forked from grate-driver/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
remoteproc_core.c
1620 lines (1365 loc) · 42.7 KB
/
remoteproc_core.c
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
/*
* Remote Processor Framework
*
* Copyright (C) 2011 Texas Instruments, Inc.
* Copyright (C) 2011 Google, Inc.
*
* Ohad Ben-Cohen <ohad@wizery.com>
* Brian Swetland <swetland@google.com>
* Mark Grosen <mgrosen@ti.com>
* Fernando Guzman Lugo <fernando.lugo@ti.com>
* Suman Anna <s-anna@ti.com>
* Robert Tivy <rtivy@ti.com>
* Armando Uribe De Leon <x0095078@ti.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* version 2 as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
#define pr_fmt(fmt) "%s: " fmt, __func__
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/slab.h>
#include <linux/mutex.h>
#include <linux/dma-mapping.h>
#include <linux/firmware.h>
#include <linux/string.h>
#include <linux/debugfs.h>
#include <linux/remoteproc.h>
#include <linux/iommu.h>
#include <linux/idr.h>
#include <linux/elf.h>
#include <linux/crc32.h>
#include <linux/virtio_ids.h>
#include <linux/virtio_ring.h>
#include <asm/byteorder.h>
#include "remoteproc_internal.h"
static DEFINE_MUTEX(rproc_list_mutex);
static LIST_HEAD(rproc_list);
typedef int (*rproc_handle_resources_t)(struct rproc *rproc,
struct resource_table *table, int len);
typedef int (*rproc_handle_resource_t)(struct rproc *rproc,
void *, int offset, int avail);
/* Unique indices for remoteproc devices */
static DEFINE_IDA(rproc_dev_index);
static const char * const rproc_crash_names[] = {
[RPROC_MMUFAULT] = "mmufault",
[RPROC_WATCHDOG] = "watchdog",
[RPROC_FATAL_ERROR] = "fatal error",
};
/* translate rproc_crash_type to string */
static const char *rproc_crash_to_string(enum rproc_crash_type type)
{
if (type < ARRAY_SIZE(rproc_crash_names))
return rproc_crash_names[type];
return "unknown";
}
/*
* This is the IOMMU fault handler we register with the IOMMU API
* (when relevant; not all remote processors access memory through
* an IOMMU).
*
* IOMMU core will invoke this handler whenever the remote processor
* will try to access an unmapped device address.
*/
static int rproc_iommu_fault(struct iommu_domain *domain, struct device *dev,
unsigned long iova, int flags, void *token)
{
struct rproc *rproc = token;
dev_err(dev, "iommu fault: da 0x%lx flags 0x%x\n", iova, flags);
rproc_report_crash(rproc, RPROC_MMUFAULT);
/*
* Let the iommu core know we're not really handling this fault;
* we just used it as a recovery trigger.
*/
return -ENOSYS;
}
static int rproc_enable_iommu(struct rproc *rproc)
{
struct iommu_domain *domain;
struct device *dev = rproc->dev.parent;
int ret;
if (!rproc->has_iommu) {
dev_dbg(dev, "iommu not present\n");
return 0;
}
domain = iommu_domain_alloc(dev->bus);
if (!domain) {
dev_err(dev, "can't alloc iommu domain\n");
return -ENOMEM;
}
iommu_set_fault_handler(domain, rproc_iommu_fault, rproc);
ret = iommu_attach_device(domain, dev);
if (ret) {
dev_err(dev, "can't attach iommu device: %d\n", ret);
goto free_domain;
}
rproc->domain = domain;
return 0;
free_domain:
iommu_domain_free(domain);
return ret;
}
static void rproc_disable_iommu(struct rproc *rproc)
{
struct iommu_domain *domain = rproc->domain;
struct device *dev = rproc->dev.parent;
if (!domain)
return;
iommu_detach_device(domain, dev);
iommu_domain_free(domain);
}
/**
* rproc_da_to_va() - lookup the kernel virtual address for a remoteproc address
* @rproc: handle of a remote processor
* @da: remoteproc device address to translate
* @len: length of the memory region @da is pointing to
*
* Some remote processors will ask us to allocate them physically contiguous
* memory regions (which we call "carveouts"), and map them to specific
* device addresses (which are hardcoded in the firmware). They may also have
* dedicated memory regions internal to the processors, and use them either
* exclusively or alongside carveouts.
*
* They may then ask us to copy objects into specific device addresses (e.g.
* code/data sections) or expose us certain symbols in other device address
* (e.g. their trace buffer).
*
* This function is a helper function with which we can go over the allocated
* carveouts and translate specific device addresses to kernel virtual addresses
* so we can access the referenced memory. This function also allows to perform
* translations on the internal remoteproc memory regions through a platform
* implementation specific da_to_va ops, if present.
*
* The function returns a valid kernel address on success or NULL on failure.
*
* Note: phys_to_virt(iommu_iova_to_phys(rproc->domain, da)) will work too,
* but only on kernel direct mapped RAM memory. Instead, we're just using
* here the output of the DMA API for the carveouts, which should be more
* correct.
*/
void *rproc_da_to_va(struct rproc *rproc, u64 da, int len)
{
struct rproc_mem_entry *carveout;
void *ptr = NULL;
if (rproc->ops->da_to_va) {
ptr = rproc->ops->da_to_va(rproc, da, len);
if (ptr)
goto out;
}
list_for_each_entry(carveout, &rproc->carveouts, node) {
int offset = da - carveout->da;
/* try next carveout if da is too small */
if (offset < 0)
continue;
/* try next carveout if da is too large */
if (offset + len > carveout->len)
continue;
ptr = carveout->va + offset;
break;
}
out:
return ptr;
}
EXPORT_SYMBOL(rproc_da_to_va);
int rproc_alloc_vring(struct rproc_vdev *rvdev, int i)
{
struct rproc *rproc = rvdev->rproc;
struct device *dev = &rproc->dev;
struct rproc_vring *rvring = &rvdev->vring[i];
struct fw_rsc_vdev *rsc;
dma_addr_t dma;
void *va;
int ret, size, notifyid;
/* actual size of vring (in bytes) */
size = PAGE_ALIGN(vring_size(rvring->len, rvring->align));
/*
* Allocate non-cacheable memory for the vring. In the future
* this call will also configure the IOMMU for us
*/
va = dma_alloc_coherent(dev->parent, size, &dma, GFP_KERNEL);
if (!va) {
dev_err(dev->parent, "dma_alloc_coherent failed\n");
return -EINVAL;
}
/*
* Assign an rproc-wide unique index for this vring
* TODO: assign a notifyid for rvdev updates as well
* TODO: support predefined notifyids (via resource table)
*/
ret = idr_alloc(&rproc->notifyids, rvring, 0, 0, GFP_KERNEL);
if (ret < 0) {
dev_err(dev, "idr_alloc failed: %d\n", ret);
dma_free_coherent(dev->parent, size, va, dma);
return ret;
}
notifyid = ret;
/* Potentially bump max_notifyid */
if (notifyid > rproc->max_notifyid)
rproc->max_notifyid = notifyid;
dev_dbg(dev, "vring%d: va %p dma %pad size 0x%x idr %d\n",
i, va, &dma, size, notifyid);
rvring->va = va;
rvring->dma = dma;
rvring->notifyid = notifyid;
/*
* Let the rproc know the notifyid and da of this vring.
* Not all platforms use dma_alloc_coherent to automatically
* set up the iommu. In this case the device address (da) will
* hold the physical address and not the device address.
*/
rsc = (void *)rproc->table_ptr + rvdev->rsc_offset;
rsc->vring[i].da = dma;
rsc->vring[i].notifyid = notifyid;
return 0;
}
static int
rproc_parse_vring(struct rproc_vdev *rvdev, struct fw_rsc_vdev *rsc, int i)
{
struct rproc *rproc = rvdev->rproc;
struct device *dev = &rproc->dev;
struct fw_rsc_vdev_vring *vring = &rsc->vring[i];
struct rproc_vring *rvring = &rvdev->vring[i];
dev_dbg(dev, "vdev rsc: vring%d: da 0x%x, qsz %d, align %d\n",
i, vring->da, vring->num, vring->align);
/* verify queue size and vring alignment are sane */
if (!vring->num || !vring->align) {
dev_err(dev, "invalid qsz (%d) or alignment (%d)\n",
vring->num, vring->align);
return -EINVAL;
}
rvring->len = vring->num;
rvring->align = vring->align;
rvring->rvdev = rvdev;
return 0;
}
void rproc_free_vring(struct rproc_vring *rvring)
{
int size = PAGE_ALIGN(vring_size(rvring->len, rvring->align));
struct rproc *rproc = rvring->rvdev->rproc;
int idx = rvring->rvdev->vring - rvring;
struct fw_rsc_vdev *rsc;
dma_free_coherent(rproc->dev.parent, size, rvring->va, rvring->dma);
idr_remove(&rproc->notifyids, rvring->notifyid);
/* reset resource entry info */
rsc = (void *)rproc->table_ptr + rvring->rvdev->rsc_offset;
rsc->vring[idx].da = 0;
rsc->vring[idx].notifyid = -1;
}
static int rproc_vdev_do_probe(struct rproc_subdev *subdev)
{
struct rproc_vdev *rvdev = container_of(subdev, struct rproc_vdev, subdev);
return rproc_add_virtio_dev(rvdev, rvdev->id);
}
static void rproc_vdev_do_remove(struct rproc_subdev *subdev)
{
struct rproc_vdev *rvdev = container_of(subdev, struct rproc_vdev, subdev);
rproc_remove_virtio_dev(rvdev);
}
/**
* rproc_handle_vdev() - handle a vdev fw resource
* @rproc: the remote processor
* @rsc: the vring resource descriptor
* @avail: size of available data (for sanity checking the image)
*
* This resource entry requests the host to statically register a virtio
* device (vdev), and setup everything needed to support it. It contains
* everything needed to make it possible: the virtio device id, virtio
* device features, vrings information, virtio config space, etc...
*
* Before registering the vdev, the vrings are allocated from non-cacheable
* physically contiguous memory. Currently we only support two vrings per
* remote processor (temporary limitation). We might also want to consider
* doing the vring allocation only later when ->find_vqs() is invoked, and
* then release them upon ->del_vqs().
*
* Note: @da is currently not really handled correctly: we dynamically
* allocate it using the DMA API, ignoring requested hard coded addresses,
* and we don't take care of any required IOMMU programming. This is all
* going to be taken care of when the generic iommu-based DMA API will be
* merged. Meanwhile, statically-addressed iommu-based firmware images should
* use RSC_DEVMEM resource entries to map their required @da to the physical
* address of their base CMA region (ouch, hacky!).
*
* Returns 0 on success, or an appropriate error code otherwise
*/
static int rproc_handle_vdev(struct rproc *rproc, struct fw_rsc_vdev *rsc,
int offset, int avail)
{
struct device *dev = &rproc->dev;
struct rproc_vdev *rvdev;
int i, ret;
/* make sure resource isn't truncated */
if (sizeof(*rsc) + rsc->num_of_vrings * sizeof(struct fw_rsc_vdev_vring)
+ rsc->config_len > avail) {
dev_err(dev, "vdev rsc is truncated\n");
return -EINVAL;
}
/* make sure reserved bytes are zeroes */
if (rsc->reserved[0] || rsc->reserved[1]) {
dev_err(dev, "vdev rsc has non zero reserved bytes\n");
return -EINVAL;
}
dev_dbg(dev, "vdev rsc: id %d, dfeatures 0x%x, cfg len %d, %d vrings\n",
rsc->id, rsc->dfeatures, rsc->config_len, rsc->num_of_vrings);
/* we currently support only two vrings per rvdev */
if (rsc->num_of_vrings > ARRAY_SIZE(rvdev->vring)) {
dev_err(dev, "too many vrings: %d\n", rsc->num_of_vrings);
return -EINVAL;
}
rvdev = kzalloc(sizeof(*rvdev), GFP_KERNEL);
if (!rvdev)
return -ENOMEM;
kref_init(&rvdev->refcount);
rvdev->id = rsc->id;
rvdev->rproc = rproc;
/* parse the vrings */
for (i = 0; i < rsc->num_of_vrings; i++) {
ret = rproc_parse_vring(rvdev, rsc, i);
if (ret)
goto free_rvdev;
}
/* remember the resource offset*/
rvdev->rsc_offset = offset;
/* allocate the vring resources */
for (i = 0; i < rsc->num_of_vrings; i++) {
ret = rproc_alloc_vring(rvdev, i);
if (ret)
goto unwind_vring_allocations;
}
list_add_tail(&rvdev->node, &rproc->rvdevs);
rproc_add_subdev(rproc, &rvdev->subdev,
rproc_vdev_do_probe, rproc_vdev_do_remove);
return 0;
unwind_vring_allocations:
for (i--; i >= 0; i--)
rproc_free_vring(&rvdev->vring[i]);
free_rvdev:
kfree(rvdev);
return ret;
}
void rproc_vdev_release(struct kref *ref)
{
struct rproc_vdev *rvdev = container_of(ref, struct rproc_vdev, refcount);
struct rproc_vring *rvring;
struct rproc *rproc = rvdev->rproc;
int id;
for (id = 0; id < ARRAY_SIZE(rvdev->vring); id++) {
rvring = &rvdev->vring[id];
if (!rvring->va)
continue;
rproc_free_vring(rvring);
}
rproc_remove_subdev(rproc, &rvdev->subdev);
list_del(&rvdev->node);
kfree(rvdev);
}
/**
* rproc_handle_trace() - handle a shared trace buffer resource
* @rproc: the remote processor
* @rsc: the trace resource descriptor
* @avail: size of available data (for sanity checking the image)
*
* In case the remote processor dumps trace logs into memory,
* export it via debugfs.
*
* Currently, the 'da' member of @rsc should contain the device address
* where the remote processor is dumping the traces. Later we could also
* support dynamically allocating this address using the generic
* DMA API (but currently there isn't a use case for that).
*
* Returns 0 on success, or an appropriate error code otherwise
*/
static int rproc_handle_trace(struct rproc *rproc, struct fw_rsc_trace *rsc,
int offset, int avail)
{
struct rproc_mem_entry *trace;
struct device *dev = &rproc->dev;
void *ptr;
char name[15];
if (sizeof(*rsc) > avail) {
dev_err(dev, "trace rsc is truncated\n");
return -EINVAL;
}
/* make sure reserved bytes are zeroes */
if (rsc->reserved) {
dev_err(dev, "trace rsc has non zero reserved bytes\n");
return -EINVAL;
}
/* what's the kernel address of this resource ? */
ptr = rproc_da_to_va(rproc, rsc->da, rsc->len);
if (!ptr) {
dev_err(dev, "erroneous trace resource entry\n");
return -EINVAL;
}
trace = kzalloc(sizeof(*trace), GFP_KERNEL);
if (!trace)
return -ENOMEM;
/* set the trace buffer dma properties */
trace->len = rsc->len;
trace->va = ptr;
/* make sure snprintf always null terminates, even if truncating */
snprintf(name, sizeof(name), "trace%d", rproc->num_traces);
/* create the debugfs entry */
trace->priv = rproc_create_trace_file(name, rproc, trace);
if (!trace->priv) {
trace->va = NULL;
kfree(trace);
return -EINVAL;
}
list_add_tail(&trace->node, &rproc->traces);
rproc->num_traces++;
dev_dbg(dev, "%s added: va %p, da 0x%x, len 0x%x\n",
name, ptr, rsc->da, rsc->len);
return 0;
}
/**
* rproc_handle_devmem() - handle devmem resource entry
* @rproc: remote processor handle
* @rsc: the devmem resource entry
* @avail: size of available data (for sanity checking the image)
*
* Remote processors commonly need to access certain on-chip peripherals.
*
* Some of these remote processors access memory via an iommu device,
* and might require us to configure their iommu before they can access
* the on-chip peripherals they need.
*
* This resource entry is a request to map such a peripheral device.
*
* These devmem entries will contain the physical address of the device in
* the 'pa' member. If a specific device address is expected, then 'da' will
* contain it (currently this is the only use case supported). 'len' will
* contain the size of the physical region we need to map.
*
* Currently we just "trust" those devmem entries to contain valid physical
* addresses, but this is going to change: we want the implementations to
* tell us ranges of physical addresses the firmware is allowed to request,
* and not allow firmwares to request access to physical addresses that
* are outside those ranges.
*/
static int rproc_handle_devmem(struct rproc *rproc, struct fw_rsc_devmem *rsc,
int offset, int avail)
{
struct rproc_mem_entry *mapping;
struct device *dev = &rproc->dev;
int ret;
/* no point in handling this resource without a valid iommu domain */
if (!rproc->domain)
return -EINVAL;
if (sizeof(*rsc) > avail) {
dev_err(dev, "devmem rsc is truncated\n");
return -EINVAL;
}
/* make sure reserved bytes are zeroes */
if (rsc->reserved) {
dev_err(dev, "devmem rsc has non zero reserved bytes\n");
return -EINVAL;
}
mapping = kzalloc(sizeof(*mapping), GFP_KERNEL);
if (!mapping)
return -ENOMEM;
ret = iommu_map(rproc->domain, rsc->da, rsc->pa, rsc->len, rsc->flags);
if (ret) {
dev_err(dev, "failed to map devmem: %d\n", ret);
goto out;
}
/*
* We'll need this info later when we'll want to unmap everything
* (e.g. on shutdown).
*
* We can't trust the remote processor not to change the resource
* table, so we must maintain this info independently.
*/
mapping->da = rsc->da;
mapping->len = rsc->len;
list_add_tail(&mapping->node, &rproc->mappings);
dev_dbg(dev, "mapped devmem pa 0x%x, da 0x%x, len 0x%x\n",
rsc->pa, rsc->da, rsc->len);
return 0;
out:
kfree(mapping);
return ret;
}
/**
* rproc_handle_carveout() - handle phys contig memory allocation requests
* @rproc: rproc handle
* @rsc: the resource entry
* @avail: size of available data (for image validation)
*
* This function will handle firmware requests for allocation of physically
* contiguous memory regions.
*
* These request entries should come first in the firmware's resource table,
* as other firmware entries might request placing other data objects inside
* these memory regions (e.g. data/code segments, trace resource entries, ...).
*
* Allocating memory this way helps utilizing the reserved physical memory
* (e.g. CMA) more efficiently, and also minimizes the number of TLB entries
* needed to map it (in case @rproc is using an IOMMU). Reducing the TLB
* pressure is important; it may have a substantial impact on performance.
*/
static int rproc_handle_carveout(struct rproc *rproc,
struct fw_rsc_carveout *rsc,
int offset, int avail)
{
struct rproc_mem_entry *carveout, *mapping;
struct device *dev = &rproc->dev;
dma_addr_t dma;
void *va;
int ret;
if (sizeof(*rsc) > avail) {
dev_err(dev, "carveout rsc is truncated\n");
return -EINVAL;
}
/* make sure reserved bytes are zeroes */
if (rsc->reserved) {
dev_err(dev, "carveout rsc has non zero reserved bytes\n");
return -EINVAL;
}
dev_dbg(dev, "carveout rsc: name: %s, da 0x%x, pa 0x%x, len 0x%x, flags 0x%x\n",
rsc->name, rsc->da, rsc->pa, rsc->len, rsc->flags);
carveout = kzalloc(sizeof(*carveout), GFP_KERNEL);
if (!carveout)
return -ENOMEM;
va = dma_alloc_coherent(dev->parent, rsc->len, &dma, GFP_KERNEL);
if (!va) {
dev_err(dev->parent,
"failed to allocate dma memory: len 0x%x\n", rsc->len);
ret = -ENOMEM;
goto free_carv;
}
dev_dbg(dev, "carveout va %p, dma %pad, len 0x%x\n",
va, &dma, rsc->len);
/*
* Ok, this is non-standard.
*
* Sometimes we can't rely on the generic iommu-based DMA API
* to dynamically allocate the device address and then set the IOMMU
* tables accordingly, because some remote processors might
* _require_ us to use hard coded device addresses that their
* firmware was compiled with.
*
* In this case, we must use the IOMMU API directly and map
* the memory to the device address as expected by the remote
* processor.
*
* Obviously such remote processor devices should not be configured
* to use the iommu-based DMA API: we expect 'dma' to contain the
* physical address in this case.
*/
if (rproc->domain) {
mapping = kzalloc(sizeof(*mapping), GFP_KERNEL);
if (!mapping) {
ret = -ENOMEM;
goto dma_free;
}
ret = iommu_map(rproc->domain, rsc->da, dma, rsc->len,
rsc->flags);
if (ret) {
dev_err(dev, "iommu_map failed: %d\n", ret);
goto free_mapping;
}
/*
* We'll need this info later when we'll want to unmap
* everything (e.g. on shutdown).
*
* We can't trust the remote processor not to change the
* resource table, so we must maintain this info independently.
*/
mapping->da = rsc->da;
mapping->len = rsc->len;
list_add_tail(&mapping->node, &rproc->mappings);
dev_dbg(dev, "carveout mapped 0x%x to %pad\n",
rsc->da, &dma);
}
/*
* Some remote processors might need to know the pa
* even though they are behind an IOMMU. E.g., OMAP4's
* remote M3 processor needs this so it can control
* on-chip hardware accelerators that are not behind
* the IOMMU, and therefor must know the pa.
*
* Generally we don't want to expose physical addresses
* if we don't have to (remote processors are generally
* _not_ trusted), so we might want to do this only for
* remote processor that _must_ have this (e.g. OMAP4's
* dual M3 subsystem).
*
* Non-IOMMU processors might also want to have this info.
* In this case, the device address and the physical address
* are the same.
*/
rsc->pa = dma;
carveout->va = va;
carveout->len = rsc->len;
carveout->dma = dma;
carveout->da = rsc->da;
list_add_tail(&carveout->node, &rproc->carveouts);
return 0;
free_mapping:
kfree(mapping);
dma_free:
dma_free_coherent(dev->parent, rsc->len, va, dma);
free_carv:
kfree(carveout);
return ret;
}
/*
* A lookup table for resource handlers. The indices are defined in
* enum fw_resource_type.
*/
static rproc_handle_resource_t rproc_loading_handlers[RSC_LAST] = {
[RSC_CARVEOUT] = (rproc_handle_resource_t)rproc_handle_carveout,
[RSC_DEVMEM] = (rproc_handle_resource_t)rproc_handle_devmem,
[RSC_TRACE] = (rproc_handle_resource_t)rproc_handle_trace,
[RSC_VDEV] = (rproc_handle_resource_t)rproc_handle_vdev,
};
/* handle firmware resource entries before booting the remote processor */
static int rproc_handle_resources(struct rproc *rproc,
rproc_handle_resource_t handlers[RSC_LAST])
{
struct device *dev = &rproc->dev;
rproc_handle_resource_t handler;
int ret = 0, i;
if (!rproc->table_ptr)
return 0;
for (i = 0; i < rproc->table_ptr->num; i++) {
int offset = rproc->table_ptr->offset[i];
struct fw_rsc_hdr *hdr = (void *)rproc->table_ptr + offset;
int avail = rproc->table_sz - offset - sizeof(*hdr);
void *rsc = (void *)hdr + sizeof(*hdr);
/* make sure table isn't truncated */
if (avail < 0) {
dev_err(dev, "rsc table is truncated\n");
return -EINVAL;
}
dev_dbg(dev, "rsc: type %d\n", hdr->type);
if (hdr->type >= RSC_LAST) {
dev_warn(dev, "unsupported resource %d\n", hdr->type);
continue;
}
handler = handlers[hdr->type];
if (!handler)
continue;
ret = handler(rproc, rsc, offset + sizeof(*hdr), avail);
if (ret)
break;
}
return ret;
}
static int rproc_probe_subdevices(struct rproc *rproc)
{
struct rproc_subdev *subdev;
int ret;
list_for_each_entry(subdev, &rproc->subdevs, node) {
ret = subdev->probe(subdev);
if (ret)
goto unroll_registration;
}
return 0;
unroll_registration:
list_for_each_entry_continue_reverse(subdev, &rproc->subdevs, node)
subdev->remove(subdev);
return ret;
}
static void rproc_remove_subdevices(struct rproc *rproc)
{
struct rproc_subdev *subdev;
list_for_each_entry_reverse(subdev, &rproc->subdevs, node)
subdev->remove(subdev);
}
/**
* rproc_resource_cleanup() - clean up and free all acquired resources
* @rproc: rproc handle
*
* This function will free all resources acquired for @rproc, and it
* is called whenever @rproc either shuts down or fails to boot.
*/
static void rproc_resource_cleanup(struct rproc *rproc)
{
struct rproc_mem_entry *entry, *tmp;
struct rproc_vdev *rvdev, *rvtmp;
struct device *dev = &rproc->dev;
/* clean up debugfs trace entries */
list_for_each_entry_safe(entry, tmp, &rproc->traces, node) {
rproc_remove_trace_file(entry->priv);
rproc->num_traces--;
list_del(&entry->node);
kfree(entry);
}
/* clean up iommu mapping entries */
list_for_each_entry_safe(entry, tmp, &rproc->mappings, node) {
size_t unmapped;
unmapped = iommu_unmap(rproc->domain, entry->da, entry->len);
if (unmapped != entry->len) {
/* nothing much to do besides complaining */
dev_err(dev, "failed to unmap %u/%zu\n", entry->len,
unmapped);
}
list_del(&entry->node);
kfree(entry);
}
/* clean up carveout allocations */
list_for_each_entry_safe(entry, tmp, &rproc->carveouts, node) {
dma_free_coherent(dev->parent, entry->len, entry->va,
entry->dma);
list_del(&entry->node);
kfree(entry);
}
/* clean up remote vdev entries */
list_for_each_entry_safe(rvdev, rvtmp, &rproc->rvdevs, node)
kref_put(&rvdev->refcount, rproc_vdev_release);
}
static int rproc_start(struct rproc *rproc, const struct firmware *fw)
{
struct resource_table *loaded_table;
struct device *dev = &rproc->dev;
int ret;
/* load the ELF segments to memory */
ret = rproc_load_segments(rproc, fw);
if (ret) {
dev_err(dev, "Failed to load program segments: %d\n", ret);
return ret;
}
/*
* The starting device has been given the rproc->cached_table as the
* resource table. The address of the vring along with the other
* allocated resources (carveouts etc) is stored in cached_table.
* In order to pass this information to the remote device we must copy
* this information to device memory. We also update the table_ptr so
* that any subsequent changes will be applied to the loaded version.
*/
loaded_table = rproc_find_loaded_rsc_table(rproc, fw);
if (loaded_table) {
memcpy(loaded_table, rproc->cached_table, rproc->table_sz);
rproc->table_ptr = loaded_table;
}
/* power up the remote processor */
ret = rproc->ops->start(rproc);
if (ret) {
dev_err(dev, "can't start rproc %s: %d\n", rproc->name, ret);
return ret;
}
/* probe any subdevices for the remote processor */
ret = rproc_probe_subdevices(rproc);
if (ret) {
dev_err(dev, "failed to probe subdevices for %s: %d\n",
rproc->name, ret);
rproc->ops->stop(rproc);
return ret;
}
rproc->state = RPROC_RUNNING;
dev_info(dev, "remote processor %s is now up\n", rproc->name);
return 0;
}
/*
* take a firmware and boot a remote processor with it.
*/
static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw)
{
struct device *dev = &rproc->dev;
const char *name = rproc->firmware;
int ret;
ret = rproc_fw_sanity_check(rproc, fw);
if (ret)
return ret;
dev_info(dev, "Booting fw image %s, size %zd\n", name, fw->size);
/*
* if enabling an IOMMU isn't relevant for this rproc, this is
* just a nop
*/
ret = rproc_enable_iommu(rproc);
if (ret) {
dev_err(dev, "can't enable iommu: %d\n", ret);
return ret;
}
rproc->bootaddr = rproc_get_boot_addr(rproc, fw);
/* load resource table */
ret = rproc_load_rsc_table(rproc, fw);
if (ret)
goto disable_iommu;
/* reset max_notifyid */
rproc->max_notifyid = -1;
/* handle fw resources which are required to boot rproc */
ret = rproc_handle_resources(rproc, rproc_loading_handlers);
if (ret) {
dev_err(dev, "Failed to process resources: %d\n", ret);
goto clean_up_resources;
}
ret = rproc_start(rproc, fw);
if (ret)
goto clean_up_resources;
return 0;
clean_up_resources:
rproc_resource_cleanup(rproc);
kfree(rproc->cached_table);
rproc->cached_table = NULL;
rproc->table_ptr = NULL;
disable_iommu:
rproc_disable_iommu(rproc);
return ret;
}
/*
* take a firmware and boot it up.
*
* Note: this function is called asynchronously upon registration of the
* remote processor (so we must wait until it completes before we try
* to unregister the device. one other option is just to use kref here,
* that might be cleaner).
*/
static void rproc_auto_boot_callback(const struct firmware *fw, void *context)
{
struct rproc *rproc = context;
rproc_boot(rproc);
release_firmware(fw);
}
static int rproc_trigger_auto_boot(struct rproc *rproc)
{
int ret;
/*
* We're initiating an asynchronous firmware loading, so we can
* be built-in kernel code, without hanging the boot process.
*/
ret = request_firmware_nowait(THIS_MODULE, FW_ACTION_HOTPLUG,
rproc->firmware, &rproc->dev, GFP_KERNEL,
rproc, rproc_auto_boot_callback);
if (ret < 0)
dev_err(&rproc->dev, "request_firmware_nowait err: %d\n", ret);
return ret;
}
static int rproc_stop(struct rproc *rproc)
{
struct device *dev = &rproc->dev;
int ret;
/* remove any subdevices for the remote processor */