summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/radeon/r600_cs.c
blob: 33b89cd8743ec9ea552fd12a5188d23d33e629b6 (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
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
/*
 * Copyright 2008 Advanced Micro Devices, Inc.
 * Copyright 2008 Red Hat Inc.
 * Copyright 2009 Jerome Glisse.
 *
 * 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: Dave Airlie
 *          Alex Deucher
 *          Jerome Glisse
 */
#include "drmP.h"
#include "radeon.h"
#include "r600d.h"
#include "avivod.h"

static int r600_cs_packet_next_reloc_mm(struct radeon_cs_parser *p,
					struct radeon_cs_reloc **cs_reloc);
static int r600_cs_packet_next_reloc_nomm(struct radeon_cs_parser *p,
					struct radeon_cs_reloc **cs_reloc);
typedef int (*next_reloc_t)(struct radeon_cs_parser*, struct radeon_cs_reloc**);
static next_reloc_t r600_cs_packet_next_reloc = &r600_cs_packet_next_reloc_mm;

/**
 * r600_cs_packet_parse() - parse cp packet and point ib index to next packet
 * @parser:	parser structure holding parsing context.
 * @pkt:	where to store packet informations
 *
 * Assume that chunk_ib_index is properly set. Will return -EINVAL
 * if packet is bigger than remaining ib size. or if packets is unknown.
 **/
int r600_cs_packet_parse(struct radeon_cs_parser *p,
			struct radeon_cs_packet *pkt,
			unsigned idx)
{
	struct radeon_cs_chunk *ib_chunk = &p->chunks[p->chunk_ib_idx];
	uint32_t header;

	if (idx >= ib_chunk->length_dw) {
		DRM_ERROR("Can not parse packet at %d after CS end %d !\n",
			  idx, ib_chunk->length_dw);
		return -EINVAL;
	}
	header = ib_chunk->kdata[idx];
	pkt->idx = idx;
	pkt->type = CP_PACKET_GET_TYPE(header);
	pkt->count = CP_PACKET_GET_COUNT(header);
	pkt->one_reg_wr = 0;
	switch (pkt->type) {
	case PACKET_TYPE0:
		pkt->reg = CP_PACKET0_GET_REG(header);
		break;
	case PACKET_TYPE3:
		pkt->opcode = CP_PACKET3_GET_OPCODE(header);
		break;
	case PACKET_TYPE2:
		pkt->count = -1;
		break;
	default:
		DRM_ERROR("Unknown packet type %d at %d !\n", pkt->type, idx);
		return -EINVAL;
	}
	if ((pkt->count + 1 + pkt->idx) >= ib_chunk->length_dw) {
		DRM_ERROR("Packet (%d:%d:%d) end after CS buffer (%d) !\n",
			  pkt->idx, pkt->type, pkt->count, ib_chunk->length_dw);
		return -EINVAL;
	}
	return 0;
}

/**
 * r600_cs_packet_next_reloc_mm() - parse next packet which should be reloc packet3
 * @parser:		parser structure holding parsing context.
 * @data:		pointer to relocation data
 * @offset_start:	starting offset
 * @offset_mask:	offset mask (to align start offset on)
 * @reloc:		reloc informations
 *
 * Check next packet is relocation packet3, do bo validation and compute
 * GPU offset using the provided start.
 **/
static int r600_cs_packet_next_reloc_mm(struct radeon_cs_parser *p,
					struct radeon_cs_reloc **cs_reloc)
{
	struct radeon_cs_chunk *ib_chunk;
	struct radeon_cs_chunk *relocs_chunk;
	struct radeon_cs_packet p3reloc;
	unsigned idx;
	int r;

	if (p->chunk_relocs_idx == -1) {
		DRM_ERROR("No relocation chunk !\n");
		return -EINVAL;
	}
	*cs_reloc = NULL;
	ib_chunk = &p->chunks[p->chunk_ib_idx];
	relocs_chunk = &p->chunks[p->chunk_relocs_idx];
	r = r600_cs_packet_parse(p, &p3reloc, p->idx);
	if (r) {
		return r;
	}
	p->idx += p3reloc.count + 2;
	if (p3reloc.type != PACKET_TYPE3 || p3reloc.opcode != PACKET3_NOP) {
		DRM_ERROR("No packet3 for relocation for packet at %d.\n",
			  p3reloc.idx);
		return -EINVAL;
	}
	idx = ib_chunk->kdata[p3reloc.idx + 1];
	if (idx >= relocs_chunk->length_dw) {
		DRM_ERROR("Relocs at %d after relocations chunk end %d !\n",
			  idx, relocs_chunk->length_dw);
		return -EINVAL;
	}
	/* FIXME: we assume reloc size is 4 dwords */
	*cs_reloc = p->relocs_ptr[(idx / 4)];
	return 0;
}

/**
 * r600_cs_packet_next_reloc_nomm() - parse next packet which should be reloc packet3
 * @parser:		parser structure holding parsing context.
 * @data:		pointer to relocation data
 * @offset_start:	starting offset
 * @offset_mask:	offset mask (to align start offset on)
 * @reloc:		reloc informations
 *
 * Check next packet is relocation packet3, do bo validation and compute
 * GPU offset using the provided start.
 **/
static int r600_cs_packet_next_reloc_nomm(struct radeon_cs_parser *p,
					struct radeon_cs_reloc **cs_reloc)
{
	struct radeon_cs_chunk *ib_chunk;
	struct radeon_cs_chunk *relocs_chunk;
	struct radeon_cs_packet p3reloc;
	unsigned idx;
	int r;

	if (p->chunk_relocs_idx == -1) {
		DRM_ERROR("No relocation chunk !\n");
		return -EINVAL;
	}
	*cs_reloc = NULL;
	ib_chunk = &p->chunks[p->chunk_ib_idx];
	relocs_chunk = &p->chunks[p->chunk_relocs_idx];
	r = r600_cs_packet_parse(p, &p3reloc, p->idx);
	if (r) {
		return r;
	}
	p->idx += p3reloc.count + 2;
	if (p3reloc.type != PACKET_TYPE3 || p3reloc.opcode != PACKET3_NOP) {
		DRM_ERROR("No packet3 for relocation for packet at %d.\n",
			  p3reloc.idx);
		return -EINVAL;
	}
	idx = ib_chunk->kdata[p3reloc.idx + 1];
	if (idx >= relocs_chunk->length_dw) {
		DRM_ERROR("Relocs at %d after relocations chunk end %d !\n",
			  idx, relocs_chunk->length_dw);
		return -EINVAL;
	}
	*cs_reloc = &p->relocs[0];
	(*cs_reloc)->lobj.gpu_offset = (u64)relocs_chunk->kdata[idx + 3] << 32;
	(*cs_reloc)->lobj.gpu_offset |= relocs_chunk->kdata[idx + 0];
	return 0;
}

static int r600_packet0_check(struct radeon_cs_parser *p,
				struct radeon_cs_packet *pkt,
				unsigned idx, unsigned reg)
{
	switch (reg) {
	case AVIVO_D1MODE_VLINE_START_END:
	case AVIVO_D2MODE_VLINE_START_END:
		break;
	default:
		printk(KERN_ERR "Forbidden register 0x%04X in cs at %d\n",
		       reg, idx);
		return -EINVAL;
	}
	return 0;
}

static int r600_cs_parse_packet0(struct radeon_cs_parser *p,
				struct radeon_cs_packet *pkt)
{
	unsigned reg, i;
	unsigned idx;
	int r;

	idx = pkt->idx + 1;
	reg = pkt->reg;
	for (i = 0; i <= pkt->count; i++, idx++, reg += 4) {
		r = r600_packet0_check(p, pkt, idx, reg);
		if (r) {
			return r;
		}
	}
	return 0;
}

static int r600_packet3_check(struct radeon_cs_parser *p,
				struct radeon_cs_packet *pkt)
{
	struct radeon_cs_chunk *ib_chunk;
	struct radeon_cs_reloc *reloc;
	volatile u32 *ib;
	unsigned idx;
	unsigned i;
	unsigned start_reg, end_reg, reg;
	int r;

	ib = p->ib->ptr;
	ib_chunk = &p->chunks[p->chunk_ib_idx];
	idx = pkt->idx + 1;
	switch (pkt->opcode) {
	case PACKET3_START_3D_CMDBUF:
		if (p->family >= CHIP_RV770 || pkt->count) {
			DRM_ERROR("bad START_3D\n");
			return -EINVAL;
		}
		break;
	case PACKET3_CONTEXT_CONTROL:
		if (pkt->count != 1) {
			DRM_ERROR("bad CONTEXT_CONTROL\n");
			return -EINVAL;
		}
		break;
	case PACKET3_INDEX_TYPE:
	case PACKET3_NUM_INSTANCES:
		if (pkt->count) {
			DRM_ERROR("bad INDEX_TYPE/NUM_INSTANCES\n");
			return -EINVAL;
		}
		break;
	case PACKET3_DRAW_INDEX:
		if (pkt->count != 3) {
			DRM_ERROR("bad DRAW_INDEX\n");
			return -EINVAL;
		}
		r = r600_cs_packet_next_reloc(p, &reloc);
		if (r) {
			DRM_ERROR("bad DRAW_INDEX\n");
			return -EINVAL;
		}
		ib[idx+0] += (u32)(reloc->lobj.gpu_offset & 0xffffffff);
		ib[idx+1] = upper_32_bits(reloc->lobj.gpu_offset) & 0xff;
		break;
	case PACKET3_DRAW_INDEX_AUTO:
		if (pkt->count != 1) {
			DRM_ERROR("bad DRAW_INDEX_AUTO\n");
			return -EINVAL;
		}
		break;
	case PACKET3_DRAW_INDEX_IMMD_BE:
	case PACKET3_DRAW_INDEX_IMMD:
		if (pkt->count < 2) {
			DRM_ERROR("bad DRAW_INDEX_IMMD\n");
			return -EINVAL;
		}
		break;
	case PACKET3_WAIT_REG_MEM:
		if (pkt->count != 5) {
			DRM_ERROR("bad WAIT_REG_MEM\n");
			return -EINVAL;
		}
		/* bit 4 is reg (0) or mem (1) */
		if (ib_chunk->kdata[idx+0] & 0x10) {
			r = r600_cs_packet_next_reloc(p, &reloc);
			if (r) {
				DRM_ERROR("bad WAIT_REG_MEM\n");
				return -EINVAL;
			}
			ib[idx+1] += (u32)(reloc->lobj.gpu_offset & 0xffffffff);
			ib[idx+2] = upper_32_bits(reloc->lobj.gpu_offset) & 0xff;
		}
		break;
	case PACKET3_SURFACE_SYNC:
		if (pkt->count != 3) {
			DRM_ERROR("bad SURFACE_SYNC\n");
			return -EINVAL;
		}
		/* 0xffffffff/0x0 is flush all cache flag */
		if (ib_chunk->kdata[idx+1] != 0xffffffff ||
		    ib_chunk->kdata[idx+2] != 0) {
			r = r600_cs_packet_next_reloc(p, &reloc);
			if (r) {
				DRM_ERROR("bad SURFACE_SYNC\n");
				return -EINVAL;
			}
			ib[idx+2] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
		}
		break;
	case PACKET3_EVENT_WRITE:
		if (pkt->count != 2 && pkt->count != 0) {
			DRM_ERROR("bad EVENT_WRITE\n");
			return -EINVAL;
		}
		if (pkt->count) {
			r = r600_cs_packet_next_reloc(p, &reloc);
			if (r) {
				DRM_ERROR("bad EVENT_WRITE\n");
				return -EINVAL;
			}
			ib[idx+1] += (u32)(reloc->lobj.gpu_offset & 0xffffffff);
			ib[idx+2] |= upper_32_bits(reloc->lobj.gpu_offset) & 0xff;
		}
		break;
	case PACKET3_EVENT_WRITE_EOP:
		if (pkt->count != 4) {
			DRM_ERROR("bad EVENT_WRITE_EOP\n");
			return -EINVAL;
		}
		r = r600_cs_packet_next_reloc(p, &reloc);
		if (r) {
			DRM_ERROR("bad EVENT_WRITE\n");
			return -EINVAL;
		}
		ib[idx+1] += (u32)(reloc->lobj.gpu_offset & 0xffffffff);
		ib[idx+2] |= upper_32_bits(reloc->lobj.gpu_offset) & 0xff;
		break;
	case PACKET3_SET_CONFIG_REG:
		start_reg = (ib[idx+0] << 2) + PACKET3_SET_CONFIG_REG_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_CONFIG_REG_OFFSET) ||
		    (start_reg >= PACKET3_SET_CONFIG_REG_END) ||
		    (end_reg >= PACKET3_SET_CONFIG_REG_END)) {
			DRM_ERROR("bad PACKET3_SET_CONFIG_REG\n");
			return -EINVAL;
		}
		for (i = 0; i < pkt->count; i++) {
			reg = start_reg + (4 * i);
			switch (reg) {
			case CP_COHER_BASE:
				/* use PACKET3_SURFACE_SYNC */
				return -EINVAL;
			default:
				break;
			}
		}
		break;
	case PACKET3_SET_CONTEXT_REG:
		start_reg = (ib[idx+0] << 2) + PACKET3_SET_CONTEXT_REG_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_CONTEXT_REG_OFFSET) ||
		    (start_reg >= PACKET3_SET_CONTEXT_REG_END) ||
		    (end_reg >= PACKET3_SET_CONTEXT_REG_END)) {
			DRM_ERROR("bad PACKET3_SET_CONTEXT_REG\n");
			return -EINVAL;
		}
		for (i = 0; i < pkt->count; i++) {
			reg = start_reg + (4 * i);
			switch (reg) {
			case DB_DEPTH_BASE:
			case CB_COLOR0_BASE:
			case CB_COLOR1_BASE:
			case CB_COLOR2_BASE:
			case CB_COLOR3_BASE:
			case CB_COLOR4_BASE:
			case CB_COLOR5_BASE:
			case CB_COLOR6_BASE:
			case CB_COLOR7_BASE:
			case SQ_PGM_START_FS:
			case SQ_PGM_START_ES:
			case SQ_PGM_START_VS:
			case SQ_PGM_START_GS:
			case SQ_PGM_START_PS:
				r = r600_cs_packet_next_reloc(p, &reloc);
				if (r) {
					DRM_ERROR("bad SET_CONTEXT_REG "
							"0x%04X\n", reg);
					return -EINVAL;
				}
				ib[idx+1+i] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
				break;
			case VGT_DMA_BASE:
			case VGT_DMA_BASE_HI:
				/* These should be handled by DRAW_INDEX packet 3 */
			case VGT_STRMOUT_BASE_OFFSET_0:
			case VGT_STRMOUT_BASE_OFFSET_1:
			case VGT_STRMOUT_BASE_OFFSET_2:
			case VGT_STRMOUT_BASE_OFFSET_3:
			case VGT_STRMOUT_BASE_OFFSET_HI_0:
			case VGT_STRMOUT_BASE_OFFSET_HI_1:
			case VGT_STRMOUT_BASE_OFFSET_HI_2:
			case VGT_STRMOUT_BASE_OFFSET_HI_3:
			case VGT_STRMOUT_BUFFER_BASE_0:
			case VGT_STRMOUT_BUFFER_BASE_1:
			case VGT_STRMOUT_BUFFER_BASE_2:
			case VGT_STRMOUT_BUFFER_BASE_3:
			case VGT_STRMOUT_BUFFER_OFFSET_0:
			case VGT_STRMOUT_BUFFER_OFFSET_1:
			case VGT_STRMOUT_BUFFER_OFFSET_2:
			case VGT_STRMOUT_BUFFER_OFFSET_3:
				/* These should be handled by STRMOUT_BUFFER packet 3 */
				DRM_ERROR("bad context reg: 0x%08x\n", reg);
				return -EINVAL;
			default:
				break;
			}
		}
		break;
	case PACKET3_SET_RESOURCE:
		if (pkt->count % 7) {
			DRM_ERROR("bad SET_RESOURCE\n");
			return -EINVAL;
		}
		start_reg = (ib[idx+0] << 2) + PACKET3_SET_RESOURCE_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_RESOURCE_OFFSET) ||
		    (start_reg >= PACKET3_SET_RESOURCE_END) ||
		    (end_reg >= PACKET3_SET_RESOURCE_END)) {
			DRM_ERROR("bad SET_RESOURCE\n");
			return -EINVAL;
		}
		for (i = 0; i < (pkt->count / 7); i++) {
			switch (G__SQ_VTX_CONSTANT_TYPE(ib[idx+(i*7)+6+1])) {
			case SQ_TEX_VTX_VALID_TEXTURE:
				/* tex base */
				r = r600_cs_packet_next_reloc(p, &reloc);
				if (r) {
					DRM_ERROR("bad SET_RESOURCE\n");
					return -EINVAL;
				}
				ib[idx+1+(i*7)+2] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
				/* tex mip base */
				r = r600_cs_packet_next_reloc(p, &reloc);
				if (r) {
					DRM_ERROR("bad SET_RESOURCE\n");
					return -EINVAL;
				}
				ib[idx+1+(i*7)+3] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
				break;
			case SQ_TEX_VTX_VALID_BUFFER:
				/* vtx base */
				r = r600_cs_packet_next_reloc(p, &reloc);
				if (r) {
					DRM_ERROR("bad SET_RESOURCE\n");
					return -EINVAL;
				}
				ib[idx+1+(i*7)+0] += (u32)((reloc->lobj.gpu_offset) & 0xffffffff);
				ib[idx+1+(i*7)+2] |= upper_32_bits(reloc->lobj.gpu_offset) & 0xff;
				break;
			case SQ_TEX_VTX_INVALID_TEXTURE:
			case SQ_TEX_VTX_INVALID_BUFFER:
			default:
				DRM_ERROR("bad SET_RESOURCE\n");
				return -EINVAL;
			}
		}
		break;
	case PACKET3_SET_ALU_CONST:
		start_reg = (ib[idx+0] << 2) + PACKET3_SET_ALU_CONST_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_ALU_CONST_OFFSET) ||
		    (start_reg >= PACKET3_SET_ALU_CONST_END) ||
		    (end_reg >= PACKET3_SET_ALU_CONST_END)) {
			DRM_ERROR("bad SET_ALU_CONST\n");
			return -EINVAL;
		}
		break;
	case PACKET3_SET_BOOL_CONST:
		start_reg = (ib[idx+0] << 2) + PACKET3_SET_BOOL_CONST_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_BOOL_CONST_OFFSET) ||
		    (start_reg >= PACKET3_SET_BOOL_CONST_END) ||
		    (end_reg >= PACKET3_SET_BOOL_CONST_END)) {
			DRM_ERROR("bad SET_BOOL_CONST\n");
			return -EINVAL;
		}
		break;
	case PACKET3_SET_LOOP_CONST:
		start_reg = (ib[idx+0] << 2) + PACKET3_SET_LOOP_CONST_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_LOOP_CONST_OFFSET) ||
		    (start_reg >= PACKET3_SET_LOOP_CONST_END) ||
		    (end_reg >= PACKET3_SET_LOOP_CONST_END)) {
			DRM_ERROR("bad SET_LOOP_CONST\n");
			return -EINVAL;
		}
		break;
	case PACKET3_SET_CTL_CONST:
		start_reg = (ib[idx+0] << 2) + PACKET3_SET_CTL_CONST_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_CTL_CONST_OFFSET) ||
		    (start_reg >= PACKET3_SET_CTL_CONST_END) ||
		    (end_reg >= PACKET3_SET_CTL_CONST_END)) {
			DRM_ERROR("bad SET_CTL_CONST\n");
			return -EINVAL;
		}
		break;
	case PACKET3_SET_SAMPLER:
		if (pkt->count % 3) {
			DRM_ERROR("bad SET_SAMPLER\n");
			return -EINVAL;
		}
		start_reg = (ib[idx+0] << 2) + PACKET3_SET_SAMPLER_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_SAMPLER_OFFSET) ||
		    (start_reg >= PACKET3_SET_SAMPLER_END) ||
		    (end_reg >= PACKET3_SET_SAMPLER_END)) {
			DRM_ERROR("bad SET_SAMPLER\n");
			return -EINVAL;
		}
		break;
	case PACKET3_SURFACE_BASE_UPDATE:
		if (p->family >= CHIP_RV770 || p->family == CHIP_R600) {
			DRM_ERROR("bad SURFACE_BASE_UPDATE\n");
			return -EINVAL;
		}
		if (pkt->count) {
			DRM_ERROR("bad SURFACE_BASE_UPDATE\n");
			return -EINVAL;
		}
		break;
	case PACKET3_NOP:
		break;
	default:
		DRM_ERROR("Packet3 opcode %x not supported\n", pkt->opcode);
		return -EINVAL;
	}
	return 0;
}

int r600_cs_parse(struct radeon_cs_parser *p)
{
	struct radeon_cs_packet pkt;
	int r;

	do {
		r = r600_cs_packet_parse(p, &pkt, p->idx);
		if (r) {
			return r;
		}
		p->idx += pkt.count + 2;
		switch (pkt.type) {
		case PACKET_TYPE0:
			r = r600_cs_parse_packet0(p, &pkt);
			break;
		case PACKET_TYPE2:
			break;
		case PACKET_TYPE3:
			r = r600_packet3_check(p, &pkt);
			break;
		default:
			DRM_ERROR("Unknown packet type %d !\n", pkt.type);
			return -EINVAL;
		}
		if (r) {
			return r;
		}
	} while (p->idx < p->chunks[p->chunk_ib_idx].length_dw);
#if 0
	for (r = 0; r < p->ib->length_dw; r++) {
		printk(KERN_INFO "%05d  0x%08X\n", r, p->ib->ptr[r]);
		mdelay(1);
	}
#endif
	return 0;
}

static int r600_cs_parser_relocs_legacy(struct radeon_cs_parser *p)
{
	if (p->chunk_relocs_idx == -1) {
		return 0;
	}
	p->relocs = kcalloc(1, sizeof(struct radeon_cs_reloc), GFP_KERNEL);
	if (p->relocs == NULL) {
		return -ENOMEM;
	}
	return 0;
}

/**
 * cs_parser_fini() - clean parser states
 * @parser:	parser structure holding parsing context.
 * @error:	error number
 *
 * If error is set than unvalidate buffer, otherwise just free memory
 * used by parsing context.
 **/
static void r600_cs_parser_fini(struct radeon_cs_parser *parser, int error)
{
	unsigned i;

	kfree(parser->relocs);
	for (i = 0; i < parser->nchunks; i++) {
		kfree(parser->chunks[i].kdata);
	}
	kfree(parser->chunks);
	kfree(parser->chunks_array);
}

int r600_cs_legacy(struct drm_device *dev, void *data, struct drm_file *filp,
			unsigned family, u32 *ib, int *l)
{
	struct radeon_cs_parser parser;
	struct radeon_cs_chunk *ib_chunk;
	struct radeon_ib	fake_ib;
	int r;

	/* initialize parser */
	memset(&parser, 0, sizeof(struct radeon_cs_parser));
	parser.filp = filp;
	parser.rdev = NULL;
	parser.family = family;
	parser.ib = &fake_ib;
	fake_ib.ptr = ib;
	r = radeon_cs_parser_init(&parser, data);
	if (r) {
		DRM_ERROR("Failed to initialize parser !\n");
		r600_cs_parser_fini(&parser, r);
		return r;
	}
	r = r600_cs_parser_relocs_legacy(&parser);
	if (r) {
		DRM_ERROR("Failed to parse relocation !\n");
		r600_cs_parser_fini(&parser, r);
		return r;
	}
	/* Copy the packet into the IB, the parser will read from the
	 * input memory (cached) and write to the IB (which can be
	 * uncached). */
	ib_chunk = &parser.chunks[parser.chunk_ib_idx];
	parser.ib->length_dw = ib_chunk->length_dw;
	memcpy((void *)parser.ib->ptr, ib_chunk->kdata, ib_chunk->length_dw*4);
	*l = parser.ib->length_dw;
	r = r600_cs_parse(&parser);
	if (r) {
		DRM_ERROR("Invalid command stream !\n");
		r600_cs_parser_fini(&parser, r);
		return r;
	}
	r600_cs_parser_fini(&parser, r);
	return r;
}

void r600_cs_legacy_init(void)
{
	r600_cs_packet_next_reloc = &r600_cs_packet_next_reloc_nomm;
}
OpenPOWER on IntegriCloud