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
|
/*
* 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/signal.h>
#include <linux/sched/mm.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/pagemap.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 sg_page_iter sg_iter;
struct page *page;
if (umem->nmap > 0)
ib_dma_unmap_sg(dev, umem->sg_head.sgl, umem->sg_nents,
DMA_BIDIRECTIONAL);
for_each_sg_page(umem->sg_head.sgl, &sg_iter, umem->sg_nents, 0) {
page = sg_page_iter_page(&sg_iter);
unpin_user_pages_dirty_lock(&page, 1, umem->writable && dirty);
}
sg_free_table(&umem->sg_head);
}
/* ib_umem_add_sg_table - Add N contiguous pages to scatter table
*
* sg: current scatterlist entry
* page_list: array of npage struct page pointers
* npages: number of pages in page_list
* max_seg_sz: maximum segment size in bytes
* nents: [out] number of entries in the scatterlist
*
* Return new end of scatterlist
*/
static struct scatterlist *ib_umem_add_sg_table(struct scatterlist *sg,
struct page **page_list,
unsigned long npages,
unsigned int max_seg_sz,
int *nents)
{
unsigned long first_pfn;
unsigned long i = 0;
bool update_cur_sg = false;
bool first = !sg_page(sg);
/* Check if new page_list is contiguous with end of previous page_list.
* sg->length here is a multiple of PAGE_SIZE and sg->offset is 0.
*/
if (!first && (page_to_pfn(sg_page(sg)) + (sg->length >> PAGE_SHIFT) ==
page_to_pfn(page_list[0])))
update_cur_sg = true;
while (i != npages) {
unsigned long len;
struct page *first_page = page_list[i];
first_pfn = page_to_pfn(first_page);
/* Compute the number of contiguous pages we have starting
* at i
*/
for (len = 0; i != npages &&
first_pfn + len == page_to_pfn(page_list[i]) &&
len < (max_seg_sz >> PAGE_SHIFT);
len++)
i++;
/* Squash N contiguous pages from page_list into current sge */
if (update_cur_sg) {
if ((max_seg_sz - sg->length) >= (len << PAGE_SHIFT)) {
sg_set_page(sg, sg_page(sg),
sg->length + (len << PAGE_SHIFT),
0);
update_cur_sg = false;
continue;
}
update_cur_sg = false;
}
/* Squash N contiguous pages into next sge or first sge */
if (!first)
sg = sg_next(sg);
(*nents)++;
sg_set_page(sg, first_page, len << PAGE_SHIFT, 0);
first = false;
}
return sg;
}
/**
* ib_umem_find_best_pgsz - Find best HW page size to use for this MR
*
* @umem: umem struct
* @pgsz_bitmap: bitmap of HW supported page sizes
* @virt: IOVA
*
* This helper is intended for HW that support multiple page
* sizes but can do only a single page size in an MR.
*
* Returns 0 if the umem requires page sizes not supported by
* the driver to be mapped. Drivers always supporting PAGE_SIZE
* or smaller will never see a 0 result.
*/
unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
unsigned long pgsz_bitmap,
unsigned long virt)
{
struct scatterlist *sg;
unsigned int best_pg_bit;
unsigned long va, pgoff;
dma_addr_t mask;
int i;
/* At minimum, drivers must support PAGE_SIZE or smaller */
if (WARN_ON(!(pgsz_bitmap & GENMASK(PAGE_SHIFT, 0))))
return 0;
va = virt;
/* max page size not to exceed MR length */
mask = roundup_pow_of_two(umem->length);
/* offset into first SGL */
pgoff = umem->address & ~PAGE_MASK;
for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i) {
/* Walk SGL and reduce max page size if VA/PA bits differ
* for any address.
*/
mask |= (sg_dma_address(sg) + pgoff) ^ va;
va += sg_dma_len(sg) - pgoff;
/* Except for the last entry, the ending iova alignment sets
* the maximum possible page size as the low bits of the iova
* must be zero when starting the next chunk.
*/
if (i != (umem->nmap - 1))
mask |= va;
pgoff = 0;
}
best_pg_bit = rdma_find_pg_bit(mask, pgsz_bitmap);
return BIT_ULL(best_pg_bit);
}
EXPORT_SYMBOL(ib_umem_find_best_pgsz);
/**
* ib_umem_get - Pin and DMA map userspace memory.
*
* @device: IB device to connect UMEM
* @addr: userspace virtual address to start at
* @size: length of region to pin
* @access: IB_ACCESS_xxx flags for memory being pinned
*/
struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
size_t size, int access)
{
struct ib_umem *umem;
struct page **page_list;
unsigned long lock_limit;
unsigned long new_pinned;
unsigned long cur_base;
unsigned long dma_attr = 0;
struct mm_struct *mm;
unsigned long npages;
int ret;
struct scatterlist *sg;
unsigned int gup_flags = FOLL_WRITE;
/*
* 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);
if (access & IB_ACCESS_ON_DEMAND)
return ERR_PTR(-EOPNOTSUPP);
umem = kzalloc(sizeof(*umem), GFP_KERNEL);
if (!umem)
return ERR_PTR(-ENOMEM);
umem->ibdev = device;
umem->length = size;
umem->address = addr;
umem->writable = ib_access_writable(access);
umem->owning_mm = mm = current->mm;
mmgrab(mm);
page_list = (struct page **) __get_free_page(GFP_KERNEL);
if (!page_list) {
ret = -ENOMEM;
goto umem_kfree;
}
npages = ib_umem_num_pages(umem);
if (npages == 0 || npages > UINT_MAX) {
ret = -EINVAL;
goto out;
}
lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
new_pinned = atomic64_add_return(npages, &mm->pinned_vm);
if (new_pinned > lock_limit && !capable(CAP_IPC_LOCK)) {
atomic64_sub(npages, &mm->pinned_vm);
ret = -ENOMEM;
goto out;
}
cur_base = addr & PAGE_MASK;
ret = sg_alloc_table(&umem->sg_head, npages, GFP_KERNEL);
if (ret)
goto vma;
if (!umem->writable)
gup_flags |= FOLL_FORCE;
sg = umem->sg_head.sgl;
while (npages) {
cond_resched();
ret = pin_user_pages_fast(cur_base,
min_t(unsigned long, npages,
PAGE_SIZE /
sizeof(struct page *)),
gup_flags | FOLL_LONGTERM, page_list);
if (ret < 0)
goto umem_release;
cur_base += ret * PAGE_SIZE;
npages -= ret;
sg = ib_umem_add_sg_table(sg, page_list, ret,
dma_get_max_seg_size(device->dma_device),
&umem->sg_nents);
}
sg_mark_end(sg);
if (access & IB_ACCESS_RELAXED_ORDERING)
dma_attr |= DMA_ATTR_WEAK_ORDERING;
umem->nmap =
ib_dma_map_sg_attrs(device, umem->sg_head.sgl, umem->sg_nents,
DMA_BIDIRECTIONAL, dma_attr);
if (!umem->nmap) {
|