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
|
/**************************************************************************
*
* Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA
* All Rights Reserved.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the
* "Software"), to deal in the Software without restriction, including
* without limitation the rights to use, copy, modify, merge, publish,
* distribute, sub license, and/or sell copies of the Software, and to
* permit persons to whom the Software is furnished to do so, subject to
* the following conditions:
*
* The above copyright notice and this permission notice (including the
* next paragraph) shall be included in all copies or substantial portions
* of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
* THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
* DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
* OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
* USE OR OTHER DEALINGS IN THE SOFTWARE.
*
**************************************************************************/
/*
* Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com>
*/
#define pr_fmt(fmt) "[TTM] " fmt
#include <ttm/ttm_module.h>
#include <ttm/ttm_bo_driver.h>
#include <ttm/ttm_placement.h>
#include <drm/drm_vma_manager.h>
#include <linux/mm.h>
#include <linux/rbtree.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#define TTM_BO_VM_NUM_PREFAULT 16
static int ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
struct vm_area_struct *vma,
struct vm_fault *vmf)
{
struct ttm_bo_device *bdev = bo->bdev;
int ret = 0;
spin_lock(&bdev->fence_lock);
if (likely(!test_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags)))
goto out_unlock;
/*
* Quick non-stalling check for idle.
*/
ret = ttm_bo_wait(bo, false, false, true);
if (likely(ret == 0))
goto out_unlock;
/*
* If possible, avoid waiting for GPU with mmap_sem
* held.
*/
if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
ret = VM_FAULT_RETRY;
if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
goto out_unlock;
up_read(&vma->vm_mm->mmap_sem);
(void) ttm_bo_wait(bo, false, true, false);
goto out_unlock;
}
/*
* Ordinary wait.
*/
ret = ttm_bo_wait(bo, false, true, false);
if (unlikely(ret != 0))
ret = (ret != -ERESTARTSYS) ? VM_FAULT_SIGBUS :
VM_FAULT_NOPAGE;
out_unlock:
spin_unlock(&bdev->fence_lock);
return ret;
}
static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct ttm_buffer_object *bo = (struct ttm_buffer_object *)
vma->vm_private_data;
struct ttm_bo_device *bdev = bo->bdev;
unsigned long page_offset;
unsigned long page_last;
unsigned long pfn;
struct ttm_tt *ttm = NULL;
struct page *page;
int ret;
int i;
unsigned long address = (unsigned long)vmf->virtual_address;
int retval = VM_FAULT_NOPAGE;
struct ttm_mem_type_manager *man =
&bdev->man[bo->mem.mem_type];
struct vm_area_struct cvma;
/*
* Work around locking order reversal in fault / nopfn
* between mmap_sem and bo_reserve: Perform a trylock operation
* for reserve, and if it fails, retry the fault after waiting
* for the buffer to become unreserved.
*/
ret = ttm_bo_reserve(bo, true, true, false, NULL);
if (unlikely(ret != 0)) {
if (ret != -EBUSY)
return VM_FAULT_NOPAGE;
if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
up_read(&vma->vm_mm->mmap_sem);
(void) ttm_bo_wait_unreserved(bo);
}
return VM_FAULT_RETRY;
}
/*
* If we'd want to change locking order to
* mmap_sem -> bo::reserve, we'd use a blocking reserve here
* instead of retrying the fault...
*/
return VM_FAULT_NOPAGE;
}
if (bdev->driver->fault_reserve_notify) {
ret = bdev->driver->fault_reserve_notify(bo);
switch (ret) {
case 0:
break;
case -EBUSY:
case -ERESTARTSYS:
retval = VM_FAULT_NOPAGE;
goto out_unlock;
default:
retval = VM_FAULT_SIGBUS;
goto out_unlock;
}
}
/*
* Wait for buffer data in transit, due to a pipelined
* move.
*/
ret = ttm_bo_vm_fault_idle(bo, vma, vmf);
if (unlikely(ret != 0)) {
retval = ret;
goto out_unlock;
}
ret = ttm_mem_io_lock(man, true);
if (unlikely(ret != 0)) {
retval = VM_FAULT_NOPAGE;
goto out_unlock;
}
ret = ttm_mem_io_reserve_vm(bo);
if (unlikely(ret != 0)) {
retval = VM_FAULT_SIGBUS;
goto out_io_unlock;
}
page_offset = ((address - vma->vm_start) >> PAGE_SHIFT) +
drm_vma_node_start(&bo->vma_node) - vma->vm_pgoff;
page_last = vma_pages(vma) +
drm_vma_node_start(&bo->vma_node) - vma->vm_pgoff;
if (unlikely(page_offset >= bo->num_pages)) {
retval = VM_FAULT_SIGBUS;
goto out_io_unlock;
}
/*
* Make a local vma copy to modify the page_prot member
* and vm_flags if necessary. The vma parameter is protected
* by mmap_sem in write mode.
*/
cvma = *vma;
cvma.vm_page_prot = vm_get_page_prot(cvma.vm_flags);
if (bo->mem.bus.is_iomem) {
cvma.vm_page_prot = ttm_io_prot(bo->mem.placement,
cvma.vm_page_prot);
} else {
ttm = bo->ttm;
if (!(bo->mem.placement & TTM_PL_FLAG_CACHED))
cvma.vm_page_prot = ttm_io_prot(bo->mem.placement,
cvma.vm_page_prot);
/* Allocate all page at once, most common usage */
if (ttm->bdev->driver->ttm_tt_populate(ttm)) {
retval = VM_FAULT_OOM;
goto out_io_unlock;
}
}
/*
* Speculatively prefault a number of pages. Only error on
* first page.
*/
for (i = 0; i < TTM_BO_VM_NUM_PREFAULT; ++i) {
if (bo->mem.bus.is_iomem)
pfn = ((bo->mem.bus.base + bo->mem.bus.offset) >> PAGE_SHIFT) + page_offset;
else {
page = ttm->pages[page_offset];
if (unlikely(!page && i == 0)) {
retval = VM_FAULT_OOM;
goto out_io_unlock;
} else if (unlikely(!page)) {
break;
}
pfn = page_to_pfn(page);
}
if (vma->vm_flags & VM_MIXEDMAP)
ret = vm_insert_mixed(&cvma, address, pfn);
else
ret = vm_insert_pfn(&cvma, address, pfn);
/*
* Somebody beat us to this PTE or prefaulting to
* an already populated PTE, or prefaulting error.
*/
if (unlikely((ret == -EBUSY) || (ret != 0 && i > 0)))
break;
else if (unlikely(ret != 0)) {
retval =
(ret == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS;
goto out_io_unlock;
}
address += PAGE_SIZE;
if (unlikely(++page_offset >= page_last))
break;
}
out_io_unlock:
ttm_mem_io_unlock(man);
out_unlock:
ttm_bo_unreserve(bo);
return retval;
}
static void ttm_bo_vm_open(struct vm_area_struct *vma)
{
struct ttm_buffer_object *bo =
(struct ttm_buffer_object *)vma->vm_private_data;
(void)ttm_bo_reference(bo);
}
static void ttm_bo_vm_close(struct vm_area_struct *vma)
{
struct ttm_buffer_object *bo = (struct ttm_buffer_object *)vma->vm_private_data;
ttm_bo_unref(&bo);
vma->vm_private_data = NULL;
}
static const struct vm_operations_struct ttm_bo_vm_ops = {
.fault = ttm_bo_vm_fault,
.open = ttm_bo_vm_open,
.close = ttm_bo_vm_close
};
static struct ttm_buffer_object *ttm_bo_vm_lookup(struct ttm_bo_device *bdev,
unsigned long offset,
unsigned long pages)
{
struct drm_vma_offset_node *node;
struct ttm_buffer_object *bo = NULL;
drm_vma_offset_lock_lookup(&bdev->vma_manager);
node = drm_vma_offset_lookup_locked(&bdev->vma_manager, offset, pages);
if (likely(node)) {
bo = container_of(node, struct ttm_buffer_object, vma_node);
if (!kref_get_unless_zero(&bo->kref))
bo = NULL;
}
drm_vma_offset_unlock_lookup(&bdev->vma_manager);
if (!bo)
pr_err("Could not find buffer object to map\n");
return bo;
}
int ttm_bo_mmap(struct file *filp, struct vm_area_struct *vma,
struct ttm_bo_device *bdev)
{
struct ttm_bo_driver *driver;
struct ttm_buffer_object *bo;
int ret;
bo = ttm_bo_vm_lookup(bdev, vma->vm_pgoff, vma_pages(vma));
if (unlikely(!bo))
return -EINVAL;
driver = bo->bdev->driver;
if (unlikely(!driver->verify_access)) {
ret = -EPERM;
goto out_unref;
}
ret = driver->verify_access(bo, filp);
if (unlikely(ret != 0))
goto out_unref;
vma->vm_ops = &ttm_bo_vm_ops;
/*
* Note: We're transferring the bo reference to
* vma->vm_private_data here.
*/
vma->vm_private_data = bo;
/*
* PFNMAP is faster than MIXEDMAP due to reduced page
* administration. So use MIXEDMAP only if private VMA, where
* we need to support COW.
*/
vma->vm_flags |= (vma->vm_flags & VM_SHARED) ? VM_PFNMAP : VM_MIXEDMAP;
vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
return 0;
out_unref:
ttm_bo_unref(&bo);
return ret;
}
EXPORT_SYMBOL(ttm_bo_mmap);
int ttm_fbdev_mmap(struct vm_area_struct *vma, struct ttm_buffer_object *bo)
{
if (vma->vm_pgoff != 0)
return -EACCES;
vma->vm_ops = &ttm_bo_vm_ops;
vma->vm_private_data = ttm_bo_reference(bo);
vma->vm_flags |= (vma->vm_flags & VM_SHARED) ? VM_PFNMAP : VM_MIXEDMAP;
vma->vm_flags |= VM_IO | VM_DONTEXPAND;
return 0;
}
EXPORT_SYMBOL(ttm_fbdev_mmap);
|