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
|
/*
* Copyright (c) 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005 Cisco Systems. All rights reserved.
* Copyright (c) 2005 Mellanox Technologies. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* 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
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* 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.
*/
#include <linux/mm.h>
#include <linux/dma-mapping.h>
#include <linux/sched.h>
#include <linux/export.h>
#include <linux/hugetlb.h>
#include <linux/dma-attrs.h>
#include <linux/slab.h>
#include <rdma/ib_umem_odp.h>
#include "uverbs.h"
static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int dirty)
{
struct scatterlist *sg;
struct page *page;
int i;
if (umem->nmap > 0)
ib_dma_unmap_sg(dev, umem->sg_head.sgl,
umem->nmap,
DMA_BIDIRECTIONAL);
for_each_sg(umem->sg_head.sgl, sg, umem->npages, i) {
page = sg_page(sg);
if (umem->writable && dirty)
set_page_dirty_lock(page);
put_page(page);
}
sg_free_table(&umem->sg_head);
return;
}
/**
* ib_umem_get - Pin and DMA map userspace memory.
*
* If access flags indicate ODP memory, avoid pinning. Instead, stores
* the mm for future page fault handling in conjunction with MMU notifiers.
*
* @context: userspace context to pin memory for
* @addr: userspace virtual address to start at
* @size: length of region to pin
* @access: IB_ACCESS_xxx flags for memory being pinned
* @dmasync: flush in-flight DMA when the memory region is written
*/
struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
size_t size, int access, int dmasync)
{
struct ib_umem *umem;
struct page **page_list;
struct vm_area_struct **vma_list;
unsigned long locked;
unsigned long lock_limit;
unsigned long cur_base;
unsigned long npages;
int ret;
int i;
DEFINE_DMA_ATTRS(attrs);
struct scatterlist *sg, *sg_list_start;
int need_release = 0;
if (dmasync)
dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs);
if (!size)
return ERR_PTR(-EINVAL);
/*
* If the combination of the addr and size requested for this memory
* region causes an integer overflow, return error.
*/
if (((addr + size) < addr) ||
PAGE_ALIGN(addr + size) < (addr + size))
return ERR_PTR(-EINVAL);
if (!can_do_mlock())
return ERR_PTR(-EPERM);
umem = kzalloc(sizeof *umem, GFP_KERNEL);
if (!umem)
return ERR_PTR(-ENOMEM);
umem->context = context;
umem->length = size;
umem->address = addr;
umem->page_size = PAGE_SIZE;
umem->pid = get_task_pid(current, PIDTYPE_PID);
/*
* We ask for writable memory if any of the following
* access flags are set. "Local write" and "remote write"
* obviously require write access. "Remote atomic" can do
* things like fetch and add, which will modify memory, and
* "MW bind" can change permissions by binding a window.
*/
umem->writable = !!(access &
(IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE |
IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND));
if (access & IB_ACCESS_ON_DEMAND) {
ret = ib_umem_odp_get(context, umem);
if (ret) {
kfree(umem);
return ERR_PTR(ret);
}
return umem;
}
umem->odp_data = NULL;
/* We assume the memory is from hugetlb until proved otherwise */
umem->hugetlb = 1;
page_list = (struct page **) __get_free_page(GFP_KERNEL);
if (!page_list) {
kfree(umem);
return ERR_PTR(-ENOMEM);
}
/*
* if we can't alloc the vma_list, it's not so bad;
* just assume the memory is not hugetlb memory
*/
vma_list = (struct vm_area_struct **) __get_free_page(GFP_KERNEL);
if (!vma_list)
umem->hugetlb = 0;
npages = ib_umem_num_pages(umem);
down_write(¤t->mm->mmap_sem);
locked = npages + current->mm->pinned_vm;
lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
if ((locked > lock_limit) && !capable(CAP_IPC_LOCK)) {
ret = -ENOMEM;
goto out;
}
cur_base = addr & PAGE_MASK;
if (npages == 0) {
ret = -EINVAL;
goto out;
}
ret = sg_alloc_table(&umem->sg_head, npages, GFP_KERNEL);
if (ret)
goto out;
need_release = 1;
sg_list_start = umem->sg_head.sgl;
while (npages) {
ret = get_user_pages(cur_base,
min_t(unsigned long, npages,
PAGE_SIZE / sizeof (struct page *)),
1, !umem->writable, page_list, vma_list);
if (ret < 0)
goto out;
umem->npages += ret;
cur_base += ret * PAGE_SIZE;
npages -= ret;
for_each_sg(sg_list_start, sg, ret, i) {
if (vma_list && !is_vm_hugetlb_page(vma_list[i]))
umem->hugetlb = 0;
sg_set_page(sg, page_list[i], PAGE_SIZE, 0);
}
/* preparing for next loop */
sg_list_start = sg;
}
umem->nmap = ib_dma_map_sg_attrs(context->device,
umem->sg_head.sgl,
umem->npages,
DMA_BIDIRECTIONAL,
&attrs);
if (umem->nmap <= 0) {
ret = -ENOMEM;
goto out;
}
ret = 0;
out:
if (ret < 0) {
if (need_release)
__ib_umem_release(context->device, umem, 0);
put_pid(umem->pid);
kfree(umem);
} else
current->mm->pinned_vm = locked;
up_write(¤t->mm->mmap_sem);
if (vma_list)
free_page((unsigned long) vma_list);
free_page((unsigned long) page_list);
return ret < 0 ? ERR_PTR(ret) : umem;
}
EXPORT_SYMBOL(ib_umem_get);
static void ib_umem_account(struct work_struct *work)
{
struct ib_umem *umem = container_of(work, struct ib_umem, work);
down_write(&umem->mm->mmap_sem);
umem->mm->pinned_vm -= umem->diff;
up_write(&umem->mm->mmap_sem);
mmput(umem->mm);
kfree(umem);
}
/**
* ib_umem_release - release memory pinned with ib_umem_get
* @umem: umem struct to release
*/
void ib_umem_release(struct ib_umem *umem)
{
struct ib_ucontext *context = umem->context;
struct mm_struct *mm;
struct task_struct *task;
unsigned long diff;
if (umem->odp_data) {
ib_umem_odp_release(umem);
return;
}
__ib_umem_release(umem->context->device, umem, 1);
task = get_pid_task(umem->pid, PIDTYPE_PID);
put_pid(umem->pid);
if (!task)
goto out;
mm = get_task_mm(task);
put_task_struct(task);
if (!mm)
goto out;
diff = ib_umem_num_pages(umem);
/*
* We may be called with the mm's mmap_sem already held. This
* can happen when a userspace munmap() is the call that drops
* the last reference to our file and calls our release
* method. If there are memory regions to destroy, we'll end
* up here and not be able to take the mmap_sem. In that case
* we defer the vm_locked accounting to the system workqueue.
*/
if (context->closing) {
if (!down_write_trylock(&mm->mmap_sem)) {
INIT_WORK(&umem->work, ib_umem_account);
umem->mm = mm;
umem->diff = diff;
queue_work(ib_wq, &umem->work);
return;
}
} else
down_write(&mm->mmap_sem);
mm->pinned_vm -= dif
|