-
Notifications
You must be signed in to change notification settings - Fork 13
/
Copy pathspapr_hcall.c
1907 lines (1604 loc) · 56.6 KB
/
spapr_hcall.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
#include "qemu/osdep.h"
#include "qapi/error.h"
#include "sysemu/hw_accel.h"
#include "sysemu/sysemu.h"
#include "qemu/log.h"
#include "qemu/error-report.h"
#include "cpu.h"
#include "exec/exec-all.h"
#include "helper_regs.h"
#include "hw/ppc/spapr.h"
#include "hw/ppc/spapr_cpu_core.h"
#include "mmu-hash64.h"
#include "cpu-models.h"
#include "trace.h"
#include "kvm_ppc.h"
#include "hw/ppc/spapr_ovec.h"
#include "mmu-book3s-v3.h"
#include "hw/mem/memory-device.h"
static bool has_spr(PowerPCCPU *cpu, int spr)
{
/* We can test whether the SPR is defined by checking for a valid name */
return cpu->env.spr_cb[spr].name != NULL;
}
static inline bool valid_ptex(PowerPCCPU *cpu, target_ulong ptex)
{
/*
* hash value/pteg group index is normalized by HPT mask
*/
if (((ptex & ~7ULL) / HPTES_PER_GROUP) & ~ppc_hash64_hpt_mask(cpu)) {
return false;
}
return true;
}
static bool is_ram_address(SpaprMachineState *spapr, hwaddr addr)
{
MachineState *machine = MACHINE(spapr);
DeviceMemoryState *dms = machine->device_memory;
if (addr < machine->ram_size) {
return true;
}
if ((addr >= dms->base)
&& ((addr - dms->base) < memory_region_size(&dms->mr))) {
return true;
}
return false;
}
static target_ulong h_enter(PowerPCCPU *cpu, SpaprMachineState *spapr,
target_ulong opcode, target_ulong *args)
{
target_ulong flags = args[0];
target_ulong ptex = args[1];
target_ulong pteh = args[2];
target_ulong ptel = args[3];
unsigned apshift;
target_ulong raddr;
target_ulong slot;
const ppc_hash_pte64_t *hptes;
apshift = ppc_hash64_hpte_page_shift_noslb(cpu, pteh, ptel);
if (!apshift) {
/* Bad page size encoding */
return H_PARAMETER;
}
raddr = (ptel & HPTE64_R_RPN) & ~((1ULL << apshift) - 1);
if (is_ram_address(spapr, raddr)) {
/* Regular RAM - should have WIMG=0010 */
if ((ptel & HPTE64_R_WIMG) != HPTE64_R_M) {
return H_PARAMETER;
}
} else {
target_ulong wimg_flags;
/* Looks like an IO address */
/* FIXME: What WIMG combinations could be sensible for IO?
* For now we allow WIMG=010x, but are there others? */
/* FIXME: Should we check against registered IO addresses? */
wimg_flags = (ptel & (HPTE64_R_W | HPTE64_R_I | HPTE64_R_M));
if (wimg_flags != HPTE64_R_I &&
wimg_flags != (HPTE64_R_I | HPTE64_R_M)) {
return H_PARAMETER;
}
}
pteh &= ~0x60ULL;
if (!valid_ptex(cpu, ptex)) {
return H_PARAMETER;
}
slot = ptex & 7ULL;
ptex = ptex & ~7ULL;
if (likely((flags & H_EXACT) == 0)) {
hptes = ppc_hash64_map_hptes(cpu, ptex, HPTES_PER_GROUP);
for (slot = 0; slot < 8; slot++) {
if (!(ppc_hash64_hpte0(cpu, hptes, slot) & HPTE64_V_VALID)) {
break;
}
}
ppc_hash64_unmap_hptes(cpu, hptes, ptex, HPTES_PER_GROUP);
if (slot == 8) {
return H_PTEG_FULL;
}
} else {
hptes = ppc_hash64_map_hptes(cpu, ptex + slot, 1);
if (ppc_hash64_hpte0(cpu, hptes, 0) & HPTE64_V_VALID) {
ppc_hash64_unmap_hptes(cpu, hptes, ptex + slot, 1);
return H_PTEG_FULL;
}
ppc_hash64_unmap_hptes(cpu, hptes, ptex, 1);
}
ppc_hash64_store_hpte(cpu, ptex + slot, pteh | HPTE64_V_HPTE_DIRTY, ptel);
args[0] = ptex + slot;
return H_SUCCESS;
}
typedef enum {
REMOVE_SUCCESS = 0,
REMOVE_NOT_FOUND = 1,
REMOVE_PARM = 2,
REMOVE_HW = 3,
} RemoveResult;
static RemoveResult remove_hpte(PowerPCCPU *cpu, target_ulong ptex,
target_ulong avpn,
target_ulong flags,
target_ulong *vp, target_ulong *rp)
{
const ppc_hash_pte64_t *hptes;
target_ulong v, r;
if (!valid_ptex(cpu, ptex)) {
return REMOVE_PARM;
}
hptes = ppc_hash64_map_hptes(cpu, ptex, 1);
v = ppc_hash64_hpte0(cpu, hptes, 0);
r = ppc_hash64_hpte1(cpu, hptes, 0);
ppc_hash64_unmap_hptes(cpu, hptes, ptex, 1);
if ((v & HPTE64_V_VALID) == 0 ||
((flags & H_AVPN) && (v & ~0x7fULL) != avpn) ||
((flags & H_ANDCOND) && (v & avpn) != 0)) {
return REMOVE_NOT_FOUND;
}
*vp = v;
*rp = r;
ppc_hash64_store_hpte(cpu, ptex, HPTE64_V_HPTE_DIRTY, 0);
ppc_hash64_tlb_flush_hpte(cpu, ptex, v, r);
return REMOVE_SUCCESS;
}
static target_ulong h_remove(PowerPCCPU *cpu, SpaprMachineState *spapr,
target_ulong opcode, target_ulong *args)
{
CPUPPCState *env = &cpu->env;
target_ulong flags = args[0];
target_ulong ptex = args[1];
target_ulong avpn = args[2];
RemoveResult ret;
ret = remove_hpte(cpu, ptex, avpn, flags,
&args[0], &args[1]);
switch (ret) {
case REMOVE_SUCCESS:
check_tlb_flush(env, true);
return H_SUCCESS;
case REMOVE_NOT_FOUND:
return H_NOT_FOUND;
case REMOVE_PARM:
return H_PARAMETER;
case REMOVE_HW:
return H_HARDWARE;
}
g_assert_not_reached();
}
#define H_BULK_REMOVE_TYPE 0xc000000000000000ULL
#define H_BULK_REMOVE_REQUEST 0x4000000000000000ULL
#define H_BULK_REMOVE_RESPONSE 0x8000000000000000ULL
#define H_BULK_REMOVE_END 0xc000000000000000ULL
#define H_BULK_REMOVE_CODE 0x3000000000000000ULL
#define H_BULK_REMOVE_SUCCESS 0x0000000000000000ULL
#define H_BULK_REMOVE_NOT_FOUND 0x1000000000000000ULL
#define H_BULK_REMOVE_PARM 0x2000000000000000ULL
#define H_BULK_REMOVE_HW 0x3000000000000000ULL
#define H_BULK_REMOVE_RC 0x0c00000000000000ULL
#define H_BULK_REMOVE_FLAGS 0x0300000000000000ULL
#define H_BULK_REMOVE_ABSOLUTE 0x0000000000000000ULL
#define H_BULK_REMOVE_ANDCOND 0x0100000000000000ULL
#define H_BULK_REMOVE_AVPN 0x0200000000000000ULL
#define H_BULK_REMOVE_PTEX 0x00ffffffffffffffULL
#define H_BULK_REMOVE_MAX_BATCH 4
static target_ulong h_bulk_remove(PowerPCCPU *cpu, SpaprMachineState *spapr,
target_ulong opcode, target_ulong *args)
{
CPUPPCState *env = &cpu->env;
int i;
target_ulong rc = H_SUCCESS;
for (i = 0; i < H_BULK_REMOVE_MAX_BATCH; i++) {
target_ulong *tsh = &args[i*2];
target_ulong tsl = args[i*2 + 1];
target_ulong v, r, ret;
if ((*tsh & H_BULK_REMOVE_TYPE) == H_BULK_REMOVE_END) {
break;
} else if ((*tsh & H_BULK_REMOVE_TYPE) != H_BULK_REMOVE_REQUEST) {
return H_PARAMETER;
}
*tsh &= H_BULK_REMOVE_PTEX | H_BULK_REMOVE_FLAGS;
*tsh |= H_BULK_REMOVE_RESPONSE;
if ((*tsh & H_BULK_REMOVE_ANDCOND) && (*tsh & H_BULK_REMOVE_AVPN)) {
*tsh |= H_BULK_REMOVE_PARM;
return H_PARAMETER;
}
ret = remove_hpte(cpu, *tsh & H_BULK_REMOVE_PTEX, tsl,
(*tsh & H_BULK_REMOVE_FLAGS) >> 26,
&v, &r);
*tsh |= ret << 60;
switch (ret) {
case REMOVE_SUCCESS:
*tsh |= (r & (HPTE64_R_C | HPTE64_R_R)) << 43;
break;
case REMOVE_PARM:
rc = H_PARAMETER;
goto exit;
case REMOVE_HW:
rc = H_HARDWARE;
goto exit;
}
}
exit:
check_tlb_flush(env, true);
return rc;
}
static target_ulong h_protect(PowerPCCPU *cpu, SpaprMachineState *spapr,
target_ulong opcode, target_ulong *args)
{
CPUPPCState *env = &cpu->env;
target_ulong flags = args[0];
target_ulong ptex = args[1];
target_ulong avpn = args[2];
const ppc_hash_pte64_t *hptes;
target_ulong v, r;
if (!valid_ptex(cpu, ptex)) {
return H_PARAMETER;
}
hptes = ppc_hash64_map_hptes(cpu, ptex, 1);
v = ppc_hash64_hpte0(cpu, hptes, 0);
r = ppc_hash64_hpte1(cpu, hptes, 0);
ppc_hash64_unmap_hptes(cpu, hptes, ptex, 1);
if ((v & HPTE64_V_VALID) == 0 ||
((flags & H_AVPN) && (v & ~0x7fULL) != avpn)) {
return H_NOT_FOUND;
}
r &= ~(HPTE64_R_PP0 | HPTE64_R_PP | HPTE64_R_N |
HPTE64_R_KEY_HI | HPTE64_R_KEY_LO);
r |= (flags << 55) & HPTE64_R_PP0;
r |= (flags << 48) & HPTE64_R_KEY_HI;
r |= flags & (HPTE64_R_PP | HPTE64_R_N | HPTE64_R_KEY_LO);
ppc_hash64_store_hpte(cpu, ptex,
(v & ~HPTE64_V_VALID) | HPTE64_V_HPTE_DIRTY, 0);
ppc_hash64_tlb_flush_hpte(cpu, ptex, v, r);
/* Flush the tlb */
check_tlb_flush(env, true);
/* Don't need a memory barrier, due to qemu's global lock */
ppc_hash64_store_hpte(cpu, ptex, v | HPTE64_V_HPTE_DIRTY, r);
return H_SUCCESS;
}
static target_ulong h_read(PowerPCCPU *cpu, SpaprMachineState *spapr,
target_ulong opcode, target_ulong *args)
{
target_ulong flags = args[0];
target_ulong ptex = args[1];
uint8_t *hpte;
int i, ridx, n_entries = 1;
if (!valid_ptex(cpu, ptex)) {
return H_PARAMETER;
}
if (flags & H_READ_4) {
/* Clear the two low order bits */
ptex &= ~(3ULL);
n_entries = 4;
}
hpte = spapr->htab + (ptex * HASH_PTE_SIZE_64);
for (i = 0, ridx = 0; i < n_entries; i++) {
args[ridx++] = ldq_p(hpte);
args[ridx++] = ldq_p(hpte + (HASH_PTE_SIZE_64/2));
hpte += HASH_PTE_SIZE_64;
}
return H_SUCCESS;
}
struct SpaprPendingHpt {
/* These fields are read-only after initialization */
int shift;
QemuThread thread;
/* These fields are protected by the BQL */
bool complete;
/* These fields are private to the preparation thread if
* !complete, otherwise protected by the BQL */
int ret;
void *hpt;
};
static void free_pending_hpt(SpaprPendingHpt *pending)
{
if (pending->hpt) {
qemu_vfree(pending->hpt);
}
g_free(pending);
}
static void *hpt_prepare_thread(void *opaque)
{
SpaprPendingHpt *pending = opaque;
size_t size = 1ULL << pending->shift;
pending->hpt = qemu_memalign(size, size);
if (pending->hpt) {
memset(pending->hpt, 0, size);
pending->ret = H_SUCCESS;
} else {
pending->ret = H_NO_MEM;
}
qemu_mutex_lock_iothread();
if (SPAPR_MACHINE(qdev_get_machine())->pending_hpt == pending) {
/* Ready to go */
pending->complete = true;
} else {
/* We've been cancelled, clean ourselves up */
free_pending_hpt(pending);
}
qemu_mutex_unlock_iothread();
return NULL;
}
/* Must be called with BQL held */
static void cancel_hpt_prepare(SpaprMachineState *spapr)
{
SpaprPendingHpt *pending = spapr->pending_hpt;
/* Let the thread know it's cancelled */
spapr->pending_hpt = NULL;
if (!pending) {
/* Nothing to do */
return;
}
if (!pending->complete) {
/* thread will clean itself up */
return;
}
free_pending_hpt(pending);
}
/* Convert a return code from the KVM ioctl()s implementing resize HPT
* into a PAPR hypercall return code */
static target_ulong resize_hpt_convert_rc(int ret)
{
if (ret >= 100000) {
return H_LONG_BUSY_ORDER_100_SEC;
} else if (ret >= 10000) {
return H_LONG_BUSY_ORDER_10_SEC;
} else if (ret >= 1000) {
return H_LONG_BUSY_ORDER_1_SEC;
} else if (ret >= 100) {
return H_LONG_BUSY_ORDER_100_MSEC;
} else if (ret >= 10) {
return H_LONG_BUSY_ORDER_10_MSEC;
} else if (ret > 0) {
return H_LONG_BUSY_ORDER_1_MSEC;
}
switch (ret) {
case 0:
return H_SUCCESS;
case -EPERM:
return H_AUTHORITY;
case -EINVAL:
return H_PARAMETER;
case -ENXIO:
return H_CLOSED;
case -ENOSPC:
return H_PTEG_FULL;
case -EBUSY:
return H_BUSY;
case -ENOMEM:
return H_NO_MEM;
default:
return H_HARDWARE;
}
}
static target_ulong h_resize_hpt_prepare(PowerPCCPU *cpu,
SpaprMachineState *spapr,
target_ulong opcode,
target_ulong *args)
{
target_ulong flags = args[0];
int shift = args[1];
SpaprPendingHpt *pending = spapr->pending_hpt;
uint64_t current_ram_size;
int rc;
if (spapr->resize_hpt == SPAPR_RESIZE_HPT_DISABLED) {
return H_AUTHORITY;
}
if (!spapr->htab_shift) {
/* Radix guest, no HPT */
return H_NOT_AVAILABLE;
}
trace_spapr_h_resize_hpt_prepare(flags, shift);
if (flags != 0) {
return H_PARAMETER;
}
if (shift && ((shift < 18) || (shift > 46))) {
return H_PARAMETER;
}
current_ram_size = MACHINE(spapr)->ram_size + get_plugged_memory_size();
/* We only allow the guest to allocate an HPT one order above what
* we'd normally give them (to stop a small guest claiming a huge
* chunk of resources in the HPT */
if (shift > (spapr_hpt_shift_for_ramsize(current_ram_size) + 1)) {
return H_RESOURCE;
}
rc = kvmppc_resize_hpt_prepare(cpu, flags, shift);
if (rc != -ENOSYS) {
return resize_hpt_convert_rc(rc);
}
if (pending) {
/* something already in progress */
if (pending->shift == shift) {
/* and it's suitable */
if (pending->complete) {
return pending->ret;
} else {
return H_LONG_BUSY_ORDER_100_MSEC;
}
}
/* not suitable, cancel and replace */
cancel_hpt_prepare(spapr);
}
if (!shift) {
/* nothing to do */
return H_SUCCESS;
}
/* start new prepare */
pending = g_new0(SpaprPendingHpt, 1);
pending->shift = shift;
pending->ret = H_HARDWARE;
qemu_thread_create(&pending->thread, "sPAPR HPT prepare",
hpt_prepare_thread, pending, QEMU_THREAD_DETACHED);
spapr->pending_hpt = pending;
/* In theory we could estimate the time more accurately based on
* the new size, but there's not much point */
return H_LONG_BUSY_ORDER_100_MSEC;
}
static uint64_t new_hpte_load0(void *htab, uint64_t pteg, int slot)
{
uint8_t *addr = htab;
addr += pteg * HASH_PTEG_SIZE_64;
addr += slot * HASH_PTE_SIZE_64;
return ldq_p(addr);
}
static void new_hpte_store(void *htab, uint64_t pteg, int slot,
uint64_t pte0, uint64_t pte1)
{
uint8_t *addr = htab;
addr += pteg * HASH_PTEG_SIZE_64;
addr += slot * HASH_PTE_SIZE_64;
stq_p(addr, pte0);
stq_p(addr + HASH_PTE_SIZE_64 / 2, pte1);
}
static int rehash_hpte(PowerPCCPU *cpu,
const ppc_hash_pte64_t *hptes,
void *old_hpt, uint64_t oldsize,
void *new_hpt, uint64_t newsize,
uint64_t pteg, int slot)
{
uint64_t old_hash_mask = (oldsize >> 7) - 1;
uint64_t new_hash_mask = (newsize >> 7) - 1;
target_ulong pte0 = ppc_hash64_hpte0(cpu, hptes, slot);
target_ulong pte1;
uint64_t avpn;
unsigned base_pg_shift;
uint64_t hash, new_pteg, replace_pte0;
if (!(pte0 & HPTE64_V_VALID) || !(pte0 & HPTE64_V_BOLTED)) {
return H_SUCCESS;
}
pte1 = ppc_hash64_hpte1(cpu, hptes, slot);
base_pg_shift = ppc_hash64_hpte_page_shift_noslb(cpu, pte0, pte1);
assert(base_pg_shift); /* H_ENTER shouldn't allow a bad encoding */
avpn = HPTE64_V_AVPN_VAL(pte0) & ~(((1ULL << base_pg_shift) - 1) >> 23);
if (pte0 & HPTE64_V_SECONDARY) {
pteg = ~pteg;
}
if ((pte0 & HPTE64_V_SSIZE) == HPTE64_V_SSIZE_256M) {
uint64_t offset, vsid;
/* We only have 28 - 23 bits of offset in avpn */
offset = (avpn & 0x1f) << 23;
vsid = avpn >> 5;
/* We can find more bits from the pteg value */
if (base_pg_shift < 23) {
offset |= ((vsid ^ pteg) & old_hash_mask) << base_pg_shift;
}
hash = vsid ^ (offset >> base_pg_shift);
} else if ((pte0 & HPTE64_V_SSIZE) == HPTE64_V_SSIZE_1T) {
uint64_t offset, vsid;
/* We only have 40 - 23 bits of seg_off in avpn */
offset = (avpn & 0x1ffff) << 23;
vsid = avpn >> 17;
if (base_pg_shift < 23) {
offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask)
<< base_pg_shift;
}
hash = vsid ^ (vsid << 25) ^ (offset >> base_pg_shift);
} else {
error_report("rehash_pte: Bad segment size in HPTE");
return H_HARDWARE;
}
new_pteg = hash & new_hash_mask;
if (pte0 & HPTE64_V_SECONDARY) {
assert(~pteg == (hash & old_hash_mask));
new_pteg = ~new_pteg;
} else {
assert(pteg == (hash & old_hash_mask));
}
assert((oldsize != newsize) || (pteg == new_pteg));
replace_pte0 = new_hpte_load0(new_hpt, new_pteg, slot);
/*
* Strictly speaking, we don't need all these tests, since we only
* ever rehash bolted HPTEs. We might in future handle non-bolted
* HPTEs, though so make the logic correct for those cases as
* well.
*/
if (replace_pte0 & HPTE64_V_VALID) {
assert(newsize < oldsize);
if (replace_pte0 & HPTE64_V_BOLTED) {
if (pte0 & HPTE64_V_BOLTED) {
/* Bolted collision, nothing we can do */
return H_PTEG_FULL;
} else {
/* Discard this hpte */
return H_SUCCESS;
}
}
}
new_hpte_store(new_hpt, new_pteg, slot, pte0, pte1);
return H_SUCCESS;
}
static int rehash_hpt(PowerPCCPU *cpu,
void *old_hpt, uint64_t oldsize,
void *new_hpt, uint64_t newsize)
{
uint64_t n_ptegs = oldsize >> 7;
uint64_t pteg;
int slot;
int rc;
for (pteg = 0; pteg < n_ptegs; pteg++) {
hwaddr ptex = pteg * HPTES_PER_GROUP;
const ppc_hash_pte64_t *hptes
= ppc_hash64_map_hptes(cpu, ptex, HPTES_PER_GROUP);
if (!hptes) {
return H_HARDWARE;
}
for (slot = 0; slot < HPTES_PER_GROUP; slot++) {
rc = rehash_hpte(cpu, hptes, old_hpt, oldsize, new_hpt, newsize,
pteg, slot);
if (rc != H_SUCCESS) {
ppc_hash64_unmap_hptes(cpu, hptes, ptex, HPTES_PER_GROUP);
return rc;
}
}
ppc_hash64_unmap_hptes(cpu, hptes, ptex, HPTES_PER_GROUP);
}
return H_SUCCESS;
}
static void do_push_sregs_to_kvm_pr(CPUState *cs, run_on_cpu_data data)
{
int ret;
cpu_synchronize_state(cs);
ret = kvmppc_put_books_sregs(POWERPC_CPU(cs));
if (ret < 0) {
error_report("failed to push sregs to KVM: %s", strerror(-ret));
exit(1);
}
}
static void push_sregs_to_kvm_pr(SpaprMachineState *spapr)
{
CPUState *cs;
/*
* This is a hack for the benefit of KVM PR - it abuses the SDR1
* slot in kvm_sregs to communicate the userspace address of the
* HPT
*/
if (!kvm_enabled() || !spapr->htab) {
return;
}
CPU_FOREACH(cs) {
run_on_cpu(cs, do_push_sregs_to_kvm_pr, RUN_ON_CPU_NULL);
}
}
static target_ulong h_resize_hpt_commit(PowerPCCPU *cpu,
SpaprMachineState *spapr,
target_ulong opcode,
target_ulong *args)
{
target_ulong flags = args[0];
target_ulong shift = args[1];
SpaprPendingHpt *pending = spapr->pending_hpt;
int rc;
size_t newsize;
if (spapr->resize_hpt == SPAPR_RESIZE_HPT_DISABLED) {
return H_AUTHORITY;
}
if (!spapr->htab_shift) {
/* Radix guest, no HPT */
return H_NOT_AVAILABLE;
}
trace_spapr_h_resize_hpt_commit(flags, shift);
rc = kvmppc_resize_hpt_commit(cpu, flags, shift);
if (rc != -ENOSYS) {
rc = resize_hpt_convert_rc(rc);
if (rc == H_SUCCESS) {
/* Need to set the new htab_shift in the machine state */
spapr->htab_shift = shift;
}
return rc;
}
if (flags != 0) {
return H_PARAMETER;
}
if (!pending || (pending->shift != shift)) {
/* no matching prepare */
return H_CLOSED;
}
if (!pending->complete) {
/* prepare has not completed */
return H_BUSY;
}
/* Shouldn't have got past PREPARE without an HPT */
g_assert(spapr->htab_shift);
newsize = 1ULL << pending->shift;
rc = rehash_hpt(cpu, spapr->htab, HTAB_SIZE(spapr),
pending->hpt, newsize);
if (rc == H_SUCCESS) {
qemu_vfree(spapr->htab);
spapr->htab = pending->hpt;
spapr->htab_shift = pending->shift;
push_sregs_to_kvm_pr(spapr);
pending->hpt = NULL; /* so it's not free()d */
}
/* Clean up */
spapr->pending_hpt = NULL;
free_pending_hpt(pending);
return rc;
}
static target_ulong h_set_sprg0(PowerPCCPU *cpu, SpaprMachineState *spapr,
target_ulong opcode, target_ulong *args)
{
cpu_synchronize_state(CPU(cpu));
cpu->env.spr[SPR_SPRG0] = args[0];
return H_SUCCESS;
}
static target_ulong h_set_dabr(PowerPCCPU *cpu, SpaprMachineState *spapr,
target_ulong opcode, target_ulong *args)
{
if (!has_spr(cpu, SPR_DABR)) {
return H_HARDWARE; /* DABR register not available */
}
cpu_synchronize_state(CPU(cpu));
if (has_spr(cpu, SPR_DABRX)) {
cpu->env.spr[SPR_DABRX] = 0x3; /* Use Problem and Privileged state */
} else if (!(args[0] & 0x4)) { /* Breakpoint Translation set? */
return H_RESERVED_DABR;
}
cpu->env.spr[SPR_DABR] = args[0];
return H_SUCCESS;
}
static target_ulong h_set_xdabr(PowerPCCPU *cpu, SpaprMachineState *spapr,
target_ulong opcode, target_ulong *args)
{
target_ulong dabrx = args[1];
if (!has_spr(cpu, SPR_DABR) || !has_spr(cpu, SPR_DABRX)) {
return H_HARDWARE;
}
if ((dabrx & ~0xfULL) != 0 || (dabrx & H_DABRX_HYPERVISOR) != 0
|| (dabrx & (H_DABRX_KERNEL | H_DABRX_USER)) == 0) {
return H_PARAMETER;
}
cpu_synchronize_state(CPU(cpu));
cpu->env.spr[SPR_DABRX] = dabrx;
cpu->env.spr[SPR_DABR] = args[0];
return H_SUCCESS;
}
static target_ulong h_page_init(PowerPCCPU *cpu, SpaprMachineState *spapr,
target_ulong opcode, target_ulong *args)
{
target_ulong flags = args[0];
hwaddr dst = args[1];
hwaddr src = args[2];
hwaddr len = TARGET_PAGE_SIZE;
uint8_t *pdst, *psrc;
target_long ret = H_SUCCESS;
if (flags & ~(H_ICACHE_SYNCHRONIZE | H_ICACHE_INVALIDATE
| H_COPY_PAGE | H_ZERO_PAGE)) {
qemu_log_mask(LOG_UNIMP, "h_page_init: Bad flags (" TARGET_FMT_lx "\n",
flags);
return H_PARAMETER;
}
/* Map-in destination */
if (!is_ram_address(spapr, dst) || (dst & ~TARGET_PAGE_MASK) != 0) {
return H_PARAMETER;
}
pdst = cpu_physical_memory_map(dst, &len, 1);
if (!pdst || len != TARGET_PAGE_SIZE) {
return H_PARAMETER;
}
if (flags & H_COPY_PAGE) {
/* Map-in source, copy to destination, and unmap source again */
if (!is_ram_address(spapr, src) || (src & ~TARGET_PAGE_MASK) != 0) {
ret = H_PARAMETER;
goto unmap_out;
}
psrc = cpu_physical_memory_map(src, &len, 0);
if (!psrc || len != TARGET_PAGE_SIZE) {
ret = H_PARAMETER;
goto unmap_out;
}
memcpy(pdst, psrc, len);
cpu_physical_memory_unmap(psrc, len, 0, len);
} else if (flags & H_ZERO_PAGE) {
memset(pdst, 0, len); /* Just clear the destination page */
}
if (kvm_enabled() && (flags & H_ICACHE_SYNCHRONIZE) != 0) {
kvmppc_dcbst_range(cpu, pdst, len);
}
if (flags & (H_ICACHE_SYNCHRONIZE | H_ICACHE_INVALIDATE)) {
if (kvm_enabled()) {
kvmppc_icbi_range(cpu, pdst, len);
} else {
tb_flush(CPU(cpu));
}
}
unmap_out:
cpu_physical_memory_unmap(pdst, TARGET_PAGE_SIZE, 1, len);
return ret;
}
#define FLAGS_REGISTER_VPA 0x0000200000000000ULL
#define FLAGS_REGISTER_DTL 0x0000400000000000ULL
#define FLAGS_REGISTER_SLBSHADOW 0x0000600000000000ULL
#define FLAGS_DEREGISTER_VPA 0x0000a00000000000ULL
#define FLAGS_DEREGISTER_DTL 0x0000c00000000000ULL
#define FLAGS_DEREGISTER_SLBSHADOW 0x0000e00000000000ULL
#define VPA_MIN_SIZE 640
#define VPA_SIZE_OFFSET 0x4
#define VPA_SHARED_PROC_OFFSET 0x9
#define VPA_SHARED_PROC_VAL 0x2
static target_ulong register_vpa(PowerPCCPU *cpu, target_ulong vpa)
{
CPUState *cs = CPU(cpu);
CPUPPCState *env = &cpu->env;
SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
uint16_t size;
uint8_t tmp;
if (vpa == 0) {
hcall_dprintf("Can't cope with registering a VPA at logical 0\n");
return H_HARDWARE;
}
if (vpa % env->dcache_line_size) {
return H_PARAMETER;
}
/* FIXME: bounds check the address */
size = lduw_be_phys(cs->as, vpa + 0x4);
if (size < VPA_MIN_SIZE) {
return H_PARAMETER;
}
/* VPA is not allowed to cross a page boundary */
if ((vpa / 4096) != ((vpa + size - 1) / 4096)) {
return H_PARAMETER;
}
spapr_cpu->vpa_addr = vpa;
tmp = ldub_phys(cs->as, spapr_cpu->vpa_addr + VPA_SHARED_PROC_OFFSET);
tmp |= VPA_SHARED_PROC_VAL;
stb_phys(cs->as, spapr_cpu->vpa_addr + VPA_SHARED_PROC_OFFSET, tmp);
return H_SUCCESS;
}
static target_ulong deregister_vpa(PowerPCCPU *cpu, target_ulong vpa)
{
SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
if (spapr_cpu->slb_shadow_addr) {
return H_RESOURCE;
}
if (spapr_cpu->dtl_addr) {
return H_RESOURCE;
}
spapr_cpu->vpa_addr = 0;
return H_SUCCESS;
}
static target_ulong register_slb_shadow(PowerPCCPU *cpu, target_ulong addr)
{
SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
uint32_t size;
if (addr == 0) {
hcall_dprintf("Can't cope with SLB shadow at logical 0\n");
return H_HARDWARE;
}
size = ldl_be_phys(CPU(cpu)->as, addr + 0x4);
if (size < 0x8) {
return H_PARAMETER;
}
if ((addr / 4096) != ((addr + size - 1) / 4096)) {
return H_PARAMETER;
}
if (!spapr_cpu->vpa_addr) {
return H_RESOURCE;
}
spapr_cpu->slb_shadow_addr = addr;
spapr_cpu->slb_shadow_size = size;
return H_SUCCESS;
}
static target_ulong deregister_slb_shadow(PowerPCCPU *cpu, target_ulong addr)
{
SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
spapr_cpu->slb_shadow_addr = 0;
spapr_cpu->slb_shadow_size = 0;
return H_SUCCESS;
}
static target_ulong register_dtl(PowerPCCPU *cpu, target_ulong addr)
{
SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
uint32_t size;
if (addr == 0) {
hcall_dprintf("Can't cope with DTL at logical 0\n");
return H_HARDWARE;
}
size = ldl_be_phys(CPU(cpu)->as, addr + 0x4);
if (size < 48) {
return H_PARAMETER;
}
if (!spapr_cpu->vpa_addr) {
return H_RESOURCE;
}
spapr_cpu->dtl_addr = addr;
spapr_cpu->dtl_size = size;
return H_SUCCESS;
}
static target_ulong deregister_dtl(PowerPCCPU *cpu, target_ulong addr)
{