summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/intel_uncore.h
blob: f419c311a0dea4d439c615d20e1e1308b7b77df6 (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
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
/*
 * Copyright © 2017 Intel Corporation
 *
 * 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 (including the next
 * paragraph) 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 AUTHORS OR COPYRIGHT HOLDERS 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.
 *
 */

#ifndef __INTEL_UNCORE_H__
#define __INTEL_UNCORE_H__

#include <linux/spinlock.h>
#include <linux/notifier.h>
#include <linux/hrtimer.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/types.h>

#include "i915_reg_defs.h"

struct drm_device;
struct drm_i915_private;
struct intel_runtime_pm;
struct intel_uncore;
struct intel_gt;

struct intel_uncore_mmio_debug {
	spinlock_t lock; /** lock is also taken in irq contexts. */
	int unclaimed_mmio_check;
	int saved_mmio_check;
	u32 suspend_count;
};

enum forcewake_domain_id {
	FW_DOMAIN_ID_RENDER = 0,
	FW_DOMAIN_ID_GT,        /* also includes blitter engine */
	FW_DOMAIN_ID_MEDIA,
	FW_DOMAIN_ID_MEDIA_VDBOX0,
	FW_DOMAIN_ID_MEDIA_VDBOX1,
	FW_DOMAIN_ID_MEDIA_VDBOX2,
	FW_DOMAIN_ID_MEDIA_VDBOX3,
	FW_DOMAIN_ID_MEDIA_VDBOX4,
	FW_DOMAIN_ID_MEDIA_VDBOX5,
	FW_DOMAIN_ID_MEDIA_VDBOX6,
	FW_DOMAIN_ID_MEDIA_VDBOX7,
	FW_DOMAIN_ID_MEDIA_VEBOX0,
	FW_DOMAIN_ID_MEDIA_VEBOX1,
	FW_DOMAIN_ID_MEDIA_VEBOX2,
	FW_DOMAIN_ID_MEDIA_VEBOX3,
	FW_DOMAIN_ID_GSC,

	FW_DOMAIN_ID_COUNT
};

enum forcewake_domains {
	FORCEWAKE_RENDER	= BIT(FW_DOMAIN_ID_RENDER),
	FORCEWAKE_GT		= BIT(FW_DOMAIN_ID_GT),
	FORCEWAKE_MEDIA		= BIT(FW_DOMAIN_ID_MEDIA),
	FORCEWAKE_MEDIA_VDBOX0	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX0),
	FORCEWAKE_MEDIA_VDBOX1	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX1),
	FORCEWAKE_MEDIA_VDBOX2	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX2),
	FORCEWAKE_MEDIA_VDBOX3	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX3),
	FORCEWAKE_MEDIA_VDBOX4	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX4),
	FORCEWAKE_MEDIA_VDBOX5	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX5),
	FORCEWAKE_MEDIA_VDBOX6	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX6),
	FORCEWAKE_MEDIA_VDBOX7	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX7),
	FORCEWAKE_MEDIA_VEBOX0	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX0),
	FORCEWAKE_MEDIA_VEBOX1	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX1),
	FORCEWAKE_MEDIA_VEBOX2	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX2),
	FORCEWAKE_MEDIA_VEBOX3	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX3),
	FORCEWAKE_GSC		= BIT(FW_DOMAIN_ID_GSC),

	FORCEWAKE_ALL = BIT(FW_DOMAIN_ID_COUNT) - 1,
};

struct intel_uncore_fw_get {
	void (*force_wake_get)(struct intel_uncore *uncore,
			       enum forcewake_domains domains);
};

struct intel_uncore_funcs {
	enum forcewake_domains (*read_fw_domains)(struct intel_uncore *uncore,
						  i915_reg_t r);
	enum forcewake_domains (*write_fw_domains)(struct intel_uncore *uncore,
						   i915_reg_t r);

	u8 (*mmio_readb)(struct intel_uncore *uncore,
			 i915_reg_t r, bool trace);
	u16 (*mmio_readw)(struct intel_uncore *uncore,
			  i915_reg_t r, bool trace);
	u32 (*mmio_readl)(struct intel_uncore *uncore,
			  i915_reg_t r, bool trace);
	u64 (*mmio_readq)(struct intel_uncore *uncore,
			  i915_reg_t r, bool trace);

	void (*mmio_writeb)(struct intel_uncore *uncore,
			    i915_reg_t r, u8 val, bool trace);
	void (*mmio_writew)(struct intel_uncore *uncore,
			    i915_reg_t r, u16 val, bool trace);
	void (*mmio_writel)(struct intel_uncore *uncore,
			    i915_reg_t r, u32 val, bool trace);
};

struct intel_forcewake_range {
	u32 start;
	u32 end;

	enum forcewake_domains domains;
};

/* Other register ranges (e.g., shadow tables, MCR tables, etc.) */
struct i915_range {
	u32 start;
	u32 end;
};

struct intel_uncore {
	void __iomem *regs;

	struct drm_i915_private *i915;
	struct intel_gt *gt;
	struct intel_runtime_pm *rpm;

	spinlock_t lock; /** lock is also taken in irq contexts. */

	/*
	 * Do we need to apply an additional offset to reach the beginning
	 * of the basic non-engine GT registers (referred to as "GSI" on
	 * newer platforms, or "GT block" on older platforms)?  If so, we'll
	 * track that here and apply it transparently to registers in the
	 * appropriate range to maintain compatibility with our existing
	 * register definitions and GT code.
	 */
	u32 gsi_offset;

	unsigned int flags;
#define UNCORE_HAS_FORCEWAKE		BIT(0)
#define UNCORE_HAS_FPGA_DBG_UNCLAIMED	BIT(1)
#define UNCORE_HAS_DBG_UNCLAIMED	BIT(2)
#define UNCORE_HAS_FIFO			BIT(3)
#define UNCORE_NEEDS_FLR_ON_FINI	BIT(4)

	const struct intel_forcewake_range *fw_domains_table;
	unsigned int fw_domains_table_entries;

	/*
	 * Shadowed registers are special cases where we can safely write
	 * to the register *without* grabbing forcewake.
	 */
	const struct i915_range *shadowed_reg_table;
	unsigned int shadowed_reg_table_entries;

	struct notifier_block pmic_bus_access_nb;
	const struct intel_uncore_fw_get *fw_get_funcs;
	struct intel_uncore_funcs funcs;

	unsigned int fifo_count;

	enum forcewake_domains fw_domains;
	enum forcewake_domains fw_domains_active;
	enum forcewake_domains fw_domains_timer;
	enum forcewake_domains fw_domains_saved; /* user domains saved for S3 */

	struct intel_uncore_forcewake_domain {
		struct intel_uncore *uncore;
		enum forcewake_domain_id id;
		enum forcewake_domains mask;
		unsigned int wake_count;
		bool active;
		struct hrtimer timer;
		u32 __iomem *reg_set;
		u32 __iomem *reg_ack;
	} *fw_domain[FW_DOMAIN_ID_COUNT];

	unsigned int user_forcewake_count;

	struct intel_uncore_mmio_debug *debug;
};

/* Iterate over initialised fw domains */
#define for_each_fw_domain_masked(domain__, mask__, uncore__, tmp__) \
	for (tmp__ = (mask__); tmp__ ;) \
		for_each_if(domain__ = (uncore__)->fw_domain[__mask_next_bit(tmp__)])

#define for_each_fw_domain(domain__, uncore__, tmp__) \
	for_each_fw_domain_masked(domain__, (uncore__)->fw_domains, uncore__, tmp__)

static inline bool
intel_uncore_has_forcewake(const struct intel_uncore *uncore)
{
	return uncore->flags & UNCORE_HAS_FORCEWAKE;
}

static inline bool
intel_uncore_has_fpga_dbg_unclaimed(const struct intel_uncore *uncore)
{
	return uncore->flags & UNCORE_HAS_FPGA_DBG_UNCLAIMED;
}

static inline bool
intel_uncore_has_dbg_unclaimed(const struct intel_uncore *uncore)
{
	return uncore->flags & UNCORE_HAS_DBG_UNCLAIMED;
}

static inline bool
intel_uncore_has_fifo(const struct intel_uncore *uncore)
{
	return uncore->flags & UNCORE_HAS_FIFO;
}

static inline bool
intel_uncore_needs_flr_on_fini(const struct intel_uncore *uncore)
{
	return uncore->flags & UNCORE_NEEDS_FLR_ON_FINI;
}

static inline bool
intel_uncore_set_flr_on_fini(struct intel_uncore *uncore)
{
	return uncore->flags |= UNCORE_NEEDS_FLR_ON_FINI;
}

void intel_uncore_mmio_debug_init_early(struct drm_i915_private *i915);
void intel_uncore_init_early(struct intel_uncore *uncore,
			     struct intel_gt *gt);
int intel_uncore_setup_mmio(struct intel_uncore *uncore, phys_addr_t phys_addr);
int intel_uncore_init_mmio(struct intel_uncore *uncore);
void intel_uncore_prune_engine_fw_domains(struct intel_uncore *uncore,
					  struct intel_gt *gt);
bool intel_uncore_unclaimed_mmio(struct intel_uncore *uncore);
bool intel_uncore_arm_unclaimed_mmio_detection(struct intel_uncore *uncore);
void intel_uncore_cleanup_mmio(struct intel_uncore *uncore);
void intel_uncore_fini_mmio(struct drm_device *dev, void *data);
void intel_uncore_suspend(struct intel_uncore *uncore);
void intel_uncore_resume_early(struct intel_uncore *uncore);
void intel_uncore_runtime_resume(struct intel_uncore *uncore);

void assert_forcewakes_inactive(struct intel_uncore *uncore);
void assert_forcewakes_active(struct intel_uncore *uncore,
			      enum forcewake_domains fw_domains);
const char *intel_uncore_forcewake_domain_to_str(const enum forcewake_domain_id id);

enum forcewake_domains
intel_uncore_forcewake_for_reg(struct intel_uncore *uncore,
			       i915_reg_t reg, unsigned int op);
#define FW_REG_READ  (1)
#define FW_REG_WRITE (2)

void intel_uncore_forcewake_get(struct intel_uncore *uncore,
				enum forcewake_domains domains);
void intel_uncore_forcewake_put(struct intel_uncore *uncore,
				enum forcewake_domains domains);
void intel_uncore_forcewake_put_delayed(struct intel_uncore *uncore,
					enum forcewake_domains domains);
void intel_uncore_forcewake_flush(struct intel_uncore *uncore,
				  enum forcewake_domains fw_domains);

/*
 * Like above but the caller must manage the uncore.lock itself.
 * Must be used with intel_uncore_read_fw() and friends.
 */
void intel_uncore_forcewake_get__locked(struct intel_uncore *uncore,
					enum forcewake_domains domains);
void intel_uncore_forcewake_put__locked(struct intel_uncore *uncore,
					enum forcewake_domains domains);

void intel_uncore_forcewake_user_get(struct intel_uncore *uncore);
void intel_uncore_forcewake_user_put(struct intel_uncore *uncore);

int __intel_wait_for_register(struct intel_uncore *uncore,
			      i915_reg_t reg,
			      u32 mask,
			      u32 value,
			      unsigned int fast_timeout_us,
			      unsigned int slow_timeout_ms,
			      u32 *out_value);
static inline int
intel_wait_for_register(struct intel_uncore *uncore,
			i915_reg_t reg,
			u32 mask,
			u32 value,
			unsigned int timeout_ms)
{
	return __intel_wait_for_register(uncore, reg, mask, value, 2,
					 timeout_ms, NULL);
}

int __intel_wait_for_register_fw(struct intel_uncore *uncore,
				 i915_reg_t reg,
				 u32 mask,
				 u32 value,
				 unsigned int fast_timeout_us,
				 unsigned int slow_timeout_ms,
				 u32 *out_value);
static inline int
intel_wait_for_register_fw(struct intel_uncore *uncore,
			   i915_reg_t reg,
			   u32 mask,
			   u32 value,
			       unsigned int timeout_ms)
{
	return __intel_wait_for_register_fw(uncore, reg, mask, value,
					    2, timeout_ms, NULL);
}

#define IS_GSI_REG(reg) ((reg) < 0x40000)

/* register access functions */
#define __raw_read(x__, s__) \
static inline u##x__ __raw_uncore_read##x__(const struct intel_uncore *uncore, \
					    i915_reg_t reg) \
{ \
	u32 offset = i915_mmio_reg_offset(reg); \
	if (IS_GSI_REG(offset)) \
		offset += uncore->gsi_offset; \
	return read##s__(uncore->regs + offset); \
}

#define __raw_write(x__, s__) \
static inline void __raw_uncore_write##x__(const struct intel_uncore *uncore, \
					   i915_reg_t reg, u##x__ val) \
{ \
	u32 offset = i915_mmio_reg_offset(reg); \
	if (IS_GSI_REG(offset)) \
		offset += uncore->gsi_offset; \
	write##s__(val, uncore->regs + offset); \
}
__raw_read(8, b)
__raw_read(16, w)
__raw_read(32, l)
__raw_read(64, q)

__raw_write(8, b)
__raw_write(16, w)
__raw_write(32, l)
__raw_write(64, q)

#undef __raw_read
#undef __raw_write

#define __uncore_read(name__, x__, s__, trace__) \
static inline u##x__ intel_uncore_##name__(struct intel_uncore *uncore, \
					   i915_reg_t reg) \
{ \
	return uncore->funcs.mmio_read##s__(uncore, reg, (trace__)); \
}

#define __uncore_write(name__, x__, s__, trace__) \
static inline void intel_uncore_##name__(struct intel_uncore *uncore, \
					 i915_reg_t reg, u##x__ val) \
{ \
	uncore->funcs.mmio_write##s__(uncore, reg, val, (trace__)); \
}

__uncore_read(read8, 8, b, true)
__uncore_read(read16, 16, w, true)
__uncore_read(read, 32, l, true)
__uncore_read(read16_notrace, 16, w, false)
__uncore_read(read_notrace, 32, l, false)

__uncore_write(write8, 8, b, true)
__uncore_write(write16, 16, w, true)
__uncore_write(write, 32, l, true)
__uncore_write(write_notrace, 32, l, false)

/* Be very careful with read/write 64-bit values. On 32-bit machines, they
 * will be implemented using 2 32-bit writes in an arbitrary order with
 * an arbitrary delay between them. This can cause the hardware to
 * act upon the intermediate value, possibly leading to corruption and
 * machine death. For this reason we do not support intel_uncore_write64,
 * or uncore->funcs.mmio_writeq.
 *
 * When reading a 64-bit value as two 32-bit values, the delay may cause
 * the two reads to mismatch, e.g. a timestamp overflowing. Also note that
 * occasionally a 64-bit register does not actually support a full readq
 * and must be read using two 32-bit reads.
 *
 * You have been warned.
 */
__uncore_read(read64, 64, q, true)

#define intel_uncore_posting_read(...) ((void)intel_uncore_read_notrace(__VA_ARGS__))
#define intel_uncore_posting_read16(...) ((void)intel_uncore_read16_notrace(__VA_ARGS__))

#undef __uncore_read
#undef __uncore_write

/* These are untraced mmio-accessors that are only valid to be used inside
 * critical sections, such as inside IRQ handlers, where forcewake is explicitly
 * controlled.
 *
 * Think twice, and think again, before using these.
 *
 * As an example, these accessors can possibly be used between:
 *
 * spin_lock_irq(&uncore->lock);
 * intel_uncore_forcewake_get__locked();
 *
 * and
 *
 * intel_uncore_forcewake_put__locked();
 * spin_unlock_irq(&uncore->lock);
 *
 *
 * Note: some registers may not need forcewake held, so
 * intel_uncore_forcewake_{get,put} can be omitted, see
 * intel_uncore_forcewake_for_reg().
 *
 * Certain architectures will die if the same cacheline is concurrently accessed
 * by different clients (e.g. on Ivybridge). Access to registers should
 * therefore generally be serialised, by either the dev_priv->uncore.lock or
 * a more localised lock guarding all access to that bank of registers.
 */
#define intel_uncore_read_fw(...) __raw_uncore_read32(__VA_ARGS__)
#define intel_uncore_write_fw(...) __raw_uncore_write32(__VA_ARGS__)
#define intel_uncore_write64_fw(...) __raw_uncore_write64(__VA_ARGS__)
#define intel_uncore_posting_read_fw(...) ((void)intel_uncore_read_fw(__VA_ARGS__))

static inline u32 intel_uncore_rmw(struct intel_uncore *uncore,
				   i915_reg_t reg, u32 clear, u32 set)
{
	u32 old, val;

	old = intel_uncore_read(uncore, reg);
	val = (old & ~clear) | set;
	intel_uncore_write(uncore, reg, val);
	return old;
}

static inline void intel_uncore_rmw_fw(struct intel_uncore *uncore,
				       i915_reg_t reg, u32 clear, u32 set)
{
	u32 old, val;

	old = intel_uncore_read_fw(uncore, reg);
	val = (old & ~clear) | set;
	if (val != old)
		intel_uncore_write_fw(uncore, reg, val);
}

static inline u64
intel_uncore_read64_2x32(struct intel_uncore *uncore,
			 i915_reg_t lower_reg, i915_reg_t upper_reg)
{
	u32 upper, lower, old_upper, loop = 0;
	enum forcewake_domains fw_domains;
	unsigned long flags;

	fw_domains = intel_uncore_forcewake_for_reg(uncore, lower_reg,
						    FW_REG_READ);

	fw_domains |= intel_uncore_forcewake_for_reg(uncore, upper_reg,
						    FW_REG_READ);

	spin_lock_irqsave(&uncore->lock, flags);
	intel_uncore_forcewake_get__locked(uncore, fw_domains);

	upper = intel_uncore_read_fw(uncore, upper_reg);
	do {
		old_upper = upper;
		lower = intel_uncore_read_fw(uncore, lower_reg);
		upper = intel_uncore_read_fw(uncore, upper_reg);
	} while (upper != old_upper && loop++ < 2);

	intel_uncore_forcewake_put__locked(uncore, fw_domains);
	spin_unlock_irqrestore(&uncore->lock, flags);

	return (u64)upper << 32 | lower;
}

static inline int intel_uncore_write_and_verify(struct intel_uncore *uncore,
						i915_reg_t reg, u32 val,
						u32 mask, u32 expected_val)
{
	u32 reg_val;

	intel_uncore_write(uncore, reg, val);
	reg_val = intel_uncore_read(uncore, reg);

	return (reg_val & mask) != expected_val ? -EINVAL : 0;
}

static inline void __iomem *intel_uncore_regs(struct intel_uncore *uncore)
{
	return uncore->regs;
}

/*
 * The raw_reg_{read,write} macros are intended as a micro-optimization for
 * interrupt handlers so that the pointer indirection on uncore->regs can
 * be computed once (and presumably cached in a register) instead of generating
 * extra load instructions for each MMIO access.
 *
 * Given that these macros are only intended for non-GSI interrupt registers
 * (and the goal is to avoid extra instructions generated by the compiler),
 * these macros do not account for uncore->gsi_offset.  Any caller that needs
 * to use these macros on a GSI register is responsible for adding the
 * appropriate GSI offset to the 'base' parameter.
 */
#define raw_reg_read(base, reg) \
	readl(base + i915_mmio_reg_offset(reg))
#define raw_reg_write(base, reg, value) \
	writel(value, base + i915_mmio_reg_offset(reg))

#endif /* !__INTEL_UNCORE_H__ */