summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/gt/intel_engine.h
blob: 7c3a1012e702046de696e82191ab1bef23bb9009 (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
/* SPDX-License-Identifier: MIT */
#ifndef _INTEL_RINGBUFFER_H_
#define _INTEL_RINGBUFFER_H_

#include <drm/drm_util.h>

#include <linux/hashtable.h>
#include <linux/irq_work.h>
#include <linux/random.h>
#include <linux/seqlock.h>

#include "i915_pmu.h"
#include "i915_reg.h"
#include "i915_request.h"
#include "i915_selftest.h"
#include "gt/intel_timeline.h"
#include "intel_engine_types.h"
#include "intel_gpu_commands.h"
#include "intel_workarounds.h"

struct drm_printer;
struct intel_gt;

/* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill,
 * but keeps the logic simple. Indeed, the whole purpose of this macro is just
 * to give some inclination as to some of the magic values used in the various
 * workarounds!
 */
#define CACHELINE_BYTES 64
#define CACHELINE_DWORDS (CACHELINE_BYTES / sizeof(u32))

#define ENGINE_TRACE(e, fmt, ...) do {					\
	const struct intel_engine_cs *e__ __maybe_unused = (e);		\
	GEM_TRACE("%s %s: " fmt,					\
		  dev_name(e__->i915->drm.dev), e__->name,		\
		  ##__VA_ARGS__);					\
} while (0)

/*
 * The register defines to be used with the following macros need to accept a
 * base param, e.g:
 *
 * REG_FOO(base) _MMIO((base) + <relative offset>)
 * ENGINE_READ(engine, REG_FOO);
 *
 * register arrays are to be defined and accessed as follows:
 *
 * REG_BAR(base, i) _MMIO((base) + <relative offset> + (i) * <shift>)
 * ENGINE_READ_IDX(engine, REG_BAR, i)
 */

#define __ENGINE_REG_OP(op__, engine__, ...) \
	intel_uncore_##op__((engine__)->uncore, __VA_ARGS__)

#define __ENGINE_READ_OP(op__, engine__, reg__) \
	__ENGINE_REG_OP(op__, (engine__), reg__((engine__)->mmio_base))

#define ENGINE_READ16(...)	__ENGINE_READ_OP(read16, __VA_ARGS__)
#define ENGINE_READ(...)	__ENGINE_READ_OP(read, __VA_ARGS__)
#define ENGINE_READ_FW(...)	__ENGINE_READ_OP(read_fw, __VA_ARGS__)
#define ENGINE_POSTING_READ(...) __ENGINE_READ_OP(posting_read_fw, __VA_ARGS__)
#define ENGINE_POSTING_READ16(...) __ENGINE_READ_OP(posting_read16, __VA_ARGS__)

#define ENGINE_READ64(engine__, lower_reg__, upper_reg__) \
	__ENGINE_REG_OP(read64_2x32, (engine__), \
			lower_reg__((engine__)->mmio_base), \
			upper_reg__((engine__)->mmio_base))

#define ENGINE_READ_IDX(engine__, reg__, idx__) \
	__ENGINE_REG_OP(read, (engine__), reg__((engine__)->mmio_base, (idx__)))

#define __ENGINE_WRITE_OP(op__, engine__, reg__, val__) \
	__ENGINE_REG_OP(op__, (engine__), reg__((engine__)->mmio_base), (val__))

#define ENGINE_WRITE16(...)	__ENGINE_WRITE_OP(write16, __VA_ARGS__)
#define ENGINE_WRITE(...)	__ENGINE_WRITE_OP(write, __VA_ARGS__)
#define ENGINE_WRITE_FW(...)	__ENGINE_WRITE_OP(write_fw, __VA_ARGS__)

#define GEN6_RING_FAULT_REG_READ(engine__) \
	intel_uncore_read((engine__)->uncore, RING_FAULT_REG(engine__))

#define GEN6_RING_FAULT_REG_POSTING_READ(engine__) \
	intel_uncore_posting_read((engine__)->uncore, RING_FAULT_REG(engine__))

#define GEN6_RING_FAULT_REG_RMW(engine__, clear__, set__) \
({ \
	u32 __val; \
\
	__val = intel_uncore_read((engine__)->uncore, \
				  RING_FAULT_REG(engine__)); \
	__val &= ~(clear__); \
	__val |= (set__); \
	intel_uncore_write((engine__)->uncore, RING_FAULT_REG(engine__), \
			   __val); \
})

/* seqno size is actually only a uint32, but since we plan to use MI_FLUSH_DW to
 * do the writes, and that must have qw aligned offsets, simply pretend it's 8b.
 */

static inline unsigned int
execlists_num_ports(const struct intel_engine_execlists * const execlists)
{
	return execlists->port_mask + 1;
}

static inline struct i915_request *
execlists_active(const struct intel_engine_execlists *execlists)
{
	struct i915_request * const *cur, * const *old, *active;

	cur = READ_ONCE(execlists->active);
	smp_rmb(); /* pairs with overwrite protection in process_csb() */
	do {
		old = cur;

		active = READ_ONCE(*cur);
		cur = READ_ONCE(execlists->active);

		smp_rmb(); /* and complete the seqlock retry */
	} while (unlikely(cur != old));

	return active;
}

static inline void
execlists_active_lock_bh(struct intel_engine_execlists *execlists)
{
	local_bh_disable(); /* prevent local softirq and lock recursion */
	tasklet_lock(&execlists->tasklet);
}

static inline void
execlists_active_unlock_bh(struct intel_engine_execlists *execlists)
{
	tasklet_unlock(&execlists->tasklet);
	local_bh_enable(); /* restore softirq, and kick ksoftirqd! */
}

struct i915_request *
execlists_unwind_incomplete_requests(struct intel_engine_execlists *execlists);

static inline u32
intel_read_status_page(const struct intel_engine_cs *engine, int reg)
{
	/* Ensure that the compiler doesn't optimize away the load. */
	return READ_ONCE(engine->status_page.addr[reg]);
}

static inline void
intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)
{
	/* Writing into the status page should be done sparingly. Since
	 * we do when we are uncertain of the device state, we take a bit
	 * of extra paranoia to try and ensure that the HWS takes the value
	 * we give and that it doesn't end up trapped inside the CPU!
	 */
	if (static_cpu_has(X86_FEATURE_CLFLUSH)) {
		mb();
		clflush(&engine->status_page.addr[reg]);
		engine->status_page.addr[reg] = value;
		clflush(&engine->status_page.addr[reg]);
		mb();
	} else {
		WRITE_ONCE(engine->status_page.addr[reg], value);
	}
}

/*
 * Reads a dword out of the status page, which is written to from the command
 * queue by automatic updates, MI_REPORT_HEAD, MI_STORE_DATA_INDEX, or
 * MI_STORE_DATA_IMM.
 *
 * The following dwords have a reserved meaning:
 * 0x00: ISR copy, updated when an ISR bit not set in the HWSTAM changes.
 * 0x04: ring 0 head pointer
 * 0x05: ring 1 head pointer (915-class)
 * 0x06: ring 2 head pointer (915-class)
 * 0x10-0x1b: Context status DWords (GM45)
 * 0x1f: Last written status offset. (GM45)
 * 0x20-0x2f: Reserved (Gen6+)
 *
 * The area from dword 0x30 to 0x3ff is available for driver usage.
 */
#define I915_GEM_HWS_PREEMPT		0x32
#define I915_GEM_HWS_PREEMPT_ADDR	(I915_GEM_HWS_PREEMPT * sizeof(u32))
#define I915_GEM_HWS_SEQNO		0x40
#define I915_GEM_HWS_SEQNO_ADDR		(I915_GEM_HWS_SEQNO * sizeof(u32))
#define I915_GEM_HWS_SCRATCH		0x80

#define I915_HWS_CSB_BUF0_INDEX		0x10
#define I915_HWS_CSB_WRITE_INDEX	0x1f
#define CNL_HWS_CSB_WRITE_INDEX		0x2f

void intel_engine_stop(struct intel_engine_cs *engine);
void intel_engine_cleanup(struct intel_engine_cs *engine);

int intel_engines_init_mmio(struct intel_gt *gt);
int intel_engines_init(struct intel_gt *gt);

void intel_engine_free_request_pool(struct intel_engine_cs *engine);

void intel_engines_release(struct intel_gt *gt);
void intel_engines_free(struct intel_gt *gt);

int intel_engine_init_common(struct intel_engine_cs *engine);
void intel_engine_cleanup_common(struct intel_engine_cs *engine);

int intel_engine_resume(struct intel_engine_cs *engine);

int intel_ring_submission_setup(struct intel_engine_cs *engine);

int intel_engine_stop_cs(struct intel_engine_cs *engine);
void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine);

void intel_engine_set_hwsp_writemask(struct intel_engine_cs *engine, u32 mask);

u64 intel_engine_get_active_head(const struct intel_engine_cs *engine);
u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine);

void intel_engine_get_instdone(const struct intel_engine_cs *engine,
			       struct intel_instdone *instdone);

void intel_engine_init_execlists(struct intel_engine_cs *engine);

static inline u32 *__gen8_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset)
{
	memset(batch, 0, 6 * sizeof(u32));

	batch[0] = GFX_OP_PIPE_CONTROL(6) | flags0;
	batch[1] = flags1;
	batch[2] = offset;

	return batch + 6;
}

static inline u32 *gen8_emit_pipe_control(u32 *batch, u32 flags, u32 offset)
{
	return __gen8_emit_pipe_control(batch, 0, flags, offset);
}

static inline u32 *gen12_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset)
{
	return __gen8_emit_pipe_control(batch, flags0, flags1, offset);
}

static inline u32 *
__gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1)
{
	/* We're using qword write, offset should be aligned to 8 bytes. */
	GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));

	/* w/a for post sync ops following a GPGPU operation we
	 * need a prior CS_STALL, which is emitted by the flush
	 * following the batch.
	 */
	*cs++ = GFX_OP_PIPE_CONTROL(6) | flags0;
	*cs++ = flags1 | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB;
	*cs++ = gtt_offset;
	*cs++ = 0;
	*cs++ = value;
	/* We're thrashing one dword of HWS. */
	*cs++ = 0;

	return cs;
}

static inline u32*
gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
{
	return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, 0, flags);
}

static inline u32*
gen12_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1)
{
	return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, flags0, flags1);
}

static inline u32 *
gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
{
	/* w/a: bit 5 needs to be zero for MI_FLUSH_DW address. */
	GEM_BUG_ON(gtt_offset & (1 << 5));
	/* Offset should be aligned to 8 bytes for both (QW/DW) write types */
	GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));

	*cs++ = (MI_FLUSH_DW + 1) | MI_FLUSH_DW_OP_STOREDW | flags;
	*cs++ = gtt_offset | MI_FLUSH_DW_USE_GTT;
	*cs++ = 0;
	*cs++ = value;

	return cs;
}

static inline void __intel_engine_reset(struct intel_engine_cs *engine,
					bool stalled)
{
	if (engine->reset.rewind)
		engine->reset.rewind(engine, stalled);
	engine->serial++; /* contexts lost */
}

bool intel_engines_are_idle(struct intel_gt *gt);
bool intel_engine_is_idle(struct intel_engine_cs *engine);
void intel_engine_flush_submission(struct intel_engine_cs *engine);

void intel_engines_reset_default_submission(struct intel_gt *gt);

bool intel_engine_can_store_dword(struct intel_engine_cs *engine);

__printf(3, 4)
void intel_engine_dump(struct intel_engine_cs *engine,
		       struct drm_printer *m,
		       const char *header, ...);

ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine,
				   ktime_t *now);

struct i915_request *
intel_engine_find_active_request(struct intel_engine_cs *engine);

u32 intel_engine_context_size(struct intel_gt *gt, u8 class);

void intel_engine_init_active(struct intel_engine_cs *engine,
			      unsigned int subclass);
#define ENGINE_PHYSICAL	0
#define ENGINE_MOCK	1
#define ENGINE_VIRTUAL	2

static inline bool
intel_engine_has_preempt_reset(const struct intel_engine_cs *engine)
{
	if (!IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT))
		return false;

	return intel_engine_has_preemption(engine);
}

static inline bool
intel_engine_has_heartbeat(const struct intel_engine_cs *engine)
{
	if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL))
		return false;

	return READ_ONCE(engine->props.heartbeat_interval_ms);
}

#endif /* _INTEL_RINGBUFFER_H_ */