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
|
/*
* VFIO: IOMMU DMA mapping support for TCE on POWER
*
* Copyright (C) 2013 IBM Corp. All rights reserved.
* Author: Alexey Kardashevskiy <aik@ozlabs.ru>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* Derived from original vfio_iommu_type1.c:
* Copyright (C) 2012 Red Hat, Inc. All rights reserved.
* Author: Alex Williamson <alex.williamson@redhat.com>
*/
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/err.h>
#include <linux/vfio.h>
#include <asm/iommu.h>
#include <asm/tce.h>
#define DRIVER_VERSION "0.1"
#define DRIVER_AUTHOR "aik@ozlabs.ru"
#define DRIVER_DESC "VFIO IOMMU SPAPR TCE"
static void tce_iommu_detach_group(void *iommu_data,
struct iommu_group *iommu_group);
/*
* VFIO IOMMU fd for SPAPR_TCE IOMMU implementation
*
* This code handles mapping and unmapping of user data buffers
* into DMA'ble space using the IOMMU
*/
/*
* The container descriptor supports only a single group per container.
* Required by the API as the container is not supplied with the IOMMU group
* at the moment of initialization.
*/
struct tce_container {
struct mutex lock;
struct iommu_table *tbl;
bool enabled;
};
static int tce_iommu_enable(struct tce_container *container)
{
int ret = 0;
unsigned long locked, lock_limit, npages;
struct iommu_table *tbl = container->tbl;
if (!container->tbl)
return -ENXIO;
if (!current->mm)
return -ESRCH; /* process exited */
if (container->enabled)
return -EBUSY;
/*
* When userspace pages are mapped into the IOMMU, they are effectively
* locked memory, so, theoretically, we need to update the accounting
* of locked pages on each map and unmap. For powerpc, the map unmap
* paths can be very hot, though, and the accounting would kill
* performance, especially since it would be difficult to impossible
* to handle the accounting in real mode only.
*
* To address that, rather than precisely accounting every page, we
* instead account for a worst case on locked memory when the iommu is
* enabled and disabled. The worst case upper bound on locked memory
* is the size of the whole iommu window, which is usually relatively
* small (compared to total memory sizes) on POWER hardware.
*
* Also we don't have a nice way to fail on H_PUT_TCE due to ulimits,
* that would effectively kill the guest at random points, much better
* enforcing the limit based on the max that the guest can map.
*/
down_write(¤t->mm->mmap_sem);
npages = (tbl->it_size << IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
locked = current->mm->locked_vm + npages;
lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
pr_warn("RLIMIT_MEMLOCK (%ld) exceeded\n",
rlimit(RLIMIT_MEMLOCK));
ret = -ENOMEM;
} else {
current->mm->locked_vm += npages;
container->enabled = true;
}
up_write(¤t->mm->mmap_sem);
return ret;
}
static void tce_iommu_disable(struct tce_container *container)
{
if (!container->enabled)
return;
container->enabled = false;
if (!container->tbl || !current->mm)
return;
down_write(¤t->mm->mmap_sem);
current->mm->locked_vm -= (container->tbl->it_size <<
IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
up_write(¤t->mm->mmap_sem);
}
static void *tce_iommu_open(unsigned long arg)
{
struct tce_container *container;
if (arg != VFIO_SPAPR_TCE_IOMMU) {
pr_err("tce_vfio: Wrong IOMMU type\n");
return ERR_PTR(-EINVAL);
}
container = kzalloc(sizeof(*container), GFP_KERNEL);
if (!container)
return ERR_PTR(-ENOMEM);
mutex_init(&container->lock);
return container;
}
static void tce_iommu_release(void *iommu_data)
{
struct tce_container *container = iommu_data;
WARN_ON(container->tbl && !container->tbl->it_group);
tce_iommu_disable(container);
if (container->tbl && container->tbl->it_group)
tce_iommu_detach_group(iommu_data, container->tbl->it_group);
mutex_destroy(&container->lock);
kfree(container);
}
static long tce_iommu_ioctl(void *iommu_data,
unsigned int cmd, unsigned long arg)
{
struct tce_container *container = iommu_data;
unsigned long minsz;
long ret;
switch (cmd) {
case VFIO_CHECK_EXTENSION:
switch (arg) {
case VFIO_SPAPR_TCE_IOMMU:
ret = 1;
break;
default:
ret = vfio_spapr_iommu_eeh_ioctl(NULL, cmd, arg);
break;
}
return (ret < 0) ? 0 : ret;
case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
struct vfio_iommu_spapr_tce_info info;
struct iommu_table *tbl = container->tbl;
if (WARN_ON(!tbl))
return -ENXIO;
minsz = offsetofend(struct vfio_iommu_spapr_tce_info,
dma32_window_size);
if (copy_from_user(&info, (void __user *)arg, minsz))
return -EFAULT;
if (info.argsz < minsz)
return -EINVAL;
info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT_4K;
info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT_4K;
info.flags = 0;
if (copy_to_user((void __user *)arg, &info, minsz))
return -EFAULT;
return 0;
}
case VFIO_IOMMU_MAP_DMA: {
struct vfio_iommu_type1_dma_map param;
struct iommu_table *tbl = container->tbl;
unsigned long tce, i;
if (!tbl)
return -ENXIO;
BUG_ON(!tbl->it_group);
minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
if (copy_from_user(¶m, (void __user *)arg, minsz))
return -EFAULT;
if (param.argsz < minsz)
return -EINVAL;
if (param.flags & ~(VFIO_DMA_MAP_FLAG_READ |
VFIO_DMA_MAP_FLAG_WRITE))
return -EINVAL;
if ((param.size & ~IOMMU_PAGE_MASK_4K) ||
(param.vaddr & ~IOMMU_PAGE_MASK_4K))
return -EINVAL;
/* iova is checked by the IOMMU API */
tce = param.vaddr;
if (param.flags & VFIO_DMA_MAP_FLAG_READ)
tce |= TCE_PCI_READ;
if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
tce |= TCE_PCI_WRITE;
ret = iommu_tce_put_param_check(tbl, param.iova, tce);
if (ret)
return ret;
for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT_4K); ++i) {
ret = iommu_put_tce_user_mode(tbl,
(param.iova >> IOMMU_PAGE_SHIFT_4K) + i,
tce);
if (ret)
break;
tce += IOMMU_PAGE_SIZE_4K;
}
if (ret)
iommu_clear_tces_and_put_pages(tbl,
param.iova >> IOMMU_PAGE_SHIFT_4K, i);
iommu_flush_tce(tbl);
return ret;
}
case VFIO_IOMMU_UNMAP_DMA: {
struct vfio_iommu_type1_dma_unmap param;
struct iommu_table *tbl = container->tbl;
if (WARN_ON(!tbl))
return -ENXIO;
minsz = offsetofend(struct vfio_iommu_type1_dma_unmap,
size);
if (copy_from_user(¶m, (void __user *)arg, minsz))
return -EFAULT;
if (param.argsz < minsz)
return -EINVAL;
/* No flag is supported now */
if (param.flags)
return -EINVAL;
if (param.size & ~IOMMU_PAGE_MASK_4K)
return -EINVAL;
ret = iommu_tce_clear_param_check(tbl, param.iova, 0,
param.size >> IOMMU_PAGE_SHIFT_4K);
if (ret)
return ret;
ret = iommu_clear_tces_and_put_pages(tbl,
param.iova >> IOMMU_PAGE_SHIFT_4K,
param.size >> IOMMU_PAGE_SHIFT_4K);
iommu_flush_tce(tbl);
return ret;
}
case VFIO_IOMMU_ENABLE:
mutex_lock(&container->lock);
ret = tce_iommu_enable(container);
mutex_unlock(
|