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
|
// SPDX-License-Identifier: (GPL-2.0 OR MIT)
/* Google virtual Ethernet (gve) driver
*
* Copyright (C) 2015-2021 Google, Inc.
*/
#include <linux/etherdevice.h>
#include <linux/pci.h>
#include "gve.h"
#include "gve_adminq.h"
#include "gve_register.h"
#define GVE_MAX_ADMINQ_RELEASE_CHECK 500
#define GVE_ADMINQ_SLEEP_LEN 20
#define GVE_MAX_ADMINQ_EVENT_COUNTER_CHECK 100
#define GVE_DEVICE_OPTION_ERROR_FMT "%s option error:\n" \
"Expected: length=%d, feature_mask=%x.\n" \
"Actual: length=%d, feature_mask=%x.\n"
#define GVE_DEVICE_OPTION_TOO_BIG_FMT "Length of %s option larger than expected. Possible older version of guest driver.\n"
static
struct gve_device_option *gve_get_next_option(struct gve_device_descriptor *descriptor,
struct gve_device_option *option)
{
void *option_end, *descriptor_end;
option_end = (void *)(option + 1) + be16_to_cpu(option->option_length);
descriptor_end = (void *)descriptor + be16_to_cpu(descriptor->total_length);
return option_end > descriptor_end ? NULL : (struct gve_device_option *)option_end;
}
static
void gve_parse_device_option(struct gve_priv *priv,
struct gve_device_descriptor *device_descriptor,
struct gve_device_option *option,
struct gve_device_option_gqi_rda **dev_op_gqi_rda,
struct gve_device_option_gqi_qpl **dev_op_gqi_qpl,
struct gve_device_option_dqo_rda **dev_op_dqo_rda,
struct gve_device_option_jumbo_frames **dev_op_jumbo_frames,
struct gve_device_option_dqo_qpl **dev_op_dqo_qpl,
struct gve_device_option_buffer_sizes **dev_op_buffer_sizes)
{
u32 req_feat_mask = be32_to_cpu(option->required_features_mask);
u16 option_length = be16_to_cpu(option->option_length);
u16 option_id = be16_to_cpu(option->option_id);
/* If the length or feature mask doesn't match, continue without
* enabling the feature.
*/
switch (option_id) {
case GVE_DEV_OPT_ID_GQI_RAW_ADDRESSING:
if (option_length != GVE_DEV_OPT_LEN_GQI_RAW_ADDRESSING ||
req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_GQI_RAW_ADDRESSING) {
dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT,
"Raw Addressing",
GVE_DEV_OPT_LEN_GQI_RAW_ADDRESSING,
GVE_DEV_OPT_REQ_FEAT_MASK_GQI_RAW_ADDRESSING,
option_length, req_feat_mask);
break;
}
dev_info(&priv->pdev->dev,
"Gqi raw addressing device option enabled.\n");
priv->queue_format = GVE_GQI_RDA_FORMAT;
break;
case GVE_DEV_OPT_ID_GQI_RDA:
if (option_length < sizeof(**dev_op_gqi_rda) ||
req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_GQI_RDA) {
dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT,
"GQI RDA", (int)sizeof(**dev_op_gqi_rda),
GVE_DEV_OPT_REQ_FEAT_MASK_GQI_RDA,
option_length, req_feat_mask);
break;
}
if (option_length > sizeof(**dev_op_gqi_rda)) {
dev_warn(&priv->pdev->dev,
GVE_DEVICE_OPTION_TOO_BIG_FMT, "GQI RDA");
}
*dev_op_gqi_rda = (void *)(option + 1);
break;
case GVE_DEV_OPT_ID_GQI_QPL:
if (option_length < sizeof(**dev_op_gqi_qpl) ||
req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_GQI_QPL) {
dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT,
"GQI QPL", (int)sizeof(**dev_op_gqi_qpl),
GVE_DEV_OPT_REQ_FEAT_MASK_GQI_QPL,
option_length, req_feat_mask);
break;
}
if (option_length > sizeof(**dev_op_gqi_qpl)) {
dev_warn(&priv->pdev->dev,
GVE_DEVICE_OPTION_TOO_BIG_FMT, "GQI QPL");
}
*dev_op_gqi_qpl = (void *)(option + 1);
break;
case GVE_DEV_OPT_ID_DQO_RDA:
if (option_length < sizeof(**dev_op_dqo_rda) ||
req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_DQO_RDA) {
dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT,
"DQO RDA", (int)sizeof(**dev_op_dqo_rda),
GVE_DEV_OPT_REQ_FEAT_MASK_DQO_RDA,
option_length, req_feat_mask);
break;
}
if (option_length > sizeof(**dev_op_dqo_rda)) {
dev_warn(&priv->pdev->dev,
GVE_DEVICE_OPTION_TOO_BIG_FMT, "DQO RDA");
}
*dev_op_dqo_rda = (void *)(option + 1);
break;
case GVE_DEV_OPT_ID_DQO_QPL:
if (option_length < sizeof(**dev_op_dqo_qpl) ||
req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_DQO_QPL) {
dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT,
"DQO QPL", (int)sizeof(**dev_op_dqo_qpl),
GVE_DEV_OPT_REQ_FEAT_MASK_DQO_QPL,
option_length, req_feat_mask);
break;
}
if (option_length > sizeof(**dev_op_dqo_qpl)) {
dev_warn(&priv->pdev->dev,
GVE_DEVICE_OPTION_TOO_BIG_FMT, "DQO QPL");
}
*dev_op_dqo_qpl = (void *)(option + 1);
break;
case GVE_DEV_OPT_ID_JUMBO_FRAMES:
if (option_length < sizeof(**dev_op_jumbo_frames) ||
req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_JUMBO_FRAMES) {
dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT,
"Jumbo Frames",
(int)sizeof(**dev_op_jumbo_frames),
GVE_DEV_OPT_REQ_FEAT_MASK_JUMBO_FRAMES,
option_length, req_feat_mask);
break;
}
if (option_length > sizeof(**dev_op_jumbo_frames)) {
dev_warn(&priv->pdev->dev,
GVE_DEVICE_OPTION_TOO_BIG_FMT,
"Jumbo Frames");
}
*dev_op_jumbo_frames = (void *)(option + 1);
break;
case GVE_DEV_OPT_ID_BUFFER_SIZES:
if (option_length < sizeof(**dev_op_buffer_sizes) ||
req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_BUFFER_SIZES) {
dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT,
"Buffer Sizes",
(int)sizeof(**dev_op_buffer_sizes),
GVE_DEV_OPT_REQ_FEAT_MASK_BUFFER_SIZES,
option_length, req_feat_mask);
break;
}
if (option_length > sizeof(**dev_op_buffer_sizes))
dev_warn(&priv->pdev->dev,
GVE_DEVICE_OPTION_TOO_BIG_FMT,
"Buffer Sizes");
*dev_op_buffer_sizes = (void *)(option + 1);
break;
default:
/* If we don't recognize the option just continue
* without doing anything.
*/
dev_dbg(&priv->pdev->dev, "Unrecognized device option 0x%hx not enabled.\n",
option_id);
}
}
/* Process all device options for a given describe device call. */
static int
gve_process_device_options(struct gve_priv *priv,
struct gve_device_descriptor *descriptor,
struct gve_device_option_gqi_rda **dev_op_gqi_rda,
struct gve_device_option_gqi_qpl **dev_op_gqi_qpl,
struct gve_device_option_dqo_rda **dev_op_dqo_rda,
struct gve_device_option_jumbo_frames **dev_op_jumbo_frames,
struct gve_device_option_dqo_qpl **dev_op_dqo_qpl,
struct gve_device_option_buffer_sizes **dev_op_buffer_sizes)
{
const int num_options = be16_to_cpu(descriptor->num_device_options);
struct gve_device_option *dev_opt;
int i;
/* The options struct directly follows the device descriptor. */
dev_opt = (void *)(descriptor + 1);
for (i = 0; i < num_options; i++) {
struct gve_device_option *next_opt;
next_opt = gve_get_next_option(descriptor, dev_opt);
if (!next_opt) {
dev_err(&priv->dev->dev,
"options exceed device_descriptor's total length.\n");
return -EINVAL;
}
gve_parse_device_option(priv, descriptor, dev_opt,
dev_op_gqi_rda, dev_op_gqi_qpl,
dev_op_dqo_rda, dev_op_jumbo_frames,
dev_op_dqo_qpl, dev_op_buffer_sizes);
dev_opt = next_opt;
}
return 0;
}
int gve_adminq_alloc(struct device *dev, struct gve_priv *priv)
{
priv->adminq_pool = dma_pool_create("adminq_pool", dev,
GVE_ADMINQ_BUFFER_SIZE, 0, 0);
if (unlikely(!priv->adminq_pool))
return -ENOMEM;
priv->adminq = dma_pool_alloc(priv->adminq_pool, GFP_KERNEL,
&priv->adminq_bus_addr);
if (unlikely(!priv->adminq)) {
dma_pool_destroy(priv->adminq_pool);
return -ENOMEM;
}
priv->adminq_mask =
(GVE_ADMINQ_BUFFER_SIZE / sizeof(union gve_adminq_command)) - 1;
priv->adminq_prod_cnt = 0;
priv->adminq_cmd_fail = 0;
priv->adminq_timeouts = 0;
priv->adminq_describe_device_cnt = 0;
priv->adminq_cfg_device_resources_cnt = 0;
priv->adminq_register_page_list_cnt = 0;
priv->adminq_unregister_page_list_cnt = 0;
priv->adminq_create_tx_queue_cnt = 0;
priv->adminq_create_rx_queue_cnt = 0;
priv->adminq_destroy_tx_queue_cnt = 0;
priv->adminq_destroy_rx_queue_cnt = 0;
priv->adminq_dcfg_device_resources_cnt = 0;
priv->adminq_set_driver_parameter_cnt = 0;
priv->adminq_report_stats_cnt = 0;
priv->adminq_report_link_speed_cnt = 0;
priv->adminq_get_ptype_map_cnt = 0;
/* Setup Admin queue with the device */
if (priv->pdev->revision < 0x1) {
iowrite32be(priv->adminq_bus_addr / PAGE_SIZE,
&priv->reg_bar0->adminq_pfn);
} else {
iowrite16be(GVE_ADMINQ_BUFFER_SIZE,
&priv->reg_bar0->adminq_length);
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
iowrite32be(priv->adminq_bus_addr >> 32,
&priv->reg_bar0->adminq_base_address_hi);
#endif
iowrite32be(priv->adminq_bus_addr,
&priv->reg_bar0->adminq_base_address_lo);
iowrite32be(GVE_DRIVER_STATUS_RUN_MASK, &priv->reg_bar0->driver_status);
}
gve_set_admin_queue_ok(priv);
return 0;
}
void gve_adminq_release(struct gve_priv *priv)
{
int i = 0;
/* Tell the device the adminq is leaving */
if (priv->pdev->revision < 0x1) {
iowrite32be(0x0, &priv->reg_bar0->adminq_pfn);
while (ioread32be(&priv->reg_bar0->adminq_pfn)) {
/* If this is reached the device is unrecoverable and still
* holding memory. Continue looping to avoid memory corruption,
* but WARN so it is visible what is going on.
*/
if (i == GVE_MAX_ADMINQ_RELEASE_CHECK)
WARN(1, "Unrecoverable platform error!");
i++;
msleep(GVE_ADMINQ_SLEEP_LEN);
}
} else {
iowrite32be(GVE_DRIVER_STATUS_RESET_MASK, &priv->reg_bar0->driver_status);
while (!(ioread32be(&priv->reg_bar0->device_status)
& GVE_DEVICE_STATUS_DEVICE_IS_RESET)) {
if (i == GVE_MAX_ADMINQ_RELEASE_CHECK)
WARN(1, "Unrecoverable platform error!");
i++;
msleep(GVE_ADMINQ_SLEEP_LEN);
}
}
gve_clear_device_rings_ok(priv);
gve_clear_device_resources_ok(priv);
gve_clear_admin_queue_ok(priv);
}
void gve_adminq_free(struct device *dev, struct gve_priv *priv)
{
if (!gve_get_admin_queue_ok(priv))
return;
gve_adminq_release(priv);
dma_pool_free(priv->adminq_pool, priv->adminq, priv->adminq_bus_addr);
dma_pool_destroy(priv->adminq_pool);
gve_clear_admin_queue_ok(priv);
}
static void gve_adminq_kick_cmd(struct gve_priv *priv, u32 prod_cnt)
{
iowrite32be(prod_cnt, &priv->reg_bar0->adminq_doorbell);
}
static bool gve_adminq_wait_for_cmd(struct gve_priv *priv, u32 prod_cnt)
{
int i;
for (i = 0; i < GVE_MAX_ADMINQ_EVENT_COUNTER_CHECK; i++) {
if (ioread32be(&priv->reg_bar0->adminq_event_counter)
== prod_cnt)
return true;
msleep(GVE_ADMINQ_SLEEP_LEN);
}
return false;
}
static int gve_adminq_parse_err(struct gve_priv *priv, u32 status)
{
if (status != GVE_ADMINQ_COMMAND_PASSED &&
status != GVE_ADMINQ_COMMAND_UNSET) {
dev_err(&priv->pdev->dev, "AQ command failed with status %d\n", status);
priv->adminq_cmd_fail++;
}
switch (status) {
case GVE_ADMINQ_COMMAND_PASSED:
return 0;
case GVE_ADMINQ_COMMAND_UNSET:
dev_err(&priv->pdev->dev, "parse_aq_err: err and status both unset, this should not be possible.\n");
return -EINVAL;
case GVE_ADMINQ_COMMAND_ERROR_ABORTED:
case GVE_ADMINQ_COMMAND_ERROR_CANCELLED:
case GVE_ADMINQ_COMMAND_ERROR_DATALOSS:
case GVE_ADMINQ_COMMAND_ERROR_FAILED_PRECONDITION:
case GVE_ADMINQ_COMMAND_ERROR_UNAVAILABLE:
return -EAGAIN;
case GVE_ADMINQ_COMMAND_ERROR_ALREADY_EXISTS:
case GVE_ADMINQ_COMMAND_ERROR_INTERNAL_ERROR:
case GVE_ADMINQ_COMMAND_ERROR_INVALID_ARGUMENT:
case GVE_ADMINQ_COMMAND_ERROR_NOT_FOUND:
case GVE_ADMINQ_COMMAND_ERROR_OUT_OF_RANGE:
case GVE_ADMINQ_COMMAND_ERROR_UNKNOWN_ERROR:
return -EINVAL;
case GVE_ADMINQ_COMMAND_ERROR_DEADLINE_EXCEEDED:
return -ETIME;
case GVE_ADMINQ_COMMAND_ERROR_PERMISSION_DENIED:
case GVE_ADMINQ_COMMAND_ERROR_UNAUTHENTICATED:
return -EACCES;
case GVE_ADMINQ_COMMAND_ERROR_RESOURCE_EXHAUSTED:
return -ENOMEM;
case GVE_ADMINQ_COMMAND_ERROR_UNIMPLEMENTED:
return -EOPNOTSUPP;
default:
dev_err(&priv->pdev->dev, "parse_aq_err: unknown status code %d\n", status);
return -EINVAL;
}
}
/* Flushes all AQ commands currently queued and waits for them to complete.
* If there are failures, it will return the first error.
*/
static int gve_adminq_kick_and_wait(struct gve_priv *priv)
{
int tail, head;
int i;
tail = ioread32be(&priv->reg_bar0->adminq_event_counter);
head = priv->adminq_prod_cnt;
gve_adminq_kick_cmd(priv, head);
if (!gve_adminq_wait_for_cmd(priv, head)) {
dev_err(&priv->pdev->dev, "AQ commands timed out, need to reset AQ\n");
priv->adminq_timeouts++;
return -ENOTRECOVERABLE;
}
for (i = tail; i < head; i++) {
union gve_adminq_command *cmd;
u32 status, err;
cmd = &priv->adminq[i & priv->adminq_mask];
status = be32_to_cpu(READ_ONCE(cmd->status));
err = gve_adminq_parse_err(priv, status);
if (err)
// Return the first error if we failed.
return err;
}
return 0;
}
/* This function is not threadsafe - the caller is responsible for any
* necessary locks.
*/
static int gve_adminq_issue_cmd(struct gve_priv *priv,
union gve_adminq_command *cmd_orig)
{
union gve_adminq_command *cmd;
u32 opcode;
u32 tail;
tail = ioread32be(&priv->reg_bar0->adminq_event_counter);
// Check if next command will overflow the buffer.
if (((priv->adminq_prod_cnt + 1) & priv->adminq_mask) ==
(tail & priv->adminq_mask)) {
int err;
// Flush existing commands to make room.
err = gve_adminq_kick_and_wait(priv);
if (err)
return err;
// Retry.
tail = ioread32be(&priv->reg_bar0->adminq_event_counter);
if (((priv->adminq_prod_cnt + 1) & priv->adminq_mask) ==
(tail & priv->adminq_mask)) {
// This should never happen. We just flushed the
// command queue so there should be enough space.
return -ENOMEM;
}
}
cmd = &priv->adminq[priv->adminq_prod_cnt & priv->adminq_mask];
priv->adminq_prod_cnt++;
memcpy(cmd, cmd_orig, sizeof(*cmd_orig));
opcode = be32_to_cpu(READ_ONCE(cmd->opcode));
switch (opcode) {
case GVE_ADMINQ_DESCRIBE_DEVICE:
priv->adminq_describe_device_cnt++;
break;
case GVE_ADMINQ_CONFIGURE_DEVICE_RESOURCES:
priv->adminq_cfg_device_resources_cnt++;
break;
case GVE_ADMINQ_REGISTER_PAGE_LIST:
priv->adminq_register_page_list_cnt++;
break;
case GVE_ADMINQ_UNREGISTER_PAGE_LIST:
priv->adminq_unregister_page_list_cnt++;
break;
case GVE_ADMINQ_CREATE_TX_QUEUE:
priv->adminq_create_tx_queue_cnt++;
break;
case GVE_ADMINQ_CREATE_RX_QUEUE:
priv->adminq_create_rx_queue_cnt++;
break;
case GVE_ADMINQ_DESTROY_TX_QUEUE:
priv->adminq_destroy_tx_queue_cnt++;
break;
case GVE_ADMINQ_DESTROY_RX_QUEUE:
priv->adminq_destroy_rx_queue_cnt++;
break;
case GVE_ADMINQ_DECONFIGURE_DEVICE_RESOURCES:
priv->adminq_dcfg_device_resources_cnt++;
break;
case GVE_ADMINQ_SET_DRIVER_PARAMETER:
priv->adminq_set_driver_parameter_cnt++;
break;
case GVE_ADMINQ_REPORT_STATS:
priv->adminq_report_stats_cnt++;
break;
case GVE_ADMINQ_REPORT_LINK_SPEED:
priv->adminq_report_link_speed_cnt++;
break;
case GVE_ADMINQ_GET_PTYPE_MAP:
priv->adminq_get_ptype_map_cnt++;
break;
case GVE_ADMINQ_VERIFY_DRIVER_COMPATIBILITY:
priv->adminq_verify_driver_compatibility_cnt++;
break;
default:
dev_err(&priv->pdev->dev, "unknown AQ command opcode %d\n", opcode);
}
return 0;
}
/* This function is not threadsafe - the caller is responsible for any
* necessary locks.
* The caller is also responsible for making sure there are no commands
* waiting to be executed.
*/
static int gve_adminq_execute_cmd(struct gve_priv *priv,
union gve_adminq_command *cmd_orig)
{
u32 tail, head;
int err;
tail = ioread32be(&priv->reg_bar0->adminq_event_counter);
head = priv->adminq_prod_cnt;
if (tail != head)
// This is not a valid path
return -EINVAL;
err = gve_adminq_issue_cmd(priv, cmd_orig);
if (err)
return err;
return gve_adminq_kick_and_wait(priv);
}
/* The device specifies that the management vector can either be the first irq
* or the last irq. ntfy_blk_msix_base_idx indicates the first irq assigned to
* the ntfy blks. It if is 0 then the management vector is last, if it is 1 then
* the management vector is first.
*
* gve arranges the msix vectors so that the management vector is last.
*/
#define GVE_NTFY_BLK_BASE_MSIX_IDX 0
int gve_adminq_configure_device_resources(struct gve_priv *priv,
dma_addr_t counter_array_bus_addr,
u32 num_counters,
dma_addr_t db_array_bus_addr,
u32 num_ntfy_blks)
{
union gve_adminq_command cmd;
memset(&cmd, 0, sizeof(cmd));
cmd.opcode = cpu_to_be32(GVE_ADMINQ_CONFIGURE_DEVICE_RESOURCES);
cmd.configure_device_resources =
(struct gve_adminq_configure_device_resources) {
.counter_array = cpu_to_be64(counter_array_bus_addr),
.num_counters = cpu_to_be32(num_counters),
.irq_db_addr = cpu_to_be64(db_array_bus_addr),
.num_irq_dbs = cpu_to_be32(num_ntfy_blks),
.irq_db_stride = cpu_to_be32(sizeof(*priv->irq_db_indices)),
.ntfy_blk_msix_base_idx =
cpu_to_be32(GVE_NTFY_BLK_BASE_MSIX_IDX),
.queue_format = priv->queue_format,
};
return gve_adminq_execute_cmd(priv, &cmd);
}
int gve_adminq_deconfigure_device_resources(struct gve_priv *priv)
{
union gve_adminq_command cmd;
memset(&cmd, 0, sizeof(cmd));
cmd.opcode = cpu_to_be32(GVE_ADMINQ_DECONFIGURE_DEVICE_RESOURCES);
return gve_adminq_execute_cmd(priv, &cmd);
}
static int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_index)
{
struct gve_tx_ring *tx = &priv->tx[queue_index];
union gve_adminq_command cmd;
memset(&cmd, 0, sizeof(cmd));
cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_TX_QUEUE);
cmd.create_tx_queue = (struct gve_adminq_create_tx_queue) {
.queue_id = cpu_to_be32(queue_index),
.queue_resources_addr =
cpu_to_be64(tx->q_resources_bus),
.tx_ring_addr = cpu_to_be64(tx->bus),
.ntfy_id = cpu_to_be32(tx->ntfy_id),
};
if (gve_is_gqi(priv)) {
u32 qpl_id = priv->queue_format == GVE_GQI_RDA_FORMAT ?
GVE_RAW_ADDRESSING_QPL_ID : tx->tx_fifo.qpl->id;
cmd.create_tx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
} else {
u16 comp_ring_size;
u32 qpl_id = 0;
if (priv->queue_format == GVE_DQO_RDA_FORMAT) {
qpl_id = GVE_RAW_ADDRESSING_QPL_ID;
comp_ring_size =
priv->options_dqo_rda.tx_comp_ring_entries;
} else {
qpl_id = tx->dqo.qpl->id;
comp_ring_size = priv->tx_desc_cnt;
}
cmd.create_tx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
cmd.create_tx_queue.tx_ring_size =
cpu_to_be16(priv->tx_desc_cnt);
cmd.create_tx_queue.tx_comp_ring_addr =
cpu_to_be64(tx->complq_bus_dqo);
cmd.create_tx_queue.tx_comp_ring_size =
cpu_to_be16(comp_ring_size);
}
return gve_adminq_issue_cmd(priv, &cmd);
}
int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_queues)
{
int err;
int i;
for (i = start_id; i < start_id + num_queues; i++) {
err = gve_adminq_create_tx_queue(priv, i);
if (err)
return err;
}
return gve_adminq_kick_and_wait(priv);
}
static int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index)
{
struct gve_rx_ring *rx = &priv->rx[queue_index];
union gve_adminq_command cmd;
memset(&cmd, 0, sizeof(cmd));
cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_RX_QUEUE);
cmd.create_rx_queue = (struct gve_adminq_create_rx_queue) {
.queue_id = cpu_to_be32(queue_index),
.ntfy_id = cpu_to_be32(rx->ntfy_id),
.queue_resources_addr = cpu_to_be64(rx->q_resources_bus),
};
if (gve_is_gqi(priv)) {
u32 qpl_id = priv->queue_format == GVE_GQI_RDA_FORMAT ?
GVE_RAW_ADDRESSING_QPL_ID : rx->data.qpl->id;
cmd.create_rx_queue.rx_desc_ring_addr =
cpu_to_be64(rx->desc.bus),
cmd.create_rx_queue.rx_data_ring_addr =
cpu_to_be64(rx->data.data_bus),
cmd.create_rx_queue.index = cpu_to_be32(queue_index);
cmd.create_rx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
cmd.create_rx_queue.packet_buffer_size = cpu_to_be16(rx->packet_buffer_size);
} else {
u16 rx_buff_ring_entries;
u32 qpl_id = 0;
if (priv->queue_format == GVE_DQO_RDA_FORMAT) {
qpl_id = GVE_RAW_ADDRESSING_QPL_ID;
rx_buff_ring_entries =
priv->options_dqo_rda.rx_buff_ring_entries;
} else {
qpl_id = rx->dqo.qpl->id;
rx_buff_ring_entries = priv->rx_desc_cnt;
}
cmd.create_rx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
cmd.create_rx_queue.rx_ring_size =
cpu_to_be16(priv->rx_desc_cnt);
cmd.create_rx_queue.rx_desc_ring_addr =
cpu_to_be64(rx->dqo.complq.bus);
cmd.create_rx_queue.rx_data_ring_addr =
cpu_to_be64(rx->dqo.bufq.bus);
cmd.create_rx_queue.packet_buffer_size =
cpu_to_be16(priv->data_buffer_size_dqo);
cmd.create_rx_queue.rx_buff_ring_size =
cpu_to_be16(rx_buff_ring_entries);
cmd.create_rx_queue.enable_rsc =
!!(priv->dev->features & NETIF_F_LRO);
}
return gve_adminq_issue_cmd(priv, &cmd);
}
int gve_adminq_create_rx_queues(struct gve_priv *priv, u32 num_queues)
{
int err;
int i;
for (i = 0; i < num_queues; i++) {
err = gve_adminq_create_rx_queue(priv, i);
if (err)
return err;
}
return gve_adminq_kick_and_wait(priv);
}
static int gve_adminq_destroy_tx_queue(struct gve_priv *priv, u32 queue_index)
{
union gve_adminq_command cmd;
int err;
memset(&cmd, 0, sizeof(cmd));
cmd.opcode = cpu_to_be32(GVE_ADMINQ_DESTROY_TX_QUEUE);
cmd.destroy_tx_queue = (struct gve_adminq_destroy_tx_queue) {
.queue_id = cpu_to_be32(queue_index),
};
err = gve_adminq_issue_cmd(priv, &cmd);
if (err)
return err;
return 0;
}
int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_queues)
{
int err;
int i;
for (i = start_id; i < start_id + num_queues; i++) {
err = gve_adminq_destroy_tx_queue(priv, i);
if (err)
return err;
}
return gve_adminq_kick_and_wait(priv);
}
static int gve_adminq_destroy_rx_queue(struct gve_priv *priv, u32 queue_index)
{
union gve_adminq_command cmd;
int err;
memset(&cmd, 0, sizeof(cmd));
cmd.opcode = cpu_to_be32(GVE_ADMINQ_DESTROY_RX_QUEUE);
cmd.destroy_rx_queue = (struct gve_adminq_destroy_rx_queue) {
.queue_id = cpu_to_be32(queue_index),
};
err = gve_adminq_issue_cmd(priv, &cmd);
if (err)
return err;
return 0;
}
int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 num_queues)
{
int err;
int i;
for (i = 0; i < num_queues; i++) {
err = gve_adminq_destroy_rx_queue(priv, i);
if (err)
return err;
}
return gve_adminq_kick_and_wait(priv);
}
static int gve_set_desc_cnt(struct gve_priv *priv,
struct gve_device_descriptor *descriptor)
{
priv->tx_desc_cnt = be16_to_cpu(descriptor->tx_queue_entries);
priv->rx_desc_cnt = be16_to_cpu(descriptor->rx_queue_entries);
return 0;
}
static int
gve_set_desc_cnt_dqo(struct gve_priv *priv,
const struct gve_device_descriptor *descriptor,
const struct gve_device_option_dqo_rda *dev_op_dqo_rda)
{
priv->tx_desc_cnt = be16_to_cpu(descriptor->tx_queue_entries);
priv->rx_desc_cnt = be16_to_cpu(descriptor->rx_queue_entries);
if (priv->queue_format == GVE_DQO_QPL_FORMAT)
return 0;
priv->options_dqo_rda.tx_comp_ring_entries =
be16_to_cpu(dev_op_dqo_rda->tx_comp_ring_entries);
priv->options_dqo_rda.rx_buff_ring_entries =
be16_to_cpu(dev_op_dqo_rda->rx_buff_ring_entries);
return 0;
}
static void gve_enable_supported_features(struct gve_priv *priv,
u32 supported_features_mask,
const struct gve_device_option_jumbo_frames
*dev_op_jumbo_frames,
const struct gve_device_option_dqo_qpl
*dev_op_dqo_qpl,
const struct gve_device_option_buffer_sizes
*dev_op_buffer_sizes)
{
/* Before control reaches this point, the page-size-capped max MTU from
* the gve_device_descriptor field has already been stored in
* priv->dev->max_mtu. We overwrite it with the true max MTU below.
*/
if (dev_op_jumbo_frames &&
(supported_features_mask & GVE_SUP_JUMBO_FRAMES_MASK)) {
dev_info(&priv->pdev->dev,
"JUMBO FRAMES device option enabled.\n");
priv->dev->max_mtu = be16_to_cpu(dev_op_jumbo_frames->max_mtu);
}
/* Override pages for qpl for DQO-QPL */
if (dev_op_dqo_qpl) {
priv->tx_pages_per_qpl =
be16_to_cpu(dev_op_dqo_qpl->tx_pages_per_qpl);
priv->rx_pages_per_qpl =
be16_to_cpu(dev_op_dqo_qpl->rx_pages_per_qpl);
if (priv->tx_pages_per_qpl == 0)
priv->tx_pages_per_qpl = DQO_QPL_DEFAULT_TX_PAGES;
if (priv->rx_pages_per_qpl == 0)
priv->rx_pages_per_qpl = DQO_QPL_DEFAULT_RX_PAGES;
}
if (dev_op_buffer_sizes &&
(supported_features_mask & GVE_SUP_BUFFER_SIZES_MASK)) {
priv->max_rx_buffer_size =
be16_to_cpu(dev_op_buffer_sizes->packet_buffer_size);
priv->header_buf_size =
be16_to_cpu(dev_op_buffer_sizes->header_buffer_size);
dev_info(&priv->pdev->dev,
"BUFFER SIZES device option enabled with max_rx_buffer_size of %u, header_buf_size of %u.\n",
priv->max_rx_buffer_size, priv->header_buf_size);
}
}
int gve_adminq_describe_device(struct gve_priv *priv)
{
struct gve_device_option_buffer_sizes *dev_op_buffer_sizes = NULL;
struct gve_device_option_jumbo_frames *dev_op_jumbo_frames = NULL;
struct gve_device_option_gqi_rda *dev_op_gqi_rda = NULL;
struct gve_device_option_gqi_qpl *dev_op_gqi_qpl = NULL;
struct gve_device_option_dqo_rda *dev_op_dqo_rda = NULL;
struct gve_device_option_dqo_qpl *dev_op_dqo_qpl = NULL;
struct gve_device_descriptor *descriptor;
u32 supported_features_mask = 0;
union gve_adminq_command cmd;
dma_addr_t descriptor_bus;
int err = 0;
u8 *mac;
u16 mtu;
memset(&cmd, 0, sizeof(cmd));
descriptor = dma_pool_alloc(priv->adminq_pool, GFP_KERNEL,
&descriptor_bus);
if (!descriptor)
return -ENOMEM;
cmd.opcode = cpu_to_be32(GVE_ADMINQ_DESCRIBE_DEVICE);
cmd.describe_device.device_descriptor_addr =
cpu_to_be64(descriptor_bus);
cmd.describe_device.device_descriptor_version =
cpu_to_be32(GVE_ADMINQ_DEVICE_DESCRIPTOR_VERSION);
cmd.describe_device.available_length =
cpu_to_be32(GVE_ADMINQ_BUFFER_SIZE);
err = gve_adminq_execute_cmd(priv, &cmd);
if (err)
goto free_device_descriptor;
err = gve_process_device_options(priv, descriptor, &dev_op_gqi_rda,
&dev_op_gqi_qpl, &dev_op_dqo_rda,
&dev_op_jumbo_frames,
&dev_op_dqo_qpl,
&dev_op_buffer_sizes);
if (err)
goto free_device_descriptor;
/* If the GQI_RAW_ADDRESSING option is not enabled and the queue format
* is not set to GqiRda, choose the queue format in a priority order:
* DqoRda, DqoQpl, GqiRda, GqiQpl. Use GqiQpl as default.
*/
if (dev_op_dqo_rda) {
priv->queue_format = GVE_DQO_RDA_FORMAT;
dev_info(&priv->pdev->dev,
"Driver is running with DQO RDA queue format.\n");
supported_features_mask =
be32_to_cpu(dev_op_dqo_rda->supported_features_mask);
} else if (dev_op_dqo_qpl) {
priv->queue_format = GVE_DQO_QPL_FORMAT;
supported_features_mask =
be32_to_cpu(dev_op_dqo_qpl->supported_features_mask);
} else if (dev_op_gqi_rda) {
priv->queue_format = GVE_GQI_RDA_FORMAT;
dev_info(&priv->pdev->dev,
"Driver is running with GQI RDA queue format.\n");
supported_features_mask =
be32_to_cpu(dev_op_gqi_rda->supported_features_mask);
} else if (priv->queue_format == GVE_GQI_RDA_FORMAT) {
dev_info(&priv->pdev->dev,
"Driver is running with GQI RDA queue format.\n");
} else {
priv->queue_format = GVE_GQI_QPL_FORMAT;
if (dev_op_gqi_qpl)
supported_features_mask =
be32_to_cpu(dev_op_gqi_qpl->supported_features_mask);
dev_info(&priv->pdev->dev,
"Driver is running with GQI QPL queue format.\n");
}
if (gve_is_gqi(priv)) {
err = gve_set_desc_cnt(priv, descriptor);
} else {
/* DQO supports LRO. */
priv->dev->hw_features |= NETIF_F_LRO;
err = gve_set_desc_cnt_dqo(priv, descriptor, dev_op_dqo_rda);
}
if (err)
goto free_device_descriptor;
priv->max_registered_pages =
be64_to_cpu(descriptor->max_registered_pages);
mtu = be16_to_cpu(descriptor->mtu);
if (mtu < ETH_MIN_MTU) {
dev_err(&priv->pdev->dev, "MTU %d below minimum MTU\n", mtu);
err = -EINVAL;
goto free_device_descriptor;
}
priv->dev->max_mtu = mtu;
priv->num_event_counters = be16_to_cpu(descriptor->counters);
eth_hw_addr_set(priv->dev, descriptor->mac);
mac = descriptor->mac;
dev_info(&priv->pdev->dev, "MAC addr: %pM\n", mac);
priv->tx_pages_per_qpl = be16_to_cpu(descriptor->tx_pages_per_qpl);
priv->rx_data_slot_cnt = be16_to_cpu(descriptor->rx_pages_per_qpl);
if (gve_is_gqi(priv) && priv->rx_data_slot_cnt < priv->rx_desc_cnt) {
dev_err(&priv->pdev->dev, "rx_data_slot_cnt cannot be smaller than rx_desc_cnt, setting rx_desc_cnt down to %d.\n",
priv->rx_data_slot_cnt);
priv->rx_desc_cnt = priv->rx_data_slot_cnt;
}
priv->default_num_queues = be16_to_cpu(descriptor->default_num_queues);
gve_enable_supported_features(priv, supported_features_mask,
dev_op_jumbo_frames, dev_op_dqo_qpl,
dev_op_buffer_sizes);
free_device_descriptor:
dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus);
return err;
}
int gve_adminq_register_page_list(struct gve_priv *priv,
struct gve_queue_page_list *qpl)
{
struct device *hdev = &priv->pdev->dev;
u32 num_entries = qpl->num_entries;
u32 size = num_entries * sizeof(qpl->page_buses[0]);
union gve_adminq_command cmd;
dma_addr_t page_list_bus;
__be64 *page_list;
int err;
int i;
memset(&cmd, 0, sizeof(cmd));
page_list = dma_alloc_coherent(hdev, size, &page_list_bus, GFP_KERNEL);
if (!page_list)
return -ENOMEM;
for (i = 0; i < num_entries; i++)
page_list[i] = cpu_to_be64(qpl->page_buses[i]);
cmd.opcode = cpu_to_be32(GVE_ADMINQ_REGISTER_PAGE_LIST);
cmd.reg_page_list = (struct gve_adminq_register_page_list) {
.page_list_id = cpu_to_be32(qpl->id),
.num_pages = cpu_to_be32(num_entries),
.page_address_list_addr = cpu_to_be64(page_list_bus),
.page_size = cpu_to_be64(PAGE_SIZE),
};
err = gve_adminq_execute_cmd(priv, &cmd);
dma_free_coherent(hdev, size, page_list, page_list_bus);
return err;
}
int gve_adminq_unregister_page_list(struct gve_priv *priv, u32 page_list_id)
{
union gve_adminq_command cmd;
memset(&cmd, 0, sizeof(cmd));
cmd.opcode = cpu_to_be32(GVE_ADMINQ_UNREGISTER_PAGE_LIST);
cmd.unreg_page_list = (struct gve_adminq_unregister_page_list) {
.page_list_id = cpu_to_be32(page_list_id),
};
return gve_adminq_execute_cmd(priv, &cmd);
}
int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu)
{
union gve_adminq_command cmd;
memset(&cmd, 0, sizeof(cmd));
cmd.opcode = cpu_to_be32(GVE_ADMINQ_SET_DRIVER_PARAMETER);
cmd.set_driver_param = (struct gve_adminq_set_driver_parameter) {
.parameter_type = cpu_to_be32(GVE_SET_PARAM_MTU),
.parameter_value = cpu_to_be64(mtu),
};
return gve_adminq_execute_cmd(priv, &cmd);
}
int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len,
dma_addr_t stats_report_addr, u64 interval)
{
union gve_adminq_command cmd;
memset(&cmd, 0, sizeof(cmd));
cmd.opcode = cpu_to_be32(GVE_ADMINQ_REPORT_STATS);
cmd.report_stats = (struct gve_adminq_report_stats) {
.stats_report_len = cpu_to_be64(stats_report_len),
.stats_report_addr = cpu_to_be64(stats_report_addr),
.interval = cpu_to_be64(interval),
};
return gve_adminq_execute_cmd(priv, &cmd);
}
int gve_adminq_verify_driver_compatibility(struct gve_priv *priv,
u64 driver_info_len,
dma_addr_t driver_info_addr)
{
union gve_adminq_command cmd;
memset(&cmd, 0, sizeof(cmd));
cmd.opcode = cpu_to_be32(GVE_ADMINQ_VERIFY_DRIVER_COMPATIBILITY);
cmd.verify_driver_compatibility = (struct gve_adminq_verify_driver_compatibility) {
.driver_info_len = cpu_to_be64(driver_info_len),
.driver_info_addr = cpu_to_be64(driver_info_addr),
};
return gve_adminq_execute_cmd(priv, &cmd);
}
int gve_adminq_report_link_speed(struct gve_priv *priv)
{
union gve_adminq_command gvnic_cmd;
dma_addr_t link_speed_region_bus;
__be64 *link_speed_region;
int err;
link_speed_region =
dma_alloc_coherent(&priv->pdev->dev, sizeof(*link_speed_region),
&link_speed_region_bus, GFP_KERNEL);
if (!link_speed_region)
return -ENOMEM;
memset(&gvnic_cmd, 0, sizeof(gvnic_cmd));
gvnic_cmd.opcode = cpu_to_be32(GVE_ADMINQ_REPORT_LINK_SPEED);
gvnic_cmd.report_link_speed.link_speed_address =
cpu_to_be64(link_speed_region_bus);
err = gve_adminq_execute_cmd(priv, &gvnic_cmd);
priv->link_speed = be64_to_cpu(*link_speed_region);
dma_free_coherent(&priv->pdev->dev, sizeof(*link_speed_region), link_speed_region,
link_speed_region_bus);
return err;
}
int gve_adminq_get_ptype_map_dqo(struct gve_priv *priv,
struct gve_ptype_lut *ptype_lut)
{
struct gve_ptype_map *ptype_map;
union gve_adminq_command cmd;
dma_addr_t ptype_map_bus;
int err = 0;
int i;
memset(&cmd, 0, sizeof(cmd));
ptype_map = dma_alloc_coherent(&priv->pdev->dev, sizeof(*ptype_map),
&ptype_map_bus, GFP_KERNEL);
if (!ptype_map)
return -ENOMEM;
cmd.opcode = cpu_to_be32(GVE_ADMINQ_GET_PTYPE_MAP);
cmd.get_ptype_map = (struct gve_adminq_get_ptype_map) {
.ptype_map_len = cpu_to_be64(sizeof(*ptype_map)),
.ptype_map_addr = cpu_to_be64(ptype_map_bus),
};
err = gve_adminq_execute_cmd(priv, &cmd);
if (err)
goto err;
/* Populate ptype_lut. */
for (i = 0; i < GVE_NUM_PTYPES; i++) {
ptype_lut->ptypes[i].l3_type =
ptype_map->ptypes[i].l3_type;
ptype_lut->ptypes[i].l4_type =
ptype_map->ptypes[i].l4_type;
}
err:
dma_free_coherent(&priv->pdev->dev, sizeof(*ptype_map), ptype_map,
ptype_map_bus);
return err;
}
|