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
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
|
/*
* linux/mm/mlock.c
*
* (C) Copyright 1995 Linus Torvalds
* (C) Copyright 2002 Christoph Hellwig
*/
#include <linux/capability.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/rmap.h>
#include <linux/mmzone.h>
#include <linux/hugetlb.h>
#include "internal.h"
int can_do_mlock(void)
{
if (capable(CAP_IPC_LOCK))
return 1;
if (current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur != 0)
return 1;
return 0;
}
EXPORT_SYMBOL(can_do_mlock);
#ifdef CONFIG_UNEVICTABLE_LRU
/*
* Mlocked pages are marked with PageMlocked() flag for efficient testing
* in vmscan and, possibly, the fault path; and to support semi-accurate
* statistics.
*
* An mlocked page [PageMlocked(page)] is unevictable. As such, it will
* be placed on the LRU "unevictable" list, rather than the [in]active lists.
* The unevictable list is an LRU sibling list to the [in]active lists.
* PageUnevictable is set to indicate the unevictable state.
*
* When lazy mlocking via vmscan, it is important to ensure that the
* vma's VM_LOCKED status is not concurrently being modified, otherwise we
* may have mlocked a page that is being munlocked. So lazy mlock must take
* the mmap_sem for read, and verify that the vma really is locked
* (see mm/rmap.c).
*/
/*
* LRU accounting for clear_page_mlock()
*/
void __clear_page_mlock(struct page *page)
{
VM_BUG_ON(!PageLocked(page));
if (!page->mapping) { /* truncated ? */
return;
}
if (!isolate_lru_page(page)) {
putback_lru_page(page);
} else {
/*
* Page not on the LRU yet. Flush all pagevecs and retry.
*/
lru_add_drain_all();
if (!isolate_lru_page(page))
putback_lru_page(page);
}
}
/*
* Mark page as mlocked if not already.
* If page on LRU, isolate and putback to move to unevictable list.
*/
void mlock_vma_page(struct page *page)
{
BUG_ON(!PageLocked(page));
if (!TestSetPageMlocked(page) && !isolate_lru_page(page))
putback_lru_page(page);
}
/*
* called from munlock()/munmap() path with page supposedly on the LRU.
*
* Note: unlike mlock_vma_page(), we can't just clear the PageMlocked
* [in try_to_munlock()] and then attempt to isolate the page. We must
* isolate the page to keep others from messing with its unevictable
* and mlocked state while trying to munlock. However, we pre-clear the
* mlocked state anyway as we might lose the isolation race and we might
* not get another chance to clear PageMlocked. If we successfully
* isolate the page and try_to_munlock() detects other VM_LOCKED vmas
* mapping the page, it will restore the PageMlocked state, unless the page
* is mapped in a non-linear vma. So, we go ahead and SetPageMlocked(),
* perhaps redundantly.
* If we lose the isolation race, and the page is mapped by other VM_LOCKED
* vmas, we'll detect this in vmscan--via try_to_munlock() or try_to_unmap()
* either of which will restore the PageMlocked state by calling
* mlock_vma_page() above, if it can grab the vma's mmap sem.
*/
static void munlock_vma_page(struct page *page)
{
BUG_ON(!PageLocked(page));
if (TestClearPageMlocked(page) && !isolate_lru_page(page)) {
try_to_munlock(page);
putback_lru_page(page);
}
}
/*
* mlock a range of pages in the vma.
*
* This takes care of making the pages present too.
*
* vma->vm_mm->mmap_sem must be held for write.
*/
static int __mlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long addr = start;
struct page *pages[16]; /* 16 gives a reasonable batch */
int write = !!(vma->vm_flags & VM_WRITE);
int nr_pages = (end - start) / PAGE_SIZE;
int ret;
VM_BUG_ON(start & ~PAGE_MASK || end & ~PAGE_MASK);
VM_BUG_ON(start < vma->vm_start || end > vma->vm_end);
VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem));
lru_add_drain_all(); /* push cached pages to LRU */
while (nr_pages > 0) {
int i;
cond_resched();
/*
* get_user_pages makes pages present if we are
* setting mlock. and this extra reference count will
* disable migration of this page. However, page may
* still be truncated out from under us.
*/
ret = get_user_pages(current, mm, addr,
min_t(int, nr_pages, ARRAY_SIZE(pages)),
write, 0, pages, NULL);
/*
* This can happen for, e.g., VM_NONLINEAR regions before
* a page has been allocated and mapped at a given offset,
* or for addresses that map beyond end of a file.
* We'll mlock the the pages if/when they get faulted in.
*/
if (ret < 0)
break;
if (ret == 0) {
/*
* We know the vma is there, so the only time
* we cannot get a single page should be an
* error (ret < 0) case.
*/
WARN_ON(1);
break;
}
lru_add_drain(); /* push cached pages to LRU */
for (i = 0; i < ret; i++) {
struct page *page = pages[i];
lock_page(page);
/*
* Because we lock page here and migration is blocked
* by the elevated reference, we need only check for
* page truncation (file-cache only).
*/
if (page->mapping)
mlock_vma_page(page);
unlock_page(page);
put_page(page); /* ref from get_user_pages() */
/*
* here we assume that get_user_pages() has given us
* a list of virtually contiguous pages.
*/
addr += PAGE_SIZE; /* for next get_user_pages() */
nr_pages--;
}
}
lru_add_drain_all(); /* to update stats */
return 0; /* count entire vma as locked_vm */
}
/*
* private structure for munlock page table walk
*/
struct munlock_page_walk {
struct vm_area_struct *vma;
pmd_t *pmd; /* for migration_entry_wait() */
};
/*
* munlock normal pages for present ptes
*/
static int __munlock_pte_handler(pte_t *ptep, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
struct munlock_page_walk *mpw = walk->private;
swp_entry_t entry;
struct page *page;
pte_t pte;
retry:
pte = *ptep;
/*
* If it's a swap pte, we might be racing with page migration.
*/
if (unlikely(!pte_present(pte))) {
if (!is_swap_pte(pte))
goto out;
entry = pte_to_swp_entry(pte);
if (is_migration_entry(entry)) {
migration_entry_wait(mpw->vma->vm_mm, mpw->pmd, addr);
goto retry;
}
goto out;
}
page = vm_normal_page(mpw->vma, addr, pte);
if (!page)
goto out;
lock_page(page);
if (!page->mapping) {
unlock_page(page);
goto retry;
}
munlock_vma_page(page);
unlock_page(page);
out:
return 0;
}
/*
* Save pmd for pte handler for waiting on migration entries
*/
static int __munlock_pmd_handler(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
struct munlock_page_walk *mpw = walk->private;
mpw->pmd = pmd;
return 0;
}
/*
* munlock a range of pages in the vma using standard page table walk.
*
* vma->vm_mm->mmap_sem must be held for write.
*/
static void __munlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
struct munlock_page_walk mpw = {
.vma = vma,
};
struct mm_walk munlock_page_walk = {
.pmd_entry = __munlock_pmd_handler,
.pte_entry = __munlock_pte_handler,
.private = &mpw,
.mm = mm,
};
VM_BUG_ON(start & ~PAGE_MASK || end & ~PAGE_MASK);
VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem));
VM_BUG_ON(start < vma->vm_start);
VM_BUG_ON(end > vma->vm_end);
lru_add_drain_all(); /* push cached pages to LRU */
walk_page_range
|