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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Secure pages management: Migration of pages between normal and secure
* memory of KVM guests.
*
* Copyright 2018 Bharata B Rao, IBM Corp. <bharata@linux.ibm.com>
*/
/*
* A pseries guest can be run as secure guest on Ultravisor-enabled
* POWER platforms. On such platforms, this driver will be used to manage
* the movement of guest pages between the normal memory managed by
* hypervisor (HV) and secure memory managed by Ultravisor (UV).
*
* The page-in or page-out requests from UV will come to HV as hcalls and
* HV will call back into UV via ultracalls to satisfy these page requests.
*
* Private ZONE_DEVICE memory equal to the amount of secure memory
* available in the platform for running secure guests is hotplugged.
* Whenever a page belonging to the guest becomes secure, a page from this
* private device memory is used to represent and track that secure page
* on the HV side. Some pages (like virtio buffers, VPA pages etc) are
* shared between UV and HV. However such pages aren't represented by
* device private memory and mappings to shared memory exist in both
* UV and HV page tables.
*/
/*
* Notes on locking
*
* kvm->arch.uvmem_lock is a per-guest lock that prevents concurrent
* page-in and page-out requests for the same GPA. Concurrent accesses
* can either come via UV (guest vCPUs requesting for same page)
* or when HV and guest simultaneously access the same page.
* This mutex serializes the migration of page from HV(normal) to
* UV(secure) and vice versa. So the serialization points are around
* migrate_vma routines and page-in/out routines.
*
* Per-guest mutex comes with a cost though. Mainly it serializes the
* fault path as page-out can occur when HV faults on accessing secure
* guest pages. Currently UV issues page-in requests for all the guest
* PFNs one at a time during early boot (UV_ESM uvcall), so this is
* not a cause for concern. Also currently the number of page-outs caused
* by HV touching secure pages is very very low. If an when UV supports
* overcommitting, then we might see concurrent guest driven page-outs.
*
* Locking order
*
* 1. kvm->srcu - Protects KVM memslots
* 2. kvm->mm->mmap_sem - find_vma, migrate_vma_pages and helpers, ksm_madvise
* 3. kvm->arch.uvmem_lock - protects read/writes to uvmem slots thus acting
* as sync-points for page-in/out
*/
/*
* Notes on page size
*
* Currently UV uses 2MB mappings internally, but will issue H_SVM_PAGE_IN
* and H_SVM_PAGE_OUT hcalls in PAGE_SIZE(64K) granularity. HV tracks
* secure GPAs at 64K page size and maintains one device PFN for each
* 64K secure GPA. UV_PAGE_IN and UV_PAGE_OUT calls by HV are also issued
* for 64K page at a time.
*
* HV faulting on secure pages: When HV touches any secure page, it
* faults and issues a UV_PAGE_OUT request with 64K page size. Currently
* UV splits and remaps the 2MB page if necessary and copies out the
* required 64K page contents.
*
* Shared pages: Whenever guest shares a secure page, UV will split and
* remap the 2MB page if required and issue H_SVM_PAGE_IN with 64K page size.
*
* HV invalidating a page: When a regular page belonging to secure
* guest gets unmapped, HV informs UV with UV_PAGE_INVAL of 64K
* page size. Using 64K page size is correct here because any non-secure
* page will essentially be of 64K page size. Splitting by UV during sharing
* and page-out ensures this.
*
* Page fault handling: When HV handles page fault of a page belonging
* to secure guest, it sends that to UV with a 64K UV_PAGE_IN request.
* Using 64K size is correct here too as UV would have split the 2MB page
* into 64k mappings and would have done page-outs earlier.
*
* In summary, the current secure pages handling code in HV assumes
* 64K page size and in fact fails any page-in/page-out requests of
* non-64K size upfront. If and when UV starts supporting multiple
* page-sizes, we need to break this assumption.
*/
#include <linux/pagemap.h>
#include <linux/migrate.h>
#include <linux/kvm_host.h>
#include <linux/ksm.h>
#include <asm/ultravisor.h>
#include <asm/mman.h>
#include <asm/kvm_ppc.h>
static struct dev_pagemap kvmppc_uvmem_pgmap;
static unsigned long *kvmppc_uvmem_bitmap;
static DEFINE_SPINLOCK(kvmppc_uvmem_bitmap_lock);
#define KVMPPC_UVMEM_PFN (1UL << 63)
struct kvmppc_uvmem_slot {
struct list_head list;
unsigned long nr_pfns;
unsigned long base_pfn;
unsigned long *pfns;
};
struct kvmppc_uvmem_page_pvt {
struct kvm *kvm;
unsigned long gpa;
bool skip_page_out;
};
int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot)
{
struct kvmppc_uvmem_slot *p;
p = kzalloc(sizeof(*p), GFP_KERNEL);
if (!p)
return -ENOMEM;
p->pfns = vzalloc(array_size(slot->npages, sizeof(*p->pfns)));
if (!p->pfns) {
kfree(p);
return -ENOMEM;
}
p->nr_pfns = slot->npages;
p->base_pfn = slot->base_gfn;
mutex_lock(&kvm->arch.uvmem_lock);
list_add(&p->list, &kvm->arch.uvmem_pfns);
mutex_unlock(&kvm->arch.uvmem_lock);
return 0;
}
/*
* All device PFNs are already released by the time we come here.
*/
void kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot)
{
struct kvmppc_uvmem_slot *p, *next;
mutex_lock(&kvm->arch.uvmem_lock);
list_for_each_entry_safe(p, next, &kvm->arch.uvmem_pfns, list) {
if (p->base_pfn == slot->base_gfn) {
vfree(p->pfns);
list_del(&p->list);
kfree(p);
break;
}
}
mutex_unlock(&kvm->arch.uvmem_lock);
}
static void kvmppc_uvmem_pfn_insert(unsigned long gfn, unsigned long uvmem_pfn,
struct kvm *kvm)
{
struct kvmppc_uvmem_slot *p;
list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) {
if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
unsigned long index = gfn - p->base_pfn;
p->pfns[index] = uvmem_pfn | KVMPPC_UVMEM_PFN;
return;
}
}
}
static void kvmppc_uvmem_pfn_remove(unsigned long gfn, struct kvm *kvm)
{
struct kvmppc_uvmem_slot *p;
list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) {
if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
p->pfns[gfn - p->base_pfn] = 0;
return;
}
}
}
static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
unsigned long *uvmem_pfn)
{
struct kvmppc_uvmem_slot *p;
list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) {
if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
unsigned long index = gfn - p->base_pfn;
if (p->pfns[index] & KVMPPC_UVMEM_PFN) {
if (uvmem_pfn)
*uvmem_pfn = p->pfns[index] &
~KVMPPC_UVMEM_PFN;
return true;
} else
return false;
}
}
return false;
}
unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int ret = H_SUCCESS;
int srcu_idx;
if (!kvmppc_uvmem_bitmap)
return H_UNSUPPORTED;
/* Only radix guests can be secure guests */
if (!kvm_is_radix(kvm))
return H_UNSUPPORTED;
srcu_idx = srcu_read_lock(&kvm->srcu);
slots = kvm_memslots(kvm);
kvm_for_each_memslot(memslot, slots) {
if (
|