_cake0_pcsout_txmeta.attr,
78
+	&pmu_attr_cake1_pcsout_txmeta.attr,
79
+	&pmu_attr_cake0_ftiinstat_reqalloc.attr,
80
+	&pmu_attr_cake1_ftiinstat_reqalloc.attr,
81
+	&pmu_attr_cake0_ftiinstat_rspalloc.attr,
82
+	&pmu_attr_cake1_ftiinstat_rspalloc.attr,
83
+	NULL
84
+};
85
+
86
+/* df event attribute group */
87
+static struct attribute_group df_v3_6_event_attr_group = {
88
+	.name = "events",
89
+	.attrs = df_v3_6_event_attrs
90
+};
91
+
92
+/* df event attr groups  */
93
+const struct attribute_group *df_v3_6_attr_groups[] = {
94
+		&df_v3_6_format_attr_group,
95
+		&df_v3_6_event_attr_group,
96
+		NULL
97
+};
98
+
99
+static uint64_t df_v3_6_get_fica(struct amdgpu_device *adev,
100
+				 uint32_t ficaa_val)
34101 {
102
+	unsigned long flags, address, data;
103
+	uint32_t ficadl_val, ficadh_val;
104
+
105
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
106
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
107
+
108
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
109
+	WREG32(address, smnDF_PIE_AON_FabricIndirectConfigAccessAddress3);
110
+	WREG32(data, ficaa_val);
111
+
112
+	WREG32(address, smnDF_PIE_AON_FabricIndirectConfigAccessDataLo3);
113
+	ficadl_val = RREG32(data);
114
+
115
+	WREG32(address, smnDF_PIE_AON_FabricIndirectConfigAccessDataHi3);
116
+	ficadh_val = RREG32(data);
117
+
118
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
119
+
120
+	return (((ficadh_val & 0xFFFFFFFFFFFFFFFF) << 32) | ficadl_val);
121
+}
122
+
123
+static void df_v3_6_set_fica(struct amdgpu_device *adev, uint32_t ficaa_val,
124
+			     uint32_t ficadl_val, uint32_t ficadh_val)
125
+{
126
+	unsigned long flags, address, data;
127
+
128
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
129
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
130
+
131
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
132
+	WREG32(address, smnDF_PIE_AON_FabricIndirectConfigAccessAddress3);
133
+	WREG32(data, ficaa_val);
134
+
135
+	WREG32(address, smnDF_PIE_AON_FabricIndirectConfigAccessDataLo3);
136
+	WREG32(data, ficadl_val);
137
+
138
+	WREG32(address, smnDF_PIE_AON_FabricIndirectConfigAccessDataHi3);
139
+	WREG32(data, ficadh_val);
140
+
141
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
142
+}
143
+
144
+/*
145
+ * df_v3_6_perfmon_rreg - read perfmon lo and hi
146
+ *
147
+ * required to be atomic.  no mmio method provided so subsequent reads for lo
148
+ * and hi require to preserve df finite state machine
149
+ */
150
+static void df_v3_6_perfmon_rreg(struct amdgpu_device *adev,
151
+			    uint32_t lo_addr, uint32_t *lo_val,
152
+			    uint32_t hi_addr, uint32_t *hi_val)
153
+{
154
+	unsigned long flags, address, data;
155
+
156
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
157
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
158
+
159
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
160
+	WREG32(address, lo_addr);
161
+	*lo_val = RREG32(data);
162
+	WREG32(address, hi_addr);
163
+	*hi_val = RREG32(data);
164
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
165
+}
166
+
167
+/*
168
+ * df_v3_6_perfmon_wreg - write to perfmon lo and hi
169
+ *
170
+ * required to be atomic.  no mmio method provided so subsequent reads after
171
+ * data writes cannot occur to preserve data fabrics finite state machine.
172
+ */
173
+static void df_v3_6_perfmon_wreg(struct amdgpu_device *adev, uint32_t lo_addr,
174
+			    uint32_t lo_val, uint32_t hi_addr, uint32_t hi_val)
175
+{
176
+	unsigned long flags, address, data;
177
+
178
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
179
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
180
+
181
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
182
+	WREG32(address, lo_addr);
183
+	WREG32(data, lo_val);
184
+	WREG32(address, hi_addr);
185
+	WREG32(data, hi_val);
186
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
187
+}
188
+
189
+/* same as perfmon_wreg but return status on write value check */
190
+static int df_v3_6_perfmon_arm_with_status(struct amdgpu_device *adev,
191
+					  uint32_t lo_addr, uint32_t lo_val,
192
+					  uint32_t hi_addr, uint32_t  hi_val)
193
+{
194
+	unsigned long flags, address, data;
195
+	uint32_t lo_val_rb, hi_val_rb;
196
+
197
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
198
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
199
+
200
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
201
+	WREG32(address, lo_addr);
202
+	WREG32(data, lo_val);
203
+	WREG32(address, hi_addr);
204
+	WREG32(data, hi_val);
205
+
206
+	WREG32(address, lo_addr);
207
+	lo_val_rb = RREG32(data);
208
+	WREG32(address, hi_addr);
209
+	hi_val_rb = RREG32(data);
210
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
211
+
212
+	if (!(lo_val == lo_val_rb && hi_val == hi_val_rb))
213
+		return -EBUSY;
214
+
215
+	return 0;
216
+}
217
+
218
+
219
+/*
220
+ * retry arming counters every 100 usecs within 1 millisecond interval.
221
+ * if retry fails after time out, return error.
222
+ */
223
+#define ARM_RETRY_USEC_TIMEOUT	1000
224
+#define ARM_RETRY_USEC_INTERVAL	100
225
+static int df_v3_6_perfmon_arm_with_retry(struct amdgpu_device *adev,
226
+					  uint32_t lo_addr, uint32_t lo_val,
227
+					  uint32_t hi_addr, uint32_t  hi_val)
228
+{
229
+	int countdown = ARM_RETRY_USEC_TIMEOUT;
230
+
231
+	while (countdown) {
232
+
233
+		if (!df_v3_6_perfmon_arm_with_status(adev, lo_addr, lo_val,
234
+						     hi_addr, hi_val))
235
+			break;
236
+
237
+		countdown -= ARM_RETRY_USEC_INTERVAL;
238
+		udelay(ARM_RETRY_USEC_INTERVAL);
239
+	}
240
+
241
+	return countdown > 0 ? 0 : -ETIME;
242
+}
243
+
244
+/* get the number of df counters available */
245
+static ssize_t df_v3_6_get_df_cntr_avail(struct device *dev,
246
+		struct device_attribute *attr,
247
+		char *buf)
248
+{
249
+	struct amdgpu_device *adev;
250
+	struct drm_device *ddev;
251
+	int i, count;
252
+
253
+	ddev = dev_get_drvdata(dev);
254
+	adev = drm_to_adev(ddev);
255
+	count = 0;
256
+
257
+	for (i = 0; i < DF_V3_6_MAX_COUNTERS; i++) {
258
+		if (adev->df_perfmon_config_assign_mask[i] == 0)
259
+			count++;
260
+	}
261
+
262
+	return snprintf(buf, PAGE_SIZE,	"%i\n", count);
263
+}
264
+
265
+/* device attr for available perfmon counters */
266
+static DEVICE_ATTR(df_cntr_avail, S_IRUGO, df_v3_6_get_df_cntr_avail, NULL);
267
+
268
+static void df_v3_6_query_hashes(struct amdgpu_device *adev)
269
+{
270
+	u32 tmp;
271
+
272
+	adev->df.hash_status.hash_64k = false;
273
+	adev->df.hash_status.hash_2m = false;
274
+	adev->df.hash_status.hash_1g = false;
275
+
276
+	if (adev->asic_type != CHIP_ARCTURUS)
277
+		return;
278
+
279
+	/* encoding for hash-enabled on Arcturus */
280
+	if (adev->df.funcs->get_fb_channel_number(adev) == 0xe) {
281
+		tmp = RREG32_SOC15(DF, 0, mmDF_CS_UMC_AON0_DfGlobalCtrl);
282
+		adev->df.hash_status.hash_64k = REG_GET_FIELD(tmp,
283
+						DF_CS_UMC_AON0_DfGlobalCtrl,
284
+						GlbHashIntlvCtl64K);
285
+		adev->df.hash_status.hash_2m = REG_GET_FIELD(tmp,
286
+						DF_CS_UMC_AON0_DfGlobalCtrl,
287
+						GlbHashIntlvCtl2M);
288
+		adev->df.hash_status.hash_1g = REG_GET_FIELD(tmp,
289
+						DF_CS_UMC_AON0_DfGlobalCtrl,
290
+						GlbHashIntlvCtl1G);
291
+	}
292
+}
293
+
294
+/* init perfmons */
295
+static void df_v3_6_sw_init(struct amdgpu_device *adev)
296
+{
297
+	int i, ret;
298
+
299
+	ret = device_create_file(adev->dev, &dev_attr_df_cntr_avail);
300
+	if (ret)
301
+		DRM_ERROR("failed to create file for available df counters\n");
302
+
303
+	for (i = 0; i < AMDGPU_MAX_DF_PERFMONS; i++)
304
+		adev->df_perfmon_config_assign_mask[i] = 0;
305
+
306
+	df_v3_6_query_hashes(adev);
307
+}
308
+
309
+static void df_v3_6_sw_fini(struct amdgpu_device *adev)
310
+{
311
+
312
+	device_remove_file(adev->dev, &dev_attr_df_cntr_avail);
313
+
35314 }
36315 
37316 static void df_v3_6_enable_broadcast_mode(struct amdgpu_device *adev,
....@@ -63,7 +342,7 @@
63342 {
64343 	int fb_channel_number;
65344 
66
-	fb_channel_number = adev->df_funcs->get_fb_channel_number(adev);
345
+	fb_channel_number = adev->df.funcs->get_fb_channel_number(adev);
67346 	if (fb_channel_number >= ARRAY_SIZE(df_v3_6_channel_number))
68347 		fb_channel_number = 0;
69348 
....@@ -77,7 +356,7 @@
77356 
78357 	if (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG) {
79358 		/* Put DF on broadcast mode */
80
-		adev->df_funcs->enable_broadcast_mode(adev, true);
359
+		adev->df.funcs->enable_broadcast_mode(adev, true);
81360 
82361 		if (enable) {
83362 			tmp = RREG32_SOC15(DF, 0,
....@@ -96,7 +375,7 @@
96375 		}
97376 
98377 		/* Exit broadcast mode */
99
-		adev->df_funcs->enable_broadcast_mode(adev, false);
378
+		adev->df.funcs->enable_broadcast_mode(adev, false);
100379 	}
101380 }
102381 
....@@ -111,12 +390,319 @@
111390 		*flags |= AMD_CG_SUPPORT_DF_MGCG;
112391 }
113392 
393
+/* get assigned df perfmon ctr as int */
394
+static int df_v3_6_pmc_config_2_cntr(struct amdgpu_device *adev,
395
+				      uint64_t config)
396
+{
397
+	int i;
398
+
399
+	for (i = 0; i < DF_V3_6_MAX_COUNTERS; i++) {
400
+		if ((config & 0x0FFFFFFUL) ==
401
+					adev->df_perfmon_config_assign_mask[i])
402
+			return i;
403
+	}
404
+
405
+	return -EINVAL;
406
+}
407
+
408
+/* get address based on counter assignment */
409
+static void df_v3_6_pmc_get_addr(struct amdgpu_device *adev,
410
+				 uint64_t config,
411
+				 int is_ctrl,
412
+				 uint32_t *lo_base_addr,
413
+				 uint32_t *hi_base_addr)
414
+{
415
+	int target_cntr = df_v3_6_pmc_config_2_cntr(adev, config);
416
+
417
+	if (target_cntr < 0)
418
+		return;
419
+
420
+	switch (target_cntr) {
421
+
422
+	case 0:
423
+		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo4 : smnPerfMonCtrLo4;
424
+		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi4 : smnPerfMonCtrHi4;
425
+		break;
426
+	case 1:
427
+		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo5 : smnPerfMonCtrLo5;
428
+		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi5 : smnPerfMonCtrHi5;
429
+		break;
430
+	case 2:
431
+		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo6 : smnPerfMonCtrLo6;
432
+		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi6 : smnPerfMonCtrHi6;
433
+		break;
434
+	case 3:
435
+		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo7 : smnPerfMonCtrLo7;
436
+		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi7 : smnPerfMonCtrHi7;
437
+		break;
438
+
439
+	}
440
+
441
+}
442
+
443
+/* get read counter address */
444
+static void df_v3_6_pmc_get_read_settings(struct amdgpu_device *adev,
445
+					  uint64_t config,
446
+					  uint32_t *lo_base_addr,
447
+					  uint32_t *hi_base_addr)
448
+{
449
+	df_v3_6_pmc_get_addr(adev, config, 0, lo_base_addr, hi_base_addr);
450
+}
451
+
452
+/* get control counter settings i.e. address and values to set */
453
+static int df_v3_6_pmc_get_ctrl_settings(struct amdgpu_device *adev,
454
+					  uint64_t config,
455
+					  uint32_t *lo_base_addr,
456
+					  uint32_t *hi_base_addr,
457
+					  uint32_t *lo_val,
458
+					  uint32_t *hi_val,
459
+					  bool is_enable)
460
+{
461
+
462
+	uint32_t eventsel, instance, unitmask;
463
+	uint32_t instance_10, instance_5432, instance_76;
464
+
465
+	df_v3_6_pmc_get_addr(adev, config, 1, lo_base_addr, hi_base_addr);
466
+
467
+	if ((*lo_base_addr == 0) || (*hi_base_addr == 0)) {
468
+		DRM_ERROR("[DF PMC] addressing not retrieved! Lo: %x, Hi: %x",
469
+				*lo_base_addr, *hi_base_addr);
470
+		return -ENXIO;
471
+	}
472
+
473
+	eventsel = DF_V3_6_GET_EVENT(config) & 0x3f;
474
+	unitmask = DF_V3_6_GET_UNITMASK(config) & 0xf;
475
+	instance = DF_V3_6_GET_INSTANCE(config);
476
+
477
+	instance_10 = instance & 0x3;
478
+	instance_5432 = (instance >> 2) & 0xf;
479
+	instance_76 = (instance >> 6) & 0x3;
480
+
481
+	*lo_val = (unitmask << 8) | (instance_10 << 6) | eventsel;
482
+	*lo_val = is_enable ? *lo_val | (1 << 22) : *lo_val & ~(1 << 22);
483
+	*hi_val = (instance_76 << 29) | instance_5432;
484
+
485
+	DRM_DEBUG_DRIVER("config=%llx addr=%08x:%08x val=%08x:%08x",
486
+		config, *lo_base_addr, *hi_base_addr, *lo_val, *hi_val);
487
+
488
+	return 0;
489
+}
490
+
491
+/* add df performance counters for read */
492
+static int df_v3_6_pmc_add_cntr(struct amdgpu_device *adev,
493
+				   uint64_t config)
494
+{
495
+	int i, target_cntr;
496
+
497
+	target_cntr = df_v3_6_pmc_config_2_cntr(adev, config);
498
+
499
+	if (target_cntr >= 0)
500
+		return 0;
501
+
502
+	for (i = 0; i < DF_V3_6_MAX_COUNTERS; i++) {
503
+		if (adev->df_perfmon_config_assign_mask[i] == 0U) {
504
+			adev->df_perfmon_config_assign_mask[i] =
505
+							config & 0x0FFFFFFUL;
506
+			return 0;
507
+		}
508
+	}
509
+
510
+	return -ENOSPC;
511
+}
512
+
513
+#define DEFERRED_ARM_MASK	(1 << 31)
514
+static int df_v3_6_pmc_set_deferred(struct amdgpu_device *adev,
515
+				    uint64_t config, bool is_deferred)
516
+{
517
+	int target_cntr;
518
+
519
+	target_cntr = df_v3_6_pmc_config_2_cntr(adev, config);
520
+
521
+	if (target_cntr < 0)
522
+		return -EINVAL;
523
+
524
+	if (is_deferred)
525
+		adev->df_perfmon_config_assign_mask[target_cntr] |=
526
+							DEFERRED_ARM_MASK;
527
+	else
528
+		adev->df_perfmon_config_assign_mask[target_cntr] &=
529
+							~DEFERRED_ARM_MASK;
530
+
531
+	return 0;
532
+}
533
+
534
+static bool df_v3_6_pmc_is_deferred(struct amdgpu_device *adev,
535
+				    uint64_t config)
536
+{
537
+	int target_cntr;
538
+
539
+	target_cntr = df_v3_6_pmc_config_2_cntr(adev, config);
540
+
541
+	/*
542
+	 * we never get target_cntr < 0 since this funciton is only called in
543
+	 * pmc_count for now but we should check anyways.
544
+	 */
545
+	return (target_cntr >= 0 &&
546
+			(adev->df_perfmon_config_assign_mask[target_cntr]
547
+			& DEFERRED_ARM_MASK));
548
+
549
+}
550
+
551
+/* release performance counter */
552
+static void df_v3_6_pmc_release_cntr(struct amdgpu_device *adev,
553
+				     uint64_t config)
554
+{
555
+	int target_cntr = df_v3_6_pmc_config_2_cntr(adev, config);
556
+
557
+	if (target_cntr >= 0)
558
+		adev->df_perfmon_config_assign_mask[target_cntr] = 0ULL;
559
+}
560
+
561
+
562
+static void df_v3_6_reset_perfmon_cntr(struct amdgpu_device *adev,
563
+					 uint64_t config)
564
+{
565
+	uint32_t lo_base_addr = 0, hi_base_addr = 0;
566
+
567
+	df_v3_6_pmc_get_read_settings(adev, config, &lo_base_addr,
568
+				      &hi_base_addr);
569
+
570
+	if ((lo_base_addr == 0) || (hi_base_addr == 0))
571
+		return;
572
+
573
+	df_v3_6_perfmon_wreg(adev, lo_base_addr, 0, hi_base_addr, 0);
574
+}
575
+
576
+static int df_v3_6_pmc_start(struct amdgpu_device *adev, uint64_t config,
577
+			     int is_add)
578
+{
579
+	uint32_t lo_base_addr, hi_base_addr, lo_val, hi_val;
580
+	int err = 0, ret = 0;
581
+
582
+	switch (adev->asic_type) {
583
+	case CHIP_VEGA20:
584
+		if (is_add)
585
+			return df_v3_6_pmc_add_cntr(adev, config);
586
+
587
+		df_v3_6_reset_perfmon_cntr(adev, config);
588
+
589
+		ret = df_v3_6_pmc_get_ctrl_settings(adev,
590
+					config,
591
+					&lo_base_addr,
592
+					&hi_base_addr,
593
+					&lo_val,
594
+					&hi_val,
595
+					true);
596
+
597
+		if (ret)
598
+			return ret;
599
+
600
+		err = df_v3_6_perfmon_arm_with_retry(adev,
601
+						     lo_base_addr,
602
+						     lo_val,
603
+						     hi_base_addr,
604
+						     hi_val);
605
+
606
+		if (err)
607
+			ret = df_v3_6_pmc_set_deferred(adev, config, true);
608
+
609
+		break;
610
+	default:
611
+		break;
612
+	}
613
+
614
+	return ret;
615
+}
616
+
617
+static int df_v3_6_pmc_stop(struct amdgpu_device *adev, uint64_t config,
618
+			    int is_remove)
619
+{
620
+	uint32_t lo_base_addr, hi_base_addr, lo_val, hi_val;
621
+	int ret = 0;
622
+
623
+	switch (adev->asic_type) {
624
+	case CHIP_VEGA20:
625
+		ret = df_v3_6_pmc_get_ctrl_settings(adev,
626
+			config,
627
+			&lo_base_addr,
628
+			&hi_base_addr,
629
+			&lo_val,
630
+			&hi_val,
631
+			false);
632
+
633
+		if (ret)
634
+			return ret;
635
+
636
+
637
+		if (is_remove) {
638
+			df_v3_6_reset_perfmon_cntr(adev, config);
639
+			df_v3_6_pmc_release_cntr(adev, config);
640
+		}
641
+
642
+		break;
643
+	default:
644
+		break;
645
+	}
646
+
647
+	return ret;
648
+}
649
+
650
+static void df_v3_6_pmc_get_count(struct amdgpu_device *adev,
651
+				  uint64_t config,
652
+				  uint64_t *count)
653
+{
654
+	uint32_t lo_base_addr = 0, hi_base_addr = 0, lo_val = 0, hi_val = 0;
655
+	*count = 0;
656
+
657
+	switch (adev->asic_type) {
658
+	case CHIP_VEGA20:
659
+		df_v3_6_pmc_get_read_settings(adev, config, &lo_base_addr,
660
+				      &hi_base_addr);
661
+
662
+		if ((lo_base_addr == 0) || (hi_base_addr == 0))
663
+			return;
664
+
665
+		/* rearm the counter or throw away count value on failure */
666
+		if (df_v3_6_pmc_is_deferred(adev, config)) {
667
+			int rearm_err = df_v3_6_perfmon_arm_with_status(adev,
668
+							lo_base_addr, lo_val,
669
+							hi_base_addr, hi_val);
670
+
671
+			if (rearm_err)
672
+				return;
673
+
674
+			df_v3_6_pmc_set_deferred(adev, config, false);
675
+		}
676
+
677
+		df_v3_6_perfmon_rreg(adev, lo_base_addr, &lo_val,
678
+				hi_base_addr, &hi_val);
679
+
680
+		*count  = ((hi_val | 0ULL) << 32) | (lo_val | 0ULL);
681
+
682
+		if (*count >= DF_V3_6_PERFMON_OVERFLOW)
683
+			*count = 0;
684
+
685
+		DRM_DEBUG_DRIVER("config=%llx addr=%08x:%08x val=%08x:%08x",
686
+			 config, lo_base_addr, hi_base_addr, lo_val, hi_val);
687
+
688
+		break;
689
+	default:
690
+		break;
691
+	}
692
+}
693
+
114694 const struct amdgpu_df_funcs df_v3_6_funcs = {
115
-	.init = df_v3_6_init,
695
+	.sw_init = df_v3_6_sw_init,
696
+	.sw_fini = df_v3_6_sw_fini,
116697 	.enable_broadcast_mode = df_v3_6_enable_broadcast_mode,
117698 	.get_fb_channel_number = df_v3_6_get_fb_channel_number,
118699 	.get_hbm_channel_number = df_v3_6_get_hbm_channel_number,
119700 	.update_medium_grain_clock_gating =
120701 			df_v3_6_update_medium_grain_clock_gating,
121702 	.get_clockgating_state = df_v3_6_get_clockgating_state,
703
+	.pmc_start = df_v3_6_pmc_start,
704
+	.pmc_stop = df_v3_6_pmc_stop,
705
+	.pmc_get_count = df_v3_6_pmc_get_count,
706
+	.get_fica = df_v3_6_get_fica,
707
+	.set_fica = df_v3_6_set_fica,
122708 };