summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/v3d/v3d_drv.h
blob: 9aad9da1eb114fbe95fe9fdee5679c5a26c086b7 (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
// SPDX-License-Identifier: GPL-2.0+
/* Copyright (C) 2015-2018 Broadcom */

#include <linux/mm_types.h>
#include <drm/drmP.h>
#include <drm/drm_encoder.h>
#include <drm/drm_gem.h>
#include <drm/drm_gem_shmem_helper.h>
#include <drm/gpu_scheduler.h>
#include "uapi/drm/v3d_drm.h"

#define GMP_GRANULARITY (128 * 1024)

/* Enum for each of the V3D queues. */
enum v3d_queue {
	V3D_BIN,
	V3D_RENDER,
	V3D_TFU,
	V3D_CSD,
	V3D_CACHE_CLEAN,
};

#define V3D_MAX_QUEUES (V3D_CACHE_CLEAN + 1)

struct v3d_queue_state {
	struct drm_gpu_scheduler sched;

	u64 fence_context;
	u64 emit_seqno;
};

struct v3d_dev {
	struct drm_device drm;

	/* Short representation (e.g. 33, 41) of the V3D tech version
	 * and revision.
	 */
	int ver;
	bool single_irq_line;

	struct device *dev;
	struct platform_device *pdev;
	void __iomem *hub_regs;
	void __iomem *core_regs[3];
	void __iomem *bridge_regs;
	void __iomem *gca_regs;
	struct clk *clk;
	struct reset_control *reset;

	/* Virtual and DMA addresses of the single shared page table. */
	volatile u32 *pt;
	dma_addr_t pt_paddr;

	/* Virtual and DMA addresses of the MMU's scratch page.  When
	 * a read or write is invalid in the MMU, it will be
	 * redirected here.
	 */
	void *mmu_scratch;
	dma_addr_t mmu_scratch_paddr;
	/* virtual address bits from V3D to the MMU. */
	int va_width;

	/* Number of V3D cores. */
	u32 cores;

	/* Allocator managing the address space.  All units are in
	 * number of pages.
	 */
	struct drm_mm mm;
	spinlock_t mm_lock;

	struct work_struct overflow_mem_work;

	struct v3d_bin_job *bin_job;
	struct v3d_render_job *render_job;
	struct v3d_tfu_job *tfu_job;
	struct v3d_csd_job *csd_job;

	struct v3d_queue_state queue[V3D_MAX_QUEUES];

	/* Spinlock used to synchronize the overflow memory
	 * management against bin job submission.
	 */
	spinlock_t job_lock;

	/* Protects bo_stats */
	struct mutex bo_lock;

	/* Lock taken when resetting the GPU, to keep multiple
	 * processes from trying to park the scheduler threads and
	 * reset at once.
	 */
	struct mutex reset_lock;

	/* Lock taken when creating and pushing the GPU scheduler
	 * jobs, to keep the sched-fence seqnos in order.
	 */
	struct mutex sched_lock;

	/* Lock taken during a cache clean and when initiating an L2
	 * flush, to keep L2 flushes from interfering with the
	 * synchronous L2 cleans.
	 */
	struct mutex cache_clean_lock;

	struct {
		u32 num_allocated;
		u32 pages_allocated;
	} bo_stats;
};

static inline struct v3d_dev *
to_v3d_dev(struct drm_device *dev)
{
	return (struct v3d_dev *)dev->dev_private;
}

static inline bool
v3d_has_csd(struct v3d_dev *v3d)
{
	return v3d->ver >= 41;
}

/* The per-fd struct, which tracks the MMU mappings. */
struct v3d_file_priv {
	struct v3d_dev *v3d;

	struct drm_sched_entity sched_entity[V3D_MAX_QUEUES];
};

struct v3d_bo {
	struct drm_gem_shmem_object base;

	struct drm_mm_node node;

	/* List entry for the BO's position in
	 * v3d_render_job->unref_list
	 */
	struct list_head unref_head;
};

static inline struct v3d_bo *
to_v3d_bo(struct drm_gem_object *bo)
{
	return (struct v3d_bo *)bo;
}

struct v3d_fence {
	struct dma_fence base;
	struct drm_device *dev;
	/* v3d seqno for signaled() test */
	u64 seqno;
	enum v3d_queue queue;
};

static inline struct v3d_fence *
to_v3d_fence(struct dma_fence *fence)
{
	return (struct v3d_fence *)fence;
}

#define V3D_READ(offset) readl(v3d->hub_regs + offset)
#define V3D_WRITE(offset, val) writel(val, v3d->hub_regs + offset)

#define V3D_BRIDGE_READ(offset) readl(v3d->bridge_regs + offset)
#define V3D_BRIDGE_WRITE(offset, val) writel(val, v3d->bridge_regs + offset)

#define V3D_GCA_READ(offset) readl(v3d->gca_regs + offset)
#define V3D_GCA_WRITE(offset, val) writel(val, v3d->gca_regs + offset)

#define V3D_CORE_READ(core, offset) readl(v3d->core_regs[core] + offset)
#define V3D_CORE_WRITE(core, offset, val) writel(val, v3d->core_regs[core] + offset)

struct v3d_job {
	struct drm_sched_job base;

	struct kref refcount;

	struct v3d_dev *v3d;

	/* This is the array of BOs that were looked up at the start
	 * of submission.
	 */
	struct drm_gem_object **bo;
	u32 bo_count;

	/* Array of struct dma_fence * to block on before submitting this job.
	 */
	struct xarray deps;
	unsigned long last_dep;

	/* v3d fence to be signaled by IRQ handler when the job is complete. */
	struct dma_fence *irq_fence;

	/* scheduler fence for when the job is considered complete and
	 * the BO reservations can be released.
	 */
	struct dma_fence *done_fence;

	/* Callback for the freeing of the job on refcount going to 0. */
	void (*free)(struct kref *ref);
};

struct v3d_bin_job {
	struct v3d_job base;

	/* GPU virtual addresses of the start/end of the CL job. */
	u32 start, end;

	u32 timedout_ctca, timedout_ctra;

	/* Corresponding render job, for attaching our overflow memory. */
	struct v3d_render_job *render;

	/* Submitted tile memory allocation start/size, tile state. */
	u32 qma, qms, qts;
};

struct v3d_render_job {
	struct v3d_job base;

	/* GPU virtual addresses of the start/end of the CL job. */
	u32 start, end;

	u32 timedout_ctca, timedout_ctra;

	/* List of overflow BOs used in the job that need to be
	 * released once the job is complete.
	 */
	struct list_head unref_list;
};

struct v3d_tfu_job {
	struct v3d_job base;

	struct drm_v3d_submit_tfu args;
};

struct v3d_csd_job {
	struct v3d_job base;

	u32 timedout_batches;

	struct drm_v3d_submit_csd args;
};

/**
 * _wait_for - magic (register) wait macro
 *
 * Does the right thing for modeset paths when run under kdgb or similar atomic
 * contexts. Note that it's important that we check the condition again after
 * having timed out, since the timeout could be due to preemption or similar and
 * we've never had a chance to check the condition before the timeout.
 */
#define wait_for(COND, MS) ({ \
	unsigned long timeout__ = jiffies + msecs_to_jiffies(MS) + 1;	\
	int ret__ = 0;							\
	while (!(COND)) {						\
		if (time_after(jiffies, timeout__)) {			\
			if (!(COND))					\
				ret__ = -ETIMEDOUT;			\
			break;						\
		}							\
		msleep(1);					\
	}								\
	ret__;								\
})

static inline unsigned long nsecs_to_jiffies_timeout(const u64 n)
{
	/* nsecs_to_jiffies64() does not guard against overflow */
	if (NSEC_PER_SEC % HZ &&
	    div_u64(n, NSEC_PER_SEC) >= MAX_JIFFY_OFFSET / HZ)
		return MAX_JIFFY_OFFSET;

	return min_t(u64, MAX_JIFFY_OFFSET, nsecs_to_jiffies64(n) + 1);
}

/* v3d_bo.c */
struct drm_gem_object *v3d_create_object(struct drm_device *dev, size_t size);
void v3d_free_object(struct drm_gem_object *gem_obj);
struct v3d_bo *v3d_bo_create(struct drm_device *dev, struct drm_file *file_priv,
			     size_t size);
int v3d_create_bo_ioctl(struct drm_device *dev, void *data,
			struct drm_file *file_priv);
int v3d_mmap_bo_ioctl(struct drm_device *dev, void *data,
		      struct drm_file *file_priv);
int v3d_get_bo_offset_ioctl(struct drm_device *dev, void *data,
			    struct drm_file *file_priv);
struct drm_gem_object *v3d_prime_import_sg_table(struct drm_device *dev,
						 struct dma_buf_attachment *attach,
						 struct sg_table *sgt);

/* v3d_debugfs.c */
int v3d_debugfs_init(struct drm_minor *minor);

/* v3d_fence.c */
extern const struct dma_fence_ops v3d_fence_ops;
struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue queue);

/* v3d_gem.c */
int v3d_gem_init(struct drm_device *dev);
void v3d_gem_destroy(struct drm_device *dev);
int v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
			struct drm_file *file_priv);
int v3d_submit_tfu_ioctl(struct drm_device *dev, void *data,
			 struct drm_file *file_priv);
int v3d_submit_csd_ioctl(struct drm_device *dev, void *data,
			 struct drm_file *file_priv);
int v3d_wait_bo_ioctl(struct drm_device *dev, void *data,
		      struct drm_file *file_priv);
void v3d_job_put(struct v3d_job *job);
void v3d_reset(struct v3d_dev *v3d);
void v3d_invalidate_caches(struct v3d_dev *v3d);
void v3d_clean_caches(struct v3d_dev *v3d);

/* v3d_irq.c */
int v3d_irq_init(struct v3d_dev *v3d);
void v3d_irq_enable(struct v3d_dev *v3d);
void v3d_irq_disable(struct v3d_dev *v3d);
void v3d_irq_reset(struct v3d_dev *v3d);

/* v3d_mmu.c */
int v3d_mmu_get_offset(struct drm_file *file_priv, struct v3d_bo *bo,
		       u32 *offset);
int v3d_mmu_set_page_table(struct v3d_dev *v3d);
void v3d_mmu_insert_ptes(struct v3d_bo *bo);
void v3d_mmu_remove_ptes(struct v3d_bo *bo);

/* v3d_sched.c */
int v3d_sched_init(struct v3d_dev *v3d);
void v3d_sched_fini(struct v3d_dev *v3d);