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
|
/*
* Copyright (c) 2006, 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.
*
* Copyright (C) 2006-2008 Intel Corporation
* Copyright IBM Corporation, 2008
* Copyright 2010 Red Hat, Inc. and/or its affiliates.
*
* Author: Allen M. Kay <allen.m.kay@intel.com>
* Author: Weidong Han <weidong.han@intel.com>
* Author: Ben-Ami Yassour <benami@il.ibm.com>
*/
#include <linux/list.h>
#include <linux/kvm_host.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/stat.h>
#include <linux/dmar.h>
#include <linux/iommu.h>
#include <linux/intel-iommu.h>
static bool allow_unsafe_assigned_interrupts;
module_param_named(allow_unsafe_assigned_interrupts,
allow_unsafe_assigned_interrupts, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(allow_unsafe_assigned_interrupts,
"Enable device assignment on platforms without interrupt remapping support.");
static int kvm_iommu_unmap_memslots(struct kvm *kvm);
static void kvm_iommu_put_pages(struct kvm *kvm,
gfn_t base_gfn, unsigned long npages);
static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
unsigned long size)
{
gfn_t end_gfn;
pfn_t pfn;
pfn = gfn_to_pfn_memslot(slot, gfn);
end_gfn = gfn + (size >> PAGE_SHIFT);
gfn += 1;
if (is_error_pfn(pfn))
return pfn;
while (gfn < end_gfn)
gfn_to_pfn_memslot(slot, gfn++);
return pfn;
}
int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
{
gfn_t gfn, end_gfn;
pfn_t pfn;
int r = 0;
struct iommu_domain *domain = kvm->arch.iommu_domain;
int flags;
/* check if iommu exists and in use */
if (!domain)
return 0;
gfn = slot->base_gfn;
end_gfn = gfn + slot->npages;
flags = IOMMU_READ | IOMMU_WRITE;
if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY)
flags |= IOMMU_CACHE;
while (gfn < end_gfn) {
unsigned long page_size;
/* Check if already mapped */
if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) {
gfn += 1;
continue;
}
/* Get the page size we could use to map */
page_size = kvm_host_page_size(kvm, gfn);
/* Make sure the page_size does not exceed the memslot */
while ((gfn + (page_size >> PAGE_SHIFT)) > end_gfn)
page_size >>= 1;
/* Make sure gfn is aligned to the page size we want to map */
while ((gfn << PAGE_SHIFT) & (page_size - 1))
page_size >>= 1;
/*
* Pin all pages we are about to map in memory. This is
* important because we unmap and unpin in 4kb steps later.
*/
pfn = kvm_pin_pages(slot, gfn, page_size);
if (is_error_pfn(pfn)) {
kvm_release_pfn_clean(pfn);
gfn += 1;
continue;
}
/* Map into IO address space */
r = iommu_map(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn),
page_size, flags);
if (r) {
printk(KERN_ERR "kvm_iommu_map_address:"
"iommu failed to map pfn=%llx\n", pfn);
goto unmap_pages;
}
gfn += page_size >> PAGE_SHIFT;
}
return 0;
unmap_pages:
kvm_iommu_put_pages(kvm, slot->base_gfn, gfn);
return r;
}
static int kvm_iommu_map_memslots(struct kvm *kvm)
{
int idx, r = 0;
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
idx = srcu_read_lock(&kvm->srcu);
slots = kvm_memslots(kvm);
kvm_for_each_memslot(memslot, slots) {
r = kvm_iommu_map_pages(kvm, memslot);
if (r)
break;
}
srcu_read_unlock(&kvm->srcu, idx);
return r;
}
int kvm_assign_device(struct kvm *kvm,
struct kvm_assigned_dev_kernel *assigned_dev)
{
struct pci_dev *pdev = NULL;
struct iommu_domain *domain = kvm->arch.iommu_domain;
int r, last_flags;
/* check if iommu exists and in use */
if (!domain)
return 0;
pdev = assigned_dev->dev;
if (pdev == NULL)
return -ENODEV;
r = iommu_attach_device(domain, &pdev->dev);
if (r) {
printk(KERN_ERR "assign device %x:%x:%x.%x failed",
pci_domain_nr(pdev->bus),
pdev->bus->number,
PCI_SLOT(pdev->devfn),
PCI_FUNC(pdev->devfn));
return r;
}
last_flags = kvm->arch.iommu_flags;
if (iommu_domain_has_cap(kvm->arch.iommu_domain,
IOMMU_CAP_CACHE_COHERENCY))
kvm->arch.iommu_flags |= KVM_IOMMU_CACHE_COHERENCY;
/* Check if need to update IOMMU page table for guest memory */
if ((last_flags ^ kvm->arch.iommu_flags) ==
KVM_IOMMU_CACHE_COHERENCY) {
kvm_iommu_unmap_memslots(kvm);
r = kvm_iommu_map_memslots(kvm);
if (r)
goto out_unmap;
}
pdev->dev_flags |= PCI_DEV_FLAGS_ASSIGNED;
printk(KERN_DEBUG "assign device %x:%x:%x.%x\n",
assigned_dev->host_segnr,
assigned_dev->host_busnr,
PCI_SLOT(assigned_dev->host_devfn),
PCI_FUNC(assigned_dev->host_devfn));
return 0;
out_unmap:
kvm_iommu_unmap_memslots(kvm);
return r;
}
int kvm_deassign_device(struct kvm *kvm,
struct kvm_assigned_dev_kernel *assigned_dev)
{
struct iommu_domain *domain = kvm->arch.iommu_domain;
struct pci_dev *pdev = NULL;
/* check if iommu exists and in use */
if (!domain)
return 0;
pdev = assigned_dev->dev;
if (pdev == NULL)
return -ENODEV;
iommu_detach_device(domain, &pdev->dev);
pdev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED;
printk(KERN_DEBUG "deassign device %x:%x:%x.%x\n",
assigned_dev->host_segnr,
assigned_dev->host_busnr,
PCI_SLOT(assigned_dev->host_devfn),
PCI_FUNC(assigned_dev->host_devfn));
return 0;
}
int kvm_iommu_map_guest(struct kvm *kvm)
{
int r;
if (!iommu_present(&pci_bus_type)) {
printk(KERN_ERR "%s: iommu not found\n", __func__);
return -ENODEV;
}
mutex_lock(&kvm->slots_lock);
kvm->arch.iommu_domain = iommu_domain_alloc(&pci_bus_type);
if (!kvm->arch.iommu_domain) {
r = -ENOMEM;
goto out_unlock;
}
if (!allow_unsafe_assigned_interrupts &&
!iommu_domain_has_cap(kvm->arch.iommu_domain,
IOMMU_CAP_INTR_REMAP)) {
printk(KERN_WARNING "%s: No interrupt remapping support,"
" disallowing device assignment."
" Re-enble with \"allow_unsafe_assigned_interrupts=1\""
" module option.\n", __func__);
iommu_domain_free(kvm->arch.iommu_domain);
kvm->arch.iommu_domain = NULL;
r = -EPERM;
goto out_unlock;
}
r = kvm_iommu_map_memslots(kvm);
if (r)
kvm_iommu_unmap_memslots(kvm);
out_unlock:
mutex_unlock(&kvm->slots_lock);
return r;
}
static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
{
unsigned long i;
for (i = 0; i < npages; ++i)
kvm_release_pfn_clean(pfn + i);
}
static void kvm_iommu_put_pages(struct kvm *kvm,
gfn_t base_gfn, unsigned long npages)
{
struct iommu_domain *domain;
gfn_t end_gfn, gfn;
pfn_t pfn;
u64 phys;
domain = kvm->arch.iommu_domain;
end_gfn = base_gfn + npages;
gfn = base_gfn;
/* check if iommu exists and in use */
if (!domain)
return;
while (gfn < end_gfn) {
unsigned long unmap_pages;
size_t size;
/* Get physical address */
phys = iommu_iova_to_phys(domain, gfn_to_gpa(
|