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
|
/*
* Copyright (c) 2009, Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program; if not, write to the Free Software Foundation, Inc., 59 Temple
* Place - Suite 330, Boston, MA 02111-1307 USA.
*
* Author: Weidong Han <weidong.han@intel.com>
*/
#include <linux/pci.h>
#include <linux/acpi.h>
#include <linux/pci-acpi.h>
#include <xen/xen.h>
#include <xen/interface/physdev.h>
#include <xen/interface/xen.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
#include "../pci/pci.h"
#ifdef CONFIG_PCI_MMCONFIG
#include <asm/pci_x86.h>
static int xen_mcfg_late(void);
#endif
static bool __read_mostly pci_seg_supported = true;
static int xen_add_device(struct device *dev)
{
int r;
struct pci_dev *pci_dev = to_pci_dev(dev);
#ifdef CONFIG_PCI_IOV
struct pci_dev *physfn = pci_dev->physfn;
#endif
#ifdef CONFIG_PCI_MMCONFIG
static bool pci_mcfg_reserved = false;
/*
* Reserve MCFG areas in Xen on first invocation due to this being
* potentially called from inside of acpi_init immediately after
* MCFG table has been finally parsed.
*/
if (!pci_mcfg_reserved) {
xen_mcfg_late();
pci_mcfg_reserved = true;
}
#endif
if (pci_seg_supported) {
struct {
struct physdev_pci_device_add add;
uint32_t pxm;
} add_ext = {
.add.seg = pci_domain_nr(pci_dev->bus),
.add.bus = pci_dev->bus->number,
.add.devfn = pci_dev->devfn
};
struct physdev_pci_device_add *add = &add_ext.add;
#ifdef CONFIG_ACPI
acpi_handle handle;
#endif
#ifdef CONFIG_PCI_IOV
if (pci_dev->is_virtfn) {
add->flags = XEN_PCI_DEV_VIRTFN;
add->physfn.bus = physfn->bus->number;
add->physfn.devfn = physfn->devfn;
} else
#endif
if (pci_ari_enabled(pci_dev->bus) && PCI_SLOT(pci_dev->devfn))
add->flags = XEN_PCI_DEV_EXTFN;
#ifdef CONFIG_ACPI
handle = ACPI_HANDLE(&pci_dev->dev);
#ifdef CONFIG_PCI_IOV
if (!handle && pci_dev->is_virtfn)
handle = ACPI_HANDLE(physfn->bus->bridge);
#endif
if (!handle) {
/*
* This device was not listed in the ACPI name space at
* all. Try to get acpi handle of parent pci bus.
*/
struct pci_bus *pbus;
for (pbus = pci_dev->bus; pbus; pbus = pbus->parent) {
handle = acpi_pci_get_bridge_handle(pbus);
if (handle)
break;
}
}
if (handle) {
acpi_status status;
do {
unsigned long long pxm;
status = acpi_evaluate_integer(handle, "_PXM",
NULL, &pxm);
if (ACPI_SUCCESS(status)) {
add->optarr[0] = pxm;
add->flags |= XEN_PCI_DEV_PXM;
break;
}
status = acpi_get_parent(handle, &handle);
} while (ACPI_SUCCESS(status));
}
#endif /* CONFIG_ACPI */
r = HYPERVISOR_physdev_op(PHYSDEVOP_pci_device_add, add);
if (r != -ENOSYS)
return r;
pci_seg_supported = false;
}
if (pci_domain_nr(pci_dev->bus))
r = -ENOSYS;
#ifdef CONFIG_PCI_IOV
else if (pci_dev->is_virtfn) {
struct physdev_manage_pci_ext manage_pci_ext = {
.bus = pci_dev->bus->number,
.devfn = pci_dev->devfn,
.is_virtfn = 1,
.physfn.bus = physfn->bus->number,
.physfn.devfn = physfn->devfn,
};
r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_add_ext,
&manage_pci_ext);
}
#endif
else if (pci_ari_enabled(pci_dev->bus) && PCI_SLOT(pci_dev->devfn)) {
struct physdev_manage_pci_ext manage_pci_ext = {
.bus = pci_dev->bus->number,
.devfn = pci_dev->devfn,
.is_extfn = 1,
};
r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_add_ext,
&manage_pci_ext);
} else {
struct physdev_manage_pci manage_pci = {
.bus = pci_dev->bus->number,
.devfn = pci_dev->devfn,
};
r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_add,
&manage_pci);
}
return r;
}
static int xen_remove_device(struct device *dev)
{
int r;
struct pci_dev *pci_dev = to_pci_dev(dev);
if (pci_seg_supported) {
struct physdev_pci_device device = {
.seg = pci_domain_nr(pci_dev->bus),
.bus = pci_dev->bus->number,
.devfn = pci_dev->devfn
};
r = HYPERVISOR_physdev_op(PHYSDEVOP_pci_device_remove,
&device);
} else if (pci_domain_nr(pci_dev->bus))
r = -ENOSYS;
else {
struct physdev_manage_pci manage_pci = {
.bus = pci_dev->bus->number,
.devfn = pci_dev->devfn
};
r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_remove,
&manage_pci);
}
return r;
}
static int xen_pci_notifier(struct notifier_block *nb,
unsigned long action, void *data)
{
struct device *dev = data;
int r = 0;
switch (action) {
case BUS_NOTIFY_ADD_DEVICE:
r = xen_add_device(dev);
break;
case BUS_NOTIFY_DEL_DEVICE:
r = xen_remove_device(dev);
break;
default:
return NOTIFY_DONE;
}
if (r)
dev_err(dev, "Failed to %s - passthrough or MSI/MSI-X might fail!\n",
action == BUS_NOTIFY_ADD_DEVICE ? "add" :
(action == BUS_NOTIFY_DEL_DEVICE ? "delete" : "?"));
return NOTIFY_OK;
}
static struct notifier_block device_nb = {
.notifier_call = xen_pci_notifier,
};
static int __init register_xen_pci_notifier(void)
{
if (!xen_initial_domain())
return 0;
return bus_register_notifier(&pci_bus_type, &device_nb);
}
arch_initcall(register_xen_pci_notifier);
#ifdef CONFIG_PCI_MMCONFIG
static int xen_mcfg_late(void)
{
struct pci_mmcfg_region *cfg;
int rc;
if (!xen_initial_domain())
return 0;
if ((pci_probe & PCI_PROBE_MMCONF) == 0)
return 0;
if (list_empty(&pci_mmcfg_list))
return 0;
/* Check whether they are in the right area. */
list_for_each_entry(cfg, &pci_mmcfg_list, list) {
struct physdev_pci_mmcfg_reserved r;
r.address = cfg->address;
r.segment = cfg->segment;
r.start_bus = cfg->start_bus;
r.end_bus = cfg->end_bus;
r.flags = XEN_PCI_MMCFG_RESERVED;
rc = HYPERVISOR_physdev_op(PHYSDEVOP_pci_mmcfg_reserved, &r);
switch (rc) {
case 0:
case -ENOSYS:
continue;
default:
pr_warn("Failed to report MMCONFIG reservation"
" state for %s to hypervisor"
" (%d)\n",
cfg->name, rc);
}
}
return 0;
}
#endif
|
