aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/i915/intel_ringbuffer.c
blob: 1ab842c6032e949a37855a3995aa161d9f276977 (plain) (blame)
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
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
/*
 * Copyright © 2008-2010 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.
 *
 * Authors:
 *    Eric Anholt <eric@anholt.net>
 *    Zou Nan hai <nanhai.zou@intel.com>
 *    Xiang Hai hao<haihao.xiang@intel.com>
 *
 */

#include "drmP.h"
#include "drm.h"
#include "i915_drv.h"
#include "i915_drm.h"
#include "i915_trace.h"
#include "intel_drv.h"

/*
 * 965+ support PIPE_CONTROL commands, which provide finer grained control
 * over cache flushing.
 */
struct pipe_control {
	struct drm_i915_gem_object *obj;
	volatile u32 *cpu_page;
	u32 gtt_offset;
};

static inline int ring_space(struct intel_ring_buffer *ring)
{
	int space = (ring->head & HEAD_ADDR) - (ring->tail + 8);
	if (space < 0)
		space += ring->size;
	return space;
}

static u32 i915_gem_get_seqno(struct drm_device *dev)
{
	drm_i915_private_t *dev_priv = dev->dev_private;
	u32 seqno;

	seqno = dev_priv->next_seqno;

	/* reserve 0 for non-seqno */
	if (++dev_priv->next_seqno == 0)
		dev_priv->next_seqno = 1;

	return seqno;
}

static int
render_ring_flush(struct intel_ring_buffer *ring,
		  u32	invalidate_domains,
		  u32	flush_domains)
{
	struct drm_device *dev = ring->dev;
	u32 cmd;
	int ret;

	/*
	 * read/write caches:
	 *
	 * I915_GEM_DOMAIN_RENDER is always invalidated, but is
	 * only flushed if MI_NO_WRITE_FLUSH is unset.  On 965, it is
	 * also flushed at 2d versus 3d pipeline switches.
	 *
	 * read-only caches:
	 *
	 * I915_GEM_DOMAIN_SAMPLER is flushed on pre-965 if
	 * MI_READ_FLUSH is set, and is always flushed on 965.
	 *
	 * I915_GEM_DOMAIN_COMMAND may not exist?
	 *
	 * I915_GEM_DOMAIN_INSTRUCTION, which exists on 965, is
	 * invalidated when MI_EXE_FLUSH is set.
	 *
	 * I915_GEM_DOMAIN_VERTEX, which exists on 965, is
	 * invalidated with every MI_FLUSH.
	 *
	 * TLBs:
	 *
	 * On 965, TLBs associated with I915_GEM_DOMAIN_COMMAND
	 * and I915_GEM_DOMAIN_CPU in are invalidated at PTE write and
	 * I915_GEM_DOMAIN_RENDER and I915_GEM_DOMAIN_SAMPLER
	 * are flushed at any MI_FLUSH.
	 */

	cmd = MI_FLUSH | MI_NO_WRITE_FLUSH;
	if ((invalidate_domains|flush_domains) &
	    I915_GEM_DOMAIN_RENDER)
		cmd &= ~MI_NO_WRITE_FLUSH;
	if (INTEL_INFO(dev)->gen < 4) {
		/*
		 * On the 965, the sampler cache always gets flushed
		 * and this bit is reserved.
		 */
		if (invalidate_domains & I915_GEM_DOMAIN_SAMPLER)
			cmd |= MI_READ_FLUSH;
	}
	if (invalidate_domains & I915_GEM_DOMAIN_INSTRUCTION)
		cmd |= MI_EXE_FLUSH;

	if (invalidate_domains & I915_GEM_DOMAIN_COMMAND &&
	    (IS_G4X(dev) || IS_GEN5(dev)))
		cmd |= MI_INVALIDATE_ISP;

	ret = intel_ring_begin(ring, 2);
	if (ret)
		return ret;

	intel_ring_emit(ring, cmd);
	intel_ring_emit(ring, MI_NOOP);
	intel_ring_advance(ring);

	return 0;
}

/**
 * Emits a PIPE_CONTROL with a non-zero post-sync operation, for
 * implementing two workarounds on gen6.  From section 1.4.7.1
 * "PIPE_CONTROL" of the Sandy Bridge PRM volume 2 part 1:
 *
 * [DevSNB-C+{W/A}] Before any depth stall flush (including those
 * produced by non-pipelined state commands), software needs to first
 * send a PIPE_CONTROL with no bits set except Post-Sync Operation !=
 * 0.
 *
 * [Dev-SNB{W/A}]: Before a PIPE_CONTROL with Write Cache Flush Enable
 * =1, a PIPE_CONTROL with any non-zero post-sync-op is required.
 *
 * And the workaround for these two requires this workaround first:
 *
 * [Dev-SNB{W/A}]: Pipe-control with CS-stall bit set must be sent
 * BEFORE the pipe-control with a post-sync op and no write-cache
 * flushes.
 *
 * And this last workaround is tricky because of the requirements on
 * that bit.  From section 1.4.7.2.3 "Stall" of the Sandy Bridge PRM
 * volume 2 part 1:
 *
 *     "1 of the following must also be set:
 *      - Render Target Cache Flush Enable ([12] of DW1)
 *      - Depth Cache Flush Enable ([0] of DW1)
 *      - Stall at Pixel Scoreboard ([1] of DW1)
 *      - Depth Stall ([13] of DW1)
 *      - Post-Sync Operation ([13] of DW1)
 *      - Notify Enable ([8] of DW1)"
 *
 * The cache flushes require the workaround flush that triggered this
 * one, so we can't use it.  Depth stall would trigger the same.
 * Post-sync nonzero is what triggered this second workaround, so we
 * can't use that one either.  Notify enable is IRQs, which aren't
 * really our business.  That leaves only stall at scoreboard.
 */
static int
intel_emit_post_sync_nonzero_flush(struct intel_ring_buffer *ring)
{
	struct pipe_control *pc = ring->private;
	u32 scratch_addr = pc->gtt_offset + 128;
	int ret;


	ret = intel_ring_begin(ring, 6);
	if (ret)
		return ret;

	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(5));
	intel_ring_emit(ring, PIPE_CONTROL_CS_STALL |
			PIPE_CONTROL_STALL_AT_SCOREBOARD);
	intel_ring_emit(ring, scratch_addr | PIPE_CONTROL_GLOBAL_GTT); /* address */
	intel_ring_emit(ring, 0); /* low dword */
	intel_ring_emit(ring, 0); /* high dword */
	intel_ring_emit(ring, MI_NOOP);
	intel_ring_advance(ring);

	ret = intel_ring_begin(ring, 6);
	if (ret)
		return ret;

	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(5));
	intel_ring_emit(ring, PIPE_CONTROL_QW_WRITE);
	intel_ring_emit(ring, scratch_addr | PIPE_CONTROL_GLOBAL_GTT); /* address */
	intel_ring_emit(ring, 0);
	intel_ring_emit(ring, 0);
	intel_ring_emit(ring, MI_NOOP);
	intel_ring_advance(ring);

	return 0;
}

static int
gen6_render_ring_flush(struct intel_ring_buffer *ring,
                         u32 invalidate_domains, u32 flush_domains)
{
	u32 flags = 0;
	struct pipe_control *pc = ring->private;
	u32 scratch_addr = pc->gtt_offset + 128;
	int ret;

	/* Force SNB workarounds for PIPE_CONTROL flushes */
	intel_emit_post_sync_nonzero_flush(ring);

	/* Just flush everything.  Experiments have shown that reducing the
	 * number of bits based on the write domains has little performance
	 * impact.
	 */
	flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
	flags |= PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE;
	flags |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE;
	flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
	flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
	flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
	flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;

	ret = intel_ring_begin(ring, 6);
	if (ret)
		return ret;

	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(5));
	intel_ring_emit(ring, flags);
	intel_ring_emit(ring, scratch_addr | PIPE_CONTROL_GLOBAL_GTT);
	intel_ring_emit(ring, 0); /* lower dword */
	intel_ring_emit(ring, 0); /* uppwer dword */
	intel_ring_emit(ring, MI_NOOP);
	intel_ring_advance(ring);

	return 0;
}

static void ring_write_tail(struct intel_ring_buffer *ring,
			    u32 value)
{
	drm_i915_private_t *dev_priv = ring->dev->dev_private;
	I915_WRITE_TAIL(ring, value);
}

u32 intel_ring_get_active_head(struct intel_ring_buffer *ring)
{
	drm_i915_private_t *dev_priv = ring->dev->dev_private;
	u32 acthd_reg = INTEL_INFO(ring->dev)->gen >= 4 ?
			RING_ACTHD(ring->mmio_base) : ACTHD;

	return I915_READ(acthd_reg);
}

static int init_ring_common(struct intel_ring_buffer *ring)
{
	drm_i915_private_t *dev_priv = ring->dev->dev_private;
	struct drm_i915_gem_object *obj = ring->obj;
	u32 head;

	/* Stop the ring if it's running. */
	I915_WRITE_CTL(ring, 0);
	I915_WRITE_HEAD(ring, 0);
	ring->write_tail(ring, 0);

	/* Initialize the ring. */
	I915_WRITE_START(ring, obj->gtt_offset);
	head = I915_READ_HEAD(ring) & HEAD_ADDR;

	/* G45 ring initialization fails to reset head to zero */
	if (head != 0) {
		DRM_DEBUG_KMS("%s head not reset to zero "
			      "ctl %08x head %08x tail %08x start %08x\n",
			      ring->name,
			      I915_READ_CTL(ring),
			      I915_READ_HEAD(ring),
			      I915_READ_TAIL(ring),
			      I915_READ_START(ring));

		I915_WRITE_HEAD(ring, 0);

		if (I915_READ_HEAD(ring) & HEAD_ADDR) {
			DRM_ERROR("failed to set %s head to zero "
				  "ctl %08x head %08x tail %08x start %08x\n",
				  ring->name,
				  I915_READ_CTL(ring),
				  I915_READ_HEAD(ring),
				  I915_READ_TAIL(ring),
				  I915_READ_START(ring));
		}
	}

	I915_WRITE_CTL(ring,
			((ring->size - PAGE_SIZE) & RING_NR_PAGES)
			| RING_REPORT_64K | RING_VALID);

	/* If the head is still not zero, the ring is dead */
	if ((I915_READ_CTL(ring) & RING_VALID) == 0 ||
	    I915_READ_START(ring) != obj->gtt_offset ||
	    (I915_READ_HEAD(ring) & HEAD_ADDR) != 0) {
		DRM_ERROR("%s initialization failed "
				"ctl %08x head %08x tail %08x start %08x\n",
				ring->name,
				I915_READ_CTL(ring),
				I915_READ_HEAD(ring),
				I915_READ_TAIL(ring),
				I915_READ_START(ring));
		return -EIO;
	}

	if (!drm_core_check_feature(ring->dev, DRIVER_MODESET))
		i915_kernel_lost_context(ring->dev);
	else {
		ring->head = I915_READ_HEAD(ring);
		ring->tail = I915_READ_TAIL(ring) & TAIL_ADDR;
		ring->space = ring_space(ring);
	}

	return 0;
}

static int
init_pipe_control(struct intel_ring_buffer *ring)
{
	struct pipe_control *pc;
	struct drm_i915_gem_object *obj;
	int ret;

	if (ring->private)
		return 0;

	pc = kmalloc(sizeof(*pc), GFP_KERNEL);
	if (!pc)
		return -ENOMEM;

	obj = i915_gem_alloc_object(ring->dev, 4096);
	if (obj == NULL) {
		DRM_ERROR("Failed to allocate seqno page\n");
		ret = -ENOMEM;
		goto err;
	}

	i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);

	ret = i915_gem_object_pin(obj, 4096, true);
	if (ret)
		goto err_unref;

	pc->gtt_offset = obj->gtt_offset;
	pc->cpu_page =  kmap(obj->pages[0]);
	if (pc->cpu_page == NULL)
		goto err_unpin;

	pc->obj = obj;
	ring->private = pc;
	return 0;

err_unpin:
	i915_gem_object_unpin(obj);
err_unref:
	drm_gem_object_unreference(&obj->base);
err:
	kfree(pc);
	return ret;
}

static void
cleanup_pipe_control(struct intel_ring_buffer *ring)
{
	struct pipe_control *pc = ring->private;
	struct drm_i915_gem_object *obj;

	if (!ring->private)
		return;

	obj = pc->obj;
	kunmap(obj->pages[0]);
	i915_gem_object_unpin(obj);
	drm_gem_object_unreference(&obj->base);

	kfree(pc);
	ring->private = NULL;
}

static int init_render_ring(struct intel_ring_buffer *ring)
{
	struct drm_device *dev = ring->dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret = init_ring_common(ring);

	if (INTEL_INFO(dev)->gen > 3) {
		int mode = VS_TIMER_DISPATCH << 16 | VS_TIMER_DISPATCH;
		if (IS_GEN6(dev) || IS_GEN7(dev))
			mode |= MI_FLUSH_ENABLE << 16 | MI_FLUSH_ENABLE;
		I915_WRITE(MI_MODE, mode);
		if (IS_GEN7(dev))
			I915_WRITE(GFX_MODE_GEN7,
				   GFX_MODE_DISABLE(GFX_TLB_INVALIDATE_ALWAYS) |
				   GFX_MODE_ENABLE(GFX_REPLAY_MODE));
	}

	if (INTEL_INFO(dev)->gen >= 5) {
		ret = init_pipe_control(ring);
		if (ret)
			return ret;
	}

	if (INTEL_INFO(dev)->gen >= 6) {
		I915_WRITE(INSTPM,
			   INSTPM_FORCE_ORDERING << 16 | INSTPM_FORCE_ORDERING);
	}

	return ret;
}

static void render_ring_cleanup(struct intel_ring_buffer *ring)
{
	if (!ring->private)
		return;

	cleanup_pipe_control(ring);
}

static void
update_mboxes(struct intel_ring_buffer *ring,
	    u32 seqno,
	    u32 mmio_offset)
{
	intel_ring_emit(ring, MI_SEMAPHORE_MBOX |
			      MI_SEMAPHORE_GLOBAL_GTT |
			      MI_SEMAPHORE_REGISTER |
			      MI_SEMAPHORE_UPDATE);
	intel_ring_emit(ring, seqno);
	intel_ring_emit(ring, mmio_offset);
}

/**
 * gen6_add_request - Update the semaphore mailbox registers
 * 
 * @ring - ring that is adding a request
 * @seqno - return seqno stuck into the ring
 *
 * Update the mailbox registers in the *other* rings with the current seqno.
 * This acts like a signal in the canonical semaphore.
 */
static int
gen6_add_request(struct intel_ring_buffer *ring,
		 u32 *seqno)
{
	u32 mbox1_reg;
	u32 mbox2_reg;
	int ret;

	ret = intel_ring_begin(ring, 10);
	if (ret)
		return ret;

	mbox1_reg = ring->signal_mbox[0];
	mbox2_reg = ring->signal_mbox[1];

	*seqno = i915_gem_get_seqno(ring->dev);

	update_mboxes(ring, *seqno, mbox1_reg);
	update_mboxes(ring, *seqno, mbox2_reg);
	intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
	intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
	intel_ring_emit(ring, *seqno);
	intel_ring_emit(ring, MI_USER_INTERRUPT);
	intel_ring_advance(ring);

	return 0;
}

/**
 * intel_ring_sync - sync the waiter to the signaller on seqno
 *
 * @waiter - ring that is waiting
 * @signaller - ring which has, or will signal
 * @seqno - seqno which the waiter will block on
 */
static int
intel_ring_sync(struct intel_ring_buffer *waiter,
		struct intel_ring_buffer *signaller,
		int ring,
		u32 seqno)
{
	int ret;
	u32 dw1 = MI_SEMAPHORE_MBOX |
		  MI_SEMAPHORE_COMPARE |
		  MI_SEMAPHORE_REGISTER;

	ret = intel_ring_begin(waiter, 4);
	if (ret)
		return ret;

	intel_ring_emit(waiter, dw1 | signaller->semaphore_register[ring]);
	intel_ring_emit(waiter, seqno);
	intel_ring_emit(waiter, 0);
	intel_ring_emit(waiter, MI_NOOP);
	intel_ring_advance(waiter);

	return 0;
}

/* VCS->RCS (RVSYNC) or BCS->RCS (RBSYNC) */
int
render_ring_sync_to(struct intel_ring_buffer *waiter,
		    struct intel_ring_buffer *signaller,
		    u32 seqno)
{
	WARN_ON(signaller->semaphore_register[RCS] == MI_SEMAPHORE_SYNC_INVALID);
	return intel_ring_sync(waiter,
			       signaller,
			       RCS,
			       seqno);
}

/* RCS->VCS (VRSYNC) or BCS->VCS (VBSYNC) */
int
gen6_bsd_ring_sync_to(struct intel_ring_buffer *waiter,
		      struct intel_ring_buffer *signaller,
		      u32 seqno)
{
	WARN_ON(signaller->semaphore_register[VCS] == MI_SEMAPHORE_SYNC_INVALID);
	return intel_ring_sync(waiter,
			       signaller,
			       VCS,
			       seqno);
}

/* RCS->BCS (BRSYNC) or VCS->BCS (BVSYNC) */
int
gen6_blt_ring_sync_to(struct intel_ring_buffer *waiter,
		      struct intel_ring_buffer *signaller,
		      u32 seqno)
{
	WARN_ON(signaller->semaphore_register[BCS] == MI_SEMAPHORE_SYNC_INVALID);
	return intel_ring_sync(waiter,
			       signaller,
			       BCS,
			       seqno);
}



#define PIPE_CONTROL_FLUSH(ring__, addr__)					\
do {									\
	intel_ring_emit(ring__, GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE |		\
		 PIPE_CONTROL_DEPTH_STALL);				\
	intel_ring_emit(ring__, (addr__) | PIPE_CONTROL_GLOBAL_GTT);			\
	intel_ring_emit(ring__, 0);							\
	intel_ring_emit(ring__, 0);							\
} while (0)

static int
pc_render_add_request(struct intel_ring_buffer *ring,
		      u32 *result)
{
	struct drm_device *dev = ring->dev;
	u32 seqno = i915_gem_get_seqno(dev);
	struct pipe_control *pc = ring->private;
	u32 scratch_addr = pc->gtt_offset + 128;
	int ret;

	/* For Ironlake, MI_USER_INTERRUPT was deprecated and apparently
	 * incoherent with writes to memory, i.e. completely fubar,
	 * so we need to use PIPE_NOTIFY instead.
	 *
	 * However, we also need to workaround the qword write
	 * incoherence by flushing the 6 PIPE_NOTIFY buffers out to
	 * memory before requesting an interrupt.
	 */
	ret = intel_ring_begin(ring, 32);
	if (ret)
		return ret;

	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE |
			PIPE_CONTROL_WRITE_FLUSH |
			PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE);
	intel_ring_emit(ring, pc->gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
	intel_ring_emit(ring, seqno);
	intel_ring_emit(ring, 0);
	PIPE_CONTROL_FLUSH(ring, scratch_addr);
	scratch_addr += 128; /* write to separate cachelines */
	PIPE_CONTROL_FLUSH(ring, scratch_addr);
	scratch_addr += 128;
	PIPE_CONTROL_FLUSH(ring, scratch_addr);
	scratch_addr += 128;
	PIPE_CONTROL_FLUSH(ring, scratch_addr);
	scratch_addr += 128;
	PIPE_CONTROL_FLUSH(ring, scratch_addr);
	scratch_addr += 128;
	PIPE_CONTROL_FLUSH(ring, scratch_addr);
	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE |
			PIPE_CONTROL_WRITE_FLUSH |
			PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
			PIPE_CONTROL_NOTIFY);
	intel_ring_emit(ring, pc->gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
	intel_ring_emit(ring, seqno);
	intel_ring_emit(ring, 0);
	intel_ring_advance(ring);

	*result = seqno;
	return 0;
}

static int
render_ring_add_request(struct intel_ring_buffer *ring,
			u32 *result)
{
	struct drm_device *dev = ring->dev;
	u32 seqno = i915_gem_get_seqno(dev);
	int ret;

	ret = intel_ring_begin(ring, 4);
	if (ret)
		return ret;

	intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
	intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
	intel_ring_emit(ring, seqno);
	intel_ring_emit(ring, MI_USER_INTERRUPT);
	intel_ring_advance(ring);

	*result = seqno;
	return 0;
}

static u32
gen6_ring_get_seqno(struct intel_ring_buffer *ring)
{
	struct drm_device *dev = ring->dev;

	/* Workaround to force correct ordering between irq and seqno writes on
	 * ivb (and maybe also on snb) by reading from a CS register (like
	 * ACTHD) before reading the status page. */
	if (IS_GEN7(dev))
		intel_ring_get_active_head(ring);
	return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
}

static u32
ring_get_seqno(struct intel_ring_buffer *ring)
{
	return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
}

static u32
pc_render_get_seqno(struct intel_ring_buffer *ring)
{
	struct pipe_control *pc = ring->private;
	return pc->cpu_page[0];
}

static void
ironlake_enable_irq(drm_i915_private_t *dev_priv, u32 mask)
{
	dev_priv->gt_irq_mask &= ~mask;
	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
	POSTING_READ(GTIMR);
}

static void
ironlake_disable_irq(drm_i915_private_t *dev_priv, u32 mask)
{
	dev_priv->gt_irq_mask |= mask;
	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
	POSTING_READ(GTIMR);
}

static void
i915_enable_irq(drm_i915_private_t *dev_priv, u32 mask)
{
	dev_priv->irq_mask &= ~mask;
	I915_WRITE(IMR, dev_priv->irq_mask);
	POSTING_READ(IMR);
}

static void
i915_disable_irq(drm_i915_private_t *dev_priv, u32 mask)
{
	dev_priv->irq_mask |= mask;
	I915_WRITE(IMR, dev_priv->irq_mask);
	POSTING_READ(IMR);
}

static bool
render_ring_get_irq(struct intel_ring_buffer *ring)
{
	struct drm_device *dev = ring->dev;
	drm_i915_private_t *dev_priv = dev->dev_private;

	if (!dev->irq_enabled)
		return false;

	spin_lock(&ring->irq_lock);
	if (ring->irq_refcount++ == 0) {
		if (HAS_PCH_SPLIT(dev))
			ironlake_enable_irq(dev_priv,
					    GT_PIPE_NOTIFY | GT_USER_INTERRUPT);
		else
			i915_enable_irq(dev_priv, I915_USER_INTERRUPT);
	}
	spin_unlock(&ring->irq_lock);

	return true;
}

static void
render_ring_put_irq(struct intel_ring_buffer *ring)
{
	struct drm_device *dev = ring->dev;
	drm_i915_private_t *dev_priv = dev->dev_private;

	spin_lock(&ring->irq_lock);
	if (--ring->irq_refcount == 0) {
		if (HAS_PCH_SPLIT(dev))
			ironlake_disable_irq(dev_priv,
					     GT_USER_INTERRUPT |
					     GT_PIPE_NOTIFY);
		else
			i915_disable_irq(dev_priv, I915_USER_INTERRUPT);
	}
	spin_unlock(&ring->irq_lock);
}

void intel_ring_setup_status_page(struct intel_ring_buffer *ring)
{
	struct drm_device *dev = ring->dev;
	drm_i915_private_t *dev_priv = ring->dev->dev_private;
	u32 mmio = 0;

	/* The ring status page addresses are no longer next to the rest of
	 * the ring registers as of gen7.
	 */
	if (IS_GEN7(dev)) {
		switch (ring->id) {
		case RING_RENDER:
			mmio = RENDER_HWS_PGA_GEN7;
			break;
		case RING_BLT:
			mmio = BLT_HWS_PGA_GEN7;
			break;
		case RING_BSD:
			mmio = BSD_HWS_PGA_GEN7;
			break;
		}
	} else if (IS_GEN6(ring->dev)) {
		mmio = RING_HWS_PGA_GEN6(ring->mmio_base);
	} else {
		mmio = RING_HWS_PGA(ring->mmio_base);
	}

	I915_WRITE(mmio, (u32)ring->status_page.gfx_addr);
	POSTING_READ(mmio);
}

static int
bsd_ring_flush(struct intel_ring_buffer *ring,
	       u32     invalidate_domains,
	       u32     flush_domains)
{
	int ret;

	ret = intel_ring_begin(ring, 2);
	if (ret)
		return ret;

	intel_ring_emit(ring, MI_FLUSH);
	intel_ring_emit(ring, MI_NOOP);
	intel_ring_advance(ring);
	return 0;
}

static int
ring_add_request(struct intel_ring_buffer *ring,
		 u32 *result)
{
	u32 seqno;
	int ret;

	ret = intel_ring_begin(ring, 4);
	if (ret)
		return ret;

	seqno = i915_gem_get_seqno(ring->dev);

	intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
	intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
	intel_ring_emit(ring, seqno);
	intel_ring_emit(ring, MI_USER_INTERRUPT);
	intel_ring_advance(ring);

	*result = seqno;
	return 0;
}

static bool
gen6_ring_get_irq(struct intel_ring_buffer *ring, u32 gflag, u32 rflag)
{
	struct drm_device *dev = ring->dev;
	drm_i915_private_t *dev_priv = dev->dev_private;

	if (!dev->irq_enabled)
	       return false;

	/* It looks like we need to prevent the gt from suspending while waiting
	 * for an notifiy irq, otherwise irqs seem to get lost on at least the
	 * blt/bsd rings on ivb. */
	if (IS_GEN7(dev))
		gen6_gt_force_wake_get(dev_priv);

	spin_lock(&ring->irq_lock);
	if (ring->irq_refcount++ == 0) {
		ring->irq_mask &= ~rflag;
		I915_WRITE_IMR(ring, ring->irq_mask);
		ironlake_enable_irq(dev_priv, gflag);
	}
	spin_unlock(&ring->irq_lock);

	return true;
}

static void
gen6_ring_put_irq(struct intel_ring_buffer *ring, u32 gflag, u32 rflag)
{
	struct drm_device *dev = ring->dev;
	drm_i915_private_t *dev_priv = dev->dev_private;

	spin_lock(&ring->irq_lock);
	if (--ring->irq_refcount == 0) {
		ring->irq_mask |= rflag;
		I915_WRITE_IMR(ring, ring->irq_mask);
		ironlake_disable_irq(dev_priv, gflag);
	}
	spin_unlock(&ring->irq_lock);

	if (IS_GEN7(dev))
		gen6_gt_force_wake_put(dev_priv);
}

static bool
bsd_ring_get_irq(struct intel_ring_buffer *ring)
{
	struct drm_device *dev = ring->dev;
	drm_i915_private_t *dev_priv = dev->dev_private;

	if (!dev->irq_enabled)
		return false;

	spin_lock(&ring->irq_lock);
	if (ring->irq_refcount++ == 0) {
		if (IS_G4X(dev))
			i915_enable_irq(dev_priv, I915_BSD_USER_INTERRUPT);
		else
			ironlake_enable_irq(dev_priv, GT_BSD_USER_INTERRUPT);
	}
	spin_unlock(&ring->irq_lock);

	return true;
}
static void
bsd_ring_put_irq(struct intel_ring_buffer *ring)
{
	struct drm_device *dev = ring->dev;
	drm_i915_private_t *dev_priv = dev->dev_private;

	spin_lock(&ring->irq_lock);
	if (--ring->irq_refcount == 0) {
		if (IS_G4X(dev))
			i915_disable_irq(dev_priv, I915_BSD_USER_INTERRUPT);
		else
			ironlake_disable_irq(dev_priv, GT_BSD_USER_INTERRUPT);
	}
	spin_unlock(&ring->irq_lock);
}

static int
ring_dispatch_execbuffer(struct intel_ring_buffer *ring, u32 offset, u32 length)
{
	int ret;

	ret = intel_ring_begin(ring, 2);
	if (ret)
		return ret;

	intel_ring_emit(ring,
			MI_BATCH_BUFFER_START | (2 << 6) |
			MI_BATCH_NON_SECURE_I965);
	intel_ring_emit(ring, offset);
	intel_ring_advance(ring);

	return 0;
}

static int
render_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
				u32 offset, u32 len)
{
	struct drm_device *dev = ring->dev;
	int ret;

	if (IS_I830(dev) || IS_845G(dev)) {
		ret = intel_ring_begin(ring, 4);
		if (ret)
			return ret;

		intel_ring_emit(ring, MI_BATCH_BUFFER);
		intel_ring_emit(ring, offset | MI_BATCH_NON_SECURE);
		intel_ring_emit(ring, offset + len - 8);
		intel_ring_emit(ring, 0);
	} else {
		ret = intel_ring_begin(ring, 2);
		if (ret)
			return ret;

		if (INTEL_INFO(dev)->gen >= 4) {
			intel_ring_emit(ring,
					MI_BATCH_BUFFER_START | (2 << 6) |
					MI_BATCH_NON_SECURE_I965);
			intel_ring_emit(ring, offset);
		} else {
			intel_ring_emit(ring,
					MI_BATCH_BUFFER_START | (2 << 6));
			intel_ring_emit(ring, offset | MI_BATCH_NON_SECURE);
		}
	}
	intel_ring_advance(ring);

	return 0;
}

static void cleanup_status_page(struct intel_ring_buffer *ring)
{
	drm_i915_private_t *dev_priv = ring->dev->dev_private;
	struct drm_i915_gem_object *obj;

	obj = ring->status_page.obj;
	if (obj == NULL)
		return;

	kunmap(obj->pages[0]);
	i915_gem_object_unpin(obj);
	drm_gem_object_unreference(&obj->base);
	ring->status_page.obj = NULL;

	memset(&dev_priv->hws_map, 0, sizeof(dev_priv->hws_map));
}

static int init_status_page(struct intel_ring_buffer *ring)
{
	struct drm_device *dev = ring->dev;
	drm_i915_private_t *dev_priv = dev->dev_private;
	struct drm_i915_gem_object *obj;
	int ret;

	obj = i915_gem_alloc_object(dev, 4096);
	if (obj == NULL) {
		DRM_ERROR("Failed to allocate status page\n");
		ret = -ENOMEM;
		goto err;
	}

	i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);

	ret = i915_gem_object_pin(obj, 4096, true);
	if (ret != 0) {
		goto err_unref;
	}

	ring->status_page.gfx_addr = obj->gtt_offset;
	ring->status_page.page_addr = kmap(obj->pages[0]);
	if (ring->status_page.page_addr == NULL) {
		memset(&dev_priv->hws_map, 0, sizeof(dev_priv->hws_map));
		goto err_unpin;
	}
	ring->status_page.obj = obj;
	memset(ring->status_page.page_addr, 0, PAGE_SIZE);

	intel_ring_setup_status_page(ring);
	DRM_DEBUG_DRIVER("%s hws offset: 0x%08x\n",
			ring->name, ring->status_page.gfx_addr);

	return 0;

err_unpin:
	i915_gem_object_unpin(obj);
err_unref:
	drm_gem_object_unreference(&obj->base);
err:
	return ret;
}

int intel_init_ring_buffer(struct drm_device *dev,
			   struct intel_ring_buffer *ring)
{
	struct drm_i915_gem_object *obj;
	int ret;

	ring->dev = dev;
	INIT_LIST_HEAD(&ring->active_list);
	INIT_LIST_HEAD(&ring->request_list);
	INIT_LIST_HEAD(&ring->gpu_write_list);

	init_waitqueue_head(&ring->irq_queue);
	spin_lock_init(&ring->irq_lock);
	ring->irq_mask = ~0;

	if (I915_NEED_GFX_HWS(dev)) {
		ret = init_status_page(ring);
		if (ret)
			return ret;
	}

	obj = i915_gem_alloc_object(dev, ring->size);
	if (obj == NULL) {
		DRM_ERROR("Failed to allocate ringbuffer\n");
		ret = -ENOMEM;
		goto err_hws;
	}

	ring->obj = obj;

	ret = i915_gem_object_pin(obj, PAGE_SIZE, true);
	if (ret)
		goto err_unref;

	ring->map.size = ring->size;
	ring->map.offset = dev->agp->base + obj->gtt_offset;
	ring->map.type = 0;
	ring->map.flags = 0;
	ring->map.mtrr = 0;

	drm_core_ioremap_wc(&ring->map, dev);
	if (ring->map.handle == NULL) {
		DRM_ERROR("Failed to map ringbuffer.\n");
		ret = -EINVAL;
		goto err_unpin;
	}

	ring->virtual_start = ring->map.handle;
	ret = ring->init(ring);
	if (ret)
		goto err_unmap;

	/* Workaround an erratum on the i830 which causes a hang if
	 * the TAIL pointer points to within the last 2 cachelines
	 * of the buffer.
	 */
	ring->effective_size = ring->size;
	if (IS_I830(ring->dev))
		ring->effective_size -= 128;

	return 0;

err_unmap:
	drm_core_ioremapfree(&ring->map, dev);
err_unpin:
	i915_gem_object_unpin(obj);
err_unref:
	drm_gem_object_unreference(&obj->base);
	ring->obj = NULL;
err_hws:
	cleanup_status_page(ring);
	return ret;
}

void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring)
{
	struct drm_i915_private *dev_priv;
	int ret;

	if (ring->obj == NULL)
		return;

	/* Disable the ring buffer. The ring must be idle at this point */
	dev_priv = ring->dev->dev_private;
	ret = intel_wait_ring_idle(ring);
	if (ret)
		DRM_ERROR("failed to quiesce %s whilst cleaning up: %d\n",
			  ring->name, ret);

	I915_WRITE_CTL(ring, 0);

	drm_core_ioremapfree(&ring->map, ring->dev);

	i915_gem_object_unpin(ring->obj);
	drm_gem_object_unreference(&ring->obj->base);
	ring->obj = NULL;

	if (ring->cleanup)
		ring->cleanup(ring);

	cleanup_status_page(ring);
}

static int intel_wrap_ring_buffer(struct intel_ring_buffer *ring)
{
	unsigned int *virt;
	int rem = ring->size - ring->tail;

	if (ring->space < rem) {
		int ret = intel_wait_ring_buffer(ring, rem);
		if (ret)
			return ret;
	}

	virt = (unsigned int *)(ring->virtual_start + ring->tail);
	rem /= 8;
	while (rem--) {
		*virt++ = MI_NOOP;
		*virt++ = MI_NOOP;
	}

	ring->tail = 0;
	ring->space = ring_space(ring);

	return 0;
}

int intel_wait_ring_buffer(struct intel_ring_buffer *ring, int n)
{
	struct drm_device *dev = ring->dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	unsigned long end;
	u32 head;

	/* If the reported head position has wrapped or hasn't advanced,
	 * fallback to the slow and accurate path.
	 */
	head = intel_read_status_page(ring, 4);
	if (head > ring->head) {
		ring->head = head;
		ring->space = ring_space(ring);
		if (ring->space >= n)
			return 0;
	}

	trace_i915_ring_wait_begin(ring);
	if (drm_core_check_feature(dev, DRIVER_GEM))
		/* With GEM the hangcheck timer should kick us out of the loop,
		 * leaving it early runs the risk of corrupting GEM state (due
		 * to running on almost untested codepaths). But on resume
		 * timers don't work yet, so prevent a complete hang in that
		 * case by choosing an insanely large timeout. */
		end = jiffies + 60 * HZ;
	else
		end = jiffies + 3 * HZ;

	do {
		ring->head = I915_READ_HEAD(ring);
		ring->space = ring_space(ring);
		if (ring->space >= n) {
			trace_i915_ring_wait_end(ring);
			return 0;
		}

		if (dev->primary->master) {
			struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
			if (master_priv->sarea_priv)
				master_priv->sarea_priv->perf_boxes |= I915_BOX_WAIT;
		}

		msleep(1);
		if (atomic_read(&dev_priv->mm.wedged))
			return -EAGAIN;
	} while (!time_after(jiffies, end));
	trace_i915_ring_wait_end(ring);
	return -EBUSY;
}

int intel_ring_begin(struct intel_ring_buffer *ring,
		     int num_dwords)
{
	struct drm_i915_private *dev_priv = ring->dev->dev_private;
	int n = 4*num_dwords;
	int ret;

	if (unlikely(atomic_read(&dev_priv->mm.wedged)))
		return -EIO;

	if (unlikely(ring->tail + n > ring->effective_size)) {
		ret = intel_wrap_ring_buffer(ring);
		if (unlikely(ret))
			return ret;
	}

	if (unlikely(ring->space < n)) {
		ret = intel_wait_ring_buffer(ring, n);
		if (unlikely(ret))
			return ret;
	}

	ring->space -= n;
	return 0;
}

void intel_ring_advance(struct intel_ring_buffer *ring)
{
	ring->tail &= ring->size - 1;
	ring->write_tail(ring, ring->tail);
}

static const struct intel_ring_buffer render_ring = {
	.name			= "render ring",
	.id			= RING_RENDER,
	.mmio_base		= RENDER_RING_BASE,
	.size			= 32 * PAGE_SIZE,
	.init			= init_render_ring,
	.write_tail		= ring_write_tail,
	.flush			= render_ring_flush,
	.add_request		= render_ring_add_request,
	.get_seqno		= ring_get_seqno,
	.irq_get		= render_ring_get_irq,
	.irq_put		= render_ring_put_irq,
	.dispatch_execbuffer	= render_ring_dispatch_execbuffer,
	.cleanup		= render_ring_cleanup,
	.sync_to		= render_ring_sync_to,
	.semaphore_register	= {MI_SEMAPHORE_SYNC_INVALID,
				   MI_SEMAPHORE_SYNC_RV,
				   MI_SEMAPHORE_SYNC_RB},
	.signal_mbox		= {GEN6_VRSYNC, GEN6_BRSYNC},
};

/* ring buffer for bit-stream decoder */

static const struct intel_ring_buffer bsd_ring = {
	.name                   = "bsd ring",
	.id			= RING_BSD,
	.mmio_base		= BSD_RING_BASE,
	.size			= 32 * PAGE_SIZE,
	.init			= init_ring_common,
	.write_tail		= ring_write_tail,
	.flush			= bsd_ring_flush,
	.add_request		= ring_add_request,
	.get_seqno		= ring_get_seqno,
	.irq_get		= bsd_ring_get_irq,
	.irq_put		= bsd_ring_put_irq,
	.dispatch_execbuffer	= ring_dispatch_execbuffer,
};


static void gen6_bsd_ring_write_tail(struct intel_ring_buffer *ring,
				     u32 value)
{
	drm_i915_private_t *dev_priv = ring->dev->dev_private;

       /* Every tail move must follow the sequence below */
	I915_WRITE(GEN6_BSD_SLEEP_PSMI_CONTROL,
		GEN6_BSD_SLEEP_PSMI_CONTROL_RC_ILDL_MESSAGE_MODIFY_MASK |
		GEN6_BSD_SLEEP_PSMI_CONTROL_RC_ILDL_MESSAGE_DISABLE);
	I915_WRITE(GEN6_BSD_RNCID, 0x0);

	if (wait_for((I915_READ(GEN6_BSD_SLEEP_PSMI_CONTROL) &
		GEN6_BSD_SLEEP_PSMI_CONTROL_IDLE_INDICATOR) == 0,
		50))
	DRM_ERROR("timed out waiting for IDLE Indicator\n");

	I915_WRITE_TAIL(ring, value);
	I915_WRITE(GEN6_BSD_SLEEP_PSMI_CONTROL,
		GEN6_BSD_SLEEP_PSMI_CONTROL_RC_ILDL_MESSAGE_MODIFY_MASK |
		GEN6_BSD_SLEEP_PSMI_CONTROL_RC_ILDL_MESSAGE_ENABLE);
}

static int gen6_ring_flush(struct intel_ring_buffer *ring,
			   u32 invalidate, u32 flush)
{
	uint32_t cmd;
	int ret;

	ret = intel_ring_begin(ring, 4);
	if (ret)
		return ret;

	cmd = MI_FLUSH_DW;
	if (invalidate & I915_GEM_GPU_DOMAINS)
		cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD;
	intel_ring_emit(ring, cmd);
	intel_ring_emit(ring, 0);
	intel_ring_emit(ring, 0);
	intel_ring_emit(ring, MI_NOOP);
	intel_ring_advance(ring);
	return 0;
}

static int
gen6_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
			      u32 offset, u32 len)
{
	int ret;

	ret = intel_ring_begin(ring, 2);
	if (ret)
		return ret;

	intel_ring_emit(ring, MI_BATCH_BUFFER_START | MI_BATCH_NON_SECURE_I965);
	/* bit0-7 is the length on GEN6+ */
	intel_ring_emit(ring, offset);
	intel_ring_advance(ring);

	return 0;
}

static bool
gen6_render_ring_get_irq(struct intel_ring_buffer *ring)
{
	return gen6_ring_get_irq(ring,
				 GT_USER_INTERRUPT,
				 GEN6_RENDER_USER_INTERRUPT);
}

static void
gen6_render_ring_put_irq(struct intel_ring_buffer *ring)
{
	return gen6_ring_put_irq(ring,
				 GT_USER_INTERRUPT,
				 GEN6_RENDER_USER_INTERRUPT);
}

static bool
gen6_bsd_ring_get_irq(struct intel_ring_buffer *ring)
{
	return gen6_ring_get_irq(ring,
				 GT_GEN6_BSD_USER_INTERRUPT,
				 GEN6_BSD_USER_INTERRUPT);
}

static void
gen6_bsd_ring_put_irq(struct intel_ring_buffer *ring)
{
	return gen6_ring_put_irq(ring,
				 GT_GEN6_BSD_USER_INTERRUPT,
				 GEN6_BSD_USER_INTERRUPT);
}

/* ring buffer for Video Codec for Gen6+ */
static const struct intel_ring_buffer gen6_bsd_ring = {
	.name			= "gen6 bsd ring",
	.id			= RING_BSD,
	.mmio_base		= GEN6_BSD_RING_BASE,
	.size			= 32 * PAGE_SIZE,
	.init			= init_ring_common,
	.write_tail		= gen6_bsd_ring_write_tail,
	.flush			= gen6_ring_flush,
	.add_request		= gen6_add_request,
	.get_seqno		= gen6_ring_get_seqno,
	.irq_get		= gen6_bsd_ring_get_irq,
	.irq_put		= gen6_bsd_ring_put_irq,
	.dispatch_execbuffer	= gen6_ring_dispatch_execbuffer,
	.sync_to		= gen6_bsd_ring_sync_to,
	.semaphore_register	= {MI_SEMAPHORE_SYNC_VR,
				   MI_SEMAPHORE_SYNC_INVALID,
				   MI_SEMAPHORE_SYNC_VB},
	.signal_mbox		= {GEN6_RVSYNC, GEN6_BVSYNC},
};

/* Blitter support (SandyBridge+) */

static bool
blt_ring_get_irq(struct intel_ring_buffer *ring)
{
	return gen6_ring_get_irq(ring,
				 GT_BLT_USER_INTERRUPT,
				 GEN6_BLITTER_USER_INTERRUPT);
}

static void
blt_ring_put_irq(struct intel_ring_buffer *ring)
{
	gen6_ring_put_irq(ring,
			  GT_BLT_USER_INTERRUPT,
			  GEN6_BLITTER_USER_INTERRUPT);
}


/* Workaround for some stepping of SNB,
 * each time when BLT engine ring tail moved,
 * the first command in the ring to be parsed
 * should be MI_BATCH_BUFFER_START
 */
#define NEED_BLT_WORKAROUND(dev) \
	(IS_GEN6(dev) && (dev->pdev->revision < 8))

static inline struct drm_i915_gem_object *
to_blt_workaround(struct intel_ring_buffer *ring)
{
	return ring->private;
}

static int blt_ring_init(struct intel_ring_buffer *ring)
{
	if (NEED_BLT_WORKAROUND(ring->dev)) {
		struct drm_i915_gem_object *obj;
		u32 *ptr;
		int ret;

		obj = i915_gem_alloc_object(ring->dev, 4096);
		if (obj == NULL)
			return -ENOMEM;

		ret = i915_gem_object_pin(obj, 4096, true);
		if (ret) {
			drm_gem_object_unreference(&obj->base);
			return ret;
		}

		ptr = kmap(obj->pages[0]);
		*ptr++ = MI_BATCH_BUFFER_END;
		*ptr++ = MI_NOOP;
		kunmap(obj->pages[0]);

		ret = i915_gem_object_set_to_gtt_domain(obj, false);
		if (ret) {
			i915_gem_object_unpin(obj);
			drm_gem_object_unreference(&obj->base);
			return ret;
		}

		ring->private = obj;
	}

	return init_ring_common(ring);
}

static int blt_ring_begin(struct intel_ring_buffer *ring,
			  int num_dwords)
{
	if (ring->private) {
		int ret = intel_ring_begin(ring, num_dwords+2);
		if (ret)
			return ret;

		intel_ring_emit(ring, MI_BATCH_BUFFER_START);
		intel_ring_emit(ring, to_blt_workaround(ring)->gtt_offset);

		return 0;
	} else
		return intel_ring_begin(ring, 4);
}

static int blt_ring_flush(struct intel_ring_buffer *ring,
			  u32 invalidate, u32 flush)
{
	uint32_t cmd;
	int ret;

	ret = blt_ring_begin(ring, 4);
	if (ret)
		return ret;

	cmd = MI_FLUSH_DW;
	if (invalidate & I915_GEM_DOMAIN_RENDER)
		cmd |= MI_INVALIDATE_TLB;
	intel_ring_emit(ring, cmd);
	intel_ring_emit(ring, 0);
	intel_ring_emit(ring, 0);
	intel_ring_emit(ring, MI_NOOP);
	intel_ring_advance(ring);
	return 0;
}

static void blt_ring_cleanup(struct intel_ring_buffer *ring)
{
	if (!ring->private)
		return;

	i915_gem_object_unpin(ring->private);
	drm_gem_object_unreference(ring->private);
	ring->private = NULL;
}

static const struct intel_ring_buffer gen6_blt_ring = {
	.name			= "blt ring",
	.id			= RING_BLT,
	.mmio_base		= BLT_RING_BASE,
	.size			= 32 * PAGE_SIZE,
	.init			= blt_ring_init,
	.write_tail		= ring_write_tail,
	.flush			= blt_ring_flush,
	.add_request		= gen6_add_request,
	.get_seqno		= gen6_ring_get_seqno,
	.irq_get		= blt_ring_get_irq,
	.irq_put		= blt_ring_put_irq,
	.dispatch_execbuffer	= gen6_ring_dispatch_execbuffer,
	.cleanup		= blt_ring_cleanup,
	.sync_to		= gen6_blt_ring_sync_to,
	.semaphore_register	= {MI_SEMAPHORE_SYNC_BR,
				   MI_SEMAPHORE_SYNC_BV,
				   MI_SEMAPHORE_SYNC_INVALID},
	.signal_mbox		= {GEN6_RBSYNC, GEN6_VBSYNC},
};

int intel_init_render_ring_buffer(struct drm_device *dev)
{
	drm_i915_private_t *dev_priv = dev->dev_private;
	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];

	*ring = render_ring;
	if (INTEL_INFO(dev)->gen >= 6) {
		ring->add_request = gen6_add_request;
		ring->flush = gen6_render_ring_flush;
		ring->irq_get = gen6_render_ring_get_irq;
		ring->irq_put = gen6_render_ring_put_irq;
		ring->get_seqno = gen6_ring_get_seqno;
	} else if (IS_GEN5(dev)) {
		ring->add_request = pc_render_add_request;
		ring->get_seqno = pc_render_get_seqno;
	}

	if (!I915_NEED_GFX_HWS(dev)) {
		ring->status_page.page_addr = dev_priv->status_page_dmah->vaddr;
		memset(ring->status_page.page_addr, 0, PAGE_SIZE);
	}

	return intel_init_ring_buffer(dev, ring);
}

int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size)
{
	drm_i915_private_t *dev_priv = dev->dev_private;
	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];

	*ring = render_ring;
	if (INTEL_INFO(dev)->gen >= 6) {
		ring->add_request = gen6_add_request;
		ring->irq_get = gen6_render_ring_get_irq;
		ring->irq_put = gen6_render_ring_put_irq;
	} else if (IS_GEN5(dev)) {
		ring->add_request = pc_render_add_request;
		ring->get_seqno = pc_render_get_seqno;
	}

	if (!I915_NEED_GFX_HWS(dev))
		ring->status_page.page_addr = dev_priv->status_page_dmah->vaddr;

	ring->dev = dev;
	INIT_LIST_HEAD(&ring->active_list);
	INIT_LIST_HEAD(&ring->request_list);
	INIT_LIST_HEAD(&ring->gpu_write_list);

	ring->size = size;
	ring->effective_size = ring->size;
	if (IS_I830(ring->dev))
		ring->effective_size -= 128;

	ring->map.offset = start;
	ring->map.size = size;
	ring->map.type = 0;
	ring->map.flags = 0;
	ring->map.mtrr = 0;

	drm_core_ioremap_wc(&ring->map, dev);
	if (ring->map.handle == NULL) {
		DRM_ERROR("can not ioremap virtual address for"
			  " ring buffer\n");
		return -ENOMEM;
	}

	ring->virtual_start = (void __force __iomem *)ring->map.handle;
	return 0;
}

int intel_init_bsd_ring_buffer(struct drm_device *dev)
{
	drm_i915_private_t *dev_priv = dev->dev_private;
	struct intel_ring_buffer *ring = &dev_priv->ring[VCS];

	if (IS_GEN6(dev) || IS_GEN7(dev))
		*ring = gen6_bsd_ring;
	else
		*ring = bsd_ring;

	return intel_init_ring_buffer(dev, ring);
}

int intel_init_blt_ring_buffer(struct drm_device *dev)
{
	drm_i915_private_t *dev_priv = dev->dev_private;
	struct intel_ring_buffer *ring = &dev_priv->ring[BCS];

	*ring = gen6_blt_ring;

	return intel_init_ring_buffer(dev, ring);
}