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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Hosting Protected Virtual Machines
*
* Copyright IBM Corp. 2019, 2020
* Author(s): Janosch Frank <frankja@linux.ibm.com>
*/
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/minmax.h>
#include <linux/pagemap.h>
#include <linux/sched/signal.h>
#include <asm/gmap.h>
#include <asm/uv.h>
#include <asm/mman.h>
#include <linux/pagewalk.h>
#include <linux/sched/mm.h>
#include <linux/mmu_notifier.h>
#include "kvm-s390.h"
bool kvm_s390_pv_is_protected(struct kvm *kvm)
{
lockdep_assert_held(&kvm->lock);
return !!kvm_s390_pv_get_handle(kvm);
}
EXPORT_SYMBOL_GPL(kvm_s390_pv_is_protected);
bool kvm_s390_pv_cpu_is_protected(struct kvm_vcpu *vcpu)
{
lockdep_assert_held(&vcpu->mutex);
return !!kvm_s390_pv_cpu_get_handle(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_s390_pv_cpu_is_protected);
/**
* struct pv_vm_to_be_destroyed - Represents a protected VM that needs to
* be destroyed
*
* @list: list head for the list of leftover VMs
* @old_gmap_table: the gmap table of the leftover protected VM
* @handle: the handle of the leftover protected VM
* @stor_var: pointer to the variable storage of the leftover protected VM
* @stor_base: address of the base storage of the leftover protected VM
*
* Represents a protected VM that is still registered with the Ultravisor,
* but which does not correspond any longer to an active KVM VM. It should
* be destroyed at some point later, either asynchronously or when the
* process terminates.
*/
struct pv_vm_to_be_destroyed {
struct list_head list;
unsigned long old_gmap_table;
u64 handle;
void *stor_var;
unsigned long stor_base;
};
static void kvm_s390_clear_pv_state(struct kvm *kvm)
{
kvm->arch.pv.handle = 0;
kvm->arch.pv.guest_len = 0;
kvm->arch.pv.stor_base = 0;
kvm->arch.pv.stor_var = NULL;
}
int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
{
int cc;
if (!kvm_s390_pv_cpu_get_handle(vcpu))
return 0;
cc = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), UVC_CMD_DESTROY_SEC_CPU, rc, rrc);
KVM_UV_EVENT(vcpu->kvm, 3, "PROTVIRT DESTROY VCPU %d: rc %x rrc %x",
vcpu->vcpu_id, *rc, *rrc);
WARN_ONCE(cc, "protvirt destroy cpu failed rc %x rrc %x", *rc, *rrc);
/* Intended memory leak for something that should never happen. */
if (!cc)
free_pages(vcpu->arch.pv.stor_base,
get_order(uv_info.guest_cpu_stor_len));
free_page((unsigned long)sida_addr(vcpu->arch.sie_block));
vcpu->arch.sie_block->pv_handle_cpu = 0;
vcpu->arch.sie_block->pv_handle_config = 0;
memset(&vcpu->arch.pv, 0, sizeof(vcpu->arch.pv));
vcpu->arch.sie_block->sdf = 0;
/*
* The sidad field (for sdf == 2) is now the gbea field (for sdf == 0).
* Use the reset value of gbea to avoid leaking the kernel pointer of
* the just freed sida.
*/
vcpu->arch.sie_block->gbea = 1;
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
return cc ? EIO : 0;
}
int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
{
struct uv_cb_csc uvcb = {
.header.cmd = UVC_CMD_CREATE_SEC_CPU,
.header.len = sizeof(uvcb),
};
void *sida_addr;
int cc;
if (kvm_s390_pv_cpu_get_handle(vcpu))
return -EINVAL;
vcpu->arch.pv.stor_base = __get_free_pages(GFP_KERNEL_ACCOUNT,
get_order(uv_info.guest_cpu_stor_len));
if (!vcpu->arch.pv.stor_base)
return -ENOMEM;
/* Input */
uvcb.guest_handle = kvm_s390_pv_get_handle(vcpu->kvm);
uvcb.num = vcpu->arch.sie_block->icpua;
uvcb.state_origin = virt_to_phys(vcpu->arch.sie_block);
uvcb.stor_origin = virt_to_phys((void *)vcpu->arch.pv.stor_base);
/* Alloc Secure Instruction Data Area Designation */
sida_addr = (void *)__get_free_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
if (!sida_addr) {
free_pages(vcpu->arch.pv.stor_base,
get_order(uv_info.guest_cpu_stor_len));
return -ENOMEM;
}
vcpu->arch.sie_block->sidad = virt_to_phys(sida_addr);
cc = uv_call(0, (u64)&uvcb);
*rc = uvcb.header.rc;
*rrc = uvcb.header.rrc;
KVM_UV_EVENT(vcpu->kvm, 3,
"PROTVIRT CREATE VCPU: cpu %d handle %llx rc %x rrc %x",
vcpu->vcpu_id, uvcb.cpu_handle, uvcb.header.rc,
uvcb.header.rrc);
if (cc) {
u16 dummy;
kvm_s390_pv_destroy_cpu(vcpu, &dummy, &dummy);
return -EIO;
}
/* Output */
vcpu->arch.pv.handle = uvcb.cpu_handle;
vcpu->arch.sie_block->pv_handle_cpu = uvcb.cpu_handle;
vcpu->arch.sie_block->pv_handle_config = kvm_s390_pv_get_handle(vcpu->kvm);
vcpu->arch.sie_block->sdf = 2;
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
return 0;
}
/* only free resources when the destroy was successful */
static void kvm_s390_pv_dealloc_vm(struct kvm *kvm)
{
vfree(kvm->arch.pv.stor_var);
free_pages(kvm->arch.pv.stor_base,
get_order(uv_info.guest_base_stor_len));
kvm_s390_clear_pv_state(kvm);
}
static int kvm_s390_pv_alloc_vm(struct kvm *kvm)
{
unsigned long base = uv_info.guest_base_stor_len;
unsigned long virt = uv_info.guest_virt_var_stor_len;
unsigned long npages = 0, vlen = 0;
kvm->arch.pv.stor_var = NULL;
kvm->arch.pv.stor_base = __get_free_pages(GFP_KERNEL_ACCOUNT, get_order(base));
if (!kvm->arch.pv.stor_base)
return -ENOMEM;
/*
* Calculate current guest storage for allocation of the
* variable storage, which is based on the length in MB.
*
* Slots are sorted by GFN
*/
mutex_lock(&kvm->slots_lock);
npages = kvm_s390_get_gfn_end(kvm_memslots(kvm));
mutex_unlock(&kvm->slots_lock);
kvm->arch.pv.guest_len = npages * PAGE_SIZE;
/* Allocate variable storage */
vlen = ALIGN(virt * ((npages * PAGE_SIZE) / HPAGE_SIZE), PAGE_SIZE);
vlen += uv_info.guest_virt_base_stor_len;
kvm->arch.pv.stor_var = vzalloc(vlen);
if (!kvm->arch.pv.stor_var)
goto out_err;
return 0;
out_err:
kvm_s390_pv_dealloc_vm(kvm);
return -ENOMEM;
}
/**
* kvm_s390_pv_dispose_one_leftover - Clean up one leftover protected VM.
* @kvm: the KVM that was associated with this leftover protected VM
* @leftover: details about the leftover protected VM that needs a clean up
* @rc: the RC code of the Destroy Secure Configuration UVC
* @rrc: the RRC code of the Destroy Secure Configuration UVC
*
* Destroy one leftover protected VM.
* On success, kvm->mm->context.protected_count will be decremented atomically
* and all other resources used by the VM will be freed.
*
* Return: 0 in case of success, otherwise 1
*/
static int kvm_s390_pv_dispose_one_leftover(struct kvm *kvm,
struct pv_vm_to_be_destroyed *leftover,
u16 *rc, u16 *rrc)
{
int cc;
/* It used the destroy-fast UVC, nothing left to do here */
if (!leftover->handle)
goto done_fast;
cc = uv_cmd_nodata(leftover->handle, UVC_CMD_DESTROY_SEC_CONF, rc, rrc);
KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY LEFTOVER VM: rc %x rrc %x", *rc, *rrc);
WARN_ONCE(cc, "protvirt destroy leftover vm failed rc %x rrc %x", *rc, *rrc);
if (cc)
return cc;
/*
* Intentionally leak unusable memory. If the UVC fails, the memory
* used for the VM and its metadata is permanently unusable.
* This can only happen in case of a serious KVM or hardware bug; it
* is not expected to happen in normal operation.
*/
free_pages(leftover->stor_base, get_order(uv_info.guest_base_stor_len));
free_pages(leftover->old_gmap_table, CRST_ALLOC_ORDER);
vfree(leftover->stor_var);
done_fast:
atomic_dec(&kvm->mm->context.protected_count);
return 0;
}
/**
* kvm_s390_destroy_lower_2g - Destroy the first 2GB of protected guest memory.
* @kvm: the VM whose memory is to be cleared.
*
* Destroy the first 2GB of guest memory, to avoid prefix issues after reboot.
* The CPUs of the protected VM need to be destroyed beforehand.
*/
static void kvm_s390_destroy_lower_2g(struct kvm *kvm)
{
const unsigned long pages_2g = SZ_2G / PAGE_SIZE;
struct kvm_memory_slot *slot;
unsigned long len;
int srcu_idx;
srcu_idx = srcu_read_lock(&kvm->srcu);
/* Take the memslot containing guest absolute address 0 */
slot = gfn_to_memslot(kvm, 0);
/* Clear all slots or parts thereof that are below 2GB */
while (slot && slot->base_gfn < pages_2g) {
len = min_t(u64, slot->npages, pages_2g - slot->base_gfn) * PAGE_SIZE;
s390_uv_destroy_range(kvm->mm, slot->userspace_addr, slot->userspace_addr + len);
/* Take the next memslot */
slot = gfn_to_memslot(kvm, slot->base_gfn + slot->npages);
}
srcu_read_unlock(&kvm->srcu, srcu_idx);
}
static int kvm_s390_pv_deinit_vm_fast(struct kvm *kvm, u16 *rc, u16 *rrc)
{
struct uv_cb_destroy_fast uvcb = {
.header.cmd = UVC_CMD_DESTROY_SEC_CONF_FAST,
.header.len = sizeof(uvcb),
.handle = kvm_s390_pv_get_handle(kvm),
};
int cc;
cc = uv_call_sched(0, (u64)&uvcb);
if (rc)
*rc = uvcb.header.rc;
if (rrc)
*rrc = uvcb.header.rrc;
WRITE_ONCE(kvm->arch.gmap->guest_handle, 0);
KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM FAST: rc %x rrc %x",
uvcb.header.rc, uvcb.header.rrc);
WARN_ONCE(cc && uvcb.header.rc != 0x104,
"protvirt destroy vm fast failed handle %llx rc %x rrc %x",
kvm_s390_pv_get_handle(kvm), uvcb.header.rc, uvcb.header.rrc);
/* Intended memory leak on "impossible" error */
if (!cc)
kvm_s390_pv_dealloc_vm(kvm);
return cc ? -EIO : 0;
}
static inline bool is_destroy_fast_available(void)
{
return test_bit_inv(BIT_UVC_CMD_DESTROY_SEC_CONF_FAST, uv_info.inst_calls_list);
}
/**
* kvm_s390_pv_set_aside - Set aside a protected VM for later teardown.
* @kvm: the VM
* @rc: return value for the RC field of the UVCB
* @rrc: return value for the RRC field of the UVCB
*
* Set aside the protected VM for a subsequent teardown. The VM will be able
* to continue immediately as a non-secure VM, and the information needed to
* properly tear down the protected VM is set aside. If another protected VM
* was already set aside without starting its teardown, this function will
* fail.
* The CPUs of the protected VM need to be destroyed beforehand.
*
* Context: kvm->lock needs to be held
*
* Return: 0 in case of success, -EINVAL if another protected VM was already set
* aside, -ENOMEM if the system ran out of memory.
*/
int kvm_s390_pv_set_aside(struct kvm *kvm, u16 *rc, u16 *rrc)
{
struct pv_vm_to_be_destroyed *priv;
int res = 0;
lockdep_assert_held(&kvm->lock);
/*
* If another protected VM was already prepared for teardown, refuse.
* A normal deinitialization has to be performed instead.
*/
if (kvm->arch.pv.set_aside)
return -EINVAL;
/* Guest with segment type ASCE, refuse to destroy asynchronously */
if ((kvm->arch.gmap->asce & _ASCE_TYPE_MASK) == _ASCE_TYPE_SEGMENT)
return -EINVAL;
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (!priv)
return -ENOMEM;
if (is_destroy_fast_available()) {
res = kvm_s390_pv_deinit_vm_fast(kvm, rc, rrc);
} else {
priv->stor_var = kvm->arch.pv.stor_var;
priv->stor_base = kvm->arch.pv.stor_base;
priv->handle = kvm_s390_pv_get_handle(kvm);
priv->old_gmap_table = (unsigned long)kvm->arch.gmap->table;
WRITE_ONCE(kvm->arch.gmap->guest_handle, 0);
if (s390_replace_asce(kvm->arch.gmap))
res = -ENOMEM;
}
if (res) {
kfree(priv);
return res;
}
kvm_s390_destroy_lower_2g(kvm);
kvm_s390_clear_pv_state(kvm);
kvm->arch.pv.set_aside = priv;
*rc = UVC_RC_EXECUTED;
*rrc = 42;
return 0;
}
/**
* kvm_s390_pv_deinit_vm - Deinitialize the current protected VM
* @kvm: the KVM whose protected VM needs to be deinitialized
* @rc: the RC code of the UVC
* @rrc: the RRC code of the UVC
*
* Deinitialize the current protected VM. This function will destroy and
* cleanup the current protected VM, but it will not cleanup the guest
* memory. This function should only be called when the protected VM has
* just been created and therefore does not have any guest memory, or when
* the caller cleans up the guest memory separately.
*
* This function should not fail, but if it does, the donated memory must
* not be freed.
*
* Context: kvm->lock needs to be held
*
* Return: 0 in case of success, otherwise -EIO
*/
int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
{
int cc;
cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm),
UVC_CMD_DESTROY_SEC_CONF, rc, rrc);
WRITE_ONCE(kvm->arch.gmap->guest_handle, 0);
if (!cc) {
atomic_dec(&kvm->mm->context.protected_count);
kvm_s390_pv_dealloc_vm(kvm);
} else {
/* Intended memory leak on "impossible" error */
s390_replace_asce(kvm->arch.gmap);
}
KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM: rc %x rrc %x", *rc, *rrc);
WARN_ONCE(cc, "protvirt destroy vm failed rc %x rrc %x", *rc, *rrc);
return cc ? -EIO : 0;
}
/**
* kvm_s390_pv_deinit_cleanup_all - Clean up all protected VMs associated
* with a specific KVM.
* @kvm: the KVM to be cleaned up
* @rc: the RC code of the first failing UVC
* @rrc: the RRC code of the first failing UVC
*
* This function will clean up all protected VMs associated with a KVM.
* This includes the active one, the one prepared for deinitialization with
* kvm_s390_pv_set_aside, and any still pending in the need_cleanup list.
*
* Context: kvm->lock needs to be held unless being called from
* kvm_arch_destroy_vm.
*
* Return: 0 if all VMs are successfully cleaned up, otherwise -EIO
*/
int kvm_s390_pv_deinit_cleanup_all(struct kvm *kvm, u16 *rc, u16 *rrc)
{
struct pv_vm_to_be_destroyed *cur;
bool need_zap = false;
u16 _rc, _rrc;
int cc = 0;
/* Make sure the counter does not reach 0 before calling s390_uv_destroy_range */
atomic_inc(&kvm->mm->context.protected_count);
*rc = 1;
/* If the current VM is protected, destroy it */
if (kvm_s390_pv_get_handle(kvm)) {
cc = kvm_s390_pv_deinit_vm(kvm, rc, rrc);
need_zap = true;
}
/* If a previous protected VM was set aside, put it in the need_cleanup list */
if (kvm->arch.pv.set_aside) {
list_add(kvm->arch.pv.set_aside, &kvm->arch.pv.need_cleanup);
kvm->arch.pv.set_aside = NULL;
}
/* Cleanup all protected VMs in the need_cleanup list */
while (!list_empty(&kvm->arch.pv.need_cleanup)) {
cur = list_first_entry(&kvm->arch.pv.need_cleanup, typeof(*cur), list);
need_zap = true;
if (kvm_s390_pv_dispose_one_leftover(kvm, cur, &_rc, &_rrc)) {
cc = 1;
/*
* Only return the first error rc and rrc, so make
* sure it is not overwritten. All destroys will
* additionally be reported via KVM_UV_EVENT().
*/
if (*rc == UVC_RC_EXECUTED) {
*rc = _rc;
*rrc = _rrc;
}
}
list_del(&cur->list);
kfree(cur);
}
/*
* If the mm still has a mapping, try to mark all its pages as
* accessible. The counter should not reach zero before this
* cleanup has been performed.
*/
if (need_zap && mmget_not_zero(kvm->mm)) {
s390_uv_destroy_range(kvm->mm, 0, TASK_SIZE);
mmput(kvm->mm);
}
/* Now the counter can safely reach 0 */
atomic_dec(&kvm->mm->context.protected_count);
return cc ? -EIO : 0;
}
/**
* kvm_s390_pv_deinit_aside_vm - Teardown a previously set aside protected VM.
* @kvm: the VM previously associated with the protected VM
* @rc: return value for the RC field of the UVCB
* @rrc: return value for the RRC field of the UVCB
*
* Tear down the protected VM that had been previously prepared for teardown
* using kvm_s390_pv_set_aside_vm. Ideally this should be called by
* userspace asynchronously from a separate thread.
*
* Context: kvm->lock must not be held.
*
* Return: 0 in case of success, -EINVAL if no protected VM had been
* prepared for asynchronous teardowm, -EIO in case of other errors.
*/
int kvm_s390_pv_deinit_aside_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
{
struct pv_vm_to_be_destroyed *p;
int ret = 0;
lockdep_assert_not_held(&kvm->lock);
mutex_lock(&kvm->lock);
p = kvm->arch.pv.set_aside;
kvm->arch.pv.set_aside = NULL;
mutex_unlock(&kvm->lock);
if (!p)
return -EINVAL;
/* When a fatal signal is received, stop immediately */
if (s390_uv_destroy_range_interruptible(kvm->mm, 0, TASK_SIZE_MAX))
goto done;
if (kvm_s390_pv_dispose_one_leftover(kvm, p, rc, rrc))
ret = -EIO;
kfree(p);
p = NULL;
done:
/*
* p is not NULL if we aborted because of a fatal signal, in which
* case queue the leftover for later cleanup.
*/
if (p) {
mutex_lock(&kvm->lock);
list_add(&p->list, &kvm->arch.pv.need_cleanup);
mutex_unlock(&kvm->lock);
/* Did not finish, but pretend things went well */
*rc = UVC_RC_EXECUTED;
*rrc = 42;
}
return ret;
}
static void kvm_s390_pv_mmu_notifier_release(struct mmu_notifier *subscription,
struct mm_struct *mm)
{
struct kvm *kvm = container_of(subscription, struct kvm, arch.pv.mmu_notifier);
u16 dummy;
int r;
/*
* No locking is needed since this is the last thread of the last user of this
* struct mm.
* When the struct kvm gets deinitialized, this notifier is also
* unregistered. This means that if this notifier runs, then the
* struct kvm is still valid.
*/
r = kvm_s390_cpus_from_pv(kvm, &dummy, &dummy);
if (!r && is_destroy_fast_available() && kvm_s390_pv_get_handle(kvm))
kvm_s390_pv_deinit_vm_fast(kvm, &dummy, &dummy);
}
static const struct mmu_notifier_ops kvm_s390_pv_mmu_notifier_ops = {
.release = kvm_s390_pv_mmu_notifier_release,
};
int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
{
struct uv_cb_cgc uvcb = {
.header.cmd = UVC_CMD_CREATE_SEC_CONF,
.header.len = sizeof(uvcb)
};
int cc, ret;
u16 dummy;
ret = kvm_s390_pv_alloc_vm(kvm);
if (ret)
return ret;
/* Inputs */
uvcb.guest_stor_origin = 0; /* MSO is 0 for KVM */
uvcb.guest_stor_len = kvm->arch.pv.guest_len;
uvcb.guest_asce = kvm->arch.gmap->asce;
uvcb.guest_sca = virt_to_phys(kvm->arch.sca);
uvcb.conf_base_stor_origin =
virt_to_phys((void *)kvm->arch.pv.stor_base);
uvcb.conf_virt_stor_origin = (u64)kvm->arch.pv.stor_var;
cc = uv_call_sched(0, (u64)&uvcb);
*rc = uvcb.header.rc;
*rrc = uvcb.header.rrc;
KVM_UV_EVENT(kvm, 3, "PROTVIRT CREATE VM: handle %llx len %llx rc %x rrc %x",
uvcb.guest_handle, uvcb.guest_stor_len, *rc, *rrc);
/* Outputs */
kvm->arch.pv.handle = uvcb.guest_handle;
atomic_inc(&kvm->mm->context.protected_count);
if (cc) {
if (uvcb.header.rc & UVC_RC_NEED_DESTROY) {
kvm_s390_pv_deinit_vm(kvm, &dummy, &dummy);
} else {
atomic_dec(&kvm->mm->context.protected_count);
kvm_s390_pv_dealloc_vm(kvm);
}
return -EIO;
}
kvm->arch.gmap->guest_handle = uvcb.guest_handle;
/* Add the notifier only once. No races because we hold kvm->lock */
if (kvm->arch.pv.mmu_notifier.ops != &kvm_s390_pv_mmu_notifier_ops) {
kvm->arch.pv.mmu_notifier.ops = &kvm_s390_pv_mmu_notifier_ops;
mmu_notifier_register(&kvm->arch.pv.mmu_notifier, kvm->mm);
}
return 0;
}
int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc,
u16 *rrc)
{
struct uv_cb_ssc uvcb = {
.header.cmd = UVC_CMD_SET_SEC_CONF_PARAMS,
.header.len = sizeof(uvcb),
.sec_header_origin = (u64)hdr,
.sec_header_len = length,
.guest_handle = kvm_s390_pv_get_handle(kvm),
};
int cc = uv_call(0, (u64)&uvcb);
*rc = uvcb.header.rc;
*rrc = uvcb.header.rrc;
KVM_UV_EVENT(kvm, 3, "PROTVIRT VM SET PARMS: rc %x rrc %x",
*rc, *rrc);
return cc ? -EINVAL : 0;
}
static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak,
u64 offset, u16 *rc, u16 *rrc)
{
struct uv_cb_unp uvcb = {
.header.cmd = UVC_CMD_UNPACK_IMG,
.header.len = sizeof(uvcb),
.guest_handle = kvm_s390_pv_get_handle(kvm),
.gaddr = addr,
.tweak[0] = tweak,
.tweak[1] = offset,
};
int ret = gmap_make_secure(kvm->arch.gmap, addr, &uvcb);
*rc = uvcb.header.rc;
*rrc = uvcb.header.rrc;
if (ret && ret != -EAGAIN)
KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: failed addr %llx with rc %x rrc %x",
uvcb.gaddr, *rc, *rrc);
return ret;
}
int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size,
unsigned long tweak, u16 *rc, u16 *rrc)
{
u64 offset = 0;
int ret = 0;
if (addr & ~PAGE_MASK || !size || size & ~PAGE_MASK)
return -EINVAL;
KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: start addr %lx size %lx",
addr, size);
while (offset < size) {
ret = unpack_one(kvm, addr, tweak, offset, rc, rrc);
if (ret == -EAGAIN) {
cond_resched();
if (fatal_signal_pending(current))
break;
continue;
}
if (ret)
break;
addr += PAGE_SIZE;
offset += PAGE_SIZE;
}
if (!ret)
KVM_UV_EVENT(kvm, 3, "%s", "PROTVIRT VM UNPACK: successful");
return ret;
}
int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state)
{
struct uv_cb_cpu_set_state uvcb = {
.header.cmd = UVC_CMD_CPU_SET_STATE,
.header.len = sizeof(uvcb),
.cpu_handle = kvm_s390_pv_cpu_get_handle(vcpu),
.state = state,
};
int cc;
cc = uv_call(0, (u64)&uvcb);
KVM_UV_EVENT(vcpu->kvm, 3, "PROTVIRT SET CPU %d STATE %d rc %x rrc %x",
vcpu->vcpu_id, state, uvcb.header.rc, uvcb.header.rrc);
if (cc)
return -EINVAL;
return 0;
}
int kvm_s390_pv_dump_cpu(struct kvm_vcpu *vcpu, void *buff, u16 *rc, u16 *rrc)
{
struct uv_cb_dump_cpu uvcb = {
.header.cmd = UVC_CMD_DUMP_CPU,
.header.len = sizeof(uvcb),
.cpu_handle = vcpu->arch.pv.handle,
.dump_area_origin = (u64)buff,
};
int cc;
cc = uv_call_sched(0, (u64)&uvcb);
*rc = uvcb.header.rc;
*rrc = uvcb.header.rrc;
return cc;
}
/* Size of the cache for the storage state dump data. 1MB for now */
#define DUMP_BUFF_LEN HPAGE_SIZE
/**
* kvm_s390_pv_dump_stor_state
*
* @kvm: pointer to the guest's KVM struct
* @buff_user: Userspace pointer where we will write the results to
* @gaddr: Starting absolute guest address for which the storage state
* is requested.
* @buff_user_len: Length of the buff_user buffer
* @rc: Pointer to where the uvcb return code is stored
* @rrc: Pointer to where the uvcb return reason code is stored
*
* Stores buff_len bytes of tweak component values to buff_user
* starting with the 1MB block specified by the absolute guest address
* (gaddr). The gaddr pointer will be updated with the last address
* for which data was written when returning to userspace. buff_user
* might be written to even if an error rc is returned. For instance
* if we encounter a fault after writing the first page of data.
*
* Context: kvm->lock needs to be held
*
* Return:
* 0 on success
* -ENOMEM if allocating the cache fails
* -EINVAL if gaddr is not aligned to 1MB
* -EINVAL if buff_user_len is not aligned to uv_info.conf_dump_storage_state_len
* -EINVAL if the UV call fails, rc and rrc will be set in this case
* -EFAULT if copying the result to buff_user failed
*/
int kvm_s390_pv_dump_stor_state(struct kvm *kvm, void __user *buff_user,
u64 *gaddr, u64 buff_user_len, u16 *rc, u16 *rrc)
{
struct uv_cb_dump_stor_state uvcb = {
.header.cmd = UVC_CMD_DUMP_CONF_STOR_STATE,
.header.len = sizeof(uvcb),
.config_handle = kvm->arch.pv.handle,
.gaddr = *gaddr,
.dump_area_origin = 0,
};
const u64 increment_len = uv_info.conf_dump_storage_state_len;
size_t buff_kvm_size;
size_t size_done = 0;
u8 *buff_kvm = NULL;
int cc, ret;
ret = -EINVAL;
/* UV call processes 1MB guest storage chunks at a time */
if (!IS_ALIGNED(*gaddr, HPAGE_SIZE))
goto out;
/*
* We provide the storage state for 1MB chunks of guest
* storage. The buffer will need to be aligned to
* conf_dump_storage_state_len so we don't end on a partial
* chunk.
*/
if (!buff_user_len ||
!IS_ALIGNED(buff_user_len, increment_len))
goto out;
/*
* Allocate a buffer from which we will later copy to the user
* process. We don't want userspace to dictate our buffer size
* so we limit it to DUMP_BUFF_LEN.
*/
ret = -ENOMEM;
buff_kvm_size = min_t(u64, buff_user_len, DUMP_BUFF_LEN);
buff_kvm = vzalloc(buff_kvm_size);
if (!buff_kvm)
goto out;
ret = 0;
uvcb.dump_area_origin = (u64)buff_kvm;
/* We will loop until the user buffer is filled or an error occurs */
do {
/* Get 1MB worth of guest storage state data */
cc = uv_call_sched(0, (u64)&uvcb);
/* All or nothing */
if (cc) {
ret = -EINVAL;
break;
}
size_done += increment_len;
uvcb.dump_area_origin += increment_len;
buff_user_len -= increment_len;
uvcb.gaddr += HPAGE_SIZE;
/* KVM Buffer full, time to copy to the process */
if (!buff_user_len || size_done == DUMP_BUFF_LEN) {
if (copy_to_user(buff_user, buff_kvm, size_done)) {
ret = -EFAULT;
break;
}
buff_user += size_done;
size_done = 0;
uvcb.dump_area_origin = (u64)buff_kvm;
}
} while (buff_user_len);
/* Report back where we ended dumping */
*gaddr = uvcb.gaddr;
/* Lets only log errors, we don't want to spam */
out:
if (ret)
KVM_UV_EVENT(kvm, 3,
"PROTVIRT DUMP STORAGE STATE: addr %llx ret %d, uvcb rc %x rrc %x",
uvcb.gaddr, ret, uvcb.header.rc, uvcb.header.rrc);
*rc = uvcb.header.rc;
*rrc = uvcb.header.rrc;
vfree(buff_kvm);
return ret;
}
/**
* kvm_s390_pv_dump_complete
*
* @kvm: pointer to the guest's KVM struct
* @buff_user: Userspace pointer where we will write the results to
* @rc: Pointer to where the uvcb return code is stored
* @rrc: Pointer to where the uvcb return reason code is stored
*
* Completes the dumping operation and writes the completion data to
* user space.
*
* Context: kvm->lock needs to be held
*
* Return:
* 0 on success
* -ENOMEM if allocating the completion buffer fails
* -EINVAL if the UV call fails, rc and rrc will be set in this case
* -EFAULT if copying the result to buff_user failed
*/
int kvm_s390_pv_dump_complete(struct kvm *kvm, void __user *buff_user,
u16 *rc, u16 *rrc)
{
struct uv_cb_dump_complete complete = {
.header.len = sizeof(complete),
.header.cmd = UVC_CMD_DUMP_COMPLETE,
.config_handle = kvm_s390_pv_get_handle(kvm),
};
u64 *compl_data;
int ret;
/* Allocate dump area */
compl_data = vzalloc(uv_info.conf_dump_finalize_len);
if (!compl_data)
return -ENOMEM;
complete.dump_area_origin = (u64)compl_data;
ret = uv_call_sched(0, (u64)&complete);
*rc = complete.header.rc;
*rrc = complete.header.rrc;
KVM_UV_EVENT(kvm, 3, "PROTVIRT DUMP COMPLETE: rc %x rrc %x",
complete.header.rc, complete.header.rrc);
if (!ret) {
/*
* kvm_s390_pv_dealloc_vm() will also (mem)set
* this to false on a reboot or other destroy
* operation for this vm.
*/
kvm->arch.pv.dumping = false;
kvm_s390_vcpu_unblock_all(kvm);
ret = copy_to_user(buff_user, compl_data, uv_info.conf_dump_finalize_len);
if (ret)
ret = -EFAULT;
}
vfree(compl_data);
/* If the UVC returned an error, translate it to -EINVAL */
if (ret > 0)
ret = -EINVAL;
return ret;
}
|