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
|
/*
* Copyright (c) 2021-2024 Oracle and/or its affiliates.
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "hw/vfio/vfio-device.h"
#include "hw/vfio/vfio-cpr.h"
#include "hw/vfio/pci.h"
#include "hw/pci/msix.h"
#include "hw/pci/msi.h"
#include "migration/cpr.h"
#include "qapi/error.h"
#include "system/runstate.h"
int vfio_cpr_reboot_notifier(NotifierWithReturn *notifier,
MigrationEvent *e, Error **errp)
{
if (e->type == MIG_EVENT_PRECOPY_SETUP &&
!runstate_check(RUN_STATE_SUSPENDED) && !vm_get_suspended()) {
error_setg(errp,
"VFIO device only supports cpr-reboot for runstate suspended");
return -1;
}
return 0;
}
#define STRDUP_VECTOR_FD_NAME(vdev, name) \
g_strdup_printf("%s_%s", (vdev)->vbasedev.name, (name))
void vfio_cpr_save_vector_fd(VFIOPCIDevice *vdev, const char *name, int nr,
int fd)
{
g_autofree char *fdname = STRDUP_VECTOR_FD_NAME(vdev, name);
cpr_save_fd(fdname, nr, fd);
}
int vfio_cpr_load_vector_fd(VFIOPCIDevice *vdev, const char *name, int nr)
{
g_autofree char *fdname = STRDUP_VECTOR_FD_NAME(vdev, name);
return cpr_find_fd(fdname, nr);
}
void vfio_cpr_delete_vector_fd(VFIOPCIDevice *vdev, const char *name, int nr)
{
g_autofree char *fdname = STRDUP_VECTOR_FD_NAME(vdev, name);
cpr_delete_fd(fdname, nr);
}
static void vfio_cpr_claim_vectors(VFIOPCIDevice *vdev, int nr_vectors,
bool msix)
{
int i, fd;
bool pending = false;
PCIDevice *pdev = &vdev->pdev;
vdev->nr_vectors = nr_vectors;
vdev->msi_vectors = g_new0(VFIOMSIVector, nr_vectors);
vdev->interrupt = msix ? VFIO_INT_MSIX : VFIO_INT_MSI;
vfio_pci_prepare_kvm_msi_virq_batch(vdev);
for (i = 0; i < nr_vectors; i++) {
VFIOMSIVector *vector = &vdev->msi_vectors[i];
fd = vfio_cpr_load_vector_fd(vdev, "interrupt", i);
if (fd >= 0) {
vfio_pci_vector_init(vdev, i);
vfio_pci_msi_set_handler(vdev, i);
}
if (vfio_cpr_load_vector_fd(vdev, "kvm_interrupt", i) >= 0) {
vfio_pci_add_kvm_msi_virq(vdev, vector, i, msix);
} else {
vdev->msi_vectors[i].virq = -1;
}
if (msix && msix_is_pending(pdev, i) && msix_is_masked(pdev, i)) {
set_bit(i, vdev->msix->pending);
pending = true;
}
}
vfio_pci_commit_kvm_msi_virq_batch(vdev);
if (msix) {
memory_region_set_enabled(&pdev->msix_pba_mmio, pending);
}
}
/*
* The kernel may change non-emulated config bits. Exclude them from the
* changed-bits check in get_pci_config_device.
*/
static int vfio_cpr_pci_pre_load(void *opaque)
{
VFIOPCIDevice *vdev = opaque;
PCIDevice *pdev = &vdev->pdev;
int size = MIN(pci_config_size(pdev), vdev->config_size);
int i;
for (i = 0; i < size; i++) {
pdev->cmask[i] &= vdev->emulated_config_bits[i];
}
return 0;
}
static int vfio_cpr_pci_post_load(void *opaque, int version_id)
{
VFIOPCIDevice *vdev = opaque;
PCIDevice *pdev = &vdev->pdev;
int nr_vectors;
vfio_sub_page_bar_update_mappings(vdev);
if (msix_enabled(pdev)) {
vfio_pci_msix_set_notifiers(vdev);
nr_vectors = vdev->msix->entries;
vfio_cpr_claim_vectors(vdev, nr_vectors, true);
} else if (msi_enabled(pdev)) {
nr_vectors = msi_nr_vectors_allocated(pdev);
vfio_cpr_claim_vectors(vdev, nr_vectors, false);
} else if (vfio_pci_read_config(pdev, PCI_INTERRUPT_PIN, 1)) {
Error *local_err = NULL;
if (!vfio_pci_intx_enable(vdev, &local_err)) {
error_report_err(local_err);
return -1;
}
}
return 0;
}
static bool pci_msix_present(void *opaque, int version_id)
{
PCIDevice *pdev = opaque;
return msix_present(pdev);
}
static const VMStateDescription vfio_intx_vmstate = {
.name = "vfio-cpr-intx",
.version_id = 0,
.minimum_version_id = 0,
.fields = (VMStateField[]) {
VMSTATE_BOOL(pending, VFIOINTx),
VMSTATE_UINT32(route.mode, VFIOINTx),
VMSTATE_INT32(route.irq, VFIOINTx),
VMSTATE_END_OF_LIST()
}
};
#define VMSTATE_VFIO_INTX(_field, _state) { \
.name = (stringify(_field)), \
.size = sizeof(VFIOINTx), \
.vmsd = &vfio_intx_vmstate, \
.flags = VMS_STRUCT, \
.offset = vmstate_offset_value(_state, _field, VFIOINTx), \
}
const VMStateDescription vfio_cpr_pci_vmstate = {
.name = "vfio-cpr-pci",
.version_id = 0,
.minimum_version_id = 0,
.pre_load = vfio_cpr_pci_pre_load,
.post_load = vfio_cpr_pci_post_load,
.needed = cpr_incoming_needed,
.fields = (VMStateField[]) {
VMSTATE_PCI_DEVICE(pdev, VFIOPCIDevice),
VMSTATE_MSIX_TEST(pdev, VFIOPCIDevice, pci_msix_present),
VMSTATE_VFIO_INTX(intx, VFIOPCIDevice),
VMSTATE_END_OF_LIST()
}
};
static NotifierWithReturn kvm_close_notifier;
static int vfio_cpr_kvm_close_notifier(NotifierWithReturn *notifier,
MigrationEvent *e,
Error **errp)
{
if (e->type == MIG_EVENT_PRECOPY_DONE) {
vfio_kvm_device_close();
}
return 0;
}
void vfio_cpr_add_kvm_notifier(void)
{
if (!kvm_close_notifier.notify) {
migration_add_notifier_mode(&kvm_close_notifier,
vfio_cpr_kvm_close_notifier,
MIG_MODE_CPR_TRANSFER);
}
}
|
