forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
hmm.c
1471 lines (1265 loc) · 39.2 KB
/
hmm.c
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
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* Copyright 2013 Red Hat Inc.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* Authors: Jérôme Glisse <[email protected]>
*/
/*
* Refer to include/linux/hmm.h for information about heterogeneous memory
* management or HMM for short.
*/
#include <linux/mm.h>
#include <linux/hmm.h>
#include <linux/init.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/mmzone.h>
#include <linux/pagemap.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>
#include <linux/memremap.h>
#include <linux/jump_label.h>
#include <linux/mmu_notifier.h>
#include <linux/memory_hotplug.h>
#define PA_SECTION_SIZE (1UL << PA_SECTION_SHIFT)
#if IS_ENABLED(CONFIG_HMM_MIRROR)
static const struct mmu_notifier_ops hmm_mmu_notifier_ops;
/*
* struct hmm - HMM per mm struct
*
* @mm: mm struct this HMM struct is bound to
* @lock: lock protecting ranges list
* @ranges: list of range being snapshotted
* @mirrors: list of mirrors for this mm
* @mmu_notifier: mmu notifier to track updates to CPU page table
* @mirrors_sem: read/write semaphore protecting the mirrors list
*/
struct hmm {
struct mm_struct *mm;
spinlock_t lock;
struct list_head ranges;
struct list_head mirrors;
struct mmu_notifier mmu_notifier;
struct rw_semaphore mirrors_sem;
};
/*
* hmm_register - register HMM against an mm (HMM internal)
*
* @mm: mm struct to attach to
*
* This is not intended to be used directly by device drivers. It allocates an
* HMM struct if mm does not have one, and initializes it.
*/
static struct hmm *hmm_register(struct mm_struct *mm)
{
struct hmm *hmm = READ_ONCE(mm->hmm);
bool cleanup = false;
/*
* The hmm struct can only be freed once the mm_struct goes away,
* hence we should always have pre-allocated an new hmm struct
* above.
*/
if (hmm)
return hmm;
hmm = kmalloc(sizeof(*hmm), GFP_KERNEL);
if (!hmm)
return NULL;
INIT_LIST_HEAD(&hmm->mirrors);
init_rwsem(&hmm->mirrors_sem);
hmm->mmu_notifier.ops = NULL;
INIT_LIST_HEAD(&hmm->ranges);
spin_lock_init(&hmm->lock);
hmm->mm = mm;
spin_lock(&mm->page_table_lock);
if (!mm->hmm)
mm->hmm = hmm;
else
cleanup = true;
spin_unlock(&mm->page_table_lock);
if (cleanup)
goto error;
/*
* We should only get here if hold the mmap_sem in write mode ie on
* registration of first mirror through hmm_mirror_register()
*/
hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops;
if (__mmu_notifier_register(&hmm->mmu_notifier, mm))
goto error_mm;
return mm->hmm;
error_mm:
spin_lock(&mm->page_table_lock);
if (mm->hmm == hmm)
mm->hmm = NULL;
spin_unlock(&mm->page_table_lock);
error:
kfree(hmm);
return NULL;
}
void hmm_mm_destroy(struct mm_struct *mm)
{
kfree(mm->hmm);
}
static int hmm_invalidate_range(struct hmm *hmm, bool device,
const struct hmm_update *update)
{
struct hmm_mirror *mirror;
struct hmm_range *range;
spin_lock(&hmm->lock);
list_for_each_entry(range, &hmm->ranges, list) {
unsigned long addr, idx, npages;
if (update->end < range->start || update->start >= range->end)
continue;
range->valid = false;
addr = max(update->start, range->start);
idx = (addr - range->start) >> PAGE_SHIFT;
npages = (min(range->end, update->end) - addr) >> PAGE_SHIFT;
memset(&range->pfns[idx], 0, sizeof(*range->pfns) * npages);
}
spin_unlock(&hmm->lock);
if (!device)
return 0;
down_read(&hmm->mirrors_sem);
list_for_each_entry(mirror, &hmm->mirrors, list) {
int ret;
ret = mirror->ops->sync_cpu_device_pagetables(mirror, update);
if (!update->blockable && ret == -EAGAIN) {
up_read(&hmm->mirrors_sem);
return -EAGAIN;
}
}
up_read(&hmm->mirrors_sem);
return 0;
}
static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
{
struct hmm_mirror *mirror;
struct hmm *hmm = mm->hmm;
down_write(&hmm->mirrors_sem);
mirror = list_first_entry_or_null(&hmm->mirrors, struct hmm_mirror,
list);
while (mirror) {
list_del_init(&mirror->list);
if (mirror->ops->release) {
/*
* Drop mirrors_sem so callback can wait on any pending
* work that might itself trigger mmu_notifier callback
* and thus would deadlock with us.
*/
up_write(&hmm->mirrors_sem);
mirror->ops->release(mirror);
down_write(&hmm->mirrors_sem);
}
mirror = list_first_entry_or_null(&hmm->mirrors,
struct hmm_mirror, list);
}
up_write(&hmm->mirrors_sem);
}
static int hmm_invalidate_range_start(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long start,
unsigned long end,
bool blockable)
{
struct hmm_update update;
struct hmm *hmm = mm->hmm;
VM_BUG_ON(!hmm);
update.start = start;
update.end = end;
update.event = HMM_UPDATE_INVALIDATE;
update.blockable = blockable;
return hmm_invalidate_range(hmm, true, &update);
}
static void hmm_invalidate_range_end(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
struct hmm_update update;
struct hmm *hmm = mm->hmm;
VM_BUG_ON(!hmm);
update.start = start;
update.end = end;
update.event = HMM_UPDATE_INVALIDATE;
update.blockable = true;
hmm_invalidate_range(hmm, false, &update);
}
static const struct mmu_notifier_ops hmm_mmu_notifier_ops = {
.release = hmm_release,
.invalidate_range_start = hmm_invalidate_range_start,
.invalidate_range_end = hmm_invalidate_range_end,
};
/*
* hmm_mirror_register() - register a mirror against an mm
*
* @mirror: new mirror struct to register
* @mm: mm to register against
*
* To start mirroring a process address space, the device driver must register
* an HMM mirror struct.
*
* THE mm->mmap_sem MUST BE HELD IN WRITE MODE !
*/
int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm)
{
/* Sanity check */
if (!mm || !mirror || !mirror->ops)
return -EINVAL;
again:
mirror->hmm = hmm_register(mm);
if (!mirror->hmm)
return -ENOMEM;
down_write(&mirror->hmm->mirrors_sem);
if (mirror->hmm->mm == NULL) {
/*
* A racing hmm_mirror_unregister() is about to destroy the hmm
* struct. Try again to allocate a new one.
*/
up_write(&mirror->hmm->mirrors_sem);
mirror->hmm = NULL;
goto again;
} else {
list_add(&mirror->list, &mirror->hmm->mirrors);
up_write(&mirror->hmm->mirrors_sem);
}
return 0;
}
EXPORT_SYMBOL(hmm_mirror_register);
/*
* hmm_mirror_unregister() - unregister a mirror
*
* @mirror: new mirror struct to register
*
* Stop mirroring a process address space, and cleanup.
*/
void hmm_mirror_unregister(struct hmm_mirror *mirror)
{
bool should_unregister = false;
struct mm_struct *mm;
struct hmm *hmm;
if (mirror->hmm == NULL)
return;
hmm = mirror->hmm;
down_write(&hmm->mirrors_sem);
list_del_init(&mirror->list);
should_unregister = list_empty(&hmm->mirrors);
mirror->hmm = NULL;
mm = hmm->mm;
hmm->mm = NULL;
up_write(&hmm->mirrors_sem);
if (!should_unregister || mm == NULL)
return;
mmu_notifier_unregister_no_release(&hmm->mmu_notifier, mm);
spin_lock(&mm->page_table_lock);
if (mm->hmm == hmm)
mm->hmm = NULL;
spin_unlock(&mm->page_table_lock);
kfree(hmm);
}
EXPORT_SYMBOL(hmm_mirror_unregister);
struct hmm_vma_walk {
struct hmm_range *range;
unsigned long last;
bool fault;
bool block;
};
static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr,
bool write_fault, uint64_t *pfn)
{
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_REMOTE;
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
struct vm_area_struct *vma = walk->vma;
vm_fault_t ret;
flags |= hmm_vma_walk->block ? 0 : FAULT_FLAG_ALLOW_RETRY;
flags |= write_fault ? FAULT_FLAG_WRITE : 0;
ret = handle_mm_fault(vma, addr, flags);
if (ret & VM_FAULT_RETRY)
return -EBUSY;
if (ret & VM_FAULT_ERROR) {
*pfn = range->values[HMM_PFN_ERROR];
return -EFAULT;
}
return -EAGAIN;
}
static int hmm_pfns_bad(unsigned long addr,
unsigned long end,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
uint64_t *pfns = range->pfns;
unsigned long i;
i = (addr - range->start) >> PAGE_SHIFT;
for (; addr < end; addr += PAGE_SIZE, i++)
pfns[i] = range->values[HMM_PFN_ERROR];
return 0;
}
/*
* hmm_vma_walk_hole() - handle a range lacking valid pmd or pte(s)
* @start: range virtual start address (inclusive)
* @end: range virtual end address (exclusive)
* @fault: should we fault or not ?
* @write_fault: write fault ?
* @walk: mm_walk structure
* Returns: 0 on success, -EAGAIN after page fault, or page fault error
*
* This function will be called whenever pmd_none() or pte_none() returns true,
* or whenever there is no page directory covering the virtual address range.
*/
static int hmm_vma_walk_hole_(unsigned long addr, unsigned long end,
bool fault, bool write_fault,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
uint64_t *pfns = range->pfns;
unsigned long i;
hmm_vma_walk->last = addr;
i = (addr - range->start) >> PAGE_SHIFT;
for (; addr < end; addr += PAGE_SIZE, i++) {
pfns[i] = range->values[HMM_PFN_NONE];
if (fault || write_fault) {
int ret;
ret = hmm_vma_do_fault(walk, addr, write_fault,
&pfns[i]);
if (ret != -EAGAIN)
return ret;
}
}
return (fault || write_fault) ? -EAGAIN : 0;
}
static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
uint64_t pfns, uint64_t cpu_flags,
bool *fault, bool *write_fault)
{
struct hmm_range *range = hmm_vma_walk->range;
*fault = *write_fault = false;
if (!hmm_vma_walk->fault)
return;
/* We aren't ask to do anything ... */
if (!(pfns & range->flags[HMM_PFN_VALID]))
return;
/* If this is device memory than only fault if explicitly requested */
if ((cpu_flags & range->flags[HMM_PFN_DEVICE_PRIVATE])) {
/* Do we fault on device memory ? */
if (pfns & range->flags[HMM_PFN_DEVICE_PRIVATE]) {
*write_fault = pfns & range->flags[HMM_PFN_WRITE];
*fault = true;
}
return;
}
/* If CPU page table is not valid then we need to fault */
*fault = !(cpu_flags & range->flags[HMM_PFN_VALID]);
/* Need to write fault ? */
if ((pfns & range->flags[HMM_PFN_WRITE]) &&
!(cpu_flags & range->flags[HMM_PFN_WRITE])) {
*write_fault = true;
*fault = true;
}
}
static void hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
const uint64_t *pfns, unsigned long npages,
uint64_t cpu_flags, bool *fault,
bool *write_fault)
{
unsigned long i;
if (!hmm_vma_walk->fault) {
*fault = *write_fault = false;
return;
}
for (i = 0; i < npages; ++i) {
hmm_pte_need_fault(hmm_vma_walk, pfns[i], cpu_flags,
fault, write_fault);
if ((*fault) || (*write_fault))
return;
}
}
static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
bool fault, write_fault;
unsigned long i, npages;
uint64_t *pfns;
i = (addr - range->start) >> PAGE_SHIFT;
npages = (end - addr) >> PAGE_SHIFT;
pfns = &range->pfns[i];
hmm_range_need_fault(hmm_vma_walk, pfns, npages,
0, &fault, &write_fault);
return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
}
static inline uint64_t pmd_to_hmm_pfn_flags(struct hmm_range *range, pmd_t pmd)
{
if (pmd_protnone(pmd))
return 0;
return pmd_write(pmd) ? range->flags[HMM_PFN_VALID] |
range->flags[HMM_PFN_WRITE] :
range->flags[HMM_PFN_VALID];
}
static int hmm_vma_handle_pmd(struct mm_walk *walk,
unsigned long addr,
unsigned long end,
uint64_t *pfns,
pmd_t pmd)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
unsigned long pfn, npages, i;
bool fault, write_fault;
uint64_t cpu_flags;
npages = (end - addr) >> PAGE_SHIFT;
cpu_flags = pmd_to_hmm_pfn_flags(range, pmd);
hmm_range_need_fault(hmm_vma_walk, pfns, npages, cpu_flags,
&fault, &write_fault);
if (pmd_protnone(pmd) || fault || write_fault)
return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
pfn = pmd_pfn(pmd) + pte_index(addr);
for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
pfns[i] = hmm_pfn_from_pfn(range, pfn) | cpu_flags;
hmm_vma_walk->last = end;
return 0;
}
static inline uint64_t pte_to_hmm_pfn_flags(struct hmm_range *range, pte_t pte)
{
if (pte_none(pte) || !pte_present(pte))
return 0;
return pte_write(pte) ? range->flags[HMM_PFN_VALID] |
range->flags[HMM_PFN_WRITE] :
range->flags[HMM_PFN_VALID];
}
static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
unsigned long end, pmd_t *pmdp, pte_t *ptep,
uint64_t *pfn)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
struct vm_area_struct *vma = walk->vma;
bool fault, write_fault;
uint64_t cpu_flags;
pte_t pte = *ptep;
uint64_t orig_pfn = *pfn;
*pfn = range->values[HMM_PFN_NONE];
cpu_flags = pte_to_hmm_pfn_flags(range, pte);
hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
&fault, &write_fault);
if (pte_none(pte)) {
if (fault || write_fault)
goto fault;
return 0;
}
if (!pte_present(pte)) {
swp_entry_t entry = pte_to_swp_entry(pte);
if (!non_swap_entry(entry)) {
if (fault || write_fault)
goto fault;
return 0;
}
/*
* This is a special swap entry, ignore migration, use
* device and report anything else as error.
*/
if (is_device_private_entry(entry)) {
cpu_flags = range->flags[HMM_PFN_VALID] |
range->flags[HMM_PFN_DEVICE_PRIVATE];
cpu_flags |= is_write_device_private_entry(entry) ?
range->flags[HMM_PFN_WRITE] : 0;
hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
&fault, &write_fault);
if (fault || write_fault)
goto fault;
*pfn = hmm_pfn_from_pfn(range, swp_offset(entry));
*pfn |= cpu_flags;
return 0;
}
if (is_migration_entry(entry)) {
if (fault || write_fault) {
pte_unmap(ptep);
hmm_vma_walk->last = addr;
migration_entry_wait(vma->vm_mm,
pmdp, addr);
return -EAGAIN;
}
return 0;
}
/* Report error for everything else */
*pfn = range->values[HMM_PFN_ERROR];
return -EFAULT;
}
if (fault || write_fault)
goto fault;
*pfn = hmm_pfn_from_pfn(range, pte_pfn(pte)) | cpu_flags;
return 0;
fault:
pte_unmap(ptep);
/* Fault any virtual address we were asked to fault */
return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
}
static int hmm_vma_walk_pmd(pmd_t *pmdp,
unsigned long start,
unsigned long end,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
struct vm_area_struct *vma = walk->vma;
uint64_t *pfns = range->pfns;
unsigned long addr = start, i;
pte_t *ptep;
pmd_t pmd;
again:
pmd = READ_ONCE(*pmdp);
if (pmd_none(pmd))
return hmm_vma_walk_hole(start, end, walk);
if (pmd_huge(pmd) && (range->vma->vm_flags & VM_HUGETLB))
return hmm_pfns_bad(start, end, walk);
if (thp_migration_supported() && is_pmd_migration_entry(pmd)) {
bool fault, write_fault;
unsigned long npages;
uint64_t *pfns;
i = (addr - range->start) >> PAGE_SHIFT;
npages = (end - addr) >> PAGE_SHIFT;
pfns = &range->pfns[i];
hmm_range_need_fault(hmm_vma_walk, pfns, npages,
0, &fault, &write_fault);
if (fault || write_fault) {
hmm_vma_walk->last = addr;
pmd_migration_entry_wait(vma->vm_mm, pmdp);
return -EAGAIN;
}
return 0;
} else if (!pmd_present(pmd))
return hmm_pfns_bad(start, end, walk);
if (pmd_devmap(pmd) || pmd_trans_huge(pmd)) {
/*
* No need to take pmd_lock here, even if some other threads
* is splitting the huge pmd we will get that event through
* mmu_notifier callback.
*
* So just read pmd value and check again its a transparent
* huge or device mapping one and compute corresponding pfn
* values.
*/
pmd = pmd_read_atomic(pmdp);
barrier();
if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd))
goto again;
i = (addr - range->start) >> PAGE_SHIFT;
return hmm_vma_handle_pmd(walk, addr, end, &pfns[i], pmd);
}
/*
* We have handled all the valid case above ie either none, migration,
* huge or transparent huge. At this point either it is a valid pmd
* entry pointing to pte directory or it is a bad pmd that will not
* recover.
*/
if (pmd_bad(pmd))
return hmm_pfns_bad(start, end, walk);
ptep = pte_offset_map(pmdp, addr);
i = (addr - range->start) >> PAGE_SHIFT;
for (; addr < end; addr += PAGE_SIZE, ptep++, i++) {
int r;
r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, &pfns[i]);
if (r) {
/* hmm_vma_handle_pte() did unmap pte directory */
hmm_vma_walk->last = addr;
return r;
}
}
pte_unmap(ptep - 1);
hmm_vma_walk->last = addr;
return 0;
}
static void hmm_pfns_clear(struct hmm_range *range,
uint64_t *pfns,
unsigned long addr,
unsigned long end)
{
for (; addr < end; addr += PAGE_SIZE, pfns++)
*pfns = range->values[HMM_PFN_NONE];
}
static void hmm_pfns_special(struct hmm_range *range)
{
unsigned long addr = range->start, i = 0;
for (; addr < range->end; addr += PAGE_SIZE, i++)
range->pfns[i] = range->values[HMM_PFN_SPECIAL];
}
/*
* hmm_vma_get_pfns() - snapshot CPU page table for a range of virtual addresses
* @range: range being snapshotted
* Returns: -EINVAL if invalid argument, -ENOMEM out of memory, -EPERM invalid
* vma permission, 0 success
*
* This snapshots the CPU page table for a range of virtual addresses. Snapshot
* validity is tracked by range struct. See hmm_vma_range_done() for further
* information.
*
* The range struct is initialized here. It tracks the CPU page table, but only
* if the function returns success (0), in which case the caller must then call
* hmm_vma_range_done() to stop CPU page table update tracking on this range.
*
* NOT CALLING hmm_vma_range_done() IF FUNCTION RETURNS 0 WILL LEAD TO SERIOUS
* MEMORY CORRUPTION ! YOU HAVE BEEN WARNED !
*/
int hmm_vma_get_pfns(struct hmm_range *range)
{
struct vm_area_struct *vma = range->vma;
struct hmm_vma_walk hmm_vma_walk;
struct mm_walk mm_walk;
struct hmm *hmm;
/* Sanity check, this really should not happen ! */
if (range->start < vma->vm_start || range->start >= vma->vm_end)
return -EINVAL;
if (range->end < vma->vm_start || range->end > vma->vm_end)
return -EINVAL;
hmm = hmm_register(vma->vm_mm);
if (!hmm)
return -ENOMEM;
/* Caller must have registered a mirror, via hmm_mirror_register() ! */
if (!hmm->mmu_notifier.ops)
return -EINVAL;
/* FIXME support hugetlb fs */
if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL) ||
vma_is_dax(vma)) {
hmm_pfns_special(range);
return -EINVAL;
}
if (!(vma->vm_flags & VM_READ)) {
/*
* If vma do not allow read access, then assume that it does
* not allow write access, either. Architecture that allow
* write without read access are not supported by HMM, because
* operations such has atomic access would not work.
*/
hmm_pfns_clear(range, range->pfns, range->start, range->end);
return -EPERM;
}
/* Initialize range to track CPU page table update */
spin_lock(&hmm->lock);
range->valid = true;
list_add_rcu(&range->list, &hmm->ranges);
spin_unlock(&hmm->lock);
hmm_vma_walk.fault = false;
hmm_vma_walk.range = range;
mm_walk.private = &hmm_vma_walk;
mm_walk.vma = vma;
mm_walk.mm = vma->vm_mm;
mm_walk.pte_entry = NULL;
mm_walk.test_walk = NULL;
mm_walk.hugetlb_entry = NULL;
mm_walk.pmd_entry = hmm_vma_walk_pmd;
mm_walk.pte_hole = hmm_vma_walk_hole;
walk_page_range(range->start, range->end, &mm_walk);
return 0;
}
EXPORT_SYMBOL(hmm_vma_get_pfns);
/*
* hmm_vma_range_done() - stop tracking change to CPU page table over a range
* @range: range being tracked
* Returns: false if range data has been invalidated, true otherwise
*
* Range struct is used to track updates to the CPU page table after a call to
* either hmm_vma_get_pfns() or hmm_vma_fault(). Once the device driver is done
* using the data, or wants to lock updates to the data it got from those
* functions, it must call the hmm_vma_range_done() function, which will then
* stop tracking CPU page table updates.
*
* Note that device driver must still implement general CPU page table update
* tracking either by using hmm_mirror (see hmm_mirror_register()) or by using
* the mmu_notifier API directly.
*
* CPU page table update tracking done through hmm_range is only temporary and
* to be used while trying to duplicate CPU page table contents for a range of
* virtual addresses.
*
* There are two ways to use this :
* again:
* hmm_vma_get_pfns(range); or hmm_vma_fault(...);
* trans = device_build_page_table_update_transaction(pfns);
* device_page_table_lock();
* if (!hmm_vma_range_done(range)) {
* device_page_table_unlock();
* goto again;
* }
* device_commit_transaction(trans);
* device_page_table_unlock();
*
* Or:
* hmm_vma_get_pfns(range); or hmm_vma_fault(...);
* device_page_table_lock();
* hmm_vma_range_done(range);
* device_update_page_table(range->pfns);
* device_page_table_unlock();
*/
bool hmm_vma_range_done(struct hmm_range *range)
{
unsigned long npages = (range->end - range->start) >> PAGE_SHIFT;
struct hmm *hmm;
if (range->end <= range->start) {
BUG();
return false;
}
hmm = hmm_register(range->vma->vm_mm);
if (!hmm) {
memset(range->pfns, 0, sizeof(*range->pfns) * npages);
return false;
}
spin_lock(&hmm->lock);
list_del_rcu(&range->list);
spin_unlock(&hmm->lock);
return range->valid;
}
EXPORT_SYMBOL(hmm_vma_range_done);
/*
* hmm_vma_fault() - try to fault some address in a virtual address range
* @range: range being faulted
* @block: allow blocking on fault (if true it sleeps and do not drop mmap_sem)
* Returns: 0 success, error otherwise (-EAGAIN means mmap_sem have been drop)
*
* This is similar to a regular CPU page fault except that it will not trigger
* any memory migration if the memory being faulted is not accessible by CPUs.
*
* On error, for one virtual address in the range, the function will mark the
* corresponding HMM pfn entry with an error flag.
*
* Expected use pattern:
* retry:
* down_read(&mm->mmap_sem);
* // Find vma and address device wants to fault, initialize hmm_pfn_t
* // array accordingly
* ret = hmm_vma_fault(range, write, block);
* switch (ret) {
* case -EAGAIN:
* hmm_vma_range_done(range);
* // You might want to rate limit or yield to play nicely, you may
* // also commit any valid pfn in the array assuming that you are
* // getting true from hmm_vma_range_monitor_end()
* goto retry;
* case 0:
* break;
* case -ENOMEM:
* case -EINVAL:
* case -EPERM:
* default:
* // Handle error !
* up_read(&mm->mmap_sem)
* return;
* }
* // Take device driver lock that serialize device page table update
* driver_lock_device_page_table_update();
* hmm_vma_range_done(range);
* // Commit pfns we got from hmm_vma_fault()
* driver_unlock_device_page_table_update();
* up_read(&mm->mmap_sem)
*
* YOU MUST CALL hmm_vma_range_done() AFTER THIS FUNCTION RETURN SUCCESS (0)
* BEFORE FREEING THE range struct OR YOU WILL HAVE SERIOUS MEMORY CORRUPTION !
*
* YOU HAVE BEEN WARNED !
*/
int hmm_vma_fault(struct hmm_range *range, bool block)
{
struct vm_area_struct *vma = range->vma;
unsigned long start = range->start;
struct hmm_vma_walk hmm_vma_walk;
struct mm_walk mm_walk;
struct hmm *hmm;
int ret;
/* Sanity check, this really should not happen ! */
if (range->start < vma->vm_start || range->start >= vma->vm_end)
return -EINVAL;
if (range->end < vma->vm_start || range->end > vma->vm_end)
return -EINVAL;
hmm = hmm_register(vma->vm_mm);
if (!hmm) {
hmm_pfns_clear(range, range->pfns, range->start, range->end);
return -ENOMEM;
}
/* Caller must have registered a mirror using hmm_mirror_register() */
if (!hmm->mmu_notifier.ops)
return -EINVAL;
/* FIXME support hugetlb fs */
if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL) ||
vma_is_dax(vma)) {
hmm_pfns_special(range);
return -EINVAL;
}
if (!(vma->vm_flags & VM_READ)) {
/*
* If vma do not allow read access, then assume that it does
* not allow write access, either. Architecture that allow
* write without read access are not supported by HMM, because
* operations such has atomic access would not work.
*/
hmm_pfns_clear(range, range->pfns, range->start, range->end);
return -EPERM;
}
/* Initialize range to track CPU page table update */
spin_lock(&hmm->lock);
range->valid = true;
list_add_rcu(&range->list, &hmm->ranges);
spin_unlock(&hmm->lock);
hmm_vma_walk.fault = true;
hmm_vma_walk.block = block;
hmm_vma_walk.range = range;
mm_walk.private = &hmm_vma_walk;
hmm_vma_walk.last = range->start;
mm_walk.vma = vma;
mm_walk.mm = vma->vm_mm;
mm_walk.pte_entry = NULL;
mm_walk.test_walk = NULL;
mm_walk.hugetlb_entry = NULL;
mm_walk.pmd_entry = hmm_vma_walk_pmd;
mm_walk.pte_hole = hmm_vma_walk_hole;
do {
ret = walk_page_range(start, range->end, &mm_walk);
start = hmm_vma_walk.last;
} while (ret == -EAGAIN);
if (ret) {
unsigned long i;
i = (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
hmm_pfns_clear(range, &range->pfns[i], hmm_vma_walk.last,
range->end);
hmm_vma_range_done(range);
}
return ret;
}
EXPORT_SYMBOL(hmm_vma_fault);
#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC)
struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma,
unsigned long addr)
{
struct page *page;
page = alloc_page_vma(GFP_HIGHUSER, vma, addr);
if (!page)
return NULL;
lock_page(page);
return page;
}
EXPORT_SYMBOL(hmm_vma_alloc_locked_page);
static void hmm_devmem_ref_release(struct percpu_ref *ref)
{
struct hmm_devmem *devmem;
devmem = container_of(ref, struct hmm_devmem, ref);
complete(&devmem->completion);
}
static void hmm_devmem_ref_exit(void *data)
{
struct percpu_ref *ref = data;
struct hmm_devmem *devmem;
devmem = container_of(ref, struct hmm_devmem, ref);
percpu_ref_exit(ref);
devm_remove_action(devmem->device, &hmm_devmem_ref_exit, data);
}
static void hmm_devmem_ref_kill(void *data)
{
struct percpu_ref *ref = data;
struct hmm_devmem *devmem;
devmem = container_of(ref, struct hmm_devmem, ref);
percpu_ref_kill(ref);
wait_for_completion(&devmem->completion);