1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* AMD Memory Encryption Support
*
* Copyright (C) 2019 SUSE
*
* Author: Joerg Roedel <jroedel@suse.de>
*/
#define pr_fmt(fmt) "SEV-ES: " fmt
#include <linux/sched/debug.h> /* For show_regs() */
#include <linux/percpu-defs.h>
#include <linux/mem_encrypt.h>
#include <linux/lockdep.h>
#include <linux/printk.h>
#include <linux/mm_types.h>
#include <linux/set_memory.h>
#include <linux/memblock.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <asm/cpu_entry_area.h>
#include <asm/stacktrace.h>
#include <asm/sev-es.h>
#include <asm/insn-eval.h>
#include <asm/fpu/internal.h>
#include <asm/processor.h>
#include <asm/realmode.h>
#include <asm/traps.h>
#include <asm/svm.h>
#include <asm/smp.h>
#include <asm/cpu.h>
#define DR7_RESET_VALUE 0x400
/* For early boot hypervisor communication in SEV-ES enabled guests */
static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE);
/*
* Needs to be in the .data section because we need it NULL before bss is
* cleared
*/
static struct ghcb __initdata *boot_ghcb;
/* #VC handler runtime per-CPU data */
struct sev_es_runtime_data {
struct ghcb ghcb_page;
/* Physical storage for the per-CPU IST stack of the #VC handler */
char ist_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE);
/*
* Physical storage for the per-CPU fall-back stack of the #VC handler.
* The fall-back stack is used when it is not safe to switch back to the
* interrupted stack in the #VC entry code.
*/
char fallback_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE);
/*
* Reserve one page per CPU as backup storage for the unencrypted GHCB.
* It is needed when an NMI happens while the #VC handler uses the real
* GHCB, and the NMI handler itself is causing another #VC exception. In
* that case the GHCB content of the first handler needs to be backed up
* and restored.
*/
struct ghcb backup_ghcb;
/*
* Mark the per-cpu GHCBs as in-use to detect nested #VC exceptions.
* There is no need for it to be atomic, because nothing is written to
* the GHCB between the read and the write of ghcb_active. So it is safe
* to use it when a nested #VC exception happens before the write.
*
* This is necessary for example in the #VC->NMI->#VC case when the NMI
* happens while the first #VC handler uses the GHCB. When the NMI code
* raises a second #VC handler it might overwrite the contents of the
* GHCB written by the first handler. To avoid this the content of the
* GHCB is saved and restored when the GHCB is detected to be in use
* already.
*/
bool ghcb_active;
bool backup_ghcb_active;
/*
* Cached DR7 value - write it on DR7 writes and return it on reads.
* That value will never make it to the real hardware DR7 as debugging
* is currently unsupported in SEV-ES guests.
*/
unsigned long dr7;
};
struct ghcb_state {
struct ghcb *ghcb;
};
static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
DEFINE_STATIC_KEY_FALSE(sev_es_enable_key);
/* Needed in vc_early_forward_exception */
void do_early_exception(struct pt_regs *regs, int trapnr);
static void __init setup_vc_stacks(int cpu)
{
struct sev_es_runtime_data *data;
struct cpu_entry_area *cea;
unsigned long vaddr;
phys_addr_t pa;
data = per_cpu(runtime_data, cpu);
cea = get_cpu_entry_area(cpu);
/* Map #VC IST stack */
vaddr = CEA_ESTACK_BOT(&cea->estacks, VC);
pa = __pa(data->ist_stack);
cea_set_pte((void *)vaddr, pa, PAGE_KERNEL);
/* Map VC fall-back stack */
vaddr = CEA_ESTACK_BOT(&cea->estacks, VC2);
pa = __pa(data->fallback_stack);
cea_set_pte((void *)vaddr, pa, PAGE_KERNEL);
}
static __always_inline bool on_vc_stack(unsigned long sp)
{
return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC)));
}
/*
* This function handles the case when an NMI is raised in the #VC exception
* handler entry code. In this case, the IST entry for #VC must be adjusted, so
* that any subsequent #VC exception will not overwrite the stack contents of the
* interrupted #VC handler.
*
* The IST entry is adjusted unconditionally so that it can be also be
* unconditionally adjusted back in sev_es_ist_exit(). Otherwise a nested
* sev_es_ist_exit() call may adjust back the IST entry too early.
*/
void noinstr __sev_es_ist_enter(struct pt_regs *regs)
{
unsigned long old_ist, new_ist;
/* Read old IST entry */
old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
/* Make room on the IST stack */
if (on_vc_stack(regs->sp))
new_ist = ALIGN_DOWN(regs->sp, 8) - sizeof(old_ist);
else
new_ist = old_ist - sizeof(old_ist);
/* Store old IST entry */
*(unsigned long *)new_ist = old_ist;
/* Set new IST entry */
this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], new_ist);
}
void noinstr __sev_es_ist_exit(void)
{
unsigned long ist;
/* Read IST entry */
ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
if (WARN_ON(ist == __this_cpu_ist_top_va(VC)))
return;
/* Read back old IST entry and write it to the TSS */
this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], *(unsigned long *)ist);
}
static __always_inline struct ghcb *sev_es_get_ghcb(struct ghcb_state *state)
{
struct sev_es_runtime_data *data;
struct ghcb *ghcb;
data = this_cpu_read(runtime_data);
ghcb = &data->ghcb_page;
if (unlikely(data->ghcb_active)) {
/* GHCB is already in use - save its contents */
if (unlikely(data->backup_ghcb_active))
return NULL;
/* Mark backup_ghcb active before writing to it */
data->backup_ghcb_active = true;
state->ghcb = &data->backup_ghcb;
/* Backup GHCB content */
*state->ghcb = *ghcb;
} else {
state->ghcb = NULL;
data->ghcb_active = true;
}
return ghcb;
}
static __always_inline void sev_es_put_ghcb(struct ghcb_state *state)
{
struct sev_es_runtime_data *data;
struct ghcb *ghcb;
data = this_cpu_read(runtime_data);
ghcb = &data->ghcb_page;
if (state->ghcb) {
/* Restore GHCB from Backup */
*ghcb = *state->ghcb;
data->backup_ghcb_active = false;
state->ghcb = NULL;
} else {
data->ghcb_active = false;
}
}
/* Needed in vc_early_forward_exception */
void do_early_exception(struct pt_regs *regs, int trapnr);
static inline u64 sev_es_rd_ghcb_msr(void)
{
return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
}
static inline void sev_es_wr_ghcb_msr(u64 val)
{
u32 low, high;
low = (u32)(val);
high = (u32)(val >> 32);
native_wrmsr(MSR_AMD64_SEV_ES_GHCB, low, high);
}
static int vc_fetch_insn_kernel(struct es_em_ctxt *ctxt,
unsigned char *buffer)
{
return copy_from_kernel_nofault(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
}
static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
{
char buffer[MAX_INSN_SIZE];
enum es_result ret;
int res;
if (user_mode(ctxt->regs)) {
res = insn_fetch_from_user(ctxt->regs, buffer);
if (!res) {
ctxt->fi.vector = X86_TRAP_PF;
ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
ctxt->fi.cr2 = ctxt->regs->ip;
return ES_EXCEPTION;
}
if (!insn_decode(&ctxt->insn, ctxt->regs, buffer, res))
return ES_DECODE_FAILED;
} else {
res = vc_fetch_insn_kernel(ctxt, buffer);
if (res) {
ctxt->fi.vector = X86_TRAP_PF;
ctxt->fi.error_code = X86_PF_INSTR;
ctxt->fi.cr2 = ctxt->regs->ip;
return ES_EXCEPTION;
}
insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE - res, 1);
insn_get_length(&ctxt->insn);
}
ret = ctxt->insn.immediate.got ? ES_OK : ES_DECODE_FAILED;
return ret;
}
static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
char *dst, char *buf, size_t size)
{
unsigned long error_code = X86_PF_PROT | X86_PF_WRITE;
char __user *target = (char __user *)dst;
u64 d8;
u32 d4;
u16 d2;
u8 d1;
switch (size) {
case 1:
memcpy(&d1, buf, 1);
if (put_user(d1, target))
goto fault;
break;
case 2:
memcpy(&d2, buf, 2);
if (put_user(d2, target))
goto fault;
break;
case 4:
memcpy(&d4, buf, 4);
if (put_user(d4, target))
goto fault;
break;
case 8:
memcpy(&d8, buf, 8);
if (put_user(d8, target))
goto fault;
break;
default:
WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
return ES_UNSUPPORTED;
}
return ES_OK;
fault:
if (user_mode(ctxt->regs))
error_code |= X86_PF_USER;
ctxt->fi.vector = X86_TRAP_PF;
ctxt->fi.error_code = error_code;
ctxt->fi.cr2 = (unsigned long)dst;
return ES_EXCEPTION;
}
static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
char *src, char *buf, size_t size)
{
unsigned long error_code = X86_PF_PROT;
char __user *s = (char __user *)src;
u64 d8;
u32 d4;
u16 d2;
u8 d1;
switch (size) {
case 1:
if (get_user(d1, s))
goto fault;
memcpy(buf, &d1, 1);
break;
case 2:
if (get_user(d2, s))
goto fault;
memcpy(buf, &d2, 2);
break;
case 4:
if (get_user(d4, s))
goto fault;
memcpy(buf, &d4, 4);
break;
case 8:
if (get_user(d8, s))
goto fault;
memcpy(buf, &d8, 8);
break;
default:
WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
return ES_UNSUPPORTED;
}
return ES_OK;
fault:
if (user_mode(ctxt->regs))
error_code |= X86_PF_USER;
ctxt->fi.vector = X86_TRAP_PF;
ctxt->fi.error_code = error_code;
ctxt->fi.cr2 = (unsigned long)src;
return ES_EXCEPTION;
}
static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
unsigned long vaddr, phys_addr_t *paddr)
{
unsigned long va = (unsigned long)vaddr;
unsigned int level;
phys_addr_t pa;
pgd_t *pgd;
pte_t *pte;
pgd = __va(read_cr3_pa());
pgd = &pgd[pgd_index(va)];
pte = lookup_address_in_pgd(pgd, va, &level);
if (!pte) {
ctxt->fi.vector = X86_TRAP_PF;
ctxt->fi.cr2 = vaddr;
ctxt->fi.error_code = 0;
if (user_mode(ctxt->regs))
ctxt->fi.error_code |= X86_PF_USER;
return false;
}
pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
pa |= va & ~page_level_mask(level);
*paddr = pa;
return true;
}
/* Include code shared with pre-decompression boot stage */
#include "sev-es-shared.c"
void noinstr __sev_es_nmi_complete(void)
{
struct ghcb_state state;
struct ghcb *ghcb;
ghcb = sev_es_get_ghcb(&state);
vc_ghcb_invalidate(ghcb);
ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_NMI_COMPLETE);
ghcb_set_sw_exit_info_1(ghcb, 0);
ghcb_set_sw_exit_info_2(ghcb, 0);
sev_es_wr_ghcb_msr(__pa_nodebug(ghcb));
VMGEXIT();
sev_es_put_ghcb(&state);
}
static u64 get_jump_table_addr(void)
{
struct ghcb_state state;
unsigned long flags;
struct ghcb *ghcb;
u64 ret = 0;
local_irq_save(flags);
ghcb = sev_es_get_ghcb(&state);
vc_ghcb_invalidate(ghcb);
ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_JUMP_TABLE);
ghcb_set_sw_exit_info_1(ghcb, SVM_VMGEXIT_GET_AP_JUMP_TABLE);
ghcb_set_sw_exit_info_2(ghcb, 0);
sev_es_wr_ghcb_msr(__pa(ghcb));
VMGEXIT();
if (ghcb_sw_exit_info_1_is_valid(ghcb) &&
ghcb_sw_exit_info_2_is_valid(ghcb))
ret = ghcb->save.sw_exit_info_2;
sev_es_put_ghcb(&state);
local_irq_restore(flags);
return ret;
}
int sev_es_setup_ap_jump_table(struct real_mode_header *rmh)
{
u16 startup_cs, startup_ip;
phys_addr_t jump_table_pa;
u64 jump_table_addr;
u16 __iomem *jump_table;
jump_table_addr = get_jump_table_addr();
/* On UP guests there is no jump table so this is not a failure */
if (!jump_table_addr)
return 0;
/* Check if AP Jump Table is page-aligned */
if (jump_table_addr & ~PAGE_MASK)
return -EINVAL;
jump_table_pa = jump_table_addr & PAGE_MASK;
startup_cs = (u16)(rmh->trampoline_start >> 4);
startup_ip = (u16)(rmh->sev_es_trampoline_start -
rmh->trampoline_start);
jump_table = ioremap_encrypted(jump_table_pa, PAGE_SIZE);
if (!jump_table)
return -EIO;
writew(startup_ip, &jump_table[0]);
writew(startup_cs, &jump_table[1]);
iounmap(jump_table);
return 0;
}
/*
* This is needed by the OVMF UEFI firmware which will use whatever it finds in
* the GHCB MSR as its GHCB to talk to the hypervisor. So make sure the per-cpu
* runtime GHCBs used by the kernel are also mapped in the EFI page-table.
*/
int __init sev_es_efi_map_ghcbs(pgd_t *pgd)
{
struct sev_es_runtime_data *data;
unsigned long address, pflags;
int cpu;
u64 pfn;
if (!sev_es_active())
return 0;
pflags = _PAGE_NX | _PAGE_RW;
for_each_possible_cpu(cpu) {
data = per_cpu(runtime_data, cpu);
address = __pa(&data->ghcb_page);
pfn = address >> PAGE_SHIFT;
if (kernel_map_pages_in_pgd(pgd, pfn, address, 1, pflags))
return 1;
}
return 0;
}
static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
{
struct pt_regs *regs = ctxt->regs;
enum es_result ret;
u64 exit_info_1;
/* Is it a WRMSR? */
exit_info_1 = (ctxt->insn.opcode.bytes[1] == 0x30) ? 1 : 0;
ghcb_set_rcx(ghcb, regs->cx);
if (exit_info_1) {
ghcb_set_rax(ghcb, regs->ax);
ghcb_set_rdx(ghcb, regs->dx);
}
ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, exit_info_1, 0);
if ((ret == ES_OK) && (!exit_info_1)) {
regs->ax = ghcb->save.rax;
regs->dx = ghcb->save.rdx;
}
return ret;
}
/*
* This function runs on the first #VC exception after the kernel
* switched to virtual addresses.
*/
static bool __init sev_es_setup_ghcb(void)
{
/* First make sure the hypervisor talks a supported protocol. */
if (!sev_es_negotiate_protocol())
return false;
/*
* Clear the boot_ghcb. The first exception comes in before the bss
* section is cleared.
*/
memset(&boot_ghcb_page, 0, PAGE_SIZE);
/* Alright - Make the boot-ghcb public */
boot_ghcb = &boot_ghcb_page;
return true;
}
#ifdef CONFIG_HOTPLUG_CPU
static void sev_es_ap_hlt_loop(void)
{
struct ghcb_state state;
struct ghcb *ghcb;
ghcb = sev_es_get_ghcb(&state);
while (true) {
vc_ghcb_invalidate(ghcb);
ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_HLT_LOOP);
ghcb_set_sw_exit_info_1(ghcb, 0);
ghcb_set_sw_exit_info_2(ghcb, 0);
sev_es_wr_ghcb_msr(__pa(ghcb));
VMGEXIT();
/* Wakeup signal? */
if (ghcb_sw_exit_info_2_is_valid(ghcb) &&
ghcb->save.sw_exit_info_2)
break;
}
sev_es_put_ghcb(&state);
}
/*
* Play_dead handler when running under SEV-ES. This is needed because
* the hypervisor can't deliver an SIPI request to restart the AP.
* Instead the kernel has to issue a VMGEXIT to halt the VCPU until the
* hypervisor wakes it up again.
*/
static void sev_es_play_dead(void)
{
play_dead_common();
/* IRQs now disabled */
sev_es_ap_hlt_loop();
/*
* If we get here, the VCPU was woken up again. Jump to CPU
* startup code to get it back online.
*/
start_cpu0();
}
#else /* CONFIG_HOTPLUG_CPU */
#define sev_es_play_dead native_play_dead
#endif /* CONFIG_HOTPLUG_CPU */
#ifdef CONFIG_SMP
static void __init sev_es_setup_play_dead(void)
{
smp_ops.play_dead = sev_es_play_dead;
}
#else
static inline void sev_es_setup_play_dead(void) { }
#endif
static void __init alloc_runtime_data(int cpu)
{
struct sev_es_runtime_data *data;
data = memblock_alloc(sizeof(*data), PAGE_SIZE);
if (!data)
panic("Can't allocate SEV-ES runtime data");
per_cpu(runtime_data, cpu) = data;
}
static void __init init_ghcb(int cpu)
{
struct sev_es_runtime_data *data;
int err;
data = per_cpu(runtime_data, cpu);
err = early_set_memory_decrypted((unsigned long)&data->ghcb_page,
sizeof(data->ghcb_page));
if (err)
panic("Can't map GHCBs unencrypted");
memset(&data->ghcb_page, 0, sizeof(data->ghcb_page));
data->ghcb_active = false;
data->backup_ghcb_active = false;
}
void __init sev_es_init_vc_handling(void)
{
int cpu;
BUILD_BUG_ON(offsetof(struct sev_es_runtime_data, ghcb_page) % PAGE_SIZE);
if (!sev_es_active())
return;
/* Enable SEV-ES special handling */
static_branch_enable(&sev_es_enable_key);
/* Initialize per-cpu GHCB pages */
for_each_possible_cpu(cpu) {
alloc_runtime_data(cpu);
init_ghcb(cpu);
setup_vc_stacks(cpu);
}
sev_es_setup_play_dead();
/* Secondary CPUs use the runtime #VC handler */
initial_vc_handler = (unsigned long)safe_stack_exc_vmm_communication;
}
static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt)
{
int trapnr = ctxt->fi.vector;
if (trapnr == X86_TRAP_PF)
native_write_cr2(ctxt->fi.cr2);
ctxt->regs->orig_ax = ctxt->fi.error_code;
do_early_exception(ctxt->regs, trapnr);
}
static long *vc_insn_get_reg(struct es_em_ctxt *ctxt)
{
long *reg_array;
int offset;
reg_array = (long *)ctxt->regs;
offset = insn_get_modrm_reg_off(&ctxt->insn, ctxt->regs);
if (offset < 0)
return NULL;
offset /= sizeof(long);
return reg_array + offset;
}
static long *vc_insn_get_rm(struct es_em_ctxt *ctxt)
{
long *reg_array;
int offset;
reg_array = (long *)ctxt->regs;
offset = insn_get_modrm_rm_off(&ctxt->insn, ctxt->regs);
if (offset < 0)
return NULL;
offset /= sizeof(long);
return reg_array + offset;
}
static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
unsigned int bytes, bool read)
{
u64 exit_code, exit_info_1, exit_info_2;
unsigned long ghcb_pa = __pa(ghcb);
phys_addr_t paddr;
void __user *ref;
ref = insn_get_addr_ref(&ctxt->insn, ctxt->regs);
if (ref == (void __user *)-1L)
return ES_UNSUPPORTED;
exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE;
if (!vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr)) {
if (!read)
ctxt->fi.error_code |= X86_PF_WRITE;
return ES_EXCEPTION;
}
exit_info_1 = paddr;
/* Can never be greater than 8 */
exit_info_2 = bytes;
ghcb->save.sw_scratch = ghcb_pa + offsetof(struct ghcb, shared_buffer);
return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2);
}
static enum es_result vc_handle_mmio_twobyte_ops(struct ghcb *ghcb,
struct es_em_ctxt *ctxt)
{
struct insn *insn = &ctxt->insn;
unsigned int bytes = 0;
enum es_result ret;
int sign_byte;
long *reg_data;
switch (insn->opcode.bytes[1]) {
/* MMIO Read w/ zero-extension */
case 0xb6:
bytes = 1;
fallthrough;
case 0xb7:
if (!bytes)
bytes = 2;
ret = vc_do_mmio(ghcb, ctxt, bytes, true);
if (ret)
break;
/* Zero extend based on operand size */
reg_data = vc_insn_get_reg(ctxt);
if (!reg_data)
return ES_DECODE_FAILED;
memset(reg_data, 0, insn->opnd_bytes);
memcpy(reg_data, ghcb->shared_buffer, bytes);
break;
/* MMIO Read w/ sign-extension */
case 0xbe:
bytes = 1;
fallthrough;
case 0xbf:
if (!bytes)
bytes = 2;
ret = vc_do_mmio(ghcb, ctxt, bytes, true);
if (ret)
break;
/* Sign extend based on operand size */
reg_data = vc_insn_get_reg(ctxt);
if (!reg_data)
return ES_DECODE_FAILED;
if (bytes == 1) {
u8 *val = (u8 *)ghcb->shared_buffer;
sign_byte = (*val & 0x80) ? 0xff : 0x00;
} else {
u16 *val = (u16 *)ghcb->shared_buffer;
sign_byte = (*val & 0x8000) ? 0xff : 0x00;
}
memset(reg_data, sign_byte, insn->opnd_bytes);
memcpy(reg_data, ghcb->shared_buffer, bytes);
break;
default:
ret = ES_UNSUPPORTED;
}
return ret;
}
/*
* The MOVS instruction has two memory operands, which raises the
* problem that it is not known whether the access to the source or the
* destination caused the #VC exception (and hence whether an MMIO read
* or write operation needs to be emulated).
*
* Instead of playing games with walking page-tables and trying to guess
* whether the source or destination is an MMIO range, split the move
* into two operations, a read and a write with only one memory operand.
* This will cause a nested #VC exception on the MMIO address which can
* then be handled.
*
* This implementation has the benefit that it also supports MOVS where
* source _and_ destination are MMIO regions.
*
* It will slow MOVS on MMIO down a lot, but in SEV-ES guests it is a
* rare operation. If it turns out to be a performance problem the split
* operations can be moved to memcpy_fromio() and memcpy_toio().
*/
static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt,
unsigned int bytes)
{
unsigned long ds_base, es_base;
unsigned char *src, *dst;
unsigned char buffer[8];
enum es_result ret;
bool rep;
int off;
ds_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_DS);
es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
if (ds_base == -1L || es_base == -1L) {
ctxt->fi.vector = X86_TRAP_GP;
ctxt->fi.error_code = 0;
return ES_EXCEPTION;
}
src = ds_base + (unsigned char *)ctxt->regs->si;
dst = es_base + (unsigned char *)ctxt->regs->di;
ret = vc_read_mem(ctxt, src, buffer, bytes);
if (ret != ES_OK)
return ret;
ret = vc_write_mem(ctxt, dst, buffer, bytes);
if (ret != ES_OK)
return ret;
if (ctxt->regs->flags & X86_EFLAGS_DF)
off = -bytes;
else
off = bytes;
ctxt->regs->si += off;
ctxt->regs->di += off;
rep = insn_has_rep_prefix(&ctxt->insn);
if (rep)
ctxt->regs->cx -= 1;
if (!rep || ctxt->regs->cx == 0)
return ES_OK;
else
return ES_RETRY;
}
static enum es_result vc_handle_mmio(struct ghcb *ghcb,
struct es_em_ctxt *ctxt)
{
struct insn *insn = &ctxt->insn;
unsigned int bytes = 0;
enum es_result ret;
long *reg_data;
switch (insn->opcode.bytes[0]) {
/* MMIO Write */
case 0x88:
bytes = 1;
fallthrough;
case 0x89:
if (!bytes)
bytes = insn->opnd_bytes;
reg_data = vc_insn_get_reg(ctxt);
if (!reg_data)
return ES_DECODE_FAILED;
memcpy(ghcb->shared_buffer, reg_data, bytes);
ret = vc_do_mmio(ghcb, ctxt, bytes, false);
break;
case 0xc6:
bytes = 1;
fallthrough;
case 0xc7:
if (!bytes)
bytes = insn->opnd_bytes;
memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes);
ret = vc_do_mmio(ghcb, ctxt, bytes, false);
break;
/* MMIO Read */
case 0x8a:
bytes = 1;
fallthrough;
case 0x8b:
if (!bytes)
bytes = insn->opnd_bytes;
ret = vc_do_mmio(ghcb, ctxt, bytes, true);
if (ret)
break;
reg_data = vc_insn_get_reg(ctxt);
if (!reg_data)
return ES_DECODE_FAILED;
/* Zero-extend for 32-bit operation */
if (bytes == 4)
*reg_data = 0;
memcpy(reg_data, ghcb->shared_buffer, bytes);
break;
/* MOVS instruction */
case 0xa4:
bytes = 1;
fallthrough;
case 0xa5:
if (!bytes)
bytes = insn->opnd_bytes;
ret = vc_handle_mmio_movs(ctxt, bytes);
break;
/* Two-Byte Opcodes */
case 0x0f:
ret = vc_handle_mmio_twobyte_ops(ghcb, ctxt);
break;
default:
ret = ES_UNSUPPORTED;
}
return ret;
}
static enum es_result vc_handle_dr7_write(struct ghcb *ghcb,
struct es_em_ctxt *ctxt)
{
struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
long val, *reg = vc_insn_get_rm(ctxt);
enum es_result ret;
if (!reg)
return ES_DECODE_FAILED;
val = *reg;
/* Upper 32 bits must be written as zeroes */
if (val >> 32) {
ctxt->fi.vector = X86_TRAP_GP;
ctxt->fi.error_code = 0;
return ES_EXCEPTION;
}
/* Clear out other reserved bits and set bit 10 */
val = (val & 0xffff23ffL) | BIT(10);
/* Early non-zero writes to DR7 are not supported */
if (!data && (val & ~DR7_RESET_VALUE))
return ES_UNSUPPORTED;
/* Using a value of 0 for ExitInfo1 means RAX holds the value */
ghcb_set_rax(ghcb, val);
ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0);
if (ret != ES_OK)
return ret;
if (data)
data->dr7 = val;
return ES_OK;
}
static enum es_result vc_handle_dr7_read(struct ghcb *ghcb,
struct es_em_ctxt *ctxt)
{
struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
long *reg = vc_insn_get_rm(ctxt);
if (!reg)
return ES_DECODE_FAILED;
if (data)
*reg = data->dr7;
else
*reg = DR7_RESET_VALUE;
return ES_OK;
}
static enum es_result vc_handle_wbinvd(struct ghcb *ghcb,
struct es_em_ctxt *ctxt)
{
return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0);
}
static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
{
enum es_result ret;
ghcb_set_rcx(ghcb, ctxt->regs->cx);
ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0);
if (ret != ES_OK)
return ret;
if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb)))
return ES_VMM_ERROR;
ctxt->regs->ax = ghcb->save.rax;
ctxt->regs->dx = ghcb->save.rdx;
return ES_OK;
}
static enum es_result vc_handle_monitor(struct ghcb *ghcb,
struct es_em_ctxt *ctxt)
{
/*
* Treat it as a NOP and do not leak a physical address to the
* hypervisor.
*/
return ES_OK;
}
static enum es_result vc_handle_mwait(struct ghcb *ghcb,
struct es_em_ctxt *ctxt)
{
/* Treat the same as MONITOR/MONITORX */
return ES_OK;
}
static enum es_result vc_handle_vmmcall(struct ghcb *ghcb,
struct es_em_ctxt *ctxt)
{
enum es_result ret;
ghcb_set_rax(ghcb, ctxt->regs->ax);
ghcb_set_cpl(ghcb, user_mode(ctxt->regs) ? 3 : 0);
if (x86_platform.hyper.sev_es_hcall_prepare)
x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs);
ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0);
if (ret != ES_OK)
return ret;
if (!ghcb_rax_is_valid(ghcb))
return ES_VMM_ERROR;
ctxt->regs->ax = ghcb->save.rax;
/*
* Call sev_es_hcall_finish() after regs->ax is already set.
* This allows the hypervisor handler to overwrite it again if
* necessary.
*/
if (x86_platform.hyper.sev_es_hcall_finish &&
!x86_platform.hyper.sev_es_hcall_finish(ghcb, ctxt->regs))
return ES_VMM_ERROR;
return ES_OK;
}
static enum es_result vc_handle_trap_ac(struct ghcb *ghcb,
struct es_em_ctxt *ctxt)
{
/*
* Calling ecx_alignment_check() directly does not work, because it
* enables IRQs and the GHCB is active. Forward the exception and call
* it later from vc_forward_exception().
*/
ctxt->fi.vector = X86_TRAP_AC;
ctxt->fi.error_code = 0;
return ES_EXCEPTION;
}
static __always_inline void vc_handle_trap_db(struct pt_regs *regs)
{
if (user_mode(regs))
noist_exc_debug(regs);
else
exc_debug(regs);
}
static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt,
struct ghcb *ghcb,
unsigned long exit_code)
{
enum es_result result;
switch (exit_code) {
case SVM_EXIT_READ_DR7:
result = vc_handle_dr7_read(ghcb, ctxt);
break;
case SVM_EXIT_WRITE_DR7:
result = vc_handle_dr7_write(ghcb, ctxt);
break;
case SVM_EXIT_EXCP_BASE + X86_TRAP_AC:
result = vc_handle_trap_ac(ghcb, ctxt);
break;
case SVM_EXIT_RDTSC:
case SVM_EXIT_RDTSCP:
result = vc_handle_rdtsc(ghcb, ctxt, exit_code);
break;
case SVM_EXIT_RDPMC:
result = vc_handle_rdpmc(ghcb, ctxt);
break;
case SVM_EXIT_INVD:
pr_err_ratelimited("#VC exception for INVD??? Seriously???\n");
result = ES_UNSUPPORTED;
break;
case SVM_EXIT_CPUID:
result = vc_handle_cpuid(ghcb, ctxt);
break;
case SVM_EXIT_IOIO:
result = vc_handle_ioio(ghcb, ctxt);
break;
case SVM_EXIT_MSR:
result = vc_handle_msr(ghcb, ctxt);
break;
case SVM_EXIT_VMMCALL:
result = vc_handle_vmmcall(ghcb, ctxt);
break;
case SVM_EXIT_WBINVD:
result = vc_handle_wbinvd(ghcb, ctxt);
break;
case SVM_EXIT_MONITOR:
result = vc_handle_monitor(ghcb, ctxt);
break;
case SVM_EXIT_MWAIT:
result = vc_handle_mwait(ghcb, ctxt);
break;
case SVM_EXIT_NPF:
result = vc_handle_mmio(ghcb, ctxt);
break;
default:
/*
* Unexpected #VC exception
*/
result = ES_UNSUPPORTED;
}
return result;
}
static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt)
{
long error_code = ctxt->fi.error_code;
int trapnr = ctxt->fi.vector;
ctxt->regs->orig_ax = ctxt->fi.error_code;
switch (trapnr) {
case X86_TRAP_GP:
exc_general_protection(ctxt->regs, error_code);
break;
case X86_TRAP_UD:
exc_invalid_op(ctxt->regs);
break;
case X86_TRAP_AC:
exc_alignment_check(ctxt->regs, error_code);
break;
default:
pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n");
BUG();
}
}
static __always_inline bool on_vc_fallback_stack(struct pt_regs *regs)
{
unsigned long sp = (unsigned long)regs;
return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2));
}
/*
* Main #VC exception handler. It is called when the entry code was able to
* switch off the IST to a safe kernel stack.
*
* With the current implementation it is always possible to switch to a safe
* stack because #VC exceptions only happen at known places, like intercepted
* instructions or accesses to MMIO areas/IO ports. They can also happen with
* code instrumentation when the hypervisor intercepts #DB, but the critical
* paths are forbidden to be instrumented, so #DB exceptions currently also
* only happen in safe places.
*/
DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
{
struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
struct ghcb_state state;
struct es_em_ctxt ctxt;
enum es_result result;
struct ghcb *ghcb;
lockdep_assert_irqs_disabled();
/*
* Handle #DB before calling into !noinstr code to avoid recursive #DB.
*/
if (error_code == SVM_EXIT_EXCP_BASE + X86_TRAP_DB) {
vc_handle_trap_db(regs);
return;
}
instrumentation_begin();
/*
* This is invoked through an interrupt gate, so IRQs are disabled. The
* code below might walk page-tables for user or kernel addresses, so
* keep the IRQs disabled to protect us against concurrent TLB flushes.
*/
ghcb = sev_es_get_ghcb(&state);
if (!ghcb) {
/*
* Mark GHCBs inactive so that panic() is able to print the
* message.
*/
data->ghcb_active = false;
data->backup_ghcb_active = false;
panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use");
}
vc_ghcb_invalidate(ghcb);
result = vc_init_em_ctxt(&ctxt, regs, error_code);
if (result == ES_OK)
result = vc_handle_exitcode(&ctxt, ghcb, error_code);
sev_es_put_ghcb(&state);
/* Done - now check the result */
switch (result) {
case ES_OK:
vc_finish_insn(&ctxt);
break;
case ES_UNSUPPORTED:
pr_err_ratelimited("Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n",
error_code, regs->ip);
goto fail;
case ES_VMM_ERROR:
pr_err_ratelimited("Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
error_code, regs->ip);
goto fail;
case ES_DECODE_FAILED:
pr_err_ratelimited("Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
error_code, regs->ip);
goto fail;
case ES_EXCEPTION:
vc_forward_exception(&ctxt);
break;
case ES_RETRY:
/* Nothing to do */
break;
default:
pr_emerg("Unknown result in %s():%d\n", __func__, result);
/*
* Emulating the instruction which caused the #VC exception
* failed - can't continue so print debug information
*/
BUG();
}
out:
instrumentation_end();
return;
fail:
if (user_mode(regs)) {
/*
* Do not kill the machine if user-space triggered the
* exception. Send SIGBUS instead and let user-space deal with
* it.
*/
force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)0);
} else {
pr_emerg("PANIC: Unhandled #VC exception in kernel space (result=%d)\n",
result);
/* Show some debug info */
show_regs(regs);
/* Ask hypervisor to sev_es_terminate */
sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
/* If that fails and we get here - just panic */
panic("Returned from Terminate-Request to Hypervisor\n");
}
goto out;
}
/* This handler runs on the #VC fall-back stack. It can cause further #VC exceptions */
DEFINE_IDTENTRY_VC_IST(exc_vmm_communication)
{
instrumentation_begin();
panic("Can't handle #VC exception from unsupported context\n");
instrumentation_end();
}
DEFINE_IDTENTRY_VC(exc_vmm_communication)
{
if (likely(!on_vc_fallback_stack(regs)))
safe_stack_exc_vmm_communication(regs, error_code);
else
ist_exc_vmm_communication(regs, error_code);
}
bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
{
unsigned long exit_code = regs->orig_ax;
struct es_em_ctxt ctxt;
enum es_result result;
/* Do initial setup or terminate the guest */
if (unlikely(boot_ghcb == NULL && !sev_es_setup_ghcb()))
sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
vc_ghcb_invalidate(boot_ghcb);
result = vc_init_em_ctxt(&ctxt, regs, exit_code);
if (result == ES_OK)
result = vc_handle_exitcode(&ctxt, boot_ghcb, exit_code);
/* Done - now check the result */
switch (result) {
case ES_OK:
vc_finish_insn(&ctxt);
break;
case ES_UNSUPPORTED:
early_printk("PANIC: Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n",
exit_code, regs->ip);
goto fail;
case ES_VMM_ERROR:
early_printk("PANIC: Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
exit_code, regs->ip);
goto fail;
case ES_DECODE_FAILED:
early_printk("PANIC: Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
exit_code, regs->ip);
goto fail;
case ES_EXCEPTION:
vc_early_forward_exception(&ctxt);
break;
case ES_RETRY:
/* Nothing to do */
break;
default:
BUG();
}
return true;
fail:
show_regs(regs);
while (true)
halt();
}
|