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
|
/*
* Copyright 2023 Advanced Micro Devices, Inc.
*
* 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.
*/
#include "kfd_debug.h"
#include "kfd_device_queue_manager.h"
#include <linux/file.h>
#include <uapi/linux/kfd_ioctl.h>
#define MAX_WATCH_ADDRESSES 4
void debug_event_write_work_handler(struct work_struct *work)
{
struct kfd_process *process;
static const char write_data = '.';
loff_t pos = 0;
process = container_of(work,
struct kfd_process,
debug_event_workarea);
kernel_write(process->dbg_ev_file, &write_data, 1, &pos);
}
/* update process/device/queue exception status, write to descriptor
* only if exception_status is enabled.
*/
bool kfd_dbg_ev_raise(uint64_t event_mask,
struct kfd_process *process, struct kfd_node *dev,
unsigned int source_id, bool use_worker,
void *exception_data, size_t exception_data_size)
{
struct process_queue_manager *pqm;
struct process_queue_node *pqn;
int i;
static const char write_data = '.';
loff_t pos = 0;
bool is_subscribed = true;
if (!(process && process->debug_trap_enabled))
return false;
mutex_lock(&process->event_mutex);
if (event_mask & KFD_EC_MASK_DEVICE) {
for (i = 0; i < process->n_pdds; i++) {
struct kfd_process_device *pdd = process->pdds[i];
if (pdd->dev != dev)
continue;
pdd->exception_status |= event_mask & KFD_EC_MASK_DEVICE;
if (event_mask & KFD_EC_MASK(EC_DEVICE_MEMORY_VIOLATION)) {
if (!pdd->vm_fault_exc_data) {
pdd->vm_fault_exc_data = kmemdup(
exception_data,
exception_data_size,
GFP_KERNEL);
if (!pdd->vm_fault_exc_data)
pr_debug("Failed to allocate exception data memory");
} else {
pr_debug("Debugger exception data not saved\n");
print_hex_dump_bytes("exception data: ",
DUMP_PREFIX_OFFSET,
exception_data,
exception_data_size);
}
}
break;
}
} else if (event_mask & KFD_EC_MASK_PROCESS) {
process->exception_status |= event_mask & KFD_EC_MASK_PROCESS;
} else {
pqm = &process->pqm;
list_for_each_entry(pqn, &pqm->queues,
process_queue_list) {
int target_id;
if (!pqn->q)
continue;
target_id = event_mask & KFD_EC_MASK(EC_QUEUE_NEW) ?
pqn->q->properties.queue_id :
pqn->q->doorbell_id;
if (pqn->q->device != dev || target_id != source_id)
continue;
pqn->q->properties.exception_status |= event_mask;
break;
}
}
if (process->exception_enable_mask & event_mask) {
if (use_worker)
schedule_work(&process->debug_event_workarea);
else
kernel_write(process->dbg_ev_file,
&write_data,
1,
&pos);
} else {
is_subscribed = false;
}
mutex_unlock(&process->event_mutex);
return is_subscribed;
}
/* set pending event queue entry from ring entry */
bool kfd_set_dbg_ev_from_interrupt(struct kfd_node *dev,
unsigned int pasid,
uint32_t doorbell_id,
uint64_t trap_mask,
void *exception_data,
size_t exception_data_size)
{
struct kfd_process *p;
bool signaled_to_debugger_or_runtime = false;
p = kfd_lookup_process_by_pasid(pasid);
if (!p)
return false;
if (!kfd_dbg_ev_raise(trap_mask, p, dev, doorbell_id, true,
exception_data, exception_data_size)) {
struct process_queue_manager *pqm;
struct process_queue_node *pqn;
if (!!(trap_mask & KFD_EC_MASK_QUEUE) &&
p->runtime_info.runtime_state == DEBUG_RUNTIME_STATE_ENABLED) {
mutex_lock(&p->mutex);
pqm = &p->pqm;
list_for_each_entry(pqn, &pqm->queues,
process_queue_list) {
if (!(pqn->q && pqn->q->device == dev &&
pqn->q->doorbell_id == doorbell_id))
continue;
kfd_send_exception_to_runtime(p, pqn->q->properties.queue_id,
trap_mask);
signaled_to_debugger_or_runtime = true;
break;
}
mutex_unlock(&p->mutex);
} else if (trap_mask & KFD_EC_MASK(EC_DEVICE_MEMORY_VIOLATION)) {
kfd_dqm_evict_pasid(dev->dqm, p->pasid);
kfd_signal_vm_fault_event(dev, p->pasid, NULL,
exception_data);
signaled_to_debugger_or_runtime = true;
}
} else {
signaled_to_debugger_or_runtime = true;
}
kfd_unref_process(p);
return signaled_to_debugger_or_runtime;
}
int kfd_dbg_send_exception_to_runtime(struct kfd_process *p,
unsigned int dev_id,
unsigned int queue_id,
uint64_t error_reason)
{
if (error_reason & KFD_EC_MASK(EC_DEVICE_MEMORY_VIOLATION)) {
struct kfd_process_device *pdd = NULL;
struct kfd_hsa_memory_exception_data *data;
int i;
for (i = 0; i < p->n_pdds; i++) {
if (p->pdds[i]->dev->id == dev_id) {
pdd = p->pdds[i];
break;
}
}
if (!pdd)
return -ENODEV;
data = (struct kfd_hsa_memory_exception_data *)
pdd->vm_fault_exc_data;
kfd_dqm_evict_pasid(pdd->dev->dqm, p->pasid);
kfd_signal_vm_fault_event(pdd->dev, p->pasid, NULL, data);
error_reason &= ~KFD_EC_MASK(EC_DEVICE_MEMORY_VIOLATION);
}
if (error_reason & (KFD_EC_MASK(EC_PROCESS_RUNTIME))) {
/*
* block should only happen after the debugger receives runtime
* enable notice.
*/
up(&p->runtime_enable_sema);
error_reason &= ~KFD_EC_MASK(EC_PROCESS_RUNTIME);
}
if (error_reason)
return kfd_send_exception_to_runtime(p, queue_id, error_reason);
return 0;
}
static int kfd_dbg_set_queue_workaround(struct queue *q, bool enable)
{
struct mqd_update_info minfo = {0};
int err;
if (!q)
return 0;
if (KFD_GC_VERSION(q->device) < IP_VERSION(11, 0, 0) ||
KFD_GC_VERSION(q->device) >= IP_VERSION(12, 0, 0))
return 0;
if (enable && q->properties.is_user_cu_masked)
return -EBUSY;
minfo.update_flag = enable ? UPDATE_FLAG_DBG_WA_ENABLE : UPDATE_FLAG_DBG_WA_DISABLE;
q->properties.is_dbg_wa = enable;
err = q->device->dqm->ops.update_queue(q->device->dqm, q, &minfo);
if (err)
q->properties.is_dbg_wa = false;
return err;
}
static int kfd_dbg_set_workaround(struct kfd_process *target, bool enable)
{
struct process_queue_manager *pqm = &target->pqm;
struct process_queue_node *pqn;
int r = 0;
list_for_each_entry(pqn, &pqm->queues, process_queue_list) {
r = kfd_dbg_set_queue_workaround(pqn->q, enable);
if (enable && r)
goto unwind;
}
return 0;
unwind:
list_for_each_entry(pqn, &pqm->queues, process_queue_list)
kfd_dbg_set_queue_workaround(pqn->q, false);
if (enable)
target->runtime_info.runtime_state = r == -EBUSY ?
DEBUG_RUNTIME_STATE_ENABLED_BUSY :
DEBUG_RUNTIME_STATE_ENABLED_ERROR;
return r;
}
int kfd_dbg_set_mes_debug_mode(struct kfd_process_device *pdd)
{
uint32_t spi_dbg_cntl = pdd->spi_dbg_override | pdd->spi_dbg_launch_mode;
uint32_t flags = pdd->process->dbg_flags;
if (!kfd_dbg_is_per_vmid_supported(pdd->dev))
return 0;
return amdgpu_mes_set_shader_debugger(pdd->dev->adev, pdd->proc_ctx_gpu_addr, spi_dbg_cntl,
pdd->watch_points, flags);
}
#define KFD_DEBUGGER_INVALID_WATCH_POINT_ID -1
static int kfd_dbg_get_dev_watch_id(struct kfd_process_device *pdd, int *watch_id)
{
int i;
*watch_id = KFD_DEBUGGER_INVALID_WATCH_POINT_ID;
spin_lock(&pdd->dev->kfd->watch_points_lock);
for (i = 0; i < MAX_WATCH_ADDRESSES; i++) {
/* device watchpoint in use so skip */
if ((pdd->dev->kfd->alloc_watch_ids >> i) & 0x1)
continue;
pdd->alloc_watch_ids |= 0x1 << i;
pdd->dev->kfd->alloc_watch_ids |= 0x1 << i;
*watch_id = i;
spin_unlock(&pdd->dev->kfd->watch_points_lock);
return 0;
}
spin_unlock(&pdd->dev->kfd->watch_points_lock);
return -ENOMEM;
}
static void kfd_dbg_clear_dev_watch_id(struct kfd_process_device *pdd, int watch_id)
{
spin_lock(&pdd->dev->kfd->watch_points_lock);
/* process owns device watch point so safe to clear */
if ((pdd->alloc_watch_ids >> watch_id) & 0x1) {
pdd->alloc_watch_ids &= ~(0x1 << watch_id);
pdd->dev->kfd->alloc_watch_ids &= ~(0x1 << watch_id);
}
spin_unlock(&pdd->dev->kfd->watch_points_lock);
}
static bool kfd_dbg_owns_dev_watch_id(struct kfd_process_device *pdd, int watch_id)
{
bool owns_watch_id = false;
spin_lock(&pdd->dev->kfd->watch_points_lock);
owns_watch_id = watch_id < MAX_WATCH_ADDRESSES &&
((pdd->alloc_watch_ids >> watch_id) & 0x1);
spin_unlock(&pdd->dev->kfd->watch_points_lock);
return owns_watch_id;
}
int kfd_dbg_trap_clear_dev_address_watch(struct kfd_process_device *pdd,
uint32_t watch_id)
{
int r;
if (!kfd_dbg_owns_dev_watch_id(pdd, watch_id))
return -EINVAL;
if (!pdd->dev->kfd->shared_resources.enable_mes) {
r = debug_lock_and_unmap(pdd->dev->dqm);
if (r)
return r;
}
amdgpu_gfx_off_ctrl(pdd->dev->adev, false);
pdd->watch_points[watch_id] = pdd->dev->kfd2kgd->clear_address_watch(
pdd->dev->adev,
watch_id);
amdgpu_gfx_off_ctrl(pdd->dev->adev, true);
if (!pdd->dev->kfd->shared_resources.enable_mes)
r = debug_map_and_unlock(pdd->dev->dqm);
else
r = kfd_dbg_set_mes_debug_mode(pdd);
kfd_dbg_clear_dev_watch_id(pdd, watch_id);
return r;
}
int kfd_dbg_trap_set_dev_address_watch(struct kfd_process_device *pdd,
uint64_t watch_address,
uint32_t watch_address_mask,
uint32_t *watch_id,
uint32_t watch_mode)
{
int r = kfd_dbg_get_dev_watch_id(pdd, watch_id);
if (r)
return r;
if (!pdd->dev->kfd->shared_resources.enable_mes) {
r = debug_lock_and_unmap(pdd->dev->dqm);
if (r) {
kfd_dbg_clear_dev_watch_id(pdd, *watch_id);
return r;
}
}
amdgpu_gfx_off_ctrl(pdd->dev->adev, false);
pdd->watch_points[*watch_id] = pdd->dev->kfd2kgd->set_address_watch(
pdd->dev->adev,
watch_address,
watch_address_mask,
*watch_id,
watch_mode,
pdd->dev->vm_info.last_vmid_kfd);
amdgpu_gfx_off_ctrl(pdd->dev->adev, true);
if (!pdd->dev->kfd->shared_resources.enable_mes)
r = debug_map_and_unlock(pdd->dev->dqm);
else
r = kfd_dbg_set_mes_debug_mode(pdd);
/* HWS is broken so no point in HW rollback but release the watchpoint anyways */
if (r)
kfd_dbg_clear_dev_watch_id(pdd, *watch_id);
return 0;
}
static void kfd_dbg_clear_process_address_watch(struct kfd_process *target)
{
int i, j;
for (i = 0; i < target->n_pdds; i++)
for (j = 0; j < MAX_WATCH_ADDRESSES; j++)
kfd_dbg_trap_clear_dev_address_watch(target->pdds[i], j);
}
int kfd_dbg_trap_set_flags(struct kfd_process *target, uint32_t *flags)
{
uint32_t prev_flags = target->dbg_flags;
int i, r = 0, rewind_count = 0;
for (i = 0; i < target->n_pdds; i++) {
if (!kfd_dbg_is_per_vmid_supported(target->pdds[i]->dev) &&
(*flags & KFD_DBG_TRAP_FLAG_SINGLE_MEM_OP)) {
*flags = prev_flags;
return -EACCES;
}
}
target->dbg_flags = *flags & KFD_DBG_TRAP_FLAG_SINGLE_MEM_OP;
*flags = prev_flags;
for (i = 0; i < target->n_pdds; i++) {
struct kfd_process_device *pdd = target->pdds[i];
if (!kfd_dbg_is_per_vmid_supported(pdd->dev))
continue;
if (!pdd->dev->kfd->shared_resources.enable_mes)
r = debug_refresh_runlist(pdd->dev->dqm);
else
r = kfd_dbg_set_mes_debug_mode(pdd);
if (r) {
target->dbg_flags = prev_flags;
break;
}
rewind_count++;
}
/* Rewind flags */
if (r) {
target->dbg_flags = prev_flags;
for (i = 0; i < rewind_count; i++) {
struct kfd_process_device *pdd = target->pdds[i];
if (!kfd_dbg_is_per_vmid_supported(pdd->dev))
continue;
if (!pdd->dev->kfd->shared_resources.enable_mes)
debug_refresh_runlist(pdd->dev->dqm);
else
kfd_dbg_set_mes_debug_mode(pdd);
}
}
return r;
}
/* kfd_dbg_trap_deactivate:
* target: target process
* unwind: If this is unwinding a failed kfd_dbg_trap_enable()
* unwind_count:
* If unwind == true, how far down the pdd list we need
* to unwind
* else: ignored
*/
void kfd_dbg_trap_deactivate(struct kfd_process *target, bool unwind, int unwind_count)
{
int i;
if (!unwind) {
uint32_t flags = 0;
cancel_work_sync(&target->debug_event_workarea);
kfd_dbg_clear_process_address_watch(target);
kfd_dbg_trap_set_wave_launch_mode(target, 0);
kfd_dbg_trap_set_flags(target, &flags);
}
for (i = 0; i < target->n_pdds; i++) {
struct kfd_process_device *pdd = target->pdds[i];
/* If this is an unwind, and we have unwound the required
* enable calls on the pdd list, we need to stop now
* otherwise we may mess up another debugger session.
*/
if (unwind && i == unwind_count)
break;
kfd_process_set_trap_debug_flag(&pdd->qpd, false);
/* GFX off is already disabled by debug activate if not RLC restore supported. */
if (kfd_dbg_is_rlc_restore_supported(pdd->dev))
amdgpu_gfx_off_ctrl(pdd->dev->adev, false);
pdd->spi_dbg_override =
pdd->dev->kfd2kgd->disable_debug_trap(
pdd->dev->adev,
target->runtime_info.ttmp_setup,
pdd->dev->vm_info.last_vmid_kfd);
amdgpu_gfx_off_ctrl(pdd->dev->adev, true);
if (!kfd_dbg_is_per_vmid_supported(pdd->dev) &&
release_debug_trap_vmid(pdd->dev->dqm, &pdd->qpd))
pr_err("Failed to release debug vmid on [%i]\n", pdd->dev->id);
if (!pdd->dev->kfd->shared_resources.enable_mes)
debug_refresh_runlist(pdd->dev->dqm);
else
kfd_dbg_set_mes_debug_mode(pdd);
}
kfd_dbg_set_workaround(target, false);
if (!unwind) {
int resume_count = resume_queues(target, 0, NULL);
if (resume_count)
pr_debug("Resumed %d queues\n", resume_count);
}
}
static void kfd_dbg_clean_exception_status(struct kfd_process *target)
{
struct process_queue_manager *pqm;
struct process_queue_node *pqn;
int i;
for (i = 0; i < target->n_pdds; i++) {
struct kfd_process_device *pdd = target->pdds[i];
kfd_process_drain_interrupts(pdd);
pdd->exception_status = 0;
}
pqm = &target->pqm;
list_for_each_entry(pqn, &pqm->queues, process_queue_list) {
if (!pqn->q)
continue;
pqn->q->properties.exception_status = 0;
}
target->exception_status = 0;
}
int kfd_dbg_trap_disable(struct kfd_process *target)
{
if (!target->debug_trap_enabled)
return 0;
/*
* Defer deactivation to runtime if runtime not enabled otherwise reset
* attached running target runtime state to enable for re-attach.
*/
if (target->runtime_info.runtime_state == DEBUG_RUNTIME_STATE_ENABLED)
kfd_dbg_trap_deactivate(target, false, 0);
else if (target->runtime_info.runtime_state != DEBUG_RUNTIME_STATE_DISABLED)
target->runtime_info.runtime_state = DEBUG_RUNTIME_STATE_ENABLED;
fput(target->dbg_ev_file);
target->dbg_ev_file = NULL;
if (target->debugger_process) {
atomic_dec(&target->debugger_process->debugged_process_count);
target->debugger_process = NULL;
}
target->debug_trap_enabled = false;
kfd_dbg_clean_exception_status(target);
kfd_unref_process(target);
return 0;
}
int kfd_dbg_trap_activate(struct kfd_process *target)
{
int i, r = 0;
r = kfd_dbg_set_workaround(target, true);
if (r)
return r;
for (i = 0; i < target->n_pdds; i++) {
struct kfd_process_device *pdd = target->pdds[i];
if (!kfd_dbg_is_per_vmid_supported(pdd->dev)) {
r = reserve_debug_trap_vmid(pdd->dev->dqm, &pdd->qpd);
if (r) {
target->runtime_info.runtime_state = (r == -EBUSY) ?
DEBUG_RUNTIME_STATE_ENABLED_BUSY :
DEBUG_RUNTIME_STATE_ENABLED_ERROR;
goto unwind_err;
}
}
/* Disable GFX OFF to prevent garbage read/writes to debug registers.
* If RLC restore of debug registers is not supported and runtime enable
* hasn't done so already on ttmp setup request, restore the trap config registers.
*
* If RLC restore of debug registers is not supported, keep gfx off disabled for
* the debug session.
*/
amdgpu_gfx_off_ctrl(pdd->dev->adev, false);
if (!(kfd_dbg_is_rlc_restore_supported(pdd->dev) ||
target->runtime_info.ttmp_setup))
pdd->dev->kfd2kgd->enable_debug_trap(pdd->dev->adev, true,
pdd->dev->vm_info.last_vmid_kfd);
pdd->spi_dbg_override = pdd->dev->kfd2kgd->enable_debug_trap(
pdd->dev->adev,
false,
pdd->dev->vm_info.last_vmid_kfd);
if (kfd_dbg_is_rlc_restore_supported(pdd->dev))
amdgpu_gfx_off_ctrl(pdd->dev->adev, true);
/*
* Setting the debug flag in the trap handler requires that the TMA has been
* allocated, which occurs during CWSR initialization.
* In the event that CWSR has not been initialized at this point, setting the
* flag will be called again during CWSR initialization if the target process
* is still debug enabled.
*/
kfd_process_set_trap_debug_flag(&pdd->qpd, true);
if (!pdd->dev->kfd->shared_resources.enable_mes)
r = debug_refresh_runlist(pdd->dev->dqm);
else
r = kfd_dbg_set_mes_debug_mode(pdd);
if (r) {
target->runtime_info.runtime_state =
DEBUG_RUNTIME_STATE_ENABLED_ERROR;
goto unwind_err;
}
}
return 0;
unwind_err:
/* Enabling debug failed, we need to disable on
* all GPUs so the enable is all or nothing.
*/
kfd_dbg_trap_deactivate(target, true, i);
return r;
}
int kfd_dbg_trap_enable(struct kfd_process *target, uint32_t fd,
void __user *runtime_info, uint32_t *runtime_size)
{
struct file *f;
uint32_t copy_size;
int i, r = 0;
if (target->debug_trap_enabled)
return -EALREADY;
/* Enable pre-checks */
for (i = 0; i < target->n_pdds; i++) {
struct kfd_process_device *pdd = target->pdds[i];
if (!KFD_IS_SOC15(pdd->dev))
return -ENODEV;
if (!kfd_dbg_has_gws_support(pdd->dev) && pdd->qpd.num_gws)
return -EBUSY;
}
copy_size = min((size_t)(*runtime_size), sizeof(target->runtime_info));
f = fget(fd);
if (!f) {
pr_err("Failed to get file for (%i)\n", fd);
return -EBADF;
}
target->dbg_ev_file = f;
/* defer activation to runtime if not runtime enabled */
if (target->runtime_info.runtime_state == DEBUG_RUNTIME_STATE_ENABLED)
kfd_dbg_trap_activate(target);
/* We already hold the process reference but hold another one for the
* debug session.
*/
kref_get(&target->ref);
target->debug_trap_enabled = true;
if (target->debugger_process)
atomic_inc(&target->debugger_process->debugged_process_count);
if (copy_to_user(runtime_info, (void *)&target->runtime_info, copy_size)) {
kfd_dbg_trap_deactivate(target, false, 0);
r = -EFAULT;
}
*runtime_size = sizeof(target->runtime_info);
return r;
}
static int kfd_dbg_validate_trap_override_request(struct kfd_process *p,
uint32_t trap_override,
uint32_t trap_mask_request,
uint32_t *trap_mask_supported)
{
int i = 0;
*trap_mask_supported = 0xffffffff;
for (i = 0; i < p->n_pdds; i++) {
struct kfd_process_device *pdd = p->pdds[i];
int err = pdd->dev->kfd2kgd->validate_trap_override_request(
pdd->dev->adev,
trap_override,
trap_mask_supported);
if (err)
return err;
}
if (trap_mask_request & ~*trap_mask_supported)
return -EACCES;
return 0;
}
int kfd_dbg_trap_set_wave_launch_override(struct kfd_process *target,
uint32_t trap_override,
uint32_t trap_mask_bits,
uint32_t trap_mask_request,
uint32_t *trap_mask_prev,
uint32_t *trap_mask_supported)
{
int r = 0, i;
r = kfd_dbg_validate_trap_override_request(target,
trap_override,
trap_mask_request,
trap_mask_supported);
if (r)
return r;
for (i = 0; i < target->n_pdds; i++) {
struct kfd_process_device *pdd = target->pdds[i];
amdgpu_gfx_off_ctrl(pdd->dev->adev, false);
pdd->spi_dbg_override = pdd->dev->kfd2kgd->set_wave_launch_trap_override(
pdd->dev->adev,
pdd->dev->vm_info.last_vmid_kfd,
trap_override,
trap_mask_bits,
trap_mask_request,
trap_mask_prev,
pdd->spi_dbg_override);
amdgpu_gfx_off_ctrl(pdd->dev->adev, true);
if (!pdd->dev->kfd->shared_resources.enable_mes)
r = debug_refresh_runlist(pdd->dev->dqm);
else
r = kfd_dbg_set_mes_debug_mode(pdd);
if (r)
break;
}
return r;
}
int kfd_dbg_trap_set_wave_launch_mode(struct kfd_process *target,
uint8_t wave_launch_mode)
{
int r = 0, i;
if (wave_launch_mode != KFD_DBG_TRAP_WAVE_LAUNCH_MODE_NORMAL &&
wave_launch_mode != KFD_DBG_TRAP_WAVE_LAUNCH_MODE_HALT &&
wave_launch_mode != KFD_DBG_TRAP_WAVE_LAUNCH_MODE_DEBUG)
return -EINVAL;
for (i = 0; i < target->n_pdds; i++) {
struct kfd_process_device *pdd = target->pdds[i];
amdgpu_gfx_off_ctrl(pdd->dev->adev, false);
pdd->spi_dbg_launch_mode = pdd->dev->kfd2kgd->set_wave_launch_mode(
pdd->dev->adev,
wave_launch_mode,
pdd->dev->vm_info.last_vmid_kfd);
amdgpu_gfx_off_ctrl(pdd->dev->adev, true);
if (!pdd->dev->kfd->shared_resources.enable_mes)
r = debug_refresh_runlist(pdd->dev->dqm);
else
r = kfd_dbg_set_mes_debug_mode(pdd);
if (r)
break;
}
return r;
}
void kfd_dbg_set_enabled_debug_exception_mask(struct kfd_process *target,
uint64_t exception_set_mask)
{
uint64_t found_mask = 0;
struct process_queue_manager *pqm;
struct process_queue_node *pqn;
static const char write_data = '.';
loff_t pos = 0;
int i;
mutex_lock(&target->event_mutex);
found_mask |= target->exception_status;
pqm = &target->pqm;
list_for_each_entry(pqn, &pqm->queues, process_queue_list) {
if (!pqn)
continue;
found_mask |= pqn->q->properties.exception_status;
}
for (i = 0; i < target->n_pdds; i++) {
struct kfd_process_device *pdd = target->pdds[i];
found_mask |= pdd->exception_status;
}
if (exception_set_mask & found_mask)
kernel_write(target->dbg_ev_file, &write_data, 1, &pos);
target->exception_enable_mask = exception_set_mask;
mutex_unlock(&target->event_mutex);
}
|