-
Notifications
You must be signed in to change notification settings - Fork 485
/
Copy pathpc.c
2330 lines (1995 loc) · 70 KB
/
pc.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 PC System Emulator
*
* Copyright (c) 2003-2004 Fabrice Bellard
*
* 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 "hw/hw.h"
#include "hw/i386/pc.h"
#include "hw/char/serial.h"
#include "hw/i386/apic.h"
#include "hw/i386/topology.h"
#include "sysemu/cpus.h"
#include "hw/block/fdc.h"
#include "hw/ide.h"
#include "hw/pci/pci.h"
#include "hw/pci/pci_bus.h"
#include "hw/nvram/fw_cfg.h"
#include "hw/timer/hpet.h"
#include "hw/smbios/smbios.h"
#include "hw/loader.h"
#include "elf.h"
#include "multiboot.h"
#include "hw/timer/mc146818rtc.h"
#include "hw/timer/i8254.h"
#include "hw/audio/pcspk.h"
#include "hw/pci/msi.h"
#include "hw/sysbus.h"
#include "sysemu/sysemu.h"
#include "sysemu/numa.h"
#include "sysemu/kvm.h"
#include "sysemu/qtest.h"
#include "kvm_i386.h"
#include "hw/xen/xen.h"
#include "sysemu/block-backend.h"
#include "hw/block/block.h"
#include "ui/qemu-spice.h"
#include "exec/memory.h"
#include "exec/address-spaces.h"
#include "sysemu/arch_init.h"
#include "qemu/bitmap.h"
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "hw/acpi/acpi.h"
#include "hw/acpi/cpu_hotplug.h"
#include "hw/boards.h"
#include "hw/pci/pci_host.h"
#include "acpi-build.h"
#include "hw/mem/pc-dimm.h"
#include "qapi/visitor.h"
#include "qapi-visit.h"
#include "qom/cpu.h"
#include "hw/nmi.h"
/* debug PC/ISA interrupts */
//#define DEBUG_IRQ
#ifdef DEBUG_IRQ
#define DPRINTF(fmt, ...) \
do { printf("CPUIRQ: " fmt , ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...)
#endif
#define FW_CFG_ACPI_TABLES (FW_CFG_ARCH_LOCAL + 0)
#define FW_CFG_SMBIOS_ENTRIES (FW_CFG_ARCH_LOCAL + 1)
#define FW_CFG_IRQ0_OVERRIDE (FW_CFG_ARCH_LOCAL + 2)
#define FW_CFG_E820_TABLE (FW_CFG_ARCH_LOCAL + 3)
#define FW_CFG_HPET (FW_CFG_ARCH_LOCAL + 4)
#define E820_NR_ENTRIES 16
struct e820_entry {
uint64_t address;
uint64_t length;
uint32_t type;
} QEMU_PACKED __attribute((__aligned__(4)));
struct e820_table {
uint32_t count;
struct e820_entry entry[E820_NR_ENTRIES];
} QEMU_PACKED __attribute((__aligned__(4)));
static struct e820_table e820_reserve;
static struct e820_entry *e820_table;
static unsigned e820_entries;
struct hpet_fw_config hpet_cfg = {.count = UINT8_MAX};
void gsi_handler(void *opaque, int n, int level)
{
GSIState *s = opaque;
DPRINTF("pc: %s GSI %d\n", level ? "raising" : "lowering", n);
if (n < ISA_NUM_IRQS) {
qemu_set_irq(s->i8259_irq[n], level);
}
qemu_set_irq(s->ioapic_irq[n], level);
}
static void ioport80_write(void *opaque, hwaddr addr, uint64_t data,
unsigned size)
{
}
static uint64_t ioport80_read(void *opaque, hwaddr addr, unsigned size)
{
return 0xffffffffffffffffULL;
}
/* MSDOS compatibility mode FPU exception support */
static qemu_irq ferr_irq;
void pc_register_ferr_irq(qemu_irq irq)
{
ferr_irq = irq;
}
/* XXX: add IGNNE support */
void cpu_set_ferr(CPUX86State *s)
{
qemu_irq_raise(ferr_irq);
}
static void ioportF0_write(void *opaque, hwaddr addr, uint64_t data,
unsigned size)
{
qemu_irq_lower(ferr_irq);
}
static uint64_t ioportF0_read(void *opaque, hwaddr addr, unsigned size)
{
return 0xffffffffffffffffULL;
}
/* TSC handling */
uint64_t cpu_get_tsc(CPUX86State *env)
{
return cpu_get_ticks();
}
/* IRQ handling */
int cpu_get_pic_interrupt(CPUX86State *env)
{
X86CPU *cpu = x86_env_get_cpu(env);
int intno;
if (!kvm_irqchip_in_kernel()) {
intno = apic_get_interrupt(cpu->apic_state);
if (intno >= 0) {
return intno;
}
/* read the irq from the PIC */
if (!apic_accept_pic_intr(cpu->apic_state)) {
return -1;
}
}
intno = pic_read_irq(isa_pic);
return intno;
}
static void pic_irq_request(void *opaque, int irq, int level)
{
CPUState *cs = first_cpu;
X86CPU *cpu = X86_CPU(cs);
DPRINTF("pic_irqs: %s irq %d\n", level? "raise" : "lower", irq);
if (cpu->apic_state && !kvm_irqchip_in_kernel()) {
CPU_FOREACH(cs) {
cpu = X86_CPU(cs);
if (apic_accept_pic_intr(cpu->apic_state)) {
apic_deliver_pic_intr(cpu->apic_state, level);
}
}
} else {
if (level) {
cpu_interrupt(cs, CPU_INTERRUPT_HARD);
} else {
cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD);
}
}
}
/* PC cmos mappings */
#define REG_EQUIPMENT_BYTE 0x14
int cmos_get_fd_drive_type(FloppyDriveType fd0)
{
int val;
switch (fd0) {
case FLOPPY_DRIVE_TYPE_144:
/* 1.44 Mb 3"5 drive */
val = 4;
break;
case FLOPPY_DRIVE_TYPE_288:
/* 2.88 Mb 3"5 drive */
val = 5;
break;
case FLOPPY_DRIVE_TYPE_120:
/* 1.2 Mb 5"5 drive */
val = 2;
break;
case FLOPPY_DRIVE_TYPE_NONE:
default:
val = 0;
break;
}
return val;
}
static void cmos_init_hd(ISADevice *s, int type_ofs, int info_ofs,
int16_t cylinders, int8_t heads, int8_t sectors)
{
rtc_set_memory(s, type_ofs, 47);
rtc_set_memory(s, info_ofs, cylinders);
rtc_set_memory(s, info_ofs + 1, cylinders >> 8);
rtc_set_memory(s, info_ofs + 2, heads);
rtc_set_memory(s, info_ofs + 3, 0xff);
rtc_set_memory(s, info_ofs + 4, 0xff);
rtc_set_memory(s, info_ofs + 5, 0xc0 | ((heads > 8) << 3));
rtc_set_memory(s, info_ofs + 6, cylinders);
rtc_set_memory(s, info_ofs + 7, cylinders >> 8);
rtc_set_memory(s, info_ofs + 8, sectors);
}
/* convert boot_device letter to something recognizable by the bios */
static int boot_device2nibble(char boot_device)
{
switch(boot_device) {
case 'a':
case 'b':
return 0x01; /* floppy boot */
case 'c':
return 0x02; /* hard drive boot */
case 'd':
return 0x03; /* CD-ROM boot */
case 'n':
return 0x04; /* Network boot */
}
return 0;
}
static void set_boot_dev(ISADevice *s, const char *boot_device, Error **errp)
{
#define PC_MAX_BOOT_DEVICES 3
int nbds, bds[3] = { 0, };
int i;
nbds = strlen(boot_device);
if (nbds > PC_MAX_BOOT_DEVICES) {
error_setg(errp, "Too many boot devices for PC");
return;
}
for (i = 0; i < nbds; i++) {
bds[i] = boot_device2nibble(boot_device[i]);
if (bds[i] == 0) {
error_setg(errp, "Invalid boot device for PC: '%c'",
boot_device[i]);
return;
}
}
rtc_set_memory(s, 0x3d, (bds[1] << 4) | bds[0]);
rtc_set_memory(s, 0x38, (bds[2] << 4) | (fd_bootchk ? 0x0 : 0x1));
}
static void pc_boot_set(void *opaque, const char *boot_device, Error **errp)
{
set_boot_dev(opaque, boot_device, errp);
}
static void pc_cmos_init_floppy(ISADevice *rtc_state, ISADevice *floppy)
{
int val, nb, i;
FloppyDriveType fd_type[2] = { FLOPPY_DRIVE_TYPE_NONE,
FLOPPY_DRIVE_TYPE_NONE };
/* floppy type */
if (floppy) {
for (i = 0; i < 2; i++) {
fd_type[i] = isa_fdc_get_drive_type(floppy, i);
}
}
val = (cmos_get_fd_drive_type(fd_type[0]) << 4) |
cmos_get_fd_drive_type(fd_type[1]);
rtc_set_memory(rtc_state, 0x10, val);
val = rtc_get_memory(rtc_state, REG_EQUIPMENT_BYTE);
nb = 0;
if (fd_type[0] != FLOPPY_DRIVE_TYPE_NONE) {
nb++;
}
if (fd_type[1] != FLOPPY_DRIVE_TYPE_NONE) {
nb++;
}
switch (nb) {
case 0:
break;
case 1:
val |= 0x01; /* 1 drive, ready for boot */
break;
case 2:
val |= 0x41; /* 2 drives, ready for boot */
break;
}
rtc_set_memory(rtc_state, REG_EQUIPMENT_BYTE, val);
}
typedef struct pc_cmos_init_late_arg {
ISADevice *rtc_state;
BusState *idebus[2];
} pc_cmos_init_late_arg;
typedef struct check_fdc_state {
ISADevice *floppy;
bool multiple;
} CheckFdcState;
static int check_fdc(Object *obj, void *opaque)
{
CheckFdcState *state = opaque;
Object *fdc;
uint32_t iobase;
Error *local_err = NULL;
fdc = object_dynamic_cast(obj, TYPE_ISA_FDC);
if (!fdc) {
return 0;
}
iobase = object_property_get_int(obj, "iobase", &local_err);
if (local_err || iobase != 0x3f0) {
error_free(local_err);
return 0;
}
if (state->floppy) {
state->multiple = true;
} else {
state->floppy = ISA_DEVICE(obj);
}
return 0;
}
static const char * const fdc_container_path[] = {
"/unattached", "/peripheral", "/peripheral-anon"
};
/*
* Locate the FDC at IO address 0x3f0, in order to configure the CMOS registers
* and ACPI objects.
*/
ISADevice *pc_find_fdc0(void)
{
int i;
Object *container;
CheckFdcState state = { 0 };
for (i = 0; i < ARRAY_SIZE(fdc_container_path); i++) {
container = container_get(qdev_get_machine(), fdc_container_path[i]);
object_child_foreach(container, check_fdc, &state);
}
if (state.multiple) {
error_report("warning: multiple floppy disk controllers with "
"iobase=0x3f0 have been found");
error_printf("the one being picked for CMOS setup might not reflect "
"your intent\n");
}
return state.floppy;
}
static void pc_cmos_init_late(void *opaque)
{
pc_cmos_init_late_arg *arg = opaque;
ISADevice *s = arg->rtc_state;
int16_t cylinders;
int8_t heads, sectors;
int val;
int i, trans;
val = 0;
if (ide_get_geometry(arg->idebus[0], 0,
&cylinders, &heads, §ors) >= 0) {
cmos_init_hd(s, 0x19, 0x1b, cylinders, heads, sectors);
val |= 0xf0;
}
if (ide_get_geometry(arg->idebus[0], 1,
&cylinders, &heads, §ors) >= 0) {
cmos_init_hd(s, 0x1a, 0x24, cylinders, heads, sectors);
val |= 0x0f;
}
rtc_set_memory(s, 0x12, val);
val = 0;
for (i = 0; i < 4; i++) {
/* NOTE: ide_get_geometry() returns the physical
geometry. It is always such that: 1 <= sects <= 63, 1
<= heads <= 16, 1 <= cylinders <= 16383. The BIOS
geometry can be different if a translation is done. */
if (ide_get_geometry(arg->idebus[i / 2], i % 2,
&cylinders, &heads, §ors) >= 0) {
trans = ide_get_bios_chs_trans(arg->idebus[i / 2], i % 2) - 1;
assert((trans & ~3) == 0);
val |= trans << (i * 2);
}
}
rtc_set_memory(s, 0x39, val);
pc_cmos_init_floppy(s, pc_find_fdc0());
qemu_unregister_reset(pc_cmos_init_late, opaque);
}
void pc_cmos_init(PCMachineState *pcms,
BusState *idebus0, BusState *idebus1,
ISADevice *s)
{
int val;
static pc_cmos_init_late_arg arg;
/* various important CMOS locations needed by PC/Bochs bios */
/* memory size */
/* base memory (first MiB) */
val = MIN(pcms->below_4g_mem_size / 1024, 640);
rtc_set_memory(s, 0x15, val);
rtc_set_memory(s, 0x16, val >> 8);
/* extended memory (next 64MiB) */
if (pcms->below_4g_mem_size > 1024 * 1024) {
val = (pcms->below_4g_mem_size - 1024 * 1024) / 1024;
} else {
val = 0;
}
if (val > 65535)
val = 65535;
rtc_set_memory(s, 0x17, val);
rtc_set_memory(s, 0x18, val >> 8);
rtc_set_memory(s, 0x30, val);
rtc_set_memory(s, 0x31, val >> 8);
/* memory between 16MiB and 4GiB */
if (pcms->below_4g_mem_size > 16 * 1024 * 1024) {
val = (pcms->below_4g_mem_size - 16 * 1024 * 1024) / 65536;
} else {
val = 0;
}
if (val > 65535)
val = 65535;
rtc_set_memory(s, 0x34, val);
rtc_set_memory(s, 0x35, val >> 8);
/* memory above 4GiB */
val = pcms->above_4g_mem_size / 65536;
rtc_set_memory(s, 0x5b, val);
rtc_set_memory(s, 0x5c, val >> 8);
rtc_set_memory(s, 0x5d, val >> 16);
object_property_add_link(OBJECT(pcms), "rtc_state",
TYPE_ISA_DEVICE,
(Object **)&pcms->rtc,
object_property_allow_set_link,
OBJ_PROP_LINK_UNREF_ON_RELEASE, &error_abort);
object_property_set_link(OBJECT(pcms), OBJECT(s),
"rtc_state", &error_abort);
set_boot_dev(s, MACHINE(pcms)->boot_order, &error_fatal);
val = 0;
val |= 0x02; /* FPU is there */
val |= 0x04; /* PS/2 mouse installed */
rtc_set_memory(s, REG_EQUIPMENT_BYTE, val);
/* hard drives and FDC */
arg.rtc_state = s;
arg.idebus[0] = idebus0;
arg.idebus[1] = idebus1;
qemu_register_reset(pc_cmos_init_late, &arg);
}
#define TYPE_PORT92 "port92"
#define PORT92(obj) OBJECT_CHECK(Port92State, (obj), TYPE_PORT92)
/* port 92 stuff: could be split off */
typedef struct Port92State {
ISADevice parent_obj;
MemoryRegion io;
uint8_t outport;
qemu_irq a20_out;
} Port92State;
static void port92_write(void *opaque, hwaddr addr, uint64_t val,
unsigned size)
{
Port92State *s = opaque;
int oldval = s->outport;
DPRINTF("port92: write 0x%02" PRIx64 "\n", val);
s->outport = val;
qemu_set_irq(s->a20_out, (val >> 1) & 1);
if ((val & 1) && !(oldval & 1)) {
qemu_system_reset_request();
}
}
static uint64_t port92_read(void *opaque, hwaddr addr,
unsigned size)
{
Port92State *s = opaque;
uint32_t ret;
ret = s->outport;
DPRINTF("port92: read 0x%02x\n", ret);
return ret;
}
static void port92_init(ISADevice *dev, qemu_irq a20_out)
{
qdev_connect_gpio_out_named(DEVICE(dev), PORT92_A20_LINE, 0, a20_out);
}
static const VMStateDescription vmstate_port92_isa = {
.name = "port92",
.version_id = 1,
.minimum_version_id = 1,
.fields = (VMStateField[]) {
VMSTATE_UINT8(outport, Port92State),
VMSTATE_END_OF_LIST()
}
};
static void port92_reset(DeviceState *d)
{
Port92State *s = PORT92(d);
s->outport &= ~1;
}
static const MemoryRegionOps port92_ops = {
.read = port92_read,
.write = port92_write,
.impl = {
.min_access_size = 1,
.max_access_size = 1,
},
.endianness = DEVICE_LITTLE_ENDIAN,
};
static void port92_initfn(Object *obj)
{
Port92State *s = PORT92(obj);
memory_region_init_io(&s->io, OBJECT(s), &port92_ops, s, "port92", 1);
s->outport = 0;
qdev_init_gpio_out_named(DEVICE(obj), &s->a20_out, PORT92_A20_LINE, 1);
}
static void port92_realizefn(DeviceState *dev, Error **errp)
{
ISADevice *isadev = ISA_DEVICE(dev);
Port92State *s = PORT92(dev);
isa_register_ioport(isadev, &s->io, 0x92);
}
static void port92_class_initfn(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
dc->realize = port92_realizefn;
dc->reset = port92_reset;
dc->vmsd = &vmstate_port92_isa;
/*
* Reason: unlike ordinary ISA devices, this one needs additional
* wiring: its A20 output line needs to be wired up by
* port92_init().
*/
dc->cannot_instantiate_with_device_add_yet = true;
}
static const TypeInfo port92_info = {
.name = TYPE_PORT92,
.parent = TYPE_ISA_DEVICE,
.instance_size = sizeof(Port92State),
.instance_init = port92_initfn,
.class_init = port92_class_initfn,
};
static void port92_register_types(void)
{
type_register_static(&port92_info);
}
type_init(port92_register_types)
static void handle_a20_line_change(void *opaque, int irq, int level)
{
X86CPU *cpu = opaque;
/* XXX: send to all CPUs ? */
/* XXX: add logic to handle multiple A20 line sources */
x86_cpu_set_a20(cpu, level);
}
int e820_add_entry(uint64_t address, uint64_t length, uint32_t type)
{
int index = le32_to_cpu(e820_reserve.count);
struct e820_entry *entry;
if (type != E820_RAM) {
/* old FW_CFG_E820_TABLE entry -- reservations only */
if (index >= E820_NR_ENTRIES) {
return -EBUSY;
}
entry = &e820_reserve.entry[index++];
entry->address = cpu_to_le64(address);
entry->length = cpu_to_le64(length);
entry->type = cpu_to_le32(type);
e820_reserve.count = cpu_to_le32(index);
}
/* new "etc/e820" file -- include ram too */
e820_table = g_renew(struct e820_entry, e820_table, e820_entries + 1);
e820_table[e820_entries].address = cpu_to_le64(address);
e820_table[e820_entries].length = cpu_to_le64(length);
e820_table[e820_entries].type = cpu_to_le32(type);
e820_entries++;
return e820_entries;
}
int e820_get_num_entries(void)
{
return e820_entries;
}
bool e820_get_entry(int idx, uint32_t type, uint64_t *address, uint64_t *length)
{
if (idx < e820_entries && e820_table[idx].type == cpu_to_le32(type)) {
*address = le64_to_cpu(e820_table[idx].address);
*length = le64_to_cpu(e820_table[idx].length);
return true;
}
return false;
}
/* Enables contiguous-apic-ID mode, for compatibility */
static bool compat_apic_id_mode;
void enable_compat_apic_id_mode(void)
{
compat_apic_id_mode = true;
}
/* Calculates initial APIC ID for a specific CPU index
*
* Currently we need to be able to calculate the APIC ID from the CPU index
* alone (without requiring a CPU object), as the QEMU<->Seabios interfaces have
* no concept of "CPU index", and the NUMA tables on fw_cfg need the APIC ID of
* all CPUs up to max_cpus.
*/
static uint32_t x86_cpu_apic_id_from_index(unsigned int cpu_index)
{
uint32_t correct_id;
static bool warned;
correct_id = x86_apicid_from_cpu_idx(smp_cores, smp_threads, cpu_index);
if (compat_apic_id_mode) {
if (cpu_index != correct_id && !warned && !qtest_enabled()) {
error_report("APIC IDs set in compatibility mode, "
"CPU topology won't match the configuration");
warned = true;
}
return cpu_index;
} else {
return correct_id;
}
}
static void pc_build_smbios(FWCfgState *fw_cfg)
{
uint8_t *smbios_tables, *smbios_anchor;
size_t smbios_tables_len, smbios_anchor_len;
struct smbios_phys_mem_area *mem_array;
unsigned i, array_count;
smbios_tables = smbios_get_table_legacy(&smbios_tables_len);
if (smbios_tables) {
fw_cfg_add_bytes(fw_cfg, FW_CFG_SMBIOS_ENTRIES,
smbios_tables, smbios_tables_len);
}
/* build the array of physical mem area from e820 table */
mem_array = g_malloc0(sizeof(*mem_array) * e820_get_num_entries());
for (i = 0, array_count = 0; i < e820_get_num_entries(); i++) {
uint64_t addr, len;
if (e820_get_entry(i, E820_RAM, &addr, &len)) {
mem_array[array_count].address = addr;
mem_array[array_count].length = len;
array_count++;
}
}
smbios_get_tables(mem_array, array_count,
&smbios_tables, &smbios_tables_len,
&smbios_anchor, &smbios_anchor_len);
g_free(mem_array);
if (smbios_anchor) {
fw_cfg_add_file(fw_cfg, "etc/smbios/smbios-tables",
smbios_tables, smbios_tables_len);
fw_cfg_add_file(fw_cfg, "etc/smbios/smbios-anchor",
smbios_anchor, smbios_anchor_len);
}
}
static FWCfgState *bochs_bios_init(AddressSpace *as, PCMachineState *pcms)
{
FWCfgState *fw_cfg;
uint64_t *numa_fw_cfg;
int i, j;
fw_cfg = fw_cfg_init_io_dma(FW_CFG_IO_BASE, FW_CFG_IO_BASE + 4, as);
/* FW_CFG_MAX_CPUS is a bit confusing/problematic on x86:
*
* SeaBIOS needs FW_CFG_MAX_CPUS for CPU hotplug, but the CPU hotplug
* QEMU<->SeaBIOS interface is not based on the "CPU index", but on the APIC
* ID of hotplugged CPUs[1]. This means that FW_CFG_MAX_CPUS is not the
* "maximum number of CPUs", but the "limit to the APIC ID values SeaBIOS
* may see".
*
* So, this means we must not use max_cpus, here, but the maximum possible
* APIC ID value, plus one.
*
* [1] The only kind of "CPU identifier" used between SeaBIOS and QEMU is
* the APIC ID, not the "CPU index"
*/
fw_cfg_add_i16(fw_cfg, FW_CFG_MAX_CPUS, (uint16_t)pcms->apic_id_limit);
fw_cfg_add_i64(fw_cfg, FW_CFG_RAM_SIZE, (uint64_t)ram_size);
fw_cfg_add_bytes(fw_cfg, FW_CFG_ACPI_TABLES,
acpi_tables, acpi_tables_len);
fw_cfg_add_i32(fw_cfg, FW_CFG_IRQ0_OVERRIDE, kvm_allows_irq0_override());
fw_cfg_add_bytes(fw_cfg, FW_CFG_E820_TABLE,
&e820_reserve, sizeof(e820_reserve));
fw_cfg_add_file(fw_cfg, "etc/e820", e820_table,
sizeof(struct e820_entry) * e820_entries);
fw_cfg_add_bytes(fw_cfg, FW_CFG_HPET, &hpet_cfg, sizeof(hpet_cfg));
/* allocate memory for the NUMA channel: one (64bit) word for the number
* of nodes, one word for each VCPU->node and one word for each node to
* hold the amount of memory.
*/
numa_fw_cfg = g_new0(uint64_t, 1 + pcms->apic_id_limit + nb_numa_nodes);
numa_fw_cfg[0] = cpu_to_le64(nb_numa_nodes);
for (i = 0; i < max_cpus; i++) {
unsigned int apic_id = x86_cpu_apic_id_from_index(i);
assert(apic_id < pcms->apic_id_limit);
for (j = 0; j < nb_numa_nodes; j++) {
if (test_bit(i, numa_info[j].node_cpu)) {
numa_fw_cfg[apic_id + 1] = cpu_to_le64(j);
break;
}
}
}
for (i = 0; i < nb_numa_nodes; i++) {
numa_fw_cfg[pcms->apic_id_limit + 1 + i] =
cpu_to_le64(numa_info[i].node_mem);
}
fw_cfg_add_bytes(fw_cfg, FW_CFG_NUMA, numa_fw_cfg,
(1 + pcms->apic_id_limit + nb_numa_nodes) *
sizeof(*numa_fw_cfg));
return fw_cfg;
}
static long get_file_size(FILE *f)
{
long where, size;
/* XXX: on Unix systems, using fstat() probably makes more sense */
where = ftell(f);
fseek(f, 0, SEEK_END);
size = ftell(f);
fseek(f, where, SEEK_SET);
return size;
}
/* setup_data types */
#define SETUP_NONE 0
#define SETUP_E820_EXT 1
#define SETUP_DTB 2
#define SETUP_PCI 3
#define SETUP_EFI 4
struct setup_data {
uint64_t next;
uint32_t type;
uint32_t len;
uint8_t data[0];
} __attribute__((packed));
static void load_linux(PCMachineState *pcms,
FWCfgState *fw_cfg)
{
uint16_t protocol;
int setup_size, kernel_size, initrd_size = 0, cmdline_size;
int dtb_size, setup_data_offset;
uint32_t initrd_max;
uint8_t header[8192], *setup, *kernel, *initrd_data;
hwaddr real_addr, prot_addr, cmdline_addr, initrd_addr = 0;
FILE *f;
char *vmode;
MachineState *machine = MACHINE(pcms);
PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms);
struct setup_data *setup_data;
const char *kernel_filename = machine->kernel_filename;
const char *initrd_filename = machine->initrd_filename;
const char *dtb_filename = machine->dtb;
const char *kernel_cmdline = machine->kernel_cmdline;
/* Align to 16 bytes as a paranoia measure */
cmdline_size = (strlen(kernel_cmdline)+16) & ~15;
/* load the kernel header */
f = fopen(kernel_filename, "rb");
if (!f || !(kernel_size = get_file_size(f)) ||
fread(header, 1, MIN(ARRAY_SIZE(header), kernel_size), f) !=
MIN(ARRAY_SIZE(header), kernel_size)) {
fprintf(stderr, "qemu: could not load kernel '%s': %s\n",
kernel_filename, strerror(errno));
exit(1);
}
/* kernel protocol version */
#if 0
fprintf(stderr, "header magic: %#x\n", ldl_p(header+0x202));
#endif
if (ldl_p(header+0x202) == 0x53726448) {
protocol = lduw_p(header+0x206);
} else {
/* This looks like a multiboot kernel. If it is, let's stop
treating it like a Linux kernel. */
if (load_multiboot(fw_cfg, f, kernel_filename, initrd_filename,
kernel_cmdline, kernel_size, header)) {
return;
}
protocol = 0;
}
if (protocol < 0x200 || !(header[0x211] & 0x01)) {
/* Low kernel */
real_addr = 0x90000;
cmdline_addr = 0x9a000 - cmdline_size;
prot_addr = 0x10000;
} else if (protocol < 0x202) {
/* High but ancient kernel */
real_addr = 0x90000;
cmdline_addr = 0x9a000 - cmdline_size;
prot_addr = 0x100000;
} else {
/* High and recent kernel */
real_addr = 0x10000;
cmdline_addr = 0x20000;
prot_addr = 0x100000;
}
#if 0
fprintf(stderr,
"qemu: real_addr = 0x" TARGET_FMT_plx "\n"
"qemu: cmdline_addr = 0x" TARGET_FMT_plx "\n"
"qemu: prot_addr = 0x" TARGET_FMT_plx "\n",
real_addr,
cmdline_addr,
prot_addr);
#endif
/* highest address for loading the initrd */
if (protocol >= 0x203) {
initrd_max = ldl_p(header+0x22c);
} else {
initrd_max = 0x37ffffff;
}
if (initrd_max >= pcms->below_4g_mem_size - pcmc->acpi_data_size) {
initrd_max = pcms->below_4g_mem_size - pcmc->acpi_data_size - 1;
}
fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_ADDR, cmdline_addr);
fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, strlen(kernel_cmdline)+1);
fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, kernel_cmdline);
if (protocol >= 0x202) {
stl_p(header+0x228, cmdline_addr);
} else {
stw_p(header+0x20, 0xA33F);
stw_p(header+0x22, cmdline_addr-real_addr);
}
/* handle vga= parameter */
vmode = strstr(kernel_cmdline, "vga=");
if (vmode) {
unsigned int video_mode;
/* skip "vga=" */
vmode += 4;
if (!strncmp(vmode, "normal", 6)) {
video_mode = 0xffff;
} else if (!strncmp(vmode, "ext", 3)) {
video_mode = 0xfffe;
} else if (!strncmp(vmode, "ask", 3)) {
video_mode = 0xfffd;
} else {
video_mode = strtol(vmode, NULL, 0);
}
stw_p(header+0x1fa, video_mode);
}
/* loader type */
/* High nybble = B reserved for QEMU; low nybble is revision number.
If this code is substantially changed, you may want to consider
incrementing the revision. */
if (protocol >= 0x200) {
header[0x210] = 0xB0;
}
/* heap */
if (protocol >= 0x201) {
header[0x211] |= 0x80; /* CAN_USE_HEAP */
stw_p(header+0x224, cmdline_addr-real_addr-0x200);
}
/* load initrd */
if (initrd_filename) {
if (protocol < 0x200) {
fprintf(stderr, "qemu: linux kernel too old to load a ram disk\n");
exit(1);
}
initrd_size = get_image_size(initrd_filename);
if (initrd_size < 0) {
fprintf(stderr, "qemu: error reading initrd %s: %s\n",
initrd_filename, strerror(errno));
exit(1);
}
initrd_addr = (initrd_max-initrd_size) & ~4095;
initrd_data = g_malloc(initrd_size);
load_image(initrd_filename, initrd_data);
fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_ADDR, initrd_addr);
fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_SIZE, initrd_size);
fw_cfg_add_bytes(fw_cfg, FW_CFG_INITRD_DATA, initrd_data, initrd_size);
stl_p(header+0x218, initrd_addr);
stl_p(header+0x21c, initrd_size);
}
/* load kernel and setup */
setup_size = header[0x1f1];
if (setup_size == 0) {
setup_size = 4;
}
setup_size = (setup_size+1)*512;
if (setup_size > kernel_size) {
fprintf(stderr, "qemu: invalid kernel header\n");
exit(1);
}
kernel_size -= setup_size;
setup = g_malloc(setup_size);
kernel = g_malloc(kernel_size);
fseek(f, 0, SEEK_SET);
if (fread(setup, 1, setup_size, f) != setup_size) {
fprintf(stderr, "fread() failed\n");
exit(1);