summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
blob: 65aae75f80fd5ee4b62b7dc2bdf4cecb24b1b859 (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
/*
 * Copyright 2018 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 OTHERWISE,
 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 * OTHER DEALINGS IN THE SOFTWARE.
 *
 *
 */
#include <linux/list.h>
#include "amdgpu.h"
#include "amdgpu_xgmi.h"
#include "amdgpu_smu.h"
#include "df/df_3_6_offset.h"

static DEFINE_MUTEX(xgmi_mutex);

#define AMDGPU_MAX_XGMI_HIVE			8
#define AMDGPU_MAX_XGMI_DEVICE_PER_HIVE		4

static struct amdgpu_hive_info xgmi_hives[AMDGPU_MAX_XGMI_HIVE];
static unsigned hive_count = 0;

void *amdgpu_xgmi_hive_try_lock(struct amdgpu_hive_info *hive)
{
	return &hive->device_list;
}

/**
 * DOC: AMDGPU XGMI Support
 *
 * XGMI is a high speed interconnect that joins multiple GPU cards
 * into a homogeneous memory space that is organized by a collective
 * hive ID and individual node IDs, both of which are 64-bit numbers.
 *
 * The file xgmi_device_id contains the unique per GPU device ID and
 * is stored in the /sys/class/drm/card${cardno}/device/ directory.
 *
 * Inside the device directory a sub-directory 'xgmi_hive_info' is
 * created which contains the hive ID and the list of nodes.
 *
 * The hive ID is stored in:
 *   /sys/class/drm/card${cardno}/device/xgmi_hive_info/xgmi_hive_id
 *
 * The node information is stored in numbered directories:
 *   /sys/class/drm/card${cardno}/device/xgmi_hive_info/node${nodeno}/xgmi_device_id
 *
 * Each device has their own xgmi_hive_info direction with a mirror
 * set of node sub-directories.
 *
 * The XGMI memory space is built by contiguously adding the power of
 * two padded VRAM space from each node to each other.
 *
 */


static ssize_t amdgpu_xgmi_show_hive_id(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct amdgpu_hive_info *hive =
			container_of(attr, struct amdgpu_hive_info, dev_attr);

	return snprintf(buf, PAGE_SIZE, "%llu\n", hive->hive_id);
}

static int amdgpu_xgmi_sysfs_create(struct amdgpu_device *adev,
				    struct amdgpu_hive_info *hive)
{
	int ret = 0;

	if (WARN_ON(hive->kobj))
		return -EINVAL;

	hive->kobj = kobject_create_and_add("xgmi_hive_info", &adev->dev->kobj);
	if (!hive->kobj) {
		dev_err(adev->dev, "XGMI: Failed to allocate sysfs entry!\n");
		return -EINVAL;
	}

	hive->dev_attr = (struct device_attribute) {
		.attr = {
			.name = "xgmi_hive_id",
			.mode = S_IRUGO,

		},
		.show = amdgpu_xgmi_show_hive_id,
	};

	ret = sysfs_create_file(hive->kobj, &hive->dev_attr.attr);
	if (ret) {
		dev_err(adev->dev, "XGMI: Failed to create device file xgmi_hive_id\n");
		kobject_del(hive->kobj);
		kobject_put(hive->kobj);
		hive->kobj = NULL;
	}

	return ret;
}

static void amdgpu_xgmi_sysfs_destroy(struct amdgpu_device *adev,
				    struct amdgpu_hive_info *hive)
{
	sysfs_remove_file(hive->kobj, &hive->dev_attr.attr);
	kobject_del(hive->kobj);
	kobject_put(hive->kobj);
	hive->kobj = NULL;
}

static ssize_t amdgpu_xgmi_show_device_id(struct device *dev,
				     struct device_attribute *attr,
				     char *buf)
{
	struct drm_device *ddev = dev_get_drvdata(dev);
	struct amdgpu_device *adev = ddev->dev_private;

	return snprintf(buf, PAGE_SIZE, "%llu\n", adev->gmc.xgmi.node_id);

}

#define AMDGPU_XGMI_SET_FICAA(o)	((o) | 0x456801)
static ssize_t amdgpu_xgmi_show_error(struct device *dev,
				      struct device_attribute *attr,
				      char *buf)
{
	struct drm_device *ddev = dev_get_drvdata(dev);
	struct amdgpu_device *adev = ddev->dev_private;
	uint32_t ficaa_pie_ctl_in, ficaa_pie_status_in;
	uint64_t fica_out;
	unsigned int error_count = 0;

	ficaa_pie_ctl_in = AMDGPU_XGMI_SET_FICAA(0x200);
	ficaa_pie_status_in = AMDGPU_XGMI_SET_FICAA(0x208);

	fica_out = adev->df_funcs->get_fica(adev, ficaa_pie_ctl_in);
	if (fica_out != 0x1f)
		pr_err("xGMI error counters not enabled!\n");

	fica_out = adev->df_funcs->get_fica(adev, ficaa_pie_status_in);

	if ((fica_out & 0xffff) == 2)
		error_count = ((fica_out >> 62) & 0x1) + (fica_out >> 63);

	adev->df_funcs->set_fica(adev, ficaa_pie_status_in, 0, 0);

	return snprintf(buf, PAGE_SIZE, "%d\n", error_count);
}


static DEVICE_ATTR(xgmi_device_id, S_IRUGO, amdgpu_xgmi_show_device_id, NULL);
static DEVICE_ATTR(xgmi_error, S_IRUGO, amdgpu_xgmi_show_error, NULL);

static int amdgpu_xgmi_sysfs_add_dev_info(struct amdgpu_device *adev,
					 struct amdgpu_hive_info *hive)
{
	int ret = 0;
	char node[10] = { 0 };

	/* Create xgmi device id file */
	ret = device_create_file(adev->dev, &dev_attr_xgmi_device_id);
	if (ret) {
		dev_err(adev->dev, "XGMI: Failed to create device file xgmi_device_id\n");
		return ret;
	}

	/* Create xgmi error file */
	ret = device_create_file(adev->dev, &dev_attr_xgmi_error);
	if (ret)
		pr_err("failed to create xgmi_error\n");


	/* Create sysfs link to hive info folder on the first device */
	if (adev != hive->adev) {
		ret = sysfs_create_link(&adev->dev->kobj, hive->kobj,
					"xgmi_hive_info");
		if (ret) {
			dev_err(adev->dev, "XGMI: Failed to create link to hive info");
			goto remove_file;
		}
	}

	sprintf(node, "node%d", hive->number_devices);
	/* Create sysfs link form the hive folder to yourself */
	ret = sysfs_create_link(hive->kobj, &adev->dev->kobj, node);
	if (ret) {
		dev_err(adev->dev, "XGMI: Failed to create link from hive info");
		goto remove_link;
	}

	goto success;


remove_link:
	sysfs_remove_link(&adev->dev->kobj, adev->ddev->unique);

remove_file:
	device_remove_file(adev->dev, &dev_attr_xgmi_device_id);

success:
	return ret;
}

static void amdgpu_xgmi_sysfs_rem_dev_info(struct amdgpu_device *adev,
					  struct amdgpu_hive_info *hive)
{
	device_remove_file(adev->dev, &dev_attr_xgmi_device_id);
	sysfs_remove_link(&adev->dev->kobj, adev->ddev->unique);
	sysfs_remove_link(hive->kobj, adev->ddev->unique);
}



struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev, int lock)
{
	int i;
	struct amdgpu_hive_info *tmp;

	if (!adev->gmc.xgmi.hive_id)
		return NULL;

	mutex_lock(&xgmi_mutex);

	for (i = 0 ; i < hive_count; ++i) {
		tmp = &xgmi_hives[i];
		if (tmp->hive_id == adev->gmc.xgmi.hive_id) {
			if (lock)
				mutex_lock(&tmp->hive_lock);
			mutex_unlock(&xgmi_mutex);
			return tmp;
		}
	}
	if (i >= AMDGPU_MAX_XGMI_HIVE) {
		mutex_unlock(&xgmi_mutex);
		return NULL;
	}

	/* initialize new hive if not exist */
	tmp = &xgmi_hives[hive_count++];

	if (amdgpu_xgmi_sysfs_create(adev, tmp)) {
		mutex_unlock(&xgmi_mutex);
		return NULL;
	}

	tmp->adev = adev;
	tmp->hive_id = adev->gmc.xgmi.hive_id;
	INIT_LIST_HEAD(&tmp->device_list);
	mutex_init(&tmp->hive_lock);
	mutex_init(&tmp->reset_lock);

	if (lock)
		mutex_lock(&tmp->hive_lock);
	tmp->pstate = -1;
	mutex_unlock(&xgmi_mutex);

	return tmp;
}

int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate)
{
	int ret = 0;
	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, 0);

	if (!hive)
		return 0;

	if (hive->pstate == pstate)
		return 0;

	dev_dbg(adev->dev, "Set xgmi pstate %d.\n", pstate);

	if (is_support_sw_smu_xgmi(adev))
		ret = smu_set_xgmi_pstate(&adev->smu, pstate);
	if (ret)
		dev_err(adev->dev,
			"XGMI: Set pstate failure on device %llx, hive %llx, ret %d",
			adev->gmc.xgmi.node_id,
			adev->gmc.xgmi.hive_id, ret);

	return ret;
}

int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_device *adev)
{
	int ret = -EINVAL;

	/* Each psp need to set the latest topology */
	ret = psp_xgmi_set_topology_info(&adev->psp,
					 hive->number_devices,
					 &adev->psp.xgmi_context.top_info);
	if (ret)
		dev_err(adev->dev,
			"XGMI: Set topology failure on device %llx, hive %llx, ret %d",
			adev->gmc.xgmi.node_id,
			adev->gmc.xgmi.hive_id, ret);

	return ret;
}


int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev,
		struct amdgpu_device *peer_adev)
{
	struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info;
	int i;

	for (i = 0 ; i < top->num_nodes; ++i)
		if (top->nodes[i].node_id == peer_adev->gmc.xgmi.node_id)
			return top->nodes[i].num_hops;
	return	-EINVAL;
}

int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
{
	struct psp_xgmi_topology_info *top_info;
	struct amdgpu_hive_info *hive;
	struct amdgpu_xgmi	*entry;
	struct amdgpu_device *tmp_adev = NULL;

	int count = 0, ret = 0;

	if (!adev->gmc.xgmi.supported)
		return 0;

	if (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
		ret = psp_xgmi_get_hive_id(&adev->psp, &adev->gmc.xgmi.hive_id);
		if (ret) {
			dev_err(adev->dev,
				"XGMI: Failed to get hive id\n");
			return ret;
		}

		ret = psp_xgmi_get_node_id(&adev->psp, &adev->gmc.xgmi.node_id);
		if (ret) {
			dev_err(adev->dev,
				"XGMI: Failed to get node id\n");
			return ret;
		}
	} else {
		adev->gmc.xgmi.hive_id = 16;
		adev->gmc.xgmi.node_id = adev->gmc.xgmi.physical_node_id + 16;
	}

	hive = amdgpu_get_xgmi_hive(adev, 1);
	if (!hive) {
		ret = -EINVAL;
		dev_err(adev->dev,
			"XGMI: node 0x%llx, can not match hive 0x%llx in the hive list.\n",
			adev->gmc.xgmi.node_id, adev->gmc.xgmi.hive_id);
		goto exit;
	}

	top_info = &adev->psp.xgmi_context.top_info;

	list_add_tail(&adev->gmc.xgmi.head, &hive->device_list);
	list_for_each_entry(entry, &hive->device_list, head)
		top_info->nodes[count++].node_id = entry->node_id;
	top_info->num_nodes = count;
	hive->number_devices = count;

	if (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
			/* update node list for other device in the hive */
			if (tmp_adev != adev) {
				top_info = &tmp_adev->psp.xgmi_context.top_info;
				top_info->nodes[count - 1].node_id =
					adev->gmc.xgmi.node_id;
				top_info->num_nodes = count;
			}
			ret = amdgpu_xgmi_update_topology(hive, tmp_adev);
			if (ret)
				goto exit;
		}

		/* get latest topology info for each device from psp */
		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
			ret = psp_xgmi_get_topology_info(&tmp_adev->psp, count,
					&tmp_adev->psp.xgmi_context.top_info);
			if (ret) {
				dev_err(tmp_adev->dev,
					"XGMI: Get topology failure on device %llx, hive %llx, ret %d",
					tmp_adev->gmc.xgmi.node_id,
					tmp_adev->gmc.xgmi.hive_id, ret);
				/* To do : continue with some node failed or disable the whole hive */
				goto exit;
			}
		}
	}

	if (!ret)
		ret = amdgpu_xgmi_sysfs_add_dev_info(adev, hive);


	mutex_unlock(&hive->hive_lock);
exit:
	if (!ret)
		dev_info(adev->dev, "XGMI: Add node %d, hive 0x%llx.\n",
			 adev->gmc.xgmi.physical_node_id, adev->gmc.xgmi.hive_id);
	else
		dev_err(adev->dev, "XGMI: Failed to add node %d, hive 0x%llx ret: %d\n",
			adev->gmc.xgmi.physical_node_id, adev->gmc.xgmi.hive_id,
			ret);

	return ret;
}

void amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
{
	struct amdgpu_hive_info *hive;

	if (!adev->gmc.xgmi.supported)
		return;

	hive = amdgpu_get_xgmi_hive(adev, 1);
	if (!hive)
		return;

	if (!(hive->number_devices--)) {
		amdgpu_xgmi_sysfs_destroy(adev, hive);
		mutex_destroy(&hive->hive_lock);
		mutex_destroy(&hive->reset_lock);
	} else {
		amdgpu_xgmi_sysfs_rem_dev_info(adev, hive);
		mutex_unlock(&hive->hive_lock);
	}
}