-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathspapr.c
4006 lines (3416 loc) · 127 KB
/
spapr.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
/*
* QEMU PowerPC pSeries Logical Partition (aka sPAPR) hardware System Emulator
*
* Copyright (c) 2004-2007 Fabrice Bellard
* Copyright (c) 2007 Jocelyn Mayer
* Copyright (c) 2010 David Gibson, IBM Corporation.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*
*/
#include "qemu/osdep.h"
#include "qapi/error.h"
#include "qapi/visitor.h"
#include "sysemu/sysemu.h"
#include "sysemu/numa.h"
#include "hw/hw.h"
#include "qemu/log.h"
#include "hw/fw-path-provider.h"
#include "elf.h"
#include "net/net.h"
#include "sysemu/device_tree.h"
#include "sysemu/block-backend.h"
#include "sysemu/cpus.h"
#include "sysemu/hw_accel.h"
#include "kvm_ppc.h"
#include "migration/misc.h"
#include "migration/global_state.h"
#include "migration/register.h"
#include "mmu-hash64.h"
#include "mmu-book3s-v3.h"
#include "qom/cpu.h"
#include "hw/boards.h"
#include "hw/ppc/ppc.h"
#include "hw/loader.h"
#include "hw/ppc/fdt.h"
#include "hw/ppc/spapr.h"
#include "hw/ppc/spapr_vio.h"
#include "hw/pci-host/spapr.h"
#include "hw/ppc/xics.h"
#include "hw/pci/msi.h"
#include "hw/pci/pci.h"
#include "hw/scsi/scsi.h"
#include "hw/virtio/virtio-scsi.h"
#include "hw/virtio/vhost-scsi-common.h"
#include "exec/address-spaces.h"
#include "hw/usb.h"
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "trace.h"
#include "hw/nmi.h"
#include "hw/intc/intc.h"
#include "hw/compat.h"
#include "qemu/cutils.h"
#include "hw/ppc/spapr_cpu_core.h"
#include "qmp-commands.h"
#include <libfdt.h>
/* SLOF memory layout:
*
* SLOF raw image loaded at 0, copies its romfs right below the flat
* device-tree, then position SLOF itself 31M below that
*
* So we set FW_OVERHEAD to 40MB which should account for all of that
* and more
*
* We load our kernel at 4M, leaving space for SLOF initial image
*/
#define FDT_MAX_SIZE 0x100000
#define RTAS_MAX_SIZE 0x10000
#define RTAS_MAX_ADDR 0x80000000 /* RTAS must stay below that */
#define FW_MAX_SIZE 0x400000
#define FW_FILE_NAME "slof.bin"
#define FW_OVERHEAD 0x2800000
#define KERNEL_LOAD_ADDR FW_MAX_SIZE
#define MIN_RMA_SLOF 128UL
#define PHANDLE_XICP 0x00001111
static ICSState *spapr_ics_create(sPAPRMachineState *spapr,
const char *type_ics,
int nr_irqs, Error **errp)
{
Error *local_err = NULL;
Object *obj;
obj = object_new(type_ics);
object_property_add_child(OBJECT(spapr), "ics", obj, &error_abort);
object_property_add_const_link(obj, ICS_PROP_XICS, OBJECT(spapr),
&error_abort);
object_property_set_int(obj, nr_irqs, "nr-irqs", &local_err);
if (local_err) {
goto error;
}
object_property_set_bool(obj, true, "realized", &local_err);
if (local_err) {
goto error;
}
return ICS_SIMPLE(obj);
error:
error_propagate(errp, local_err);
return NULL;
}
static bool pre_2_10_vmstate_dummy_icp_needed(void *opaque)
{
/* Dummy entries correspond to unused ICPState objects in older QEMUs,
* and newer QEMUs don't even have them. In both cases, we don't want
* to send anything on the wire.
*/
return false;
}
static const VMStateDescription pre_2_10_vmstate_dummy_icp = {
.name = "icp/server",
.version_id = 1,
.minimum_version_id = 1,
.needed = pre_2_10_vmstate_dummy_icp_needed,
.fields = (VMStateField[]) {
VMSTATE_UNUSED(4), /* uint32_t xirr */
VMSTATE_UNUSED(1), /* uint8_t pending_priority */
VMSTATE_UNUSED(1), /* uint8_t mfrr */
VMSTATE_END_OF_LIST()
},
};
static void pre_2_10_vmstate_register_dummy_icp(int i)
{
vmstate_register(NULL, i, &pre_2_10_vmstate_dummy_icp,
(void *)(uintptr_t) i);
}
static void pre_2_10_vmstate_unregister_dummy_icp(int i)
{
vmstate_unregister(NULL, &pre_2_10_vmstate_dummy_icp,
(void *)(uintptr_t) i);
}
static inline int xics_max_server_number(void)
{
return DIV_ROUND_UP(max_cpus * kvmppc_smt_threads(), smp_threads);
}
static void xics_system_init(MachineState *machine, int nr_irqs, Error **errp)
{
sPAPRMachineState *spapr = SPAPR_MACHINE(machine);
sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(machine);
if (kvm_enabled()) {
if (machine_kernel_irqchip_allowed(machine) &&
!xics_kvm_init(spapr, errp)) {
spapr->icp_type = TYPE_KVM_ICP;
spapr->ics = spapr_ics_create(spapr, TYPE_ICS_KVM, nr_irqs, errp);
}
if (machine_kernel_irqchip_required(machine) && !spapr->ics) {
error_prepend(errp, "kernel_irqchip requested but unavailable: ");
return;
}
}
if (!spapr->ics) {
xics_spapr_init(spapr);
spapr->icp_type = TYPE_ICP;
spapr->ics = spapr_ics_create(spapr, TYPE_ICS_SIMPLE, nr_irqs, errp);
if (!spapr->ics) {
return;
}
}
if (smc->pre_2_10_has_unused_icps) {
int i;
for (i = 0; i < xics_max_server_number(); i++) {
/* Dummy entries get deregistered when real ICPState objects
* are registered during CPU core hotplug.
*/
pre_2_10_vmstate_register_dummy_icp(i);
}
}
}
static int spapr_fixup_cpu_smt_dt(void *fdt, int offset, PowerPCCPU *cpu,
int smt_threads)
{
int i, ret = 0;
uint32_t servers_prop[smt_threads];
uint32_t gservers_prop[smt_threads * 2];
int index = spapr_vcpu_id(cpu);
if (cpu->compat_pvr) {
ret = fdt_setprop_cell(fdt, offset, "cpu-version", cpu->compat_pvr);
if (ret < 0) {
return ret;
}
}
/* Build interrupt servers and gservers properties */
for (i = 0; i < smt_threads; i++) {
servers_prop[i] = cpu_to_be32(index + i);
/* Hack, direct the group queues back to cpu 0 */
gservers_prop[i*2] = cpu_to_be32(index + i);
gservers_prop[i*2 + 1] = 0;
}
ret = fdt_setprop(fdt, offset, "ibm,ppc-interrupt-server#s",
servers_prop, sizeof(servers_prop));
if (ret < 0) {
return ret;
}
ret = fdt_setprop(fdt, offset, "ibm,ppc-interrupt-gserver#s",
gservers_prop, sizeof(gservers_prop));
return ret;
}
static int spapr_fixup_cpu_numa_dt(void *fdt, int offset, PowerPCCPU *cpu)
{
int index = spapr_vcpu_id(cpu);
uint32_t associativity[] = {cpu_to_be32(0x5),
cpu_to_be32(0x0),
cpu_to_be32(0x0),
cpu_to_be32(0x0),
cpu_to_be32(cpu->node_id),
cpu_to_be32(index)};
/* Advertise NUMA via ibm,associativity */
return fdt_setprop(fdt, offset, "ibm,associativity", associativity,
sizeof(associativity));
}
/* Populate the "ibm,pa-features" property */
static void spapr_populate_pa_features(CPUPPCState *env, void *fdt, int offset,
bool legacy_guest)
{
uint8_t pa_features_206[] = { 6, 0,
0xf6, 0x1f, 0xc7, 0x00, 0x80, 0xc0 };
uint8_t pa_features_207[] = { 24, 0,
0xf6, 0x1f, 0xc7, 0xc0, 0x80, 0xf0,
0x80, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x80, 0x00,
0x80, 0x00, 0x80, 0x00, 0x00, 0x00 };
uint8_t pa_features_300[] = { 66, 0,
/* 0: MMU|FPU|SLB|RUN|DABR|NX, 1: fri[nzpm]|DABRX|SPRG3|SLB0|PP110 */
/* 2: VPM|DS205|PPR|DS202|DS206, 3: LSD|URG, SSO, 5: LE|CFAR|EB|LSQ */
0xf6, 0x1f, 0xc7, 0xc0, 0x80, 0xf0, /* 0 - 5 */
/* 6: DS207 */
0x80, 0x00, 0x00, 0x00, 0x00, 0x00, /* 6 - 11 */
/* 16: Vector */
0x00, 0x00, 0x00, 0x00, 0x80, 0x00, /* 12 - 17 */
/* 18: Vec. Scalar, 20: Vec. XOR, 22: HTM */
0x80, 0x00, 0x80, 0x00, 0x00, 0x00, /* 18 - 23 */
/* 24: Ext. Dec, 26: 64 bit ftrs, 28: PM ftrs */
0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 24 - 29 */
/* 30: MMR, 32: LE atomic, 34: EBB + ext EBB */
0x80, 0x00, 0x80, 0x00, 0xC0, 0x00, /* 30 - 35 */
/* 36: SPR SO, 38: Copy/Paste, 40: Radix MMU */
0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 36 - 41 */
/* 42: PM, 44: PC RA, 46: SC vec'd */
0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 42 - 47 */
/* 48: SIMD, 50: QP BFP, 52: String */
0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 48 - 53 */
/* 54: DecFP, 56: DecI, 58: SHA */
0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 54 - 59 */
/* 60: NM atomic, 62: RNG */
0x80, 0x00, 0x80, 0x00, 0x00, 0x00, /* 60 - 65 */
};
uint8_t *pa_features;
size_t pa_size;
switch (POWERPC_MMU_VER(env->mmu_model)) {
case POWERPC_MMU_VER_2_06:
pa_features = pa_features_206;
pa_size = sizeof(pa_features_206);
break;
case POWERPC_MMU_VER_2_07:
pa_features = pa_features_207;
pa_size = sizeof(pa_features_207);
break;
case POWERPC_MMU_VER_3_00:
pa_features = pa_features_300;
pa_size = sizeof(pa_features_300);
break;
default:
return;
}
if (env->ci_large_pages) {
/*
* Note: we keep CI large pages off by default because a 64K capable
* guest provisioned with large pages might otherwise try to map a qemu
* framebuffer (or other kind of memory mapped PCI BAR) using 64K pages
* even if that qemu runs on a 4k host.
* We dd this bit back here if we are confident this is not an issue
*/
pa_features[3] |= 0x20;
}
if (kvmppc_has_cap_htm() && pa_size > 24) {
pa_features[24] |= 0x80; /* Transactional memory support */
}
if (legacy_guest && pa_size > 40) {
/* Workaround for broken kernels that attempt (guest) radix
* mode when they can't handle it, if they see the radix bit set
* in pa-features. So hide it from them. */
pa_features[40 + 2] &= ~0x80; /* Radix MMU */
}
_FDT((fdt_setprop(fdt, offset, "ibm,pa-features", pa_features, pa_size)));
}
static int spapr_fixup_cpu_dt(void *fdt, sPAPRMachineState *spapr)
{
int ret = 0, offset, cpus_offset;
CPUState *cs;
char cpu_model[32];
int smt = kvmppc_smt_threads();
uint32_t pft_size_prop[] = {0, cpu_to_be32(spapr->htab_shift)};
CPU_FOREACH(cs) {
PowerPCCPU *cpu = POWERPC_CPU(cs);
CPUPPCState *env = &cpu->env;
DeviceClass *dc = DEVICE_GET_CLASS(cs);
int index = spapr_vcpu_id(cpu);
int compat_smt = MIN(smp_threads, ppc_compat_max_threads(cpu));
if ((index % smt) != 0) {
continue;
}
snprintf(cpu_model, 32, "%s@%x", dc->fw_name, index);
cpus_offset = fdt_path_offset(fdt, "/cpus");
if (cpus_offset < 0) {
cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"),
"cpus");
if (cpus_offset < 0) {
return cpus_offset;
}
}
offset = fdt_subnode_offset(fdt, cpus_offset, cpu_model);
if (offset < 0) {
offset = fdt_add_subnode(fdt, cpus_offset, cpu_model);
if (offset < 0) {
return offset;
}
}
ret = fdt_setprop(fdt, offset, "ibm,pft-size",
pft_size_prop, sizeof(pft_size_prop));
if (ret < 0) {
return ret;
}
if (nb_numa_nodes > 1) {
ret = spapr_fixup_cpu_numa_dt(fdt, offset, cpu);
if (ret < 0) {
return ret;
}
}
ret = spapr_fixup_cpu_smt_dt(fdt, offset, cpu, compat_smt);
if (ret < 0) {
return ret;
}
spapr_populate_pa_features(env, fdt, offset,
spapr->cas_legacy_guest_workaround);
}
return ret;
}
static hwaddr spapr_node0_size(MachineState *machine)
{
if (nb_numa_nodes) {
int i;
for (i = 0; i < nb_numa_nodes; ++i) {
if (numa_info[i].node_mem) {
return MIN(pow2floor(numa_info[i].node_mem),
machine->ram_size);
}
}
}
return machine->ram_size;
}
static void add_str(GString *s, const gchar *s1)
{
g_string_append_len(s, s1, strlen(s1) + 1);
}
static int spapr_populate_memory_node(void *fdt, int nodeid, hwaddr start,
hwaddr size)
{
uint32_t associativity[] = {
cpu_to_be32(0x4), /* length */
cpu_to_be32(0x0), cpu_to_be32(0x0),
cpu_to_be32(0x0), cpu_to_be32(nodeid)
};
char mem_name[32];
uint64_t mem_reg_property[2];
int off;
mem_reg_property[0] = cpu_to_be64(start);
mem_reg_property[1] = cpu_to_be64(size);
sprintf(mem_name, "memory@" TARGET_FMT_lx, start);
off = fdt_add_subnode(fdt, 0, mem_name);
_FDT(off);
_FDT((fdt_setprop_string(fdt, off, "device_type", "memory")));
_FDT((fdt_setprop(fdt, off, "reg", mem_reg_property,
sizeof(mem_reg_property))));
_FDT((fdt_setprop(fdt, off, "ibm,associativity", associativity,
sizeof(associativity))));
return off;
}
static int spapr_populate_memory(sPAPRMachineState *spapr, void *fdt)
{
MachineState *machine = MACHINE(spapr);
hwaddr mem_start, node_size;
int i, nb_nodes = nb_numa_nodes;
NodeInfo *nodes = numa_info;
NodeInfo ramnode;
/* No NUMA nodes, assume there is just one node with whole RAM */
if (!nb_numa_nodes) {
nb_nodes = 1;
ramnode.node_mem = machine->ram_size;
nodes = &ramnode;
}
for (i = 0, mem_start = 0; i < nb_nodes; ++i) {
if (!nodes[i].node_mem) {
continue;
}
if (mem_start >= machine->ram_size) {
node_size = 0;
} else {
node_size = nodes[i].node_mem;
if (node_size > machine->ram_size - mem_start) {
node_size = machine->ram_size - mem_start;
}
}
if (!mem_start) {
/* ppc_spapr_init() checks for rma_size <= node0_size already */
spapr_populate_memory_node(fdt, i, 0, spapr->rma_size);
mem_start += spapr->rma_size;
node_size -= spapr->rma_size;
}
for ( ; node_size; ) {
hwaddr sizetmp = pow2floor(node_size);
/* mem_start != 0 here */
if (ctzl(mem_start) < ctzl(sizetmp)) {
sizetmp = 1ULL << ctzl(mem_start);
}
spapr_populate_memory_node(fdt, i, mem_start, sizetmp);
node_size -= sizetmp;
mem_start += sizetmp;
}
}
return 0;
}
static void spapr_populate_cpu_dt(CPUState *cs, void *fdt, int offset,
sPAPRMachineState *spapr)
{
PowerPCCPU *cpu = POWERPC_CPU(cs);
CPUPPCState *env = &cpu->env;
PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cs);
int index = spapr_vcpu_id(cpu);
uint32_t segs[] = {cpu_to_be32(28), cpu_to_be32(40),
0xffffffff, 0xffffffff};
uint32_t tbfreq = kvm_enabled() ? kvmppc_get_tbfreq()
: SPAPR_TIMEBASE_FREQ;
uint32_t cpufreq = kvm_enabled() ? kvmppc_get_clockfreq() : 1000000000;
uint32_t page_sizes_prop[64];
size_t page_sizes_prop_size;
uint32_t vcpus_per_socket = smp_threads * smp_cores;
uint32_t pft_size_prop[] = {0, cpu_to_be32(spapr->htab_shift)};
int compat_smt = MIN(smp_threads, ppc_compat_max_threads(cpu));
sPAPRDRConnector *drc;
int drc_index;
uint32_t radix_AP_encodings[PPC_PAGE_SIZES_MAX_SZ];
int i;
drc = spapr_drc_by_id(TYPE_SPAPR_DRC_CPU, index);
if (drc) {
drc_index = spapr_drc_index(drc);
_FDT((fdt_setprop_cell(fdt, offset, "ibm,my-drc-index", drc_index)));
}
_FDT((fdt_setprop_cell(fdt, offset, "reg", index)));
_FDT((fdt_setprop_string(fdt, offset, "device_type", "cpu")));
_FDT((fdt_setprop_cell(fdt, offset, "cpu-version", env->spr[SPR_PVR])));
_FDT((fdt_setprop_cell(fdt, offset, "d-cache-block-size",
env->dcache_line_size)));
_FDT((fdt_setprop_cell(fdt, offset, "d-cache-line-size",
env->dcache_line_size)));
_FDT((fdt_setprop_cell(fdt, offset, "i-cache-block-size",
env->icache_line_size)));
_FDT((fdt_setprop_cell(fdt, offset, "i-cache-line-size",
env->icache_line_size)));
if (pcc->l1_dcache_size) {
_FDT((fdt_setprop_cell(fdt, offset, "d-cache-size",
pcc->l1_dcache_size)));
} else {
warn_report("Unknown L1 dcache size for cpu");
}
if (pcc->l1_icache_size) {
_FDT((fdt_setprop_cell(fdt, offset, "i-cache-size",
pcc->l1_icache_size)));
} else {
warn_report("Unknown L1 icache size for cpu");
}
_FDT((fdt_setprop_cell(fdt, offset, "timebase-frequency", tbfreq)));
_FDT((fdt_setprop_cell(fdt, offset, "clock-frequency", cpufreq)));
_FDT((fdt_setprop_cell(fdt, offset, "slb-size", env->slb_nr)));
_FDT((fdt_setprop_cell(fdt, offset, "ibm,slb-size", env->slb_nr)));
_FDT((fdt_setprop_string(fdt, offset, "status", "okay")));
_FDT((fdt_setprop(fdt, offset, "64-bit", NULL, 0)));
if (env->spr_cb[SPR_PURR].oea_read) {
_FDT((fdt_setprop(fdt, offset, "ibm,purr", NULL, 0)));
}
if (env->mmu_model & POWERPC_MMU_1TSEG) {
_FDT((fdt_setprop(fdt, offset, "ibm,processor-segment-sizes",
segs, sizeof(segs))));
}
/* Advertise VMX/VSX (vector extensions) if available
* 0 / no property == no vector extensions
* 1 == VMX / Altivec available
* 2 == VSX available */
if (env->insns_flags & PPC_ALTIVEC) {
uint32_t vmx = (env->insns_flags2 & PPC2_VSX) ? 2 : 1;
_FDT((fdt_setprop_cell(fdt, offset, "ibm,vmx", vmx)));
}
/* Advertise DFP (Decimal Floating Point) if available
* 0 / no property == no DFP
* 1 == DFP available */
if (env->insns_flags2 & PPC2_DFP) {
_FDT((fdt_setprop_cell(fdt, offset, "ibm,dfp", 1)));
}
page_sizes_prop_size = ppc_create_page_sizes_prop(env, page_sizes_prop,
sizeof(page_sizes_prop));
if (page_sizes_prop_size) {
_FDT((fdt_setprop(fdt, offset, "ibm,segment-page-sizes",
page_sizes_prop, page_sizes_prop_size)));
}
spapr_populate_pa_features(env, fdt, offset, false);
_FDT((fdt_setprop_cell(fdt, offset, "ibm,chip-id",
cs->cpu_index / vcpus_per_socket)));
_FDT((fdt_setprop(fdt, offset, "ibm,pft-size",
pft_size_prop, sizeof(pft_size_prop))));
if (nb_numa_nodes > 1) {
_FDT(spapr_fixup_cpu_numa_dt(fdt, offset, cpu));
}
_FDT(spapr_fixup_cpu_smt_dt(fdt, offset, cpu, compat_smt));
if (pcc->radix_page_info) {
for (i = 0; i < pcc->radix_page_info->count; i++) {
radix_AP_encodings[i] =
cpu_to_be32(pcc->radix_page_info->entries[i]);
}
_FDT((fdt_setprop(fdt, offset, "ibm,processor-radix-AP-encodings",
radix_AP_encodings,
pcc->radix_page_info->count *
sizeof(radix_AP_encodings[0]))));
}
}
static void spapr_populate_cpus_dt_node(void *fdt, sPAPRMachineState *spapr)
{
CPUState *cs;
int cpus_offset;
char *nodename;
int smt = kvmppc_smt_threads();
cpus_offset = fdt_add_subnode(fdt, 0, "cpus");
_FDT(cpus_offset);
_FDT((fdt_setprop_cell(fdt, cpus_offset, "#address-cells", 0x1)));
_FDT((fdt_setprop_cell(fdt, cpus_offset, "#size-cells", 0x0)));
/*
* We walk the CPUs in reverse order to ensure that CPU DT nodes
* created by fdt_add_subnode() end up in the right order in FDT
* for the guest kernel the enumerate the CPUs correctly.
*/
CPU_FOREACH_REVERSE(cs) {
PowerPCCPU *cpu = POWERPC_CPU(cs);
int index = spapr_vcpu_id(cpu);
DeviceClass *dc = DEVICE_GET_CLASS(cs);
int offset;
if ((index % smt) != 0) {
continue;
}
nodename = g_strdup_printf("%s@%x", dc->fw_name, index);
offset = fdt_add_subnode(fdt, cpus_offset, nodename);
g_free(nodename);
_FDT(offset);
spapr_populate_cpu_dt(cs, fdt, offset, spapr);
}
}
/*
* Adds ibm,dynamic-reconfiguration-memory node.
* Refer to docs/specs/ppc-spapr-hotplug.txt for the documentation
* of this device tree node.
*/
static int spapr_populate_drconf_memory(sPAPRMachineState *spapr, void *fdt)
{
MachineState *machine = MACHINE(spapr);
int ret, i, offset;
uint64_t lmb_size = SPAPR_MEMORY_BLOCK_SIZE;
uint32_t prop_lmb_size[] = {0, cpu_to_be32(lmb_size)};
uint32_t hotplug_lmb_start = spapr->hotplug_memory.base / lmb_size;
uint32_t nr_lmbs = (spapr->hotplug_memory.base +
memory_region_size(&spapr->hotplug_memory.mr)) /
lmb_size;
uint32_t *int_buf, *cur_index, buf_len;
int nr_nodes = nb_numa_nodes ? nb_numa_nodes : 1;
/*
* Don't create the node if there is no hotpluggable memory
*/
if (machine->ram_size == machine->maxram_size) {
return 0;
}
/*
* Allocate enough buffer size to fit in ibm,dynamic-memory
* or ibm,associativity-lookup-arrays
*/
buf_len = MAX(nr_lmbs * SPAPR_DR_LMB_LIST_ENTRY_SIZE + 1, nr_nodes * 4 + 2)
* sizeof(uint32_t);
cur_index = int_buf = g_malloc0(buf_len);
offset = fdt_add_subnode(fdt, 0, "ibm,dynamic-reconfiguration-memory");
ret = fdt_setprop(fdt, offset, "ibm,lmb-size", prop_lmb_size,
sizeof(prop_lmb_size));
if (ret < 0) {
goto out;
}
ret = fdt_setprop_cell(fdt, offset, "ibm,memory-flags-mask", 0xff);
if (ret < 0) {
goto out;
}
ret = fdt_setprop_cell(fdt, offset, "ibm,memory-preservation-time", 0x0);
if (ret < 0) {
goto out;
}
/* ibm,dynamic-memory */
int_buf[0] = cpu_to_be32(nr_lmbs);
cur_index++;
for (i = 0; i < nr_lmbs; i++) {
uint64_t addr = i * lmb_size;
uint32_t *dynamic_memory = cur_index;
if (i >= hotplug_lmb_start) {
sPAPRDRConnector *drc;
drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, i);
g_assert(drc);
dynamic_memory[0] = cpu_to_be32(addr >> 32);
dynamic_memory[1] = cpu_to_be32(addr & 0xffffffff);
dynamic_memory[2] = cpu_to_be32(spapr_drc_index(drc));
dynamic_memory[3] = cpu_to_be32(0); /* reserved */
dynamic_memory[4] = cpu_to_be32(numa_get_node(addr, NULL));
if (memory_region_present(get_system_memory(), addr)) {
dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_ASSIGNED);
} else {
dynamic_memory[5] = cpu_to_be32(0);
}
} else {
/*
* LMB information for RMA, boot time RAM and gap b/n RAM and
* hotplug memory region -- all these are marked as reserved
* and as having no valid DRC.
*/
dynamic_memory[0] = cpu_to_be32(addr >> 32);
dynamic_memory[1] = cpu_to_be32(addr & 0xffffffff);
dynamic_memory[2] = cpu_to_be32(0);
dynamic_memory[3] = cpu_to_be32(0); /* reserved */
dynamic_memory[4] = cpu_to_be32(-1);
dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_RESERVED |
SPAPR_LMB_FLAGS_DRC_INVALID);
}
cur_index += SPAPR_DR_LMB_LIST_ENTRY_SIZE;
}
ret = fdt_setprop(fdt, offset, "ibm,dynamic-memory", int_buf, buf_len);
if (ret < 0) {
goto out;
}
/* ibm,associativity-lookup-arrays */
cur_index = int_buf;
int_buf[0] = cpu_to_be32(nr_nodes);
int_buf[1] = cpu_to_be32(4); /* Number of entries per associativity list */
cur_index += 2;
for (i = 0; i < nr_nodes; i++) {
uint32_t associativity[] = {
cpu_to_be32(0x0),
cpu_to_be32(0x0),
cpu_to_be32(0x0),
cpu_to_be32(i)
};
memcpy(cur_index, associativity, sizeof(associativity));
cur_index += 4;
}
ret = fdt_setprop(fdt, offset, "ibm,associativity-lookup-arrays", int_buf,
(cur_index - int_buf) * sizeof(uint32_t));
out:
g_free(int_buf);
return ret;
}
static int spapr_dt_cas_updates(sPAPRMachineState *spapr, void *fdt,
sPAPROptionVector *ov5_updates)
{
sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
int ret = 0, offset;
/* Generate ibm,dynamic-reconfiguration-memory node if required */
if (spapr_ovec_test(ov5_updates, OV5_DRCONF_MEMORY)) {
g_assert(smc->dr_lmb_enabled);
ret = spapr_populate_drconf_memory(spapr, fdt);
if (ret) {
goto out;
}
}
offset = fdt_path_offset(fdt, "/chosen");
if (offset < 0) {
offset = fdt_add_subnode(fdt, 0, "chosen");
if (offset < 0) {
return offset;
}
}
ret = spapr_ovec_populate_dt(fdt, offset, spapr->ov5_cas,
"ibm,architecture-vec-5");
out:
return ret;
}
static bool spapr_hotplugged_dev_before_cas(void)
{
Object *drc_container, *obj;
ObjectProperty *prop;
ObjectPropertyIterator iter;
drc_container = container_get(object_get_root(), "/dr-connector");
object_property_iter_init(&iter, drc_container);
while ((prop = object_property_iter_next(&iter))) {
if (!strstart(prop->type, "link<", NULL)) {
continue;
}
obj = object_property_get_link(drc_container, prop->name, NULL);
if (spapr_drc_needed(obj)) {
return true;
}
}
return false;
}
int spapr_h_cas_compose_response(sPAPRMachineState *spapr,
target_ulong addr, target_ulong size,
sPAPROptionVector *ov5_updates)
{
void *fdt, *fdt_skel;
sPAPRDeviceTreeUpdateHeader hdr = { .version_id = 1 };
if (spapr_hotplugged_dev_before_cas()) {
return 1;
}
size -= sizeof(hdr);
/* Create skeleton */
fdt_skel = g_malloc0(size);
_FDT((fdt_create(fdt_skel, size)));
_FDT((fdt_begin_node(fdt_skel, "")));
_FDT((fdt_end_node(fdt_skel)));
_FDT((fdt_finish(fdt_skel)));
fdt = g_malloc0(size);
_FDT((fdt_open_into(fdt_skel, fdt, size)));
g_free(fdt_skel);
/* Fixup cpu nodes */
_FDT((spapr_fixup_cpu_dt(fdt, spapr)));
if (spapr_dt_cas_updates(spapr, fdt, ov5_updates)) {
return -1;
}
/* Pack resulting tree */
_FDT((fdt_pack(fdt)));
if (fdt_totalsize(fdt) + sizeof(hdr) > size) {
trace_spapr_cas_failed(size);
return -1;
}
cpu_physical_memory_write(addr, &hdr, sizeof(hdr));
cpu_physical_memory_write(addr + sizeof(hdr), fdt, fdt_totalsize(fdt));
trace_spapr_cas_continue(fdt_totalsize(fdt) + sizeof(hdr));
g_free(fdt);
return 0;
}
static void spapr_dt_rtas(sPAPRMachineState *spapr, void *fdt)
{
int rtas;
GString *hypertas = g_string_sized_new(256);
GString *qemu_hypertas = g_string_sized_new(256);
uint32_t refpoints[] = { cpu_to_be32(0x4), cpu_to_be32(0x4) };
uint64_t max_hotplug_addr = spapr->hotplug_memory.base +
memory_region_size(&spapr->hotplug_memory.mr);
uint32_t lrdr_capacity[] = {
cpu_to_be32(max_hotplug_addr >> 32),
cpu_to_be32(max_hotplug_addr & 0xffffffff),
0, cpu_to_be32(SPAPR_MEMORY_BLOCK_SIZE),
cpu_to_be32(max_cpus / smp_threads),
};
_FDT(rtas = fdt_add_subnode(fdt, 0, "rtas"));
/* hypertas */
add_str(hypertas, "hcall-pft");
add_str(hypertas, "hcall-term");
add_str(hypertas, "hcall-dabr");
add_str(hypertas, "hcall-interrupt");
add_str(hypertas, "hcall-tce");
add_str(hypertas, "hcall-vio");
add_str(hypertas, "hcall-splpar");
add_str(hypertas, "hcall-bulk");
add_str(hypertas, "hcall-set-mode");
add_str(hypertas, "hcall-sprg0");
add_str(hypertas, "hcall-copy");
add_str(hypertas, "hcall-debug");
add_str(qemu_hypertas, "hcall-memop1");
if (!kvm_enabled() || kvmppc_spapr_use_multitce()) {
add_str(hypertas, "hcall-multi-tce");
}
if (spapr->resize_hpt != SPAPR_RESIZE_HPT_DISABLED) {
add_str(hypertas, "hcall-hpt-resize");
}
_FDT(fdt_setprop(fdt, rtas, "ibm,hypertas-functions",
hypertas->str, hypertas->len));
g_string_free(hypertas, TRUE);
_FDT(fdt_setprop(fdt, rtas, "qemu,hypertas-functions",
qemu_hypertas->str, qemu_hypertas->len));
g_string_free(qemu_hypertas, TRUE);
_FDT(fdt_setprop(fdt, rtas, "ibm,associativity-reference-points",
refpoints, sizeof(refpoints)));
_FDT(fdt_setprop_cell(fdt, rtas, "rtas-error-log-max",
RTAS_ERROR_LOG_MAX));
_FDT(fdt_setprop_cell(fdt, rtas, "rtas-event-scan-rate",
RTAS_EVENT_SCAN_RATE));
if (msi_nonbroken) {
_FDT(fdt_setprop(fdt, rtas, "ibm,change-msix-capable", NULL, 0));
}
/*
* According to PAPR, rtas ibm,os-term does not guarantee a return
* back to the guest cpu.
*
* While an additional ibm,extended-os-term property indicates
* that rtas call return will always occur. Set this property.
*/
_FDT(fdt_setprop(fdt, rtas, "ibm,extended-os-term", NULL, 0));
_FDT(fdt_setprop(fdt, rtas, "ibm,lrdr-capacity",
lrdr_capacity, sizeof(lrdr_capacity)));
spapr_dt_rtas_tokens(fdt, rtas);
}
/* Prepare ibm,arch-vec-5-platform-support, which indicates the MMU features
* that the guest may request and thus the valid values for bytes 24..26 of
* option vector 5: */
static void spapr_dt_ov5_platform_support(void *fdt, int chosen)
{
PowerPCCPU *first_ppc_cpu = POWERPC_CPU(first_cpu);
char val[2 * 4] = {
23, 0x00, /* Xive mode, filled in below. */
24, 0x00, /* Hash/Radix, filled in below. */
25, 0x00, /* Hash options: Segment Tables == no, GTSE == no. */
26, 0x40, /* Radix options: GTSE == yes. */
};
if (kvm_enabled()) {
if (kvmppc_has_cap_mmu_radix() && kvmppc_has_cap_mmu_hash_v3()) {
val[3] = 0x80; /* OV5_MMU_BOTH */
} else if (kvmppc_has_cap_mmu_radix()) {
val[3] = 0x40; /* OV5_MMU_RADIX_300 */
} else {
val[3] = 0x00; /* Hash */
}
} else {
if (first_ppc_cpu->env.mmu_model & POWERPC_MMU_V3) {
/* V3 MMU supports both hash and radix (with dynamic switching) */
val[3] = 0xC0;
} else {
/* Otherwise we can only do hash */
val[3] = 0x00;
}
}
_FDT(fdt_setprop(fdt, chosen, "ibm,arch-vec-5-platform-support",
val, sizeof(val)));
}
static void spapr_dt_chosen(sPAPRMachineState *spapr, void *fdt)
{
MachineState *machine = MACHINE(spapr);
int chosen;
const char *boot_device = machine->boot_order;
char *stdout_path = spapr_vio_stdout_path(spapr->vio_bus);
size_t cb = 0;
char *bootlist = get_boot_devices_list(&cb, true);
_FDT(chosen = fdt_add_subnode(fdt, 0, "chosen"));
_FDT(fdt_setprop_string(fdt, chosen, "bootargs", machine->kernel_cmdline));
_FDT(fdt_setprop_cell(fdt, chosen, "linux,initrd-start",
spapr->initrd_base));
_FDT(fdt_setprop_cell(fdt, chosen, "linux,initrd-end",
spapr->initrd_base + spapr->initrd_size));
if (spapr->kernel_size) {
uint64_t kprop[2] = { cpu_to_be64(KERNEL_LOAD_ADDR),
cpu_to_be64(spapr->kernel_size) };
_FDT(fdt_setprop(fdt, chosen, "qemu,boot-kernel",
&kprop, sizeof(kprop)));
if (spapr->kernel_le) {
_FDT(fdt_setprop(fdt, chosen, "qemu,boot-kernel-le", NULL, 0));
}
}
if (boot_menu) {
_FDT((fdt_setprop_cell(fdt, chosen, "qemu,boot-menu", boot_menu)));
}
_FDT(fdt_setprop_cell(fdt, chosen, "qemu,graphic-width", graphic_width));
_FDT(fdt_setprop_cell(fdt, chosen, "qemu,graphic-height", graphic_height));
_FDT(fdt_setprop_cell(fdt, chosen, "qemu,graphic-depth", graphic_depth));