aboutsummaryrefslogtreecommitdiffstats
path: root/target/linux/brcm2708/patches-4.19/950-0585-drm-v3d-Refactor-job-management.patch
blob: 64be2b080dc2a1c65849637a7f00a3005e218a23 (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
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
From ccf319a0265bfdb4a622a52645f159461bc88079 Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Thu, 27 Dec 2018 12:11:52 -0800
Subject: [PATCH 585/806] drm/v3d: Refactor job management.

The CL submission had two jobs embedded in an exec struct.  When I
added TFU support, I had to replicate some of the exec stuff and some
of the job stuff.  As I went to add CSD, it became clear that actually
what was in exec should just be in the two CL jobs, and it would let
us share a lot more code between the 4 queues.

Signed-off-by: Eric Anholt <eric@anholt.net>
---
 drivers/gpu/drm/v3d/v3d_drv.h   |  77 ++++----
 drivers/gpu/drm/v3d/v3d_gem.c   | 331 +++++++++++++++++---------------
 drivers/gpu/drm/v3d/v3d_irq.c   |   8 +-
 drivers/gpu/drm/v3d/v3d_sched.c | 264 ++++++++++++++-----------
 4 files changed, 373 insertions(+), 307 deletions(-)

--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -67,8 +67,8 @@ struct v3d_dev {
 
 	struct work_struct overflow_mem_work;
 
-	struct v3d_exec_info *bin_job;
-	struct v3d_exec_info *render_job;
+	struct v3d_bin_job *bin_job;
+	struct v3d_render_job *render_job;
 	struct v3d_tfu_job *tfu_job;
 
 	struct v3d_queue_state queue[V3D_MAX_QUEUES];
@@ -132,7 +132,7 @@ struct v3d_bo {
 	struct list_head vmas;    /* list of v3d_vma */
 
 	/* List entry for the BO's position in
-	 * v3d_exec_info->unref_list
+	 * v3d_render_job->unref_list
 	 */
 	struct list_head unref_head;
 
@@ -176,7 +176,15 @@ to_v3d_fence(struct dma_fence *fence)
 struct v3d_job {
 	struct drm_sched_job base;
 
-	struct v3d_exec_info *exec;
+	struct kref refcount;
+
+	struct v3d_dev *v3d;
+
+	/* This is the array of BOs that were looked up at the start
+	 * of submission.
+	 */
+	struct v3d_bo **bo;
+	u32 bo_count;
 
 	/* An optional fence userspace can pass in for the job to depend on. */
 	struct dma_fence *in_fence;
@@ -184,59 +192,53 @@ struct v3d_job {
 	/* v3d fence to be signaled by IRQ handler when the job is complete. */
 	struct dma_fence *irq_fence;
 
+	/* scheduler fence for when the job is considered complete and
+	 * the BO reservations can be released.
+	 */
+	struct dma_fence *done_fence;
+
+	/* Callback for the freeing of the job on refcount going to 0. */
+	void (*free)(struct kref *ref);
+};
+
+struct v3d_bin_job {
+	struct v3d_job base;
+
 	/* GPU virtual addresses of the start/end of the CL job. */
 	u32 start, end;
 
 	u32 timedout_ctca, timedout_ctra;
-};
 
-struct v3d_exec_info {
-	struct v3d_dev *v3d;
+	/* Corresponding render job, for attaching our overflow memory. */
+	struct v3d_render_job *render;
+
+	/* Submitted tile memory allocation start/size, tile state. */
+	u32 qma, qms, qts;
+};
 
-	struct v3d_job bin, render;
+struct v3d_render_job {
+	struct v3d_job base;
 
-	/* Fence for when the scheduler considers the binner to be
-	 * done, for render to depend on.
+	/* Optional fence for the binner, to depend on before starting
+	 * our job.
 	 */
 	struct dma_fence *bin_done_fence;
 
-	/* Fence for when the scheduler considers the render to be
-	 * done, for when the BOs reservations should be complete.
-	 */
-	struct dma_fence *render_done_fence;
-
-	struct kref refcount;
+	/* GPU virtual addresses of the start/end of the CL job. */
+	u32 start, end;
 
-	/* This is the array of BOs that were looked up at the start of exec. */
-	struct v3d_bo **bo;
-	u32 bo_count;
+	u32 timedout_ctca, timedout_ctra;
 
 	/* List of overflow BOs used in the job that need to be
 	 * released once the job is complete.
 	 */
 	struct list_head unref_list;
-
-	/* Submitted tile memory allocation start/size, tile state. */
-	u32 qma, qms, qts;
 };
 
 struct v3d_tfu_job {
-	struct drm_sched_job base;
+	struct v3d_job base;
 
 	struct drm_v3d_submit_tfu args;
-
-	/* An optional fence userspace can pass in for the job to depend on. */
-	struct dma_fence *in_fence;
-
-	/* v3d fence to be signaled by IRQ handler when the job is complete. */
-	struct dma_fence *irq_fence;
-
-	struct v3d_dev *v3d;
-
-	struct kref refcount;
-
-	/* This is the array of BOs that were looked up at the start of exec. */
-	struct v3d_bo *bo[4];
 };
 
 /**
@@ -306,8 +308,7 @@ int v3d_submit_tfu_ioctl(struct drm_devi
 			 struct drm_file *file_priv);
 int v3d_wait_bo_ioctl(struct drm_device *dev, void *data,
 		      struct drm_file *file_priv);
-void v3d_exec_put(struct v3d_exec_info *exec);
-void v3d_tfu_job_put(struct v3d_tfu_job *exec);
+void v3d_job_put(struct v3d_job *job);
 void v3d_reset(struct v3d_dev *v3d);
 void v3d_invalidate_caches(struct v3d_dev *v3d);
 
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -293,11 +293,11 @@ retry:
 }
 
 /**
- * v3d_cl_lookup_bos() - Sets up exec->bo[] with the GEM objects
+ * v3d_lookup_bos() - Sets up job->bo[] with the GEM objects
  * referenced by the job.
  * @dev: DRM device
  * @file_priv: DRM file for this fd
- * @exec: V3D job being set up
+ * @job: V3D job being set up
  *
  * The command validator needs to reference BOs by their index within
  * the submitted job's BO list.  This does the validation of the job's
@@ -307,18 +307,19 @@ retry:
  * failure, because that will happen at v3d_exec_cleanup() time.
  */
 static int
-v3d_cl_lookup_bos(struct drm_device *dev,
-		  struct drm_file *file_priv,
-		  struct drm_v3d_submit_cl *args,
-		  struct v3d_exec_info *exec)
+v3d_lookup_bos(struct drm_device *dev,
+	       struct drm_file *file_priv,
+	       struct v3d_job *job,
+	       u64 bo_handles,
+	       u32 bo_count)
 {
 	u32 *handles;
 	int ret = 0;
 	int i;
 
-	exec->bo_count = args->bo_handle_count;
+	job->bo_count = bo_count;
 
-	if (!exec->bo_count) {
+	if (!job->bo_count) {
 		/* See comment on bo_index for why we have to check
 		 * this.
 		 */
@@ -326,15 +327,15 @@ v3d_cl_lookup_bos(struct drm_device *dev
 		return -EINVAL;
 	}
 
-	exec->bo = kvmalloc_array(exec->bo_count,
-				  sizeof(struct drm_gem_cma_object *),
-				  GFP_KERNEL | __GFP_ZERO);
-	if (!exec->bo) {
+	job->bo = kvmalloc_array(job->bo_count,
+				 sizeof(struct drm_gem_cma_object *),
+				 GFP_KERNEL | __GFP_ZERO);
+	if (!job->bo) {
 		DRM_DEBUG("Failed to allocate validated BO pointers\n");
 		return -ENOMEM;
 	}
 
-	handles = kvmalloc_array(exec->bo_count, sizeof(u32), GFP_KERNEL);
+	handles = kvmalloc_array(job->bo_count, sizeof(u32), GFP_KERNEL);
 	if (!handles) {
 		ret = -ENOMEM;
 		DRM_DEBUG("Failed to allocate incoming GEM handles\n");
@@ -342,15 +343,15 @@ v3d_cl_lookup_bos(struct drm_device *dev
 	}
 
 	if (copy_from_user(handles,
-			   (void __user *)(uintptr_t)args->bo_handles,
-			   exec->bo_count * sizeof(u32))) {
+			   (void __user *)(uintptr_t)bo_handles,
+			   job->bo_count * sizeof(u32))) {
 		ret = -EFAULT;
 		DRM_DEBUG("Failed to copy in GEM handles\n");
 		goto fail;
 	}
 
 	spin_lock(&file_priv->table_lock);
-	for (i = 0; i < exec->bo_count; i++) {
+	for (i = 0; i < job->bo_count; i++) {
 		struct drm_gem_object *bo = idr_find(&file_priv->object_idr,
 						     handles[i]);
 		if (!bo) {
@@ -361,7 +362,7 @@ v3d_cl_lookup_bos(struct drm_device *dev
 			goto fail;
 		}
 		drm_gem_object_get(bo);
-		exec->bo[i] = to_v3d_bo(bo);
+		job->bo[i] = to_v3d_bo(bo);
 	}
 	spin_unlock(&file_priv->table_lock);
 
@@ -371,59 +372,41 @@ fail:
 }
 
 static void
-v3d_exec_cleanup(struct kref *ref)
+v3d_job_free(struct kref *ref)
 {
-	struct v3d_exec_info *exec = container_of(ref, struct v3d_exec_info,
-						  refcount);
-	unsigned int i;
-	struct v3d_bo *bo, *save;
-
-	dma_fence_put(exec->bin.in_fence);
-	dma_fence_put(exec->render.in_fence);
-
-	dma_fence_put(exec->bin.irq_fence);
-	dma_fence_put(exec->render.irq_fence);
-
-	dma_fence_put(exec->bin_done_fence);
-	dma_fence_put(exec->render_done_fence);
-
-	for (i = 0; i < exec->bo_count; i++)
-		drm_gem_object_put_unlocked(&exec->bo[i]->base);
-	kvfree(exec->bo);
+	struct v3d_job *job = container_of(ref, struct v3d_job, refcount);
+	int i;
 
-	list_for_each_entry_safe(bo, save, &exec->unref_list, unref_head) {
-		drm_gem_object_put_unlocked(&bo->base);
+	for (i = 0; i < job->bo_count; i++) {
+		if (job->bo[i])
+			drm_gem_object_put_unlocked(&job->bo[i]->base);
 	}
+	kvfree(job->bo);
 
-	kfree(exec);
-}
+	dma_fence_put(job->in_fence);
+	dma_fence_put(job->irq_fence);
+	dma_fence_put(job->done_fence);
 
-void v3d_exec_put(struct v3d_exec_info *exec)
-{
-	kref_put(&exec->refcount, v3d_exec_cleanup);
+	kfree(job);
 }
 
 static void
-v3d_tfu_job_cleanup(struct kref *ref)
+v3d_render_job_free(struct kref *ref)
 {
-	struct v3d_tfu_job *job = container_of(ref, struct v3d_tfu_job,
-					       refcount);
-	unsigned int i;
-
-	dma_fence_put(job->in_fence);
-	dma_fence_put(job->irq_fence);
+	struct v3d_render_job *job = container_of(ref, struct v3d_render_job,
+						  base.refcount);
+	struct v3d_bo *bo, *save;
 
-	for (i = 0; i < ARRAY_SIZE(job->bo); i++) {
-		if (job->bo[i])
-			drm_gem_object_put_unlocked(&job->bo[i]->base);
+	list_for_each_entry_safe(bo, save, &job->unref_list, unref_head) {
+		drm_gem_object_put_unlocked(&bo->base);
 	}
 
-	kfree(job);
+	v3d_job_free(ref);
 }
 
-void v3d_tfu_job_put(struct v3d_tfu_job *job)
+void v3d_job_put(struct v3d_job *job)
 {
-	kref_put(&job->refcount, v3d_tfu_job_cleanup);
+	kref_put(&job->refcount, job->free);
 }
 
 int
@@ -476,6 +459,65 @@ v3d_wait_bo_ioctl(struct drm_device *dev
 	return ret;
 }
 
+static int
+v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv,
+	     struct v3d_job *job, void (*free)(struct kref *ref),
+	     u32 in_sync)
+{
+	int ret;
+
+	job->v3d = v3d;
+	job->free = free;
+
+	ret = drm_syncobj_find_fence(file_priv, in_sync, 0, &job->in_fence);
+	if (ret == -EINVAL)
+		return ret;
+
+	kref_init(&job->refcount);
+
+	return 0;
+}
+
+static int
+v3d_push_job(struct v3d_file_priv *v3d_priv,
+	     struct v3d_job *job, enum v3d_queue queue)
+{
+	int ret;
+
+	ret = drm_sched_job_init(&job->base, &v3d_priv->sched_entity[queue],
+				 v3d_priv);
+	if (ret)
+		return ret;
+
+	job->done_fence = dma_fence_get(&job->base.s_fence->finished);
+
+	/* put by scheduler job completion */
+	kref_get(&job->refcount);
+
+	drm_sched_entity_push_job(&job->base, &v3d_priv->sched_entity[queue]);
+
+	return 0;
+}
+
+static void
+v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv,
+					 struct v3d_job *job,
+					 struct ww_acquire_ctx *acquire_ctx,
+					 u32 out_sync)
+{
+	struct drm_syncobj *sync_out;
+
+	v3d_attach_object_fences(job->bo, job->bo_count, job->done_fence);
+	v3d_unlock_bo_reservations(job->bo, job->bo_count, acquire_ctx);
+
+	/* Update the return sync object for the job */
+	sync_out = drm_syncobj_find(file_priv, out_sync);
+	if (sync_out) {
+		drm_syncobj_replace_fence(sync_out, job->done_fence);
+		drm_syncobj_put(sync_out);
+	}
+}
+
 /**
  * v3d_submit_cl_ioctl() - Submits a job (frame) to the V3D.
  * @dev: DRM device
@@ -495,9 +537,9 @@ v3d_submit_cl_ioctl(struct drm_device *d
 	struct v3d_dev *v3d = to_v3d_dev(dev);
 	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
 	struct drm_v3d_submit_cl *args = data;
-	struct v3d_exec_info *exec;
+	struct v3d_bin_job *bin = NULL;
+	struct v3d_render_job *render;
 	struct ww_acquire_ctx acquire_ctx;
-	struct drm_syncobj *sync_out;
 	int ret = 0;
 
 	trace_v3d_submit_cl_ioctl(&v3d->drm, args->rcl_start, args->rcl_end);
@@ -507,95 +549,84 @@ v3d_submit_cl_ioctl(struct drm_device *d
 		return -EINVAL;
 	}
 
-	exec = kcalloc(1, sizeof(*exec), GFP_KERNEL);
-	if (!exec)
+	render = kcalloc(1, sizeof(*render), GFP_KERNEL);
+	if (!render)
 		return -ENOMEM;
 
-	kref_init(&exec->refcount);
+	render->start = args->rcl_start;
+	render->end = args->rcl_end;
+	INIT_LIST_HEAD(&render->unref_list);
 
-	ret = drm_syncobj_find_fence(file_priv, args->in_sync_bcl,
-				     0, &exec->bin.in_fence);
-	if (ret == -EINVAL)
-		goto fail;
+	ret = v3d_job_init(v3d, file_priv, &render->base,
+			   v3d_render_job_free, args->in_sync_rcl);
+	if (ret) {
+		kfree(bin);
+		kfree(render);
+		return ret;
+	}
 
-	ret = drm_syncobj_find_fence(file_priv, args->in_sync_rcl,
-				     0, &exec->render.in_fence);
-	if (ret == -EINVAL)
-		goto fail;
+	if (args->bcl_start != args->bcl_end) {
+		bin = kcalloc(1, sizeof(*bin), GFP_KERNEL);
+		if (!bin)
+			return -ENOMEM;
+
+		ret = v3d_job_init(v3d, file_priv, &bin->base,
+				   v3d_job_free, args->in_sync_bcl);
+		if (ret) {
+			v3d_job_put(&render->base);
+			return ret;
+		}
 
-	exec->qma = args->qma;
-	exec->qms = args->qms;
-	exec->qts = args->qts;
-	exec->bin.exec = exec;
-	exec->bin.start = args->bcl_start;
-	exec->bin.end = args->bcl_end;
-	exec->render.exec = exec;
-	exec->render.start = args->rcl_start;
-	exec->render.end = args->rcl_end;
-	exec->v3d = v3d;
-	INIT_LIST_HEAD(&exec->unref_list);
+		bin->start = args->bcl_start;
+		bin->end = args->bcl_end;
+		bin->qma = args->qma;
+		bin->qms = args->qms;
+		bin->qts = args->qts;
+		bin->render = render;
+	}
 
-	ret = v3d_cl_lookup_bos(dev, file_priv, args, exec);
+	ret = v3d_lookup_bos(dev, file_priv, &render->base,
+			     args->bo_handles, args->bo_handle_count);
 	if (ret)
 		goto fail;
 
-	ret = v3d_lock_bo_reservations(exec->bo, exec->bo_count,
+	ret = v3d_lock_bo_reservations(render->base.bo, render->base.bo_count,
 				       &acquire_ctx);
 	if (ret)
 		goto fail;
 
 	mutex_lock(&v3d->sched_lock);
-	if (exec->bin.start != exec->bin.end) {
-		ret = drm_sched_job_init(&exec->bin.base,
-					 &v3d_priv->sched_entity[V3D_BIN],
-					 v3d_priv);
+	if (bin) {
+		ret = v3d_push_job(v3d_priv, &bin->base, V3D_BIN);
 		if (ret)
 			goto fail_unreserve;
 
-		exec->bin_done_fence =
-			dma_fence_get(&exec->bin.base.s_fence->finished);
-
-		kref_get(&exec->refcount); /* put by scheduler job completion */
-		drm_sched_entity_push_job(&exec->bin.base,
-					  &v3d_priv->sched_entity[V3D_BIN]);
+		render->bin_done_fence = dma_fence_get(bin->base.done_fence);
 	}
 
-	ret = drm_sched_job_init(&exec->render.base,
-				 &v3d_priv->sched_entity[V3D_RENDER],
-				 v3d_priv);
+	ret = v3d_push_job(v3d_priv, &render->base, V3D_RENDER);
 	if (ret)
 		goto fail_unreserve;
-
-	exec->render_done_fence =
-		dma_fence_get(&exec->render.base.s_fence->finished);
-
-	kref_get(&exec->refcount); /* put by scheduler job completion */
-	drm_sched_entity_push_job(&exec->render.base,
-				  &v3d_priv->sched_entity[V3D_RENDER]);
 	mutex_unlock(&v3d->sched_lock);
 
-	v3d_attach_object_fences(exec->bo, exec->bo_count,
-				 exec->render_done_fence);
-
-	v3d_unlock_bo_reservations(exec->bo, exec->bo_count, &acquire_ctx);
-
-	/* Update the return sync object for the */
-	sync_out = drm_syncobj_find(file_priv, args->out_sync);
-	if (sync_out) {
-		drm_syncobj_replace_fence(sync_out,
-					  exec->render_done_fence);
-		drm_syncobj_put(sync_out);
-	}
-
-	v3d_exec_put(exec);
+	v3d_attach_fences_and_unlock_reservation(file_priv,
+						 &render->base, &acquire_ctx,
+						 args->out_sync);
+
+	if (bin)
+		v3d_job_put(&bin->base);
+	v3d_job_put(&render->base);
 
 	return 0;
 
 fail_unreserve:
 	mutex_unlock(&v3d->sched_lock);
-	v3d_unlock_bo_reservations(exec->bo, exec->bo_count, &acquire_ctx);
+	v3d_unlock_bo_reservations(render->base.bo,
+				   render->base.bo_count, &acquire_ctx);
 fail:
-	v3d_exec_put(exec);
+	if (bin)
+		v3d_job_put(&bin->base);
+	v3d_job_put(&render->base);
 
 	return ret;
 }
@@ -618,10 +649,7 @@ v3d_submit_tfu_ioctl(struct drm_device *
 	struct drm_v3d_submit_tfu *args = data;
 	struct v3d_tfu_job *job;
 	struct ww_acquire_ctx acquire_ctx;
-	struct drm_syncobj *sync_out;
-	struct dma_fence *sched_done_fence;
 	int ret = 0;
-	int bo_count;
 
 	trace_v3d_submit_tfu_ioctl(&v3d->drm, args->iia);
 
@@ -629,75 +657,66 @@ v3d_submit_tfu_ioctl(struct drm_device *
 	if (!job)
 		return -ENOMEM;
 
-	kref_init(&job->refcount);
-
-	ret = drm_syncobj_find_fence(file_priv, args->in_sync,
-				     0, &job->in_fence);
-	if (ret == -EINVAL)
-		goto fail;
+	ret = v3d_job_init(v3d, file_priv, &job->base,
+			   v3d_job_free, args->in_sync);
+	if (ret) {
+		kfree(job);
+		return ret;
+	}
 
+	job->base.bo = kcalloc(ARRAY_SIZE(args->bo_handles),
+			       sizeof(*job->base.bo), GFP_KERNEL);
 	job->args = *args;
-	job->v3d = v3d;
 
 	spin_lock(&file_priv->table_lock);
-	for (bo_count = 0; bo_count < ARRAY_SIZE(job->bo); bo_count++) {
+	for (job->base.bo_count = 0;
+	     job->base.bo_count < ARRAY_SIZE(args->bo_handles);
+	     job->base.bo_count++) {
 		struct drm_gem_object *bo;
 
-		if (!args->bo_handles[bo_count])
+		if (!args->bo_handles[job->base.bo_count])
 			break;
 
 		bo = idr_find(&file_priv->object_idr,
-			      args->bo_handles[bo_count]);
+			      args->bo_handles[job->base.bo_count]);
 		if (!bo) {
 			DRM_DEBUG("Failed to look up GEM BO %d: %d\n",
-				  bo_count, args->bo_handles[bo_count]);
+				  job->base.bo_count,
+				  args->bo_handles[job->base.bo_count]);
 			ret = -ENOENT;
 			spin_unlock(&file_priv->table_lock);
 			goto fail;
 		}
 		drm_gem_object_get(bo);
-		job->bo[bo_count] = to_v3d_bo(bo);
+		job->base.bo[job->base.bo_count] = to_v3d_bo(bo);
 	}
 	spin_unlock(&file_priv->table_lock);
 
-	ret = v3d_lock_bo_reservations(job->bo, bo_count, &acquire_ctx);
+	ret = v3d_lock_bo_reservations(job->base.bo, job->base.bo_count,
+				       &acquire_ctx);
 	if (ret)
 		goto fail;
 
 	mutex_lock(&v3d->sched_lock);
-	ret = drm_sched_job_init(&job->base,
-				 &v3d_priv->sched_entity[V3D_TFU],
-				 v3d_priv);
+	ret = v3d_push_job(v3d_priv, &job->base, V3D_TFU);
 	if (ret)
 		goto fail_unreserve;
-
-	sched_done_fence = dma_fence_get(&job->base.s_fence->finished);
-
-	kref_get(&job->refcount); /* put by scheduler job completion */
-	drm_sched_entity_push_job(&job->base, &v3d_priv->sched_entity[V3D_TFU]);
 	mutex_unlock(&v3d->sched_lock);
 
-	v3d_attach_object_fences(job->bo, bo_count, sched_done_fence);
-
-	v3d_unlock_bo_reservations(job->bo, bo_count, &acquire_ctx);
-
-	/* Update the return sync object */
-	sync_out = drm_syncobj_find(file_priv, args->out_sync);
-	if (sync_out) {
-		drm_syncobj_replace_fence(sync_out, sched_done_fence);
-		drm_syncobj_put(sync_out);
-	}
-	dma_fence_put(sched_done_fence);
+	v3d_attach_fences_and_unlock_reservation(file_priv,
+						 &job->base, &acquire_ctx,
+						 args->out_sync);
 
-	v3d_tfu_job_put(job);
+	v3d_job_put(&job->base);
 
 	return 0;
 
 fail_unreserve:
 	mutex_unlock(&v3d->sched_lock);
-	v3d_unlock_bo_reservations(job->bo, bo_count, &acquire_ctx);
+	v3d_unlock_bo_reservations(job->base.bo, job->base.bo_count,
+				   &acquire_ctx);
 fail:
-	v3d_tfu_job_put(job);
+	v3d_job_put(&job->base);
 
 	return ret;
 }
@@ -755,7 +774,7 @@ v3d_gem_destroy(struct drm_device *dev)
 
 	v3d_sched_fini(v3d);
 
-	/* Waiting for exec to finish would need to be done before
+	/* Waiting for jobs to finish would need to be done before
 	 * unregistering V3D.
 	 */
 	WARN_ON(v3d->bin_job);
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -60,7 +60,7 @@ v3d_overflow_mem_work(struct work_struct
 	}
 
 	drm_gem_object_get(&bo->base);
-	list_add_tail(&bo->unref_head, &v3d->bin_job->unref_list);
+	list_add_tail(&bo->unref_head, &v3d->bin_job->render->unref_list);
 	spin_unlock_irqrestore(&v3d->job_lock, irqflags);
 
 	V3D_CORE_WRITE(0, V3D_PTB_BPOA, bo->node.start << PAGE_SHIFT);
@@ -93,7 +93,7 @@ v3d_irq(int irq, void *arg)
 
 	if (intsts & V3D_INT_FLDONE) {
 		struct v3d_fence *fence =
-			to_v3d_fence(v3d->bin_job->bin.irq_fence);
+			to_v3d_fence(v3d->bin_job->base.irq_fence);
 
 		trace_v3d_bcl_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
@@ -102,7 +102,7 @@ v3d_irq(int irq, void *arg)
 
 	if (intsts & V3D_INT_FRDONE) {
 		struct v3d_fence *fence =
-			to_v3d_fence(v3d->render_job->render.irq_fence);
+			to_v3d_fence(v3d->render_job->base.irq_fence);
 
 		trace_v3d_rcl_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
@@ -138,7 +138,7 @@ v3d_hub_irq(int irq, void *arg)
 
 	if (intsts & V3D_HUB_INT_TFUC) {
 		struct v3d_fence *fence =
-			to_v3d_fence(v3d->tfu_job->irq_fence);
+			to_v3d_fence(v3d->tfu_job->base.irq_fence);
 
 		trace_v3d_tfu_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -30,39 +30,43 @@ to_v3d_job(struct drm_sched_job *sched_j
 	return container_of(sched_job, struct v3d_job, base);
 }
 
-static struct v3d_tfu_job *
-to_tfu_job(struct drm_sched_job *sched_job)
+static struct v3d_bin_job *
+to_bin_job(struct drm_sched_job *sched_job)
 {
-	return container_of(sched_job, struct v3d_tfu_job, base);
+	return container_of(sched_job, struct v3d_bin_job, base.base);
 }
 
-static void
-v3d_job_free(struct drm_sched_job *sched_job)
+static struct v3d_render_job *
+to_render_job(struct drm_sched_job *sched_job)
 {
-	struct v3d_job *job = to_v3d_job(sched_job);
+	return container_of(sched_job, struct v3d_render_job, base.base);
+}
 
-	v3d_exec_put(job->exec);
+static struct v3d_tfu_job *
+to_tfu_job(struct drm_sched_job *sched_job)
+{
+	return container_of(sched_job, struct v3d_tfu_job, base.base);
 }
 
 static void
-v3d_tfu_job_free(struct drm_sched_job *sched_job)
+v3d_job_free(struct drm_sched_job *sched_job)
 {
-	struct v3d_tfu_job *job = to_tfu_job(sched_job);
+	struct v3d_job *job = to_v3d_job(sched_job);
 
-	v3d_tfu_job_put(job);
+	v3d_job_put(job);
 }
 
 /**
- * Returns the fences that the bin or render job depends on, one by one.
- * v3d_job_run() won't be called until all of them have been signaled.
+ * Returns the fences that the job depends on, one by one.
+ *
+ * If placed in the scheduler's .dependency method, the corresponding
+ * .run_job won't be called until all of them have been signaled.
  */
 static struct dma_fence *
 v3d_job_dependency(struct drm_sched_job *sched_job,
 		   struct drm_sched_entity *s_entity)
 {
 	struct v3d_job *job = to_v3d_job(sched_job);
-	struct v3d_exec_info *exec = job->exec;
-	enum v3d_queue q = job == &exec->bin ? V3D_BIN : V3D_RENDER;
 	struct dma_fence *fence;
 
 	fence = job->in_fence;
@@ -71,113 +75,132 @@ v3d_job_dependency(struct drm_sched_job
 		return fence;
 	}
 
-	if (q == V3D_RENDER) {
-		/* If we had a bin job, the render job definitely depends on
-		 * it. We first have to wait for bin to be scheduled, so that
-		 * its done_fence is created.
-		 */
-		fence = exec->bin_done_fence;
-		if (fence) {
-			exec->bin_done_fence = NULL;
-			return fence;
-		}
-	}
-
-	/* XXX: Wait on a fence for switching the GMP if necessary,
-	 * and then do so.
-	 */
-
-	return fence;
+	return NULL;
 }
 
 /**
- * Returns the fences that the TFU job depends on, one by one.
- * v3d_tfu_job_run() won't be called until all of them have been
- * signaled.
+ * Returns the fences that the render job depends on, one by one.
+ * v3d_job_run() won't be called until all of them have been signaled.
  */
 static struct dma_fence *
-v3d_tfu_job_dependency(struct drm_sched_job *sched_job,
-		       struct drm_sched_entity *s_entity)
+v3d_render_job_dependency(struct drm_sched_job *sched_job,
+			  struct drm_sched_entity *s_entity)
 {
-	struct v3d_tfu_job *job = to_tfu_job(sched_job);
+	struct v3d_render_job *job = to_render_job(sched_job);
 	struct dma_fence *fence;
 
-	fence = job->in_fence;
+	fence = v3d_job_dependency(sched_job, s_entity);
+	if (fence)
+		return fence;
+
+	/* If we had a bin job, the render job definitely depends on
+	 * it. We first have to wait for bin to be scheduled, so that
+	 * its done_fence is created.
+	 */
+	fence = job->bin_done_fence;
 	if (fence) {
-		job->in_fence = NULL;
+		job->bin_done_fence = NULL;
 		return fence;
 	}
 
-	return NULL;
+	/* XXX: Wait on a fence for switching the GMP if necessary,
+	 * and then do so.
+	 */
+
+	return fence;
 }
 
-static struct dma_fence *v3d_job_run(struct drm_sched_job *sched_job)
+static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)
 {
-	struct v3d_job *job = to_v3d_job(sched_job);
-	struct v3d_exec_info *exec = job->exec;
-	enum v3d_queue q = job == &exec->bin ? V3D_BIN : V3D_RENDER;
-	struct v3d_dev *v3d = exec->v3d;
+	struct v3d_bin_job *job = to_bin_job(sched_job);
+	struct v3d_dev *v3d = job->base.v3d;
 	struct drm_device *dev = &v3d->drm;
 	struct dma_fence *fence;
 	unsigned long irqflags;
 
-	if (unlikely(job->base.s_fence->finished.error))
+	if (unlikely(job->base.base.s_fence->finished.error))
 		return NULL;
 
 	/* Lock required around bin_job update vs
 	 * v3d_overflow_mem_work().
 	 */
 	spin_lock_irqsave(&v3d->job_lock, irqflags);
-	if (q == V3D_BIN) {
-		v3d->bin_job = job->exec;
+	v3d->bin_job = job;
+	/* Clear out the overflow allocation, so we don't
+	 * reuse the overflow attached to a previous job.
+	 */
+	V3D_CORE_WRITE(0, V3D_PTB_BPOS, 0);
+	spin_unlock_irqrestore(&v3d->job_lock, irqflags);
+
+	v3d_invalidate_caches(v3d);
 
-		/* Clear out the overflow allocation, so we don't
-		 * reuse the overflow attached to a previous job.
-		 */
-		V3D_CORE_WRITE(0, V3D_PTB_BPOS, 0);
-	} else {
-		v3d->render_job = job->exec;
+	fence = v3d_fence_create(v3d, V3D_BIN);
+	if (IS_ERR(fence))
+		return NULL;
+
+	if (job->base.irq_fence)
+		dma_fence_put(job->base.irq_fence);
+	job->base.irq_fence = dma_fence_get(fence);
+
+	trace_v3d_submit_cl(dev, false, to_v3d_fence(fence)->seqno,
+			    job->start, job->end);
+
+	/* Set the current and end address of the control list.
+	 * Writing the end register is what starts the job.
+	 */
+	if (job->qma) {
+		V3D_CORE_WRITE(0, V3D_CLE_CT0QMA, job->qma);
+		V3D_CORE_WRITE(0, V3D_CLE_CT0QMS, job->qms);
 	}
-	spin_unlock_irqrestore(&v3d->job_lock, irqflags);
+	if (job->qts) {
+		V3D_CORE_WRITE(0, V3D_CLE_CT0QTS,
+			       V3D_CLE_CT0QTS_ENABLE |
+			       job->qts);
+	}
+	V3D_CORE_WRITE(0, V3D_CLE_CT0QBA, job->start);
+	V3D_CORE_WRITE(0, V3D_CLE_CT0QEA, job->end);
+
+	return fence;
+}
+
+static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job)
+{
+	struct v3d_render_job *job = to_render_job(sched_job);
+	struct v3d_dev *v3d = job->base.v3d;
+	struct drm_device *dev = &v3d->drm;
+	struct dma_fence *fence;
+
+	if (unlikely(job->base.base.s_fence->finished.error))
+		return NULL;
 
-	/* Can we avoid this flush when q==RENDER?  We need to be
-	 * careful of scheduling, though -- imagine job0 rendering to
-	 * texture and job1 reading, and them being executed as bin0,
-	 * bin1, render0, render1, so that render1's flush at bin time
+	v3d->render_job = job;
+
+	/* Can we avoid this flush?  We need to be careful of
+	 * scheduling, though -- imagine job0 rendering to texture and
+	 * job1 reading, and them being executed as bin0, bin1,
+	 * render0, render1, so that render1's flush at bin time
 	 * wasn't enough.
 	 */
 	v3d_invalidate_caches(v3d);
 
-	fence = v3d_fence_create(v3d, q);
+	fence = v3d_fence_create(v3d, V3D_RENDER);
 	if (IS_ERR(fence))
 		return NULL;
 
-	if (job->irq_fence)
-		dma_fence_put(job->irq_fence);
-	job->irq_fence = dma_fence_get(fence);
+	if (job->base.irq_fence)
+		dma_fence_put(job->base.irq_fence);
+	job->base.irq_fence = dma_fence_get(fence);
 
-	trace_v3d_submit_cl(dev, q == V3D_RENDER, to_v3d_fence(fence)->seqno,
+	trace_v3d_submit_cl(dev, true, to_v3d_fence(fence)->seqno,
 			    job->start, job->end);
 
-	if (q == V3D_BIN) {
-		if (exec->qma) {
-			V3D_CORE_WRITE(0, V3D_CLE_CT0QMA, exec->qma);
-			V3D_CORE_WRITE(0, V3D_CLE_CT0QMS, exec->qms);
-		}
-		if (exec->qts) {
-			V3D_CORE_WRITE(0, V3D_CLE_CT0QTS,
-				       V3D_CLE_CT0QTS_ENABLE |
-				       exec->qts);
-		}
-	} else {
-		/* XXX: Set the QCFG */
-	}
+	/* XXX: Set the QCFG */
 
 	/* Set the current and end address of the control list.
 	 * Writing the end register is what starts the job.
 	 */
-	V3D_CORE_WRITE(0, V3D_CLE_CTNQBA(q), job->start);
-	V3D_CORE_WRITE(0, V3D_CLE_CTNQEA(q), job->end);
+	V3D_CORE_WRITE(0, V3D_CLE_CT1QBA, job->start);
+	V3D_CORE_WRITE(0, V3D_CLE_CT1QEA, job->end);
 
 	return fence;
 }
@@ -186,7 +209,7 @@ static struct dma_fence *
 v3d_tfu_job_run(struct drm_sched_job *sched_job)
 {
 	struct v3d_tfu_job *job = to_tfu_job(sched_job);
-	struct v3d_dev *v3d = job->v3d;
+	struct v3d_dev *v3d = job->base.v3d;
 	struct drm_device *dev = &v3d->drm;
 	struct dma_fence *fence;
 
@@ -195,9 +218,9 @@ v3d_tfu_job_run(struct drm_sched_job *sc
 		return NULL;
 
 	v3d->tfu_job = job;
-	if (job->irq_fence)
-		dma_fence_put(job->irq_fence);
-	job->irq_fence = dma_fence_get(fence);
+	if (job->base.irq_fence)
+		dma_fence_put(job->base.irq_fence);
+	job->base.irq_fence = dma_fence_get(fence);
 
 	trace_v3d_submit_tfu(dev, to_v3d_fence(fence)->seqno);
 
@@ -247,25 +270,23 @@ v3d_gpu_reset_for_timeout(struct v3d_dev
 	mutex_unlock(&v3d->reset_lock);
 }
 
+/* If the current address or return address have changed, then the GPU
+ * has probably made progress and we should delay the reset.  This
+ * could fail if the GPU got in an infinite loop in the CL, but that
+ * is pretty unlikely outside of an i-g-t testcase.
+ */
 static void
-v3d_job_timedout(struct drm_sched_job *sched_job)
+v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q,
+		      u32 *timedout_ctca, u32 *timedout_ctra)
 {
 	struct v3d_job *job = to_v3d_job(sched_job);
-	struct v3d_exec_info *exec = job->exec;
-	struct v3d_dev *v3d = exec->v3d;
-	enum v3d_queue job_q = job == &exec->bin ? V3D_BIN : V3D_RENDER;
-	u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(job_q));
-	u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(job_q));
-
-	/* If the current address or return address have changed, then
-	 * the GPU has probably made progress and we should delay the
-	 * reset.  This could fail if the GPU got in an infinite loop
-	 * in the CL, but that is pretty unlikely outside of an i-g-t
-	 * testcase.
-	 */
-	if (job->timedout_ctca != ctca || job->timedout_ctra != ctra) {
-		job->timedout_ctca = ctca;
-		job->timedout_ctra = ctra;
+	struct v3d_dev *v3d = job->v3d;
+	u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(q));
+	u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(q));
+
+	if (*timedout_ctca != ctca || *timedout_ctra != ctra) {
+		*timedout_ctca = ctca;
+		*timedout_ctra = ctra;
 		schedule_delayed_work(&job->base.work_tdr,
 				      job->base.sched->timeout);
 		return;
@@ -275,25 +296,50 @@ v3d_job_timedout(struct drm_sched_job *s
 }
 
 static void
+v3d_bin_job_timedout(struct drm_sched_job *sched_job)
+{
+	struct v3d_bin_job *job = to_bin_job(sched_job);
+
+	v3d_cl_job_timedout(sched_job, V3D_BIN,
+			    &job->timedout_ctca, &job->timedout_ctra);
+}
+
+static void
+v3d_render_job_timedout(struct drm_sched_job *sched_job)
+{
+	struct v3d_render_job *job = to_render_job(sched_job);
+
+	v3d_cl_job_timedout(sched_job, V3D_RENDER,
+			    &job->timedout_ctca, &job->timedout_ctra);
+}
+
+static void
 v3d_tfu_job_timedout(struct drm_sched_job *sched_job)
 {
-	struct v3d_tfu_job *job = to_tfu_job(sched_job);
+	struct v3d_job *job = to_v3d_job(sched_job);
 
 	v3d_gpu_reset_for_timeout(job->v3d, sched_job);
 }
 
-static const struct drm_sched_backend_ops v3d_sched_ops = {
+static const struct drm_sched_backend_ops v3d_bin_sched_ops = {
 	.dependency = v3d_job_dependency,
-	.run_job = v3d_job_run,
-	.timedout_job = v3d_job_timedout,
-	.free_job = v3d_job_free
+	.run_job = v3d_bin_job_run,
+	.timedout_job = v3d_bin_job_timedout,
+	.free_job = v3d_job_free,
+};
+
+static const struct drm_sched_backend_ops v3d_render_sched_ops = {
+	.dependency = v3d_render_job_dependency,
+	.run_job = v3d_render_job_run,
+	.timedout_job = v3d_render_job_timedout,
+	.free_job = v3d_job_free,
 };
 
 static const struct drm_sched_backend_ops v3d_tfu_sched_ops = {
-	.dependency = v3d_tfu_job_dependency,
+	.dependency = v3d_job_dependency,
 	.run_job = v3d_tfu_job_run,
 	.timedout_job = v3d_tfu_job_timedout,
-	.free_job = v3d_tfu_job_free
+	.free_job = v3d_job_free,
 };
 
 int
@@ -305,7 +351,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 	int ret;
 
 	ret = drm_sched_init(&v3d->queue[V3D_BIN].sched,
-			     &v3d_sched_ops,
+			     &v3d_bin_sched_ops,
 			     hw_jobs_limit, job_hang_limit,
 			     msecs_to_jiffies(hang_limit_ms),
 			     "v3d_bin");
@@ -315,7 +361,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 	}
 
 	ret = drm_sched_init(&v3d->queue[V3D_RENDER].sched,
-			     &v3d_sched_ops,
+			     &v3d_render_sched_ops,
 			     hw_jobs_limit, job_hang_limit,
 			     msecs_to_jiffies(hang_limit_ms),
 			     "v3d_render");