summaryrefslogtreecommitdiff
path: root/xen/arch/x86/mm/hap/hap.c
blob: 0fdb7d4a59030ac31381a0fbd66bb2be0a280ae9 (plain)
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
/******************************************************************************
 * arch/x86/mm/hap/hap.c
 *
 * hardware assisted paging
 * Copyright (c) 2007 Advanced Micro Devices (Wei Huang)
 * Parts of this code are Copyright (c) 2007 by XenSource 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.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; If not, see <http://www.gnu.org/licenses/>.
 */

#include <xen/types.h>
#include <xen/mm.h>
#include <xen/trace.h>
#include <xen/sched.h>
#include <xen/perfc.h>
#include <xen/irq.h>
#include <xen/domain_page.h>
#include <xen/guest_access.h>
#include <xen/keyhandler.h>
#include <asm/event.h>
#include <asm/page.h>
#include <asm/current.h>
#include <asm/flushtlb.h>
#include <asm/shared.h>
#include <asm/hap.h>
#include <asm/paging.h>
#include <asm/p2m.h>
#include <asm/domain.h>
#include <xen/numa.h>
#include <asm/hvm/nestedhvm.h>

#include "private.h"

/************************************************/
/*          HAP VRAM TRACKING SUPPORT           */
/************************************************/

/*
 * hap_track_dirty_vram()
 * Create the domain's dv_dirty_vram struct on demand.
 * Create a dirty vram range on demand when some [begin_pfn:begin_pfn+nr] is
 * first encountered.
 * Collect the guest_dirty bitmask, a bit mask of the dirty vram pages, by
 * calling paging_log_dirty_range(), which interrogates each vram
 * page's p2m type looking for pages that have been made writable.
 */

int hap_track_dirty_vram(struct domain *d,
                         unsigned long begin_pfn,
                         unsigned int nr_frames,
                         XEN_GUEST_HANDLE(void) guest_dirty_bitmap)
{
    long rc = 0;
    struct sh_dirty_vram *dirty_vram;
    uint8_t *dirty_bitmap = NULL;

    if ( nr_frames )
    {
        unsigned int size = DIV_ROUND_UP(nr_frames, BITS_PER_BYTE);

        if ( !paging_mode_log_dirty(d) )
        {
            rc = paging_log_dirty_enable(d, false);
            if ( rc )
                goto out;
        }

        rc = -ENOMEM;
        dirty_bitmap = vzalloc(size);
        if ( !dirty_bitmap )
            goto out;

        paging_lock(d);

        dirty_vram = d->arch.hvm.dirty_vram;
        if ( !dirty_vram )
        {
            rc = -ENOMEM;
            if ( (dirty_vram = xzalloc(struct sh_dirty_vram)) == NULL )
            {
                paging_unlock(d);
                goto out;
            }

            d->arch.hvm.dirty_vram = dirty_vram;
        }

        if ( begin_pfn != dirty_vram->begin_pfn ||
             begin_pfn + nr_frames != dirty_vram->end_pfn )
        {
            unsigned long ostart = dirty_vram->begin_pfn;
            unsigned long oend = dirty_vram->end_pfn;

            dirty_vram->begin_pfn = begin_pfn;
            dirty_vram->end_pfn = begin_pfn + nr_frames;

            paging_unlock(d);

            if ( oend > ostart )
                p2m_change_type_range(d, ostart, oend,
                                      p2m_ram_logdirty, p2m_ram_rw);

            /*
             * Switch vram to log dirty mode, either by setting l1e entries of
             * P2M table to be read-only, or via hardware-assisted log-dirty.
             */
            p2m_change_type_range(d, begin_pfn, begin_pfn + nr_frames,
                                  p2m_ram_rw, p2m_ram_logdirty);

            guest_flush_tlb_mask(d, d->dirty_cpumask);

            memset(dirty_bitmap, 0xff, size); /* consider all pages dirty */
        }
        else
        {
            paging_unlock(d);

            domain_pause(d);

            /* Flush dirty GFNs potentially cached by hardware. */
            p2m_flush_hardware_cached_dirty(d);

            /* get the bitmap */
            paging_log_dirty_range(d, begin_pfn, nr_frames, dirty_bitmap);

            domain_unpause(d);
        }

        rc = -EFAULT;
        if ( copy_to_guest(guest_dirty_bitmap, dirty_bitmap, size) == 0 )
            rc = 0;
    }
    else
    {
        paging_lock(d);

        dirty_vram = d->arch.hvm.dirty_vram;
        if ( dirty_vram )
        {
            /*
             * If zero pages specified while tracking dirty vram
             * then stop tracking
             */
            begin_pfn = dirty_vram->begin_pfn;
            nr_frames = dirty_vram->end_pfn - dirty_vram->begin_pfn;
            xfree(dirty_vram);
            d->arch.hvm.dirty_vram = NULL;
        }

        paging_unlock(d);

        if ( nr_frames )
            p2m_change_type_range(d, begin_pfn, begin_pfn + nr_frames,
                                  p2m_ram_logdirty, p2m_ram_rw);
    }
out:
    vfree(dirty_bitmap);

    return rc;
}

/************************************************/
/*            HAP LOG DIRTY SUPPORT             */
/************************************************/

/*
 * hap code to call when log_dirty is enable. return 0 if no problem found.
 *
 * NB: Domain that having device assigned should not set log_global. Because
 * there is no way to track the memory updating from device.
 */
static int hap_enable_log_dirty(struct domain *d, bool_t log_global)
{
    struct p2m_domain *p2m = p2m_get_hostp2m(d);

    /*
     * Refuse to turn on global log-dirty mode if
     * there are outstanding p2m_ioreq_server pages.
     */
    if ( log_global && read_atomic(&p2m->ioreq.entry_count) )
        return -EBUSY;

    /* turn on PG_log_dirty bit in paging mode */
    paging_lock(d);
    d->arch.paging.mode |= PG_log_dirty;
    paging_unlock(d);

    /* Enable hardware-assisted log-dirty if it is supported. */
    p2m_enable_hardware_log_dirty(d);

    if ( log_global )
    {
        /*
         * Switch to log dirty mode, either by setting l1e entries of P2M table
         * to be read-only, or via hardware-assisted log-dirty.
         */
        p2m_change_entry_type_global(d, p2m_ram_rw, p2m_ram_logdirty);
        guest_flush_tlb_mask(d, d->dirty_cpumask);
    }
    return 0;
}

static int hap_disable_log_dirty(struct domain *d)
{
    paging_lock(d);
    d->arch.paging.mode &= ~PG_log_dirty;
    paging_unlock(d);

    /* Disable hardware-assisted log-dirty if it is supported. */
    p2m_disable_hardware_log_dirty(d);

    /*
     * switch to normal mode, either by setting l1e entries of P2M table to
     * normal mode, or via hardware-assisted log-dirty.
     */
    p2m_change_entry_type_global(d, p2m_ram_logdirty, p2m_ram_rw);
    return 0;
}

static void hap_clean_dirty_bitmap(struct domain *d)
{
    /*
     * Switch to log-dirty mode, either by setting l1e entries of P2M table to
     * be read-only, or via hardware-assisted log-dirty.
     */
    p2m_change_entry_type_global(d, p2m_ram_rw, p2m_ram_logdirty);
    guest_flush_tlb_mask(d, d->dirty_cpumask);
}

/************************************************/
/*             HAP SUPPORT FUNCTIONS            */
/************************************************/
static struct page_info *hap_alloc(struct domain *d)
{
    struct page_info *pg;

    ASSERT(paging_locked_by_me(d));

    pg = page_list_remove_head(&d->arch.paging.hap.freelist);
    if ( unlikely(!pg) )
        return NULL;

    d->arch.paging.hap.free_pages--;

    clear_domain_page(page_to_mfn(pg));

    return pg;
}

static void hap_free(struct domain *d, mfn_t mfn)
{
    struct page_info *pg = mfn_to_page(mfn);

    ASSERT(paging_locked_by_me(d));

    d->arch.paging.hap.free_pages++;
    page_list_add_tail(pg, &d->arch.paging.hap.freelist);
}

static struct page_info *hap_alloc_p2m_page(struct domain *d)
{
    struct page_info *pg;

    /* This is called both from the p2m code (which never holds the 
     * paging lock) and the log-dirty code (which always does). */
    paging_lock_recursive(d);
    pg = hap_alloc(d);

    if ( likely(pg != NULL) )
    {
        d->arch.paging.hap.total_pages--;
        d->arch.paging.hap.p2m_pages++;
        ASSERT(!page_get_owner(pg) && !(pg->count_info & PGC_count_mask));
    }
    else if ( !d->arch.paging.p2m_alloc_failed )
    {
        d->arch.paging.p2m_alloc_failed = 1;
        dprintk(XENLOG_ERR, "d%i failed to allocate from HAP pool\n",
                d->domain_id);
    }

    paging_unlock(d);
    return pg;
}

static void hap_free_p2m_page(struct domain *d, struct page_info *pg)
{
    struct domain *owner = page_get_owner(pg);

    /* This is called both from the p2m code (which never holds the 
     * paging lock) and the log-dirty code (which always does). */
    paging_lock_recursive(d);

    /* Should still have no owner and count zero. */
    if ( owner || (pg->count_info & PGC_count_mask) )
    {
        printk(XENLOG_WARNING
               "d%d: Odd p2m page %"PRI_mfn" d=%d c=%lx t=%"PRtype_info"\n",
               d->domain_id, mfn_x(page_to_mfn(pg)),
               owner ? owner->domain_id : DOMID_INVALID,
               pg->count_info, pg->u.inuse.type_info);
        WARN();
        pg->count_info &= ~PGC_count_mask;
        page_set_owner(pg, NULL);
    }
    d->arch.paging.hap.p2m_pages--;
    d->arch.paging.hap.total_pages++;
    hap_free(d, page_to_mfn(pg));

    paging_unlock(d);
}

/* Return the size of the pool, rounded up to the nearest MB */
unsigned int hap_get_allocation(struct domain *d)
{
    unsigned int pg = d->arch.paging.hap.total_pages
        + d->arch.paging.hap.p2m_pages;

    return ((pg >> (20 - PAGE_SHIFT))
            + ((pg & ((1 << (20 - PAGE_SHIFT)) - 1)) ? 1 : 0));
}

/* Set the pool of pages to the required number of pages.
 * Returns 0 for success, non-zero for failure. */
int hap_set_allocation(struct domain *d, unsigned int pages, bool *preempted)
{
    struct page_info *pg;

    ASSERT(paging_locked_by_me(d));

    if ( pages < d->arch.paging.hap.p2m_pages )
        pages = 0;
    else
        pages -= d->arch.paging.hap.p2m_pages;

    for ( ; ; )
    {
        if ( d->arch.paging.hap.total_pages < pages )
        {
            /* Need to allocate more memory from domheap */
            pg = alloc_domheap_page(d, MEMF_no_owner);
            if ( pg == NULL )
            {
                HAP_PRINTK("failed to allocate hap pages.\n");
                return -ENOMEM;
            }
            d->arch.paging.hap.free_pages++;
            d->arch.paging.hap.total_pages++;
            page_list_add_tail(pg, &d->arch.paging.hap.freelist);
        }
        else if ( d->arch.paging.hap.total_pages > pages )
        {
            /* Need to return memory to domheap */
            if ( page_list_empty(&d->arch.paging.hap.freelist) )
            {
                HAP_PRINTK("failed to free enough hap pages.\n");
                return -ENOMEM;
            }
            pg = page_list_remove_head(&d->arch.paging.hap.freelist);
            ASSERT(pg);
            d->arch.paging.hap.free_pages--;
            d->arch.paging.hap.total_pages--;
            free_domheap_page(pg);
        }
        else
            break;

        /* Check to see if we need to yield and try again */
        if ( preempted && general_preempt_check() )
        {
            *preempted = true;
            return 0;
        }
    }

    return 0;
}

static mfn_t hap_make_monitor_table(struct vcpu *v)
{
    struct domain *d = v->domain;
    struct page_info *pg;
    l4_pgentry_t *l4e;
    mfn_t m4mfn;

    ASSERT(pagetable_get_pfn(v->arch.hvm.monitor_table) == 0);

    if ( (pg = hap_alloc(d)) == NULL )
        goto oom;

    m4mfn = page_to_mfn(pg);
    l4e = map_domain_page(m4mfn);

    init_xen_l4_slots(l4e, m4mfn, d, INVALID_MFN, false);
    unmap_domain_page(l4e);

    return m4mfn;

 oom:
    printk(XENLOG_G_ERR "out of memory building monitor pagetable\n");
    domain_crash(d);
    return INVALID_MFN;
}

static void hap_destroy_monitor_table(struct vcpu* v, mfn_t mmfn)
{
    struct domain *d = v->domain;

    /* Put the memory back in the pool */
    hap_free(d, mmfn);
}

/************************************************/
/*          HAP DOMAIN LEVEL FUNCTIONS          */
/************************************************/
void hap_domain_init(struct domain *d)
{
    static const struct log_dirty_ops hap_ops = {
        .enable  = hap_enable_log_dirty,
        .disable = hap_disable_log_dirty,
        .clean   = hap_clean_dirty_bitmap,
    };

    INIT_PAGE_LIST_HEAD(&d->arch.paging.hap.freelist);

    /* Use HAP logdirty mechanism. */
    paging_log_dirty_init(d, &hap_ops);
}

/* return 0 for success, -errno for failure */
int hap_enable(struct domain *d, u32 mode)
{
    unsigned int old_pages;
    unsigned int i;
    int rv = 0;

    if ( mode != (PG_external | PG_translate | PG_refcounts) )
        return -EINVAL;

    /* The function can only be called once per domain. */
    if ( d->arch.paging.mode != 0 )
        return -EEXIST;

    domain_pause(d);

    old_pages = d->arch.paging.hap.total_pages;
    if ( old_pages == 0 )
    {
        paging_lock(d);
        rv = hap_set_allocation(d, 256, NULL);
        if ( rv != 0 )
        {
            hap_set_allocation(d, 0, NULL);
            paging_unlock(d);
            goto out;
        }
        paging_unlock(d);
    }

    /* Allow p2m and log-dirty code to borrow our memory */
    d->arch.paging.alloc_page = hap_alloc_p2m_page;
    d->arch.paging.free_page = hap_free_p2m_page;

    /* allocate P2M table */
    rv = p2m_alloc_table(p2m_get_hostp2m(d));
    if ( rv != 0 )
        goto out;

    for ( i = 0; i < MAX_NESTEDP2M; i++ )
    {
        rv = p2m_alloc_table(d->arch.nested_p2m[i]);
        if ( rv != 0 )
           goto out;
    }

    if ( hvm_altp2m_supported() )
    {
        /* Init alternate p2m data */
        if ( (d->arch.altp2m_eptp = alloc_xenheap_page()) == NULL )
        {
            rv = -ENOMEM;
            goto out;
        }

        if ( (d->arch.altp2m_visible_eptp = alloc_xenheap_page()) == NULL )
        {
            rv = -ENOMEM;
            goto out;
        }

        for ( i = 0; i < MAX_EPTP; i++ )
        {
            d->arch.altp2m_eptp[i] = mfn_x(INVALID_MFN);
            d->arch.altp2m_visible_eptp[i] = mfn_x(INVALID_MFN);
        }

        for ( i = 0; i < MAX_ALTP2M; i++ )
        {
            rv = p2m_alloc_table(d->arch.altp2m_p2m[i]);
            if ( rv != 0 )
               goto out;
        }

        d->arch.altp2m_active = 0;
    }

    /* Now let other users see the new mode */
    d->arch.paging.mode = mode | PG_HAP_enable;

 out:
    domain_unpause(d);
    return rv;
}

void hap_final_teardown(struct domain *d)
{
    unsigned int i;

    if ( hvm_altp2m_supported() )
    {
        d->arch.altp2m_active = 0;

        if ( d->arch.altp2m_eptp )
        {
            free_xenheap_page(d->arch.altp2m_eptp);
            d->arch.altp2m_eptp = NULL;
        }

        if ( d->arch.altp2m_visible_eptp )
        {
            free_xenheap_page(d->arch.altp2m_visible_eptp);
            d->arch.altp2m_visible_eptp = NULL;
        }

        for ( i = 0; i < MAX_ALTP2M; i++ )
            p2m_teardown(d->arch.altp2m_p2m[i]);
    }

    /* Destroy nestedp2m's first */
    for (i = 0; i < MAX_NESTEDP2M; i++) {
        p2m_teardown(d->arch.nested_p2m[i]);
    }

    if ( d->arch.paging.hap.total_pages != 0 )
        hap_teardown(d, NULL);

    p2m_teardown(p2m_get_hostp2m(d));
    /* Free any memory that the p2m teardown released */
    paging_lock(d);
    hap_set_allocation(d, 0, NULL);
    ASSERT(d->arch.paging.hap.p2m_pages == 0);
    paging_unlock(d);
}

void hap_teardown(struct domain *d, bool *preempted)
{
    struct vcpu *v;
    mfn_t mfn;

    ASSERT(d->is_dying);
    ASSERT(d != current->domain);

    paging_lock(d); /* Keep various asserts happy */

    if ( paging_mode_enabled(d) )
    {
        /* release the monitor table held by each vcpu */
        for_each_vcpu ( d, v )
        {
            if ( paging_get_hostmode(v) && paging_mode_external(d) )
            {
                mfn = pagetable_get_mfn(v->arch.hvm.monitor_table);
                if ( mfn_valid(mfn) && (mfn_x(mfn) != 0) )
                    hap_destroy_monitor_table(v, mfn);
                v->arch.hvm.monitor_table = pagetable_null();
            }
        }
    }

    if ( d->arch.paging.hap.total_pages != 0 )
    {
        hap_set_allocation(d, 0, preempted);

        if ( preempted && *preempted )
            goto out;

        ASSERT(d->arch.paging.hap.total_pages == 0);
    }

    d->arch.paging.mode &= ~PG_log_dirty;

    XFREE(d->arch.hvm.dirty_vram);

out:
    paging_unlock(d);
}

int hap_domctl(struct domain *d, struct xen_domctl_shadow_op *sc,
               XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
{
    int rc;
    bool preempted = false;

    switch ( sc->op )
    {
    case XEN_DOMCTL_SHADOW_OP_SET_ALLOCATION:
        paging_lock(d);
        rc = hap_set_allocation(d, sc->mb << (20 - PAGE_SHIFT), &preempted);
        paging_unlock(d);
        if ( preempted )
            /* Not finished.  Set up to re-run the call. */
            rc = hypercall_create_continuation(__HYPERVISOR_domctl, "h",
                                               u_domctl);
        else
            /* Finished.  Return the new allocation */
            sc->mb = hap_get_allocation(d);
        return rc;
    case XEN_DOMCTL_SHADOW_OP_GET_ALLOCATION:
        sc->mb = hap_get_allocation(d);
        /* Fall through... */
    case XEN_DOMCTL_SHADOW_OP_OFF:
        return 0;
    default:
        HAP_PRINTK("Bad hap domctl op %u\n", sc->op);
        return -EINVAL;
    }
}

static const struct paging_mode hap_paging_real_mode;
static const struct paging_mode hap_paging_protected_mode;
static const struct paging_mode hap_paging_pae_mode;
static const struct paging_mode hap_paging_long_mode;

void hap_vcpu_init(struct vcpu *v)
{
    v->arch.paging.mode = &hap_paging_real_mode;
    v->arch.paging.nestedmode = &hap_paging_real_mode;
}

/************************************************/
/*          HAP PAGING MODE FUNCTIONS           */
/************************************************/
/*
 * HAP guests can handle page faults (in the guest page tables) without
 * needing any action from Xen, so we should not be intercepting them.
 */
static int hap_page_fault(struct vcpu *v, unsigned long va,
                          struct cpu_user_regs *regs)
{
    struct domain *d = v->domain;

    printk(XENLOG_G_ERR "Intercepted #PF from %pv with HAP enabled\n", v);
    domain_crash(d);
    return 0;
}

/*
 * HAP guests can handle invlpg without needing any action from Xen, so
 * should not be intercepting it.  However, we need to correctly handle
 * getting here from instruction emulation.
 */
static bool_t hap_invlpg(struct vcpu *v, unsigned long linear)
{
    /*
     * Emulate INVLPGA:
     * Must perform the flush right now or an other vcpu may
     * use it when we use the next VMRUN emulation, otherwise.
     */
    if ( nestedhvm_enabled(v->domain) && vcpu_nestedhvm(v).nv_p2m )
        p2m_flush(v, vcpu_nestedhvm(v).nv_p2m);

    return 1;
}

static void hap_update_cr3(struct vcpu *v, int do_locking, bool noflush)
{
    v->arch.hvm.hw_cr[3] = v->arch.hvm.guest_cr[3];
    hvm_update_guest_cr3(v, noflush);
}

/*
 * Dummy function to use with on_selected_cpus in order to trigger a vmexit on
 * selected pCPUs. When the VM resumes execution it will get a new ASID/VPID
 * and thus a clean TLB.
 */
static void dummy_flush(void *data)
{
}

static bool flush_tlb(bool (*flush_vcpu)(void *ctxt, struct vcpu *v),
                      void *ctxt)
{
    static DEFINE_PER_CPU(cpumask_t, flush_cpumask);
    cpumask_t *mask = &this_cpu(flush_cpumask);
    struct domain *d = current->domain;
    unsigned int this_cpu = smp_processor_id();
    struct vcpu *v;

    cpumask_clear(mask);

    /* Flush paging-mode soft state (e.g., va->gfn cache; PAE PDPE cache). */
    for_each_vcpu ( d, v )
    {
        unsigned int cpu;

        if ( !flush_vcpu(ctxt, v) )
            continue;

        hvm_asid_flush_vcpu(v);

        cpu = read_atomic(&v->dirty_cpu);
        if ( cpu != this_cpu && is_vcpu_dirty_cpu(cpu) && v->is_running )
            __cpumask_set_cpu(cpu, mask);
    }

    /*
     * Trigger a vmexit on all pCPUs with dirty vCPU state in order to force an
     * ASID/VPID change and hence accomplish a guest TLB flush. Note that vCPUs
     * not currently running will already be flushed when scheduled because of
     * the ASID tickle done in the loop above.
     */
    on_selected_cpus(mask, dummy_flush, NULL, 0);

    return true;
}

const struct paging_mode *
hap_paging_get_mode(struct vcpu *v)
{
    return (!hvm_paging_enabled(v)  ? &hap_paging_real_mode :
            hvm_long_mode_active(v) ? &hap_paging_long_mode :
            hvm_pae_enabled(v)      ? &hap_paging_pae_mode  :
                                      &hap_paging_protected_mode);
}

static void hap_update_paging_modes(struct vcpu *v)
{
    struct domain *d = v->domain;
    unsigned long cr3_gfn = v->arch.hvm.guest_cr[3] >> PAGE_SHIFT;
    p2m_type_t t;

    /* We hold onto the cr3 as it may be modified later, and
     * we need to respect lock ordering. No need for 
     * checks here as they are performed by vmx_load_pdptrs
     * (the potential user of the cr3) */
    (void)get_gfn(d, cr3_gfn, &t);
    paging_lock(d);

    v->arch.paging.mode = hap_paging_get_mode(v);

    if ( pagetable_is_null(v->arch.hvm.monitor_table) )
    {
        mfn_t mmfn = hap_make_monitor_table(v);
        v->arch.hvm.monitor_table = pagetable_from_mfn(mmfn);
        make_cr3(v, mmfn);
        hvm_update_host_cr3(v);
    }

    /* CR3 is effectively updated by a mode change. Flush ASIDs, etc. */
    hap_update_cr3(v, 0, false);

    paging_unlock(d);
    put_gfn(d, cr3_gfn);
}

static void
hap_write_p2m_entry_post(struct p2m_domain *p2m, unsigned int oflags)
{
    struct domain *d = p2m->domain;

    if ( oflags & _PAGE_PRESENT )
        guest_flush_tlb_mask(d, d->dirty_cpumask);
}

void hap_p2m_init(struct p2m_domain *p2m)
{
    p2m->write_p2m_entry_post = hap_write_p2m_entry_post;
}

static unsigned long hap_gva_to_gfn_real_mode(
    struct vcpu *v, struct p2m_domain *p2m, unsigned long gva, uint32_t *pfec)
{
    return ((paddr_t)gva >> PAGE_SHIFT);
}

static unsigned long hap_p2m_ga_to_gfn_real_mode(
    struct vcpu *v, struct p2m_domain *p2m, unsigned long cr3,
    paddr_t ga, uint32_t *pfec, unsigned int *page_order)
{
    if ( page_order )
        *page_order = PAGE_ORDER_4K;
    return (ga >> PAGE_SHIFT);
}

/* Entry points into this mode of the hap code. */
static const struct paging_mode hap_paging_real_mode = {
    .page_fault             = hap_page_fault,
    .invlpg                 = hap_invlpg,
    .gva_to_gfn             = hap_gva_to_gfn_real_mode,
    .p2m_ga_to_gfn          = hap_p2m_ga_to_gfn_real_mode,
    .update_cr3             = hap_update_cr3,
    .update_paging_modes    = hap_update_paging_modes,
    .flush_tlb              = flush_tlb,
    .guest_levels           = 1
};

static const struct paging_mode hap_paging_protected_mode = {
    .page_fault             = hap_page_fault,
    .invlpg                 = hap_invlpg,
    .gva_to_gfn             = hap_gva_to_gfn_2_levels,
    .p2m_ga_to_gfn          = hap_p2m_ga_to_gfn_2_levels,
    .update_cr3             = hap_update_cr3,
    .update_paging_modes    = hap_update_paging_modes,
    .flush_tlb              = flush_tlb,
    .guest_levels           = 2
};

static const struct paging_mode hap_paging_pae_mode = {
    .page_fault             = hap_page_fault,
    .invlpg                 = hap_invlpg,
    .gva_to_gfn             = hap_gva_to_gfn_3_levels,
    .p2m_ga_to_gfn          = hap_p2m_ga_to_gfn_3_levels,
    .update_cr3             = hap_update_cr3,
    .update_paging_modes    = hap_update_paging_modes,
    .flush_tlb              = flush_tlb,
    .guest_levels           = 3
};

static const struct paging_mode hap_paging_long_mode = {
    .page_fault             = hap_page_fault,
    .invlpg                 = hap_invlpg,
    .gva_to_gfn             = hap_gva_to_gfn_4_levels,
    .p2m_ga_to_gfn          = hap_p2m_ga_to_gfn_4_levels,
    .update_cr3             = hap_update_cr3,
    .update_paging_modes    = hap_update_paging_modes,
    .flush_tlb              = flush_tlb,
    .guest_levels           = 4
};

/*
 * Local variables:
 * mode: C
 * c-file-style: "BSD"
 * c-basic-offset: 4
 * indent-tabs-mode: nil
 * End:
 */