-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathvfio.c
3732 lines (3118 loc) · 116 KB
/
vfio.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
/*
* vfio based device assignment support
*
* Copyright Red Hat, Inc. 2012
*
* Authors:
* Alex Williamson <alex.williamson@redhat.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
* Based on qemu-kvm device-assignment:
* Adapted for KVM by Qumranet.
* Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com)
* Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com)
* Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com)
* Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com)
* Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com)
*/
#include <dirent.h>
#include <linux/vfio.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <unistd.h>
#include "config.h"
#include "exec/address-spaces.h"
#include "exec/memory.h"
#include "hw/pci/msi.h"
#include "hw/pci/msix.h"
#include "hw/pci/pci.h"
#include "qemu-common.h"
#include "qemu/error-report.h"
#include "qemu/event_notifier.h"
#include "qemu/queue.h"
#include "qemu/range.h"
#include "sysemu/kvm.h"
#include "sysemu/sysemu.h"
/* #define DEBUG_VFIO */
#ifdef DEBUG_VFIO
#define DPRINTF(fmt, ...) \
do { fprintf(stderr, "vfio: " fmt, ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...) \
do { } while (0)
#endif
/* Extra debugging, trap acceleration paths for more logging */
#define VFIO_ALLOW_MMAP 1
#define VFIO_ALLOW_KVM_INTX 1
struct VFIODevice;
typedef struct VFIOQuirk {
MemoryRegion mem;
struct VFIODevice *vdev;
QLIST_ENTRY(VFIOQuirk) next;
struct {
uint32_t base_offset:TARGET_PAGE_BITS;
uint32_t address_offset:TARGET_PAGE_BITS;
uint32_t address_size:3;
uint32_t bar:3;
uint32_t address_match;
uint32_t address_mask;
uint32_t address_val:TARGET_PAGE_BITS;
uint32_t data_offset:TARGET_PAGE_BITS;
uint32_t data_size:3;
uint8_t flags;
uint8_t read_flags;
uint8_t write_flags;
} data;
} VFIOQuirk;
typedef struct VFIOBAR {
off_t fd_offset; /* offset of BAR within device fd */
int fd; /* device fd, allows us to pass VFIOBAR as opaque data */
MemoryRegion mem; /* slow, read/write access */
MemoryRegion mmap_mem; /* direct mapped access */
void *mmap;
size_t size;
uint32_t flags; /* VFIO region flags (rd/wr/mmap) */
uint8_t nr; /* cache the BAR number for debug */
bool ioport;
bool mem64;
QLIST_HEAD(, VFIOQuirk) quirks;
} VFIOBAR;
typedef struct VFIOVGARegion {
MemoryRegion mem;
off_t offset;
int nr;
QLIST_HEAD(, VFIOQuirk) quirks;
} VFIOVGARegion;
typedef struct VFIOVGA {
off_t fd_offset;
int fd;
VFIOVGARegion region[QEMU_PCI_VGA_NUM_REGIONS];
} VFIOVGA;
typedef struct VFIOINTx {
bool pending; /* interrupt pending */
bool kvm_accel; /* set when QEMU bypass through KVM enabled */
uint8_t pin; /* which pin to pull for qemu_set_irq */
EventNotifier interrupt; /* eventfd triggered on interrupt */
EventNotifier unmask; /* eventfd for unmask on QEMU bypass */
PCIINTxRoute route; /* routing info for QEMU bypass */
uint32_t mmap_timeout; /* delay to re-enable mmaps after interrupt */
QEMUTimer *mmap_timer; /* enable mmaps after periods w/o interrupts */
} VFIOINTx;
typedef struct VFIOMSIVector {
EventNotifier interrupt; /* eventfd triggered on interrupt */
struct VFIODevice *vdev; /* back pointer to device */
MSIMessage msg; /* cache the MSI message so we know when it changes */
int virq; /* KVM irqchip route for QEMU bypass */
bool use;
} VFIOMSIVector;
enum {
VFIO_INT_NONE = 0,
VFIO_INT_INTx = 1,
VFIO_INT_MSI = 2,
VFIO_INT_MSIX = 3,
};
struct VFIOGroup;
typedef struct VFIOContainer {
int fd; /* /dev/vfio/vfio, empowered by the attached groups */
struct {
/* enable abstraction to support various iommu backends */
union {
MemoryListener listener; /* Used by type1 iommu */
};
void (*release)(struct VFIOContainer *);
} iommu_data;
QLIST_HEAD(, VFIOGroup) group_list;
QLIST_ENTRY(VFIOContainer) next;
} VFIOContainer;
/* Cache of MSI-X setup plus extra mmap and memory region for split BAR map */
typedef struct VFIOMSIXInfo {
uint8_t table_bar;
uint8_t pba_bar;
uint16_t entries;
uint32_t table_offset;
uint32_t pba_offset;
MemoryRegion mmap_mem;
void *mmap;
} VFIOMSIXInfo;
typedef struct VFIODevice {
PCIDevice pdev;
int fd;
VFIOINTx intx;
unsigned int config_size;
uint8_t *emulated_config_bits; /* QEMU emulated bits, little-endian */
off_t config_offset; /* Offset of config space region within device fd */
unsigned int rom_size;
off_t rom_offset; /* Offset of ROM region within device fd */
void *rom;
int msi_cap_size;
VFIOMSIVector *msi_vectors;
VFIOMSIXInfo *msix;
int nr_vectors; /* Number of MSI/MSIX vectors currently in use */
int interrupt; /* Current interrupt type */
VFIOBAR bars[PCI_NUM_REGIONS - 1]; /* No ROM */
VFIOVGA vga; /* 0xa0000, 0x3b0, 0x3c0 */
PCIHostDeviceAddress host;
QLIST_ENTRY(VFIODevice) next;
struct VFIOGroup *group;
EventNotifier err_notifier;
uint32_t features;
#define VFIO_FEATURE_ENABLE_VGA_BIT 0
#define VFIO_FEATURE_ENABLE_VGA (1 << VFIO_FEATURE_ENABLE_VGA_BIT)
int32_t bootindex;
uint8_t pm_cap;
bool reset_works;
bool has_vga;
bool pci_aer;
bool has_flr;
bool has_pm_reset;
bool needs_reset;
} VFIODevice;
typedef struct VFIOGroup {
int fd;
int groupid;
VFIOContainer *container;
QLIST_HEAD(, VFIODevice) device_list;
QLIST_ENTRY(VFIOGroup) next;
QLIST_ENTRY(VFIOGroup) container_next;
} VFIOGroup;
#define MSIX_CAP_LENGTH 12
static QLIST_HEAD(, VFIOContainer)
container_list = QLIST_HEAD_INITIALIZER(container_list);
static QLIST_HEAD(, VFIOGroup)
group_list = QLIST_HEAD_INITIALIZER(group_list);
static void vfio_disable_interrupts(VFIODevice *vdev);
static uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len);
static void vfio_pci_write_config(PCIDevice *pdev, uint32_t addr,
uint32_t val, int len);
static void vfio_mmap_set_enabled(VFIODevice *vdev, bool enabled);
/*
* Common VFIO interrupt disable
*/
static void vfio_disable_irqindex(VFIODevice *vdev, int index)
{
struct vfio_irq_set irq_set = {
.argsz = sizeof(irq_set),
.flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER,
.index = index,
.start = 0,
.count = 0,
};
ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
}
/*
* INTx
*/
static void vfio_unmask_intx(VFIODevice *vdev)
{
struct vfio_irq_set irq_set = {
.argsz = sizeof(irq_set),
.flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK,
.index = VFIO_PCI_INTX_IRQ_INDEX,
.start = 0,
.count = 1,
};
ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
}
#ifdef CONFIG_KVM /* Unused outside of CONFIG_KVM code */
static void vfio_mask_intx(VFIODevice *vdev)
{
struct vfio_irq_set irq_set = {
.argsz = sizeof(irq_set),
.flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK,
.index = VFIO_PCI_INTX_IRQ_INDEX,
.start = 0,
.count = 1,
};
ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
}
#endif
/*
* Disabling BAR mmaping can be slow, but toggling it around INTx can
* also be a huge overhead. We try to get the best of both worlds by
* waiting until an interrupt to disable mmaps (subsequent transitions
* to the same state are effectively no overhead). If the interrupt has
* been serviced and the time gap is long enough, we re-enable mmaps for
* performance. This works well for things like graphics cards, which
* may not use their interrupt at all and are penalized to an unusable
* level by read/write BAR traps. Other devices, like NICs, have more
* regular interrupts and see much better latency by staying in non-mmap
* mode. We therefore set the default mmap_timeout such that a ping
* is just enough to keep the mmap disabled. Users can experiment with
* other options with the x-intx-mmap-timeout-ms parameter (a value of
* zero disables the timer).
*/
static void vfio_intx_mmap_enable(void *opaque)
{
VFIODevice *vdev = opaque;
if (vdev->intx.pending) {
timer_mod(vdev->intx.mmap_timer,
qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + vdev->intx.mmap_timeout);
return;
}
vfio_mmap_set_enabled(vdev, true);
}
static void vfio_intx_interrupt(void *opaque)
{
VFIODevice *vdev = opaque;
if (!event_notifier_test_and_clear(&vdev->intx.interrupt)) {
return;
}
DPRINTF("%s(%04x:%02x:%02x.%x) Pin %c\n", __func__, vdev->host.domain,
vdev->host.bus, vdev->host.slot, vdev->host.function,
'A' + vdev->intx.pin);
vdev->intx.pending = true;
pci_irq_assert(&vdev->pdev);
vfio_mmap_set_enabled(vdev, false);
if (vdev->intx.mmap_timeout) {
timer_mod(vdev->intx.mmap_timer,
qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + vdev->intx.mmap_timeout);
}
}
static void vfio_eoi(VFIODevice *vdev)
{
if (!vdev->intx.pending) {
return;
}
DPRINTF("%s(%04x:%02x:%02x.%x) EOI\n", __func__, vdev->host.domain,
vdev->host.bus, vdev->host.slot, vdev->host.function);
vdev->intx.pending = false;
pci_irq_deassert(&vdev->pdev);
vfio_unmask_intx(vdev);
}
static void vfio_enable_intx_kvm(VFIODevice *vdev)
{
#ifdef CONFIG_KVM
struct kvm_irqfd irqfd = {
.fd = event_notifier_get_fd(&vdev->intx.interrupt),
.gsi = vdev->intx.route.irq,
.flags = KVM_IRQFD_FLAG_RESAMPLE,
};
struct vfio_irq_set *irq_set;
int ret, argsz;
int32_t *pfd;
if (!VFIO_ALLOW_KVM_INTX || !kvm_irqfds_enabled() ||
vdev->intx.route.mode != PCI_INTX_ENABLED ||
!kvm_check_extension(kvm_state, KVM_CAP_IRQFD_RESAMPLE)) {
return;
}
/* Get to a known interrupt state */
qemu_set_fd_handler(irqfd.fd, NULL, NULL, vdev);
vfio_mask_intx(vdev);
vdev->intx.pending = false;
pci_irq_deassert(&vdev->pdev);
/* Get an eventfd for resample/unmask */
if (event_notifier_init(&vdev->intx.unmask, 0)) {
error_report("vfio: Error: event_notifier_init failed eoi");
goto fail;
}
/* KVM triggers it, VFIO listens for it */
irqfd.resamplefd = event_notifier_get_fd(&vdev->intx.unmask);
if (kvm_vm_ioctl(kvm_state, KVM_IRQFD, &irqfd)) {
error_report("vfio: Error: Failed to setup resample irqfd: %m");
goto fail_irqfd;
}
argsz = sizeof(*irq_set) + sizeof(*pfd);
irq_set = g_malloc0(argsz);
irq_set->argsz = argsz;
irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_UNMASK;
irq_set->index = VFIO_PCI_INTX_IRQ_INDEX;
irq_set->start = 0;
irq_set->count = 1;
pfd = (int32_t *)&irq_set->data;
*pfd = irqfd.resamplefd;
ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set);
g_free(irq_set);
if (ret) {
error_report("vfio: Error: Failed to setup INTx unmask fd: %m");
goto fail_vfio;
}
/* Let'em rip */
vfio_unmask_intx(vdev);
vdev->intx.kvm_accel = true;
DPRINTF("%s(%04x:%02x:%02x.%x) KVM INTx accel enabled\n",
__func__, vdev->host.domain, vdev->host.bus,
vdev->host.slot, vdev->host.function);
return;
fail_vfio:
irqfd.flags = KVM_IRQFD_FLAG_DEASSIGN;
kvm_vm_ioctl(kvm_state, KVM_IRQFD, &irqfd);
fail_irqfd:
event_notifier_cleanup(&vdev->intx.unmask);
fail:
qemu_set_fd_handler(irqfd.fd, vfio_intx_interrupt, NULL, vdev);
vfio_unmask_intx(vdev);
#endif
}
static void vfio_disable_intx_kvm(VFIODevice *vdev)
{
#ifdef CONFIG_KVM
struct kvm_irqfd irqfd = {
.fd = event_notifier_get_fd(&vdev->intx.interrupt),
.gsi = vdev->intx.route.irq,
.flags = KVM_IRQFD_FLAG_DEASSIGN,
};
if (!vdev->intx.kvm_accel) {
return;
}
/*
* Get to a known state, hardware masked, QEMU ready to accept new
* interrupts, QEMU IRQ de-asserted.
*/
vfio_mask_intx(vdev);
vdev->intx.pending = false;
pci_irq_deassert(&vdev->pdev);
/* Tell KVM to stop listening for an INTx irqfd */
if (kvm_vm_ioctl(kvm_state, KVM_IRQFD, &irqfd)) {
error_report("vfio: Error: Failed to disable INTx irqfd: %m");
}
/* We only need to close the eventfd for VFIO to cleanup the kernel side */
event_notifier_cleanup(&vdev->intx.unmask);
/* QEMU starts listening for interrupt events. */
qemu_set_fd_handler(irqfd.fd, vfio_intx_interrupt, NULL, vdev);
vdev->intx.kvm_accel = false;
/* If we've missed an event, let it re-fire through QEMU */
vfio_unmask_intx(vdev);
DPRINTF("%s(%04x:%02x:%02x.%x) KVM INTx accel disabled\n",
__func__, vdev->host.domain, vdev->host.bus,
vdev->host.slot, vdev->host.function);
#endif
}
static void vfio_update_irq(PCIDevice *pdev)
{
VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev);
PCIINTxRoute route;
if (vdev->interrupt != VFIO_INT_INTx) {
return;
}
route = pci_device_route_intx_to_irq(&vdev->pdev, vdev->intx.pin);
if (!pci_intx_route_changed(&vdev->intx.route, &route)) {
return; /* Nothing changed */
}
DPRINTF("%s(%04x:%02x:%02x.%x) IRQ moved %d -> %d\n", __func__,
vdev->host.domain, vdev->host.bus, vdev->host.slot,
vdev->host.function, vdev->intx.route.irq, route.irq);
vfio_disable_intx_kvm(vdev);
vdev->intx.route = route;
if (route.mode != PCI_INTX_ENABLED) {
return;
}
vfio_enable_intx_kvm(vdev);
/* Re-enable the interrupt in cased we missed an EOI */
vfio_eoi(vdev);
}
static int vfio_enable_intx(VFIODevice *vdev)
{
uint8_t pin = vfio_pci_read_config(&vdev->pdev, PCI_INTERRUPT_PIN, 1);
int ret, argsz;
struct vfio_irq_set *irq_set;
int32_t *pfd;
if (!pin) {
return 0;
}
vfio_disable_interrupts(vdev);
vdev->intx.pin = pin - 1; /* Pin A (1) -> irq[0] */
pci_config_set_interrupt_pin(vdev->pdev.config, pin);
#ifdef CONFIG_KVM
/*
* Only conditional to avoid generating error messages on platforms
* where we won't actually use the result anyway.
*/
if (kvm_irqfds_enabled() &&
kvm_check_extension(kvm_state, KVM_CAP_IRQFD_RESAMPLE)) {
vdev->intx.route = pci_device_route_intx_to_irq(&vdev->pdev,
vdev->intx.pin);
}
#endif
ret = event_notifier_init(&vdev->intx.interrupt, 0);
if (ret) {
error_report("vfio: Error: event_notifier_init failed");
return ret;
}
argsz = sizeof(*irq_set) + sizeof(*pfd);
irq_set = g_malloc0(argsz);
irq_set->argsz = argsz;
irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER;
irq_set->index = VFIO_PCI_INTX_IRQ_INDEX;
irq_set->start = 0;
irq_set->count = 1;
pfd = (int32_t *)&irq_set->data;
*pfd = event_notifier_get_fd(&vdev->intx.interrupt);
qemu_set_fd_handler(*pfd, vfio_intx_interrupt, NULL, vdev);
ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set);
g_free(irq_set);
if (ret) {
error_report("vfio: Error: Failed to setup INTx fd: %m");
qemu_set_fd_handler(*pfd, NULL, NULL, vdev);
event_notifier_cleanup(&vdev->intx.interrupt);
return -errno;
}
vfio_enable_intx_kvm(vdev);
vdev->interrupt = VFIO_INT_INTx;
DPRINTF("%s(%04x:%02x:%02x.%x)\n", __func__, vdev->host.domain,
vdev->host.bus, vdev->host.slot, vdev->host.function);
return 0;
}
static void vfio_disable_intx(VFIODevice *vdev)
{
int fd;
timer_del(vdev->intx.mmap_timer);
vfio_disable_intx_kvm(vdev);
vfio_disable_irqindex(vdev, VFIO_PCI_INTX_IRQ_INDEX);
vdev->intx.pending = false;
pci_irq_deassert(&vdev->pdev);
vfio_mmap_set_enabled(vdev, true);
fd = event_notifier_get_fd(&vdev->intx.interrupt);
qemu_set_fd_handler(fd, NULL, NULL, vdev);
event_notifier_cleanup(&vdev->intx.interrupt);
vdev->interrupt = VFIO_INT_NONE;
DPRINTF("%s(%04x:%02x:%02x.%x)\n", __func__, vdev->host.domain,
vdev->host.bus, vdev->host.slot, vdev->host.function);
}
/*
* MSI/X
*/
static void vfio_msi_interrupt(void *opaque)
{
VFIOMSIVector *vector = opaque;
VFIODevice *vdev = vector->vdev;
int nr = vector - vdev->msi_vectors;
if (!event_notifier_test_and_clear(&vector->interrupt)) {
return;
}
DPRINTF("%s(%04x:%02x:%02x.%x) vector %d\n", __func__,
vdev->host.domain, vdev->host.bus, vdev->host.slot,
vdev->host.function, nr);
if (vdev->interrupt == VFIO_INT_MSIX) {
msix_notify(&vdev->pdev, nr);
} else if (vdev->interrupt == VFIO_INT_MSI) {
msi_notify(&vdev->pdev, nr);
} else {
error_report("vfio: MSI interrupt receieved, but not enabled?");
}
}
static int vfio_enable_vectors(VFIODevice *vdev, bool msix)
{
struct vfio_irq_set *irq_set;
int ret = 0, i, argsz;
int32_t *fds;
argsz = sizeof(*irq_set) + (vdev->nr_vectors * sizeof(*fds));
irq_set = g_malloc0(argsz);
irq_set->argsz = argsz;
irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER;
irq_set->index = msix ? VFIO_PCI_MSIX_IRQ_INDEX : VFIO_PCI_MSI_IRQ_INDEX;
irq_set->start = 0;
irq_set->count = vdev->nr_vectors;
fds = (int32_t *)&irq_set->data;
for (i = 0; i < vdev->nr_vectors; i++) {
if (!vdev->msi_vectors[i].use) {
fds[i] = -1;
continue;
}
fds[i] = event_notifier_get_fd(&vdev->msi_vectors[i].interrupt);
}
ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set);
g_free(irq_set);
return ret;
}
static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
MSIMessage *msg, IOHandler *handler)
{
VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev);
VFIOMSIVector *vector;
int ret;
DPRINTF("%s(%04x:%02x:%02x.%x) vector %d used\n", __func__,
vdev->host.domain, vdev->host.bus, vdev->host.slot,
vdev->host.function, nr);
vector = &vdev->msi_vectors[nr];
vector->vdev = vdev;
vector->use = true;
msix_vector_use(pdev, nr);
if (event_notifier_init(&vector->interrupt, 0)) {
error_report("vfio: Error: event_notifier_init failed");
}
/*
* Attempt to enable route through KVM irqchip,
* default to userspace handling if unavailable.
*/
vector->virq = msg ? kvm_irqchip_add_msi_route(kvm_state, *msg) : -1;
if (vector->virq < 0 ||
kvm_irqchip_add_irqfd_notifier(kvm_state, &vector->interrupt,
NULL, vector->virq) < 0) {
if (vector->virq >= 0) {
kvm_irqchip_release_virq(kvm_state, vector->virq);
vector->virq = -1;
}
qemu_set_fd_handler(event_notifier_get_fd(&vector->interrupt),
handler, NULL, vector);
}
/*
* We don't want to have the host allocate all possible MSI vectors
* for a device if they're not in use, so we shutdown and incrementally
* increase them as needed.
*/
if (vdev->nr_vectors < nr + 1) {
vfio_disable_irqindex(vdev, VFIO_PCI_MSIX_IRQ_INDEX);
vdev->nr_vectors = nr + 1;
ret = vfio_enable_vectors(vdev, true);
if (ret) {
error_report("vfio: failed to enable vectors, %d", ret);
}
} else {
int argsz;
struct vfio_irq_set *irq_set;
int32_t *pfd;
argsz = sizeof(*irq_set) + sizeof(*pfd);
irq_set = g_malloc0(argsz);
irq_set->argsz = argsz;
irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD |
VFIO_IRQ_SET_ACTION_TRIGGER;
irq_set->index = VFIO_PCI_MSIX_IRQ_INDEX;
irq_set->start = nr;
irq_set->count = 1;
pfd = (int32_t *)&irq_set->data;
*pfd = event_notifier_get_fd(&vector->interrupt);
ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set);
g_free(irq_set);
if (ret) {
error_report("vfio: failed to modify vector, %d", ret);
}
}
return 0;
}
static int vfio_msix_vector_use(PCIDevice *pdev,
unsigned int nr, MSIMessage msg)
{
return vfio_msix_vector_do_use(pdev, nr, &msg, vfio_msi_interrupt);
}
static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr)
{
VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev);
VFIOMSIVector *vector = &vdev->msi_vectors[nr];
int argsz;
struct vfio_irq_set *irq_set;
int32_t *pfd;
DPRINTF("%s(%04x:%02x:%02x.%x) vector %d released\n", __func__,
vdev->host.domain, vdev->host.bus, vdev->host.slot,
vdev->host.function, nr);
/*
* XXX What's the right thing to do here? This turns off the interrupt
* completely, but do we really just want to switch the interrupt to
* bouncing through userspace and let msix.c drop it? Not sure.
*/
msix_vector_unuse(pdev, nr);
argsz = sizeof(*irq_set) + sizeof(*pfd);
irq_set = g_malloc0(argsz);
irq_set->argsz = argsz;
irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD |
VFIO_IRQ_SET_ACTION_TRIGGER;
irq_set->index = VFIO_PCI_MSIX_IRQ_INDEX;
irq_set->start = nr;
irq_set->count = 1;
pfd = (int32_t *)&irq_set->data;
*pfd = -1;
ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set);
g_free(irq_set);
if (vector->virq < 0) {
qemu_set_fd_handler(event_notifier_get_fd(&vector->interrupt),
NULL, NULL, NULL);
} else {
kvm_irqchip_remove_irqfd_notifier(kvm_state, &vector->interrupt,
vector->virq);
kvm_irqchip_release_virq(kvm_state, vector->virq);
vector->virq = -1;
}
event_notifier_cleanup(&vector->interrupt);
vector->use = false;
}
static void vfio_enable_msix(VFIODevice *vdev)
{
vfio_disable_interrupts(vdev);
vdev->msi_vectors = g_malloc0(vdev->msix->entries * sizeof(VFIOMSIVector));
vdev->interrupt = VFIO_INT_MSIX;
/*
* Some communication channels between VF & PF or PF & fw rely on the
* physical state of the device and expect that enabling MSI-X from the
* guest enables the same on the host. When our guest is Linux, the
* guest driver call to pci_enable_msix() sets the enabling bit in the
* MSI-X capability, but leaves the vector table masked. We therefore
* can't rely on a vector_use callback (from request_irq() in the guest)
* to switch the physical device into MSI-X mode because that may come a
* long time after pci_enable_msix(). This code enables vector 0 with
* triggering to userspace, then immediately release the vector, leaving
* the physical device with no vectors enabled, but MSI-X enabled, just
* like the guest view.
*/
vfio_msix_vector_do_use(&vdev->pdev, 0, NULL, NULL);
vfio_msix_vector_release(&vdev->pdev, 0);
if (msix_set_vector_notifiers(&vdev->pdev, vfio_msix_vector_use,
vfio_msix_vector_release, NULL)) {
error_report("vfio: msix_set_vector_notifiers failed");
}
DPRINTF("%s(%04x:%02x:%02x.%x)\n", __func__, vdev->host.domain,
vdev->host.bus, vdev->host.slot, vdev->host.function);
}
static void vfio_enable_msi(VFIODevice *vdev)
{
int ret, i;
vfio_disable_interrupts(vdev);
vdev->nr_vectors = msi_nr_vectors_allocated(&vdev->pdev);
retry:
vdev->msi_vectors = g_malloc0(vdev->nr_vectors * sizeof(VFIOMSIVector));
for (i = 0; i < vdev->nr_vectors; i++) {
VFIOMSIVector *vector = &vdev->msi_vectors[i];
vector->vdev = vdev;
vector->use = true;
if (event_notifier_init(&vector->interrupt, 0)) {
error_report("vfio: Error: event_notifier_init failed");
}
vector->msg = msi_get_message(&vdev->pdev, i);
/*
* Attempt to enable route through KVM irqchip,
* default to userspace handling if unavailable.
*/
vector->virq = kvm_irqchip_add_msi_route(kvm_state, vector->msg);
if (vector->virq < 0 ||
kvm_irqchip_add_irqfd_notifier(kvm_state, &vector->interrupt,
NULL, vector->virq) < 0) {
qemu_set_fd_handler(event_notifier_get_fd(&vector->interrupt),
vfio_msi_interrupt, NULL, vector);
}
}
ret = vfio_enable_vectors(vdev, false);
if (ret) {
if (ret < 0) {
error_report("vfio: Error: Failed to setup MSI fds: %m");
} else if (ret != vdev->nr_vectors) {
error_report("vfio: Error: Failed to enable %d "
"MSI vectors, retry with %d", vdev->nr_vectors, ret);
}
for (i = 0; i < vdev->nr_vectors; i++) {
VFIOMSIVector *vector = &vdev->msi_vectors[i];
if (vector->virq >= 0) {
kvm_irqchip_remove_irqfd_notifier(kvm_state, &vector->interrupt,
vector->virq);
kvm_irqchip_release_virq(kvm_state, vector->virq);
vector->virq = -1;
} else {
qemu_set_fd_handler(event_notifier_get_fd(&vector->interrupt),
NULL, NULL, NULL);
}
event_notifier_cleanup(&vector->interrupt);
}
g_free(vdev->msi_vectors);
if (ret > 0 && ret != vdev->nr_vectors) {
vdev->nr_vectors = ret;
goto retry;
}
vdev->nr_vectors = 0;
return;
}
vdev->interrupt = VFIO_INT_MSI;
DPRINTF("%s(%04x:%02x:%02x.%x) Enabled %d MSI vectors\n", __func__,
vdev->host.domain, vdev->host.bus, vdev->host.slot,
vdev->host.function, vdev->nr_vectors);
}
static void vfio_disable_msi_common(VFIODevice *vdev)
{
g_free(vdev->msi_vectors);
vdev->msi_vectors = NULL;
vdev->nr_vectors = 0;
vdev->interrupt = VFIO_INT_NONE;
vfio_enable_intx(vdev);
}
static void vfio_disable_msix(VFIODevice *vdev)
{
msix_unset_vector_notifiers(&vdev->pdev);
if (vdev->nr_vectors) {
vfio_disable_irqindex(vdev, VFIO_PCI_MSIX_IRQ_INDEX);
}
vfio_disable_msi_common(vdev);
DPRINTF("%s(%04x:%02x:%02x.%x)\n", __func__, vdev->host.domain,
vdev->host.bus, vdev->host.slot, vdev->host.function);
}
static void vfio_disable_msi(VFIODevice *vdev)
{
int i;
vfio_disable_irqindex(vdev, VFIO_PCI_MSI_IRQ_INDEX);
for (i = 0; i < vdev->nr_vectors; i++) {
VFIOMSIVector *vector = &vdev->msi_vectors[i];
if (!vector->use) {
continue;
}
if (vector->virq >= 0) {
kvm_irqchip_remove_irqfd_notifier(kvm_state,
&vector->interrupt, vector->virq);
kvm_irqchip_release_virq(kvm_state, vector->virq);
vector->virq = -1;
} else {
qemu_set_fd_handler(event_notifier_get_fd(&vector->interrupt),
NULL, NULL, NULL);
}
event_notifier_cleanup(&vector->interrupt);
}
vfio_disable_msi_common(vdev);
DPRINTF("%s(%04x:%02x:%02x.%x)\n", __func__, vdev->host.domain,
vdev->host.bus, vdev->host.slot, vdev->host.function);
}
static void vfio_update_msi(VFIODevice *vdev)
{
int i;
for (i = 0; i < vdev->nr_vectors; i++) {
VFIOMSIVector *vector = &vdev->msi_vectors[i];
MSIMessage msg;
if (!vector->use || vector->virq < 0) {
continue;
}
msg = msi_get_message(&vdev->pdev, i);
if (msg.address != vector->msg.address ||
msg.data != vector->msg.data) {
DPRINTF("%s(%04x:%02x:%02x.%x) MSI vector %d changed\n",
__func__, vdev->host.domain, vdev->host.bus,
vdev->host.slot, vdev->host.function, i);
kvm_irqchip_update_msi_route(kvm_state, vector->virq, msg);
vector->msg = msg;
}
}
}
/*
* IO Port/MMIO - Beware of the endians, VFIO is always little endian
*/
static void vfio_bar_write(void *opaque, hwaddr addr,
uint64_t data, unsigned size)
{
VFIOBAR *bar = opaque;
union {
uint8_t byte;
uint16_t word;
uint32_t dword;
uint64_t qword;
} buf;
switch (size) {
case 1:
buf.byte = data;
break;
case 2:
buf.word = cpu_to_le16(data);
break;
case 4:
buf.dword = cpu_to_le32(data);
break;
default:
hw_error("vfio: unsupported write size, %d bytes\n", size);
break;
}
if (pwrite(bar->fd, &buf, size, bar->fd_offset + addr) != size) {
error_report("%s(,0x%"HWADDR_PRIx", 0x%"PRIx64", %d) failed: %m",
__func__, addr, data, size);
}
#ifdef DEBUG_VFIO
{
VFIODevice *vdev = container_of(bar, VFIODevice, bars[bar->nr]);
DPRINTF("%s(%04x:%02x:%02x.%x:BAR%d+0x%"HWADDR_PRIx", 0x%"PRIx64
", %d)\n", __func__, vdev->host.domain, vdev->host.bus,
vdev->host.slot, vdev->host.function, bar->nr, addr,
data, size);
}
#endif
/*
* A read or write to a BAR always signals an INTx EOI. This will
* do nothing if not pending (including not in INTx mode). We assume
* that a BAR access is in response to an interrupt and that BAR