summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
blob: 400c66ba4c6bdc49ecdf30a3cb9deb9a79dffa71 (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
/*
 * 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 OTHERWISE,
 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 * OTHER DEALINGS IN THE SOFTWARE.
 *
 * Authors: monk liu <monk.liu@amd.com>
 */

#include <drm/drmP.h>
#include "amdgpu.h"

static int amdgpu_ctx_init(struct amdgpu_device *adev, struct amdgpu_ctx *ctx)
{
	unsigned i, j;
	int r;

	memset(ctx, 0, sizeof(*ctx));
	ctx->adev = adev;
	kref_init(&ctx->refcount);
	spin_lock_init(&ctx->ring_lock);
	ctx->fences = kcalloc(amdgpu_sched_jobs * AMDGPU_MAX_RINGS,
			      sizeof(struct dma_fence*), GFP_KERNEL);
	if (!ctx->fences)
		return -ENOMEM;

	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
		ctx->rings[i].sequence = 1;
		ctx->rings[i].fences = &ctx->fences[amdgpu_sched_jobs * i];
	}

	ctx->reset_counter = atomic_read(&adev->gpu_reset_counter);

	/* create context entity for each ring */
	for (i = 0; i < adev->num_rings; i++) {
		struct amdgpu_ring *ring = adev->rings[i];
		struct amd_sched_rq *rq;

		rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
		r = amd_sched_entity_init(&ring->sched, &ctx->rings[i].entity,
					  rq, amdgpu_sched_jobs);
		if (r)
			goto failed;
	}

	return 0;

failed:
	for (j = 0; j < i; j++)
		amd_sched_entity_fini(&adev->rings[j]->sched,
				      &ctx->rings[j].entity);
	kfree(ctx->fences);
	ctx->fences = NULL;
	return r;
}

static void amdgpu_ctx_fini(struct amdgpu_ctx *ctx)
{
	struct amdgpu_device *adev = ctx->adev;
	unsigned i, j;

	if (!adev)
		return;

	for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
		for (j = 0; j < amdgpu_sched_jobs; ++j)
			dma_fence_put(ctx->rings[i].fences[j]);
	kfree(ctx->fences);
	ctx->fences = NULL;

	for (i = 0; i < adev->num_rings; i++)
		amd_sched_entity_fini(&adev->rings[i]->sched,
				      &ctx->rings[i].entity);
}

static int amdgpu_ctx_alloc(struct amdgpu_device *adev,
			    struct amdgpu_fpriv *fpriv,
			    uint32_t *id)
{
	struct amdgpu_ctx_mgr *mgr = &fpriv->ctx_mgr;
	struct amdgpu_ctx *ctx;
	int r;

	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
	if (!ctx)
		return -ENOMEM;

	mutex_lock(&mgr->lock);
	r = idr_alloc(&mgr->ctx_handles, ctx, 1, 0, GFP_KERNEL);
	if (r < 0) {
		mutex_unlock(&mgr->lock);
		kfree(ctx);
		return r;
	}
	*id = (uint32_t)r;
	r = amdgpu_ctx_init(adev, ctx);
	if (r) {
		idr_remove(&mgr->ctx_handles, *id);
		*id = 0;
		kfree(ctx);
	}
	mutex_unlock(&mgr->lock);
	return r;
}

static void amdgpu_ctx_do_release(struct kref *ref)
{
	struct amdgpu_ctx *ctx;

	ctx = container_of(ref, struct amdgpu_ctx, refcount);

	amdgpu_ctx_fini(ctx);

	kfree(ctx);
}

static int amdgpu_ctx_free(struct amdgpu_fpriv *fpriv, uint32_t id)
{
	struct amdgpu_ctx_mgr *mgr = &fpriv->ctx_mgr;
	struct amdgpu_ctx *ctx;

	mutex_lock(&mgr->lock);
	ctx = idr_find(&mgr->ctx_handles, id);
	if (ctx) {
		idr_remove(&mgr->ctx_handles, id);
		kref_put(&ctx->refcount, amdgpu_ctx_do_release);
		mutex_unlock(&mgr->lock);
		return 0;
	}
	mutex_unlock(&mgr->lock);
	return -EINVAL;
}

static int amdgpu_ctx_query(struct amdgpu_device *adev,
			    struct amdgpu_fpriv *fpriv, uint32_t id,
			    union drm_amdgpu_ctx_out *out)
{
	struct amdgpu_ctx *ctx;
	struct amdgpu_ctx_mgr *mgr;
	unsigned reset_counter;

	if (!fpriv)
		return -EINVAL;

	mgr = &fpriv->ctx_mgr;
	mutex_lock(&mgr->lock);
	ctx = idr_find(&mgr->ctx_handles, id);
	if (!ctx) {
		mutex_unlock(&mgr->lock);
		return -EINVAL;
	}

	/* TODO: these two are always zero */
	out->state.flags = 0x0;
	out->state.hangs = 0x0;

	/* determine if a GPU reset has occured since the last call */
	reset_counter = atomic_read(&adev->gpu_reset_counter);
	/* TODO: this should ideally return NO, GUILTY, or INNOCENT. */
	if (ctx->reset_counter == reset_counter)
		out->state.reset_status = AMDGPU_CTX_NO_RESET;
	else
		out->state.reset_status = AMDGPU_CTX_UNKNOWN_RESET;
	ctx->reset_counter = reset_counter;

	mutex_unlock(&mgr->lock);
	return 0;
}

int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
		     struct drm_file *filp)
{
	int r;
	uint32_t id;

	union drm_amdgpu_ctx *args = data;
	struct amdgpu_device *adev = dev->dev_private;
	struct amdgpu_fpriv *fpriv = filp->driver_priv;

	r = 0;
	id = args->in.ctx_id;

	switch (args->in.op) {
	case AMDGPU_CTX_OP_ALLOC_CTX:
		r = amdgpu_ctx_alloc(adev, fpriv, &id);
		args->out.alloc.ctx_id = id;
		break;
	case AMDGPU_CTX_OP_FREE_CTX:
		r = amdgpu_ctx_free(fpriv, id);
		break;
	case AMDGPU_CTX_OP_QUERY_STATE:
		r = amdgpu_ctx_query(adev, fpriv, id, &args->out);
		break;
	default:
		return -EINVAL;
	}

	return r;
}

struct amdgpu_ctx *amdgpu_ctx_get(struct amdgpu_fpriv *fpriv, uint32_t id)
{
	struct amdgpu_ctx *ctx;
	struct amdgpu_ctx_mgr *mgr;

	if (!fpriv)
		return NULL;

	mgr = &fpriv->ctx_mgr;

	mutex_lock(&mgr->lock);
	ctx = idr_find(&mgr->ctx_handles, id);
	if (ctx)
		kref_get(&ctx->refcount);
	mutex_unlock(&mgr->lock);
	return ctx;
}

int amdgpu_ctx_put(struct amdgpu_ctx *ctx)
{
	if (ctx == NULL)
		return -EINVAL;

	kref_put(&ctx->refcount, amdgpu_ctx_do_release);
	return 0;
}

uint64_t amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx, struct amdgpu_ring *ring,
			      struct dma_fence *fence)
{
	struct amdgpu_ctx_ring *cring = & ctx->rings[ring->idx];
	uint64_t seq = cring->sequence;
	unsigned idx = 0;
	struct dma_fence *other = NULL;

	idx = seq & (amdgpu_sched_jobs - 1);
	other = cring->fences[idx];
	if (other) {
		signed long r;
		r = dma_fence_wait_timeout(other, false, MAX_SCHEDULE_TIMEOUT);
		if (r < 0)
			DRM_ERROR("Error (%ld) waiting for fence!\n", r);
	}

	dma_fence_get(fence);

	spin_lock(&ctx->ring_lock);
	cring->fences[idx] = fence;
	cring->sequence++;
	spin_unlock(&ctx->ring_lock);

	dma_fence_put(other);

	return seq;
}

struct dma_fence *amdgpu_ctx_get_fence(struct amdgpu_ctx *ctx,
				       struct amdgpu_ring *ring, uint64_t seq)
{
	struct amdgpu_ctx_ring *cring = & ctx->rings[ring->idx];
	struct dma_fence *fence;

	spin_lock(&ctx->ring_lock);

	if (seq >= cring->sequence) {
		spin_unlock(&ctx->ring_lock);
		return ERR_PTR(-EINVAL);
	}


	if (seq + amdgpu_sched_jobs < cring->sequence) {
		spin_unlock(&ctx->ring_lock);
		return NULL;
	}

	fence = dma_fence_get(cring->fences[seq & (amdgpu_sched_jobs - 1)]);
	spin_unlock(&ctx->ring_lock);

	return fence;
}

void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr)
{
	mutex_init(&mgr->lock);
	idr_init(&mgr->ctx_handles);
}

void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr)
{
	struct amdgpu_ctx *ctx;
	struct idr *idp;
	uint32_t id;

	idp = &mgr->ctx_handles;

	idr_for_each_entry(idp, ctx, id) {
		if (kref_put(&ctx->refcount, amdgpu_ctx_do_release) != 1)
			DRM_ERROR("ctx %p is still alive\n", ctx);
	}

	idr_destroy(&mgr->ctx_handles);
	mutex_destroy(&mgr->lock);
}
OpenPOWER on IntegriCloud