summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/v3d/v3d_bo.c
blob: a07ede668cc1617c84fa956cfb78b5cab77af003 (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
// SPDX-License-Identifier: GPL-2.0+
/* Copyright (C) 2015-2018 Broadcom */

/**
 * DOC: V3D GEM BO management support
 *
 * Compared to VC4 (V3D 2.x), V3D 3.3 introduces an MMU between the
 * GPU and the bus, allowing us to use shmem objects for our storage
 * instead of CMA.
 *
 * Physically contiguous objects may still be imported to V3D, but the
 * driver doesn't allocate physically contiguous objects on its own.
 * Display engines requiring physically contiguous allocations should
 * look into Mesa's "renderonly" support (as used by the Mesa pl111
 * driver) for an example of how to integrate with V3D.
 *
 * Long term, we should support evicting pages from the MMU when under
 * memory pressure (thus the v3d_bo_get_pages() refcounting), but
 * that's not a high priority since our systems tend to not have swap.
 */

#include <linux/dma-buf.h>
#include <linux/pfn_t.h>

#include "v3d_drv.h"
#include "uapi/drm/v3d_drm.h"

/* Called DRM core on the last userspace/kernel unreference of the
 * BO.
 */
void v3d_free_object(struct drm_gem_object *obj)
{
	struct v3d_dev *v3d = to_v3d_dev(obj->dev);
	struct v3d_bo *bo = to_v3d_bo(obj);

	if (bo->vaddr)
		v3d_put_bo_vaddr(bo);

	v3d_mmu_remove_ptes(bo);

	mutex_lock(&v3d->bo_lock);
	v3d->bo_stats.num_allocated--;
	v3d->bo_stats.pages_allocated -= obj->size >> V3D_MMU_PAGE_SHIFT;
	mutex_unlock(&v3d->bo_lock);

	spin_lock(&v3d->mm_lock);
	drm_mm_remove_node(&bo->node);
	spin_unlock(&v3d->mm_lock);

	/* GPU execution may have dirtied any pages in the BO. */
	bo->base.pages_mark_dirty_on_put = true;

	drm_gem_shmem_free(&bo->base);
}

static const struct drm_gem_object_funcs v3d_gem_funcs = {
	.free = v3d_free_object,
	.print_info = drm_gem_shmem_object_print_info,
	.pin = drm_gem_shmem_object_pin,
	.unpin = drm_gem_shmem_object_unpin,
	.get_sg_table = drm_gem_shmem_object_get_sg_table,
	.vmap = drm_gem_shmem_object_vmap,
	.vunmap = drm_gem_shmem_object_vunmap,
	.mmap = drm_gem_shmem_object_mmap,
	.vm_ops = &drm_gem_shmem_vm_ops,
};

/* gem_create_object function for allocating a BO struct and doing
 * early setup.
 */
struct drm_gem_object *v3d_create_object(struct drm_device *dev, size_t size)
{
	struct v3d_bo *bo;
	struct drm_gem_object *obj;

	if (size == 0)
		return ERR_PTR(-EINVAL);

	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
	if (!bo)
		return ERR_PTR(-ENOMEM);
	obj = &bo->base.base;

	obj->funcs = &v3d_gem_funcs;
	bo->base.map_wc = true;
	INIT_LIST_HEAD(&bo->unref_head);

	return &bo->base.base;
}

static int
v3d_bo_create_finish(struct drm_gem_object *obj)
{
	struct v3d_dev *v3d = to_v3d_dev(obj->dev);
	struct v3d_bo *bo = to_v3d_bo(obj);
	struct sg_table *sgt;
	int ret;

	/* So far we pin the BO in the MMU for its lifetime, so use
	 * shmem's helper for getting a lifetime sgt.
	 */
	sgt = drm_gem_shmem_get_pages_sgt(&bo->base);
	if (IS_ERR(sgt))
		return PTR_ERR(sgt);

	spin_lock(&v3d->mm_lock);
	/* Allocate the object's space in the GPU's page tables.
	 * Inserting PTEs will happen later, but the offset is for the
	 * lifetime of the BO.
	 */
	ret = drm_mm_insert_node_generic(&v3d->mm, &bo->node,
					 obj->size >> V3D_MMU_PAGE_SHIFT,
					 GMP_GRANULARITY >> V3D_MMU_PAGE_SHIFT, 0, 0);
	spin_unlock(&v3d->mm_lock);
	if (ret)
		return ret;

	/* Track stats for /debug/dri/n/bo_stats. */
	mutex_lock(&v3d->bo_lock);
	v3d->bo_stats.num_allocated++;
	v3d->bo_stats.pages_allocated += obj->size >> V3D_MMU_PAGE_SHIFT;
	mutex_unlock(&v3d->bo_lock);

	v3d_mmu_insert_ptes(bo);

	return 0;
}

struct v3d_bo *v3d_bo_create(struct drm_device *dev, struct drm_file *file_priv,
			     size_t unaligned_size)
{
	struct drm_gem_shmem_object *shmem_obj;
	struct v3d_bo *bo;
	int ret;

	shmem_obj = drm_gem_shmem_create(dev, unaligned_size);
	if (IS_ERR(shmem_obj))
		return ERR_CAST(shmem_obj);
	bo = to_v3d_bo(&shmem_obj->base);
	bo->vaddr = NULL;

	ret = v3d_bo_create_finish(&shmem_obj->base);
	if (ret)
		goto free_obj;

	return bo;

free_obj:
	drm_gem_shmem_free(shmem_obj);
	return ERR_PTR(ret);
}

struct drm_gem_object *
v3d_prime_import_sg_table(struct drm_device *dev,
			  struct dma_buf_attachment *attach,
			  struct sg_table *sgt)
{
	struct drm_gem_object *obj;
	int ret;

	obj = drm_gem_shmem_prime_import_sg_table(dev, attach, sgt);
	if (IS_ERR(obj))
		return obj;

	ret = v3d_bo_create_finish(obj);
	if (ret) {
		drm_gem_shmem_free(&to_v3d_bo(obj)->base);
		return ERR_PTR(ret);
	}

	return obj;
}

void v3d_get_bo_vaddr(struct v3d_bo *bo)
{
	struct drm_gem_shmem_object *obj = &bo->base;

	bo->vaddr = vmap(obj->pages, obj->base.size >> PAGE_SHIFT, VM_MAP,
			 pgprot_writecombine(PAGE_KERNEL));
}

void v3d_put_bo_vaddr(struct v3d_bo *bo)
{
	vunmap(bo->vaddr);
	bo->vaddr = NULL;
}

int v3d_create_bo_ioctl(struct drm_device *dev, void *data,
			struct drm_file *file_priv)
{
	struct drm_v3d_create_bo *args = data;
	struct v3d_bo *bo = NULL;
	int ret;

	if (args->flags != 0) {
		DRM_INFO("unknown create_bo flags: %d\n", args->flags);
		return -EINVAL;
	}

	bo = v3d_bo_create(dev, file_priv, PAGE_ALIGN(args->size));
	if (IS_ERR(bo))
		return PTR_ERR(bo);

	args->offset = bo->node.start << V3D_MMU_PAGE_SHIFT;

	ret = drm_gem_handle_create(file_priv, &bo->base.base, &args->handle);
	drm_gem_object_put(&bo->base.base);

	return ret;
}

int v3d_mmap_bo_ioctl(struct drm_device *dev, void *data,
		      struct drm_file *file_priv)
{
	struct drm_v3d_mmap_bo *args = data;
	struct drm_gem_object *gem_obj;

	if (args->flags != 0) {
		DRM_INFO("unknown mmap_bo flags: %d\n", args->flags);
		return -EINVAL;
	}

	gem_obj = drm_gem_object_lookup(file_priv, args->handle);
	if (!gem_obj) {
		DRM_DEBUG("Failed to look up GEM BO %d\n", args->handle);
		return -ENOENT;
	}

	args->offset = drm_vma_node_offset_addr(&gem_obj->vma_node);
	drm_gem_object_put(gem_obj);

	return 0;
}

int v3d_get_bo_offset_ioctl(struct drm_device *dev, void *data,
			    struct drm_file *file_priv)
{
	struct drm_v3d_get_bo_offset *args = data;
	struct drm_gem_object *gem_obj;
	struct v3d_bo *bo;

	gem_obj = drm_gem_object_lookup(file_priv, args->handle);
	if (!gem_obj) {
		DRM_DEBUG("Failed to look up GEM BO %d\n", args->handle);
		return -ENOENT;
	}
	bo = to_v3d_bo(gem_obj);

	args->offset = bo->node.start << V3D_MMU_PAGE_SHIFT;

	drm_gem_object_put(gem_obj);
	return 0;
}

int
v3d_wait_bo_ioctl(struct drm_device *dev, void *data,
		  struct drm_file *file_priv)
{
	int ret;
	struct drm_v3d_wait_bo *args = data;
	ktime_t start = ktime_get();
	u64 delta_ns;
	unsigned long timeout_jiffies =
		nsecs_to_jiffies_timeout(args->timeout_ns);

	if (args->pad != 0)
		return -EINVAL;

	ret = drm_gem_dma_resv_wait(file_priv, args->handle,
				    true, timeout_jiffies);

	/* Decrement the user's timeout, in case we got interrupted
	 * such that the ioctl will be restarted.
	 */
	delta_ns = ktime_to_ns(ktime_sub(ktime_get(), start));
	if (delta_ns < args->timeout_ns)
		args->timeout_ns -= delta_ns;
	else
		args->timeout_ns = 0;

	/* Asked to wait beyond the jiffie/scheduler precision? */
	if (ret == -ETIME && args->timeout_ns)
		ret = -EAGAIN;

	return ret;
}