Blame view

kvm-all.c 24.4 KB
1
2
3
4
/*
 * QEMU KVM support
 *
 * Copyright IBM, Corp. 2008
5
 *           Red Hat, Inc. 2008
6
7
8
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
9
 *  Glauber Costa     <gcosta@redhat.com>
10
11
12
13
14
15
16
17
18
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 *
 */

#include <sys/types.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
19
#include <stdarg.h>
20
21
22
23
24

#include <linux/kvm.h>

#include "qemu-common.h"
#include "sysemu.h"
25
#include "gdbstub.h"
26
27
#include "kvm.h"
aliguori authored
28
29
30
/* KVM uses PAGE_SIZE in it's definition of COALESCED_MMIO_MAX */
#define PAGE_SIZE TARGET_PAGE_SIZE
31
32
33
34
35
36
37
38
39
40
//#define DEBUG_KVM

#ifdef DEBUG_KVM
#define dprintf(fmt, ...) \
    do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0)
#else
#define dprintf(fmt, ...) \
    do { } while (0)
#endif
41
42
43
44
45
46
47
48
typedef struct KVMSlot
{
    target_phys_addr_t start_addr;
    ram_addr_t memory_size;
    ram_addr_t phys_offset;
    int slot;
    int flags;
} KVMSlot;
49
50
51
typedef struct kvm_dirty_log KVMDirtyLog;
52
53
54
55
56
57
58
int kvm_allowed = 0;

struct KVMState
{
    KVMSlot slots[32];
    int fd;
    int vmfd;
aliguori authored
59
    int coalesced_mmio;
60
61
62
#ifdef KVM_CAP_SET_GUEST_DEBUG
    struct kvm_sw_breakpoint_head kvm_sw_breakpoints;
#endif
63
64
65
66
67
68
69
70
71
};

static KVMState *kvm_state;

static KVMSlot *kvm_alloc_slot(KVMState *s)
{
    int i;

    for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
72
73
74
        /* KVM private memory slots */
        if (i >= 8 && i < 12)
            continue;
75
76
77
78
        if (s->slots[i].memory_size == 0)
            return &s->slots[i];
    }
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
    fprintf(stderr, "%s: no free slot available\n", __func__);
    abort();
}

static KVMSlot *kvm_lookup_matching_slot(KVMState *s,
                                         target_phys_addr_t start_addr,
                                         target_phys_addr_t end_addr)
{
    int i;

    for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
        KVMSlot *mem = &s->slots[i];

        if (start_addr == mem->start_addr &&
            end_addr == mem->start_addr + mem->memory_size) {
            return mem;
        }
    }
98
99
100
    return NULL;
}
101
102
103
104
105
106
/*
 * Find overlapping slot with lowest start address
 */
static KVMSlot *kvm_lookup_overlapping_slot(KVMState *s,
                                            target_phys_addr_t start_addr,
                                            target_phys_addr_t end_addr)
107
{
108
    KVMSlot *found = NULL;
109
110
111
112
113
    int i;

    for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
        KVMSlot *mem = &s->slots[i];
114
115
116
117
118
119
120
121
122
        if (mem->memory_size == 0 ||
            (found && found->start_addr < mem->start_addr)) {
            continue;
        }

        if (end_addr > mem->start_addr &&
            start_addr < mem->start_addr + mem->memory_size) {
            found = mem;
        }
123
124
    }
125
    return found;
126
127
}
128
129
130
131
132
133
134
static int kvm_set_user_memory_region(KVMState *s, KVMSlot *slot)
{
    struct kvm_userspace_memory_region mem;

    mem.slot = slot->slot;
    mem.guest_phys_addr = slot->start_addr;
    mem.memory_size = slot->memory_size;
135
    mem.userspace_addr = (unsigned long)qemu_get_ram_ptr(slot->phys_offset);
136
137
138
139
140
141
    mem.flags = slot->flags;

    return kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
}
142
143
144
145
146
147
148
149
int kvm_init_vcpu(CPUState *env)
{
    KVMState *s = kvm_state;
    long mmap_size;
    int ret;

    dprintf("kvm_init_vcpu\n");
150
    ret = kvm_vm_ioctl(s, KVM_CREATE_VCPU, env->cpu_index);
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
    if (ret < 0) {
        dprintf("kvm_create_vcpu failed\n");
        goto err;
    }

    env->kvm_fd = ret;
    env->kvm_state = s;

    mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0);
    if (mmap_size < 0) {
        dprintf("KVM_GET_VCPU_MMAP_SIZE failed\n");
        goto err;
    }

    env->kvm_run = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED,
                        env->kvm_fd, 0);
    if (env->kvm_run == MAP_FAILED) {
        ret = -errno;
        dprintf("mmap'ing vcpu state failed\n");
        goto err;
    }

    ret = kvm_arch_init_vcpu(env);

err:
    return ret;
}
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
int kvm_sync_vcpus(void)
{
    CPUState *env;

    for (env = first_cpu; env != NULL; env = env->next_cpu) {
        int ret;

        ret = kvm_arch_put_registers(env);
        if (ret)
            return ret;
    }

    return 0;
}
194
195
196
/*
 * dirty pages logging control
 */
197
198
static int kvm_dirty_pages_log_change(target_phys_addr_t phys_addr,
                                      ram_addr_t size, unsigned flags,
199
200
201
                                      unsigned mask)
{
    KVMState *s = kvm_state;
202
    KVMSlot *mem = kvm_lookup_matching_slot(s, phys_addr, phys_addr + size);
203
    if (mem == NULL)  {
204
205
206
            fprintf(stderr, "BUG: %s: invalid parameters " TARGET_FMT_plx "-"
                    TARGET_FMT_plx "\n", __func__, phys_addr,
                    phys_addr + size - 1);
207
208
209
210
211
212
213
214
215
216
217
218
219
            return -EINVAL;
    }

    flags = (mem->flags & ~mask) | flags;
    /* Nothing changed, no need to issue ioctl */
    if (flags == mem->flags)
            return 0;

    mem->flags = flags;

    return kvm_set_user_memory_region(s, mem);
}
220
int kvm_log_start(target_phys_addr_t phys_addr, ram_addr_t size)
221
{
222
        return kvm_dirty_pages_log_change(phys_addr, size,
223
224
225
226
                                          KVM_MEM_LOG_DIRTY_PAGES,
                                          KVM_MEM_LOG_DIRTY_PAGES);
}
227
int kvm_log_stop(target_phys_addr_t phys_addr, ram_addr_t size)
228
{
229
        return kvm_dirty_pages_log_change(phys_addr, size,
230
231
232
233
234
235
236
237
238
                                          0,
                                          KVM_MEM_LOG_DIRTY_PAGES);
}

/**
 * kvm_physical_sync_dirty_bitmap - Grab dirty bitmap from kernel space
 * This function updates qemu's dirty bitmap using cpu_physical_memory_set_dirty().
 * This means all bits are set to dirty.
 *
239
 * @start_add: start of logged region.
240
241
 * @end_addr: end of logged region.
 */
242
243
void kvm_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
                                    target_phys_addr_t end_addr)
244
245
246
{
    KVMState *s = kvm_state;
    KVMDirtyLog d;
247
    KVMSlot *mem = kvm_lookup_matching_slot(s, start_addr, end_addr);
248
249
250
251
    unsigned long alloc_size;
    ram_addr_t addr;
    target_phys_addr_t phys_addr = start_addr;
252
253
    dprintf("sync addr: " TARGET_FMT_lx " into %lx\n", start_addr,
            mem->phys_offset);
254
    if (mem == NULL) {
255
256
            fprintf(stderr, "BUG: %s: invalid parameters " TARGET_FMT_plx "-"
                    TARGET_FMT_plx "\n", __func__, phys_addr, end_addr - 1);
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
            return;
    }

    alloc_size = mem->memory_size >> TARGET_PAGE_BITS / sizeof(d.dirty_bitmap);
    d.dirty_bitmap = qemu_mallocz(alloc_size);

    d.slot = mem->slot;
    dprintf("slot %d, phys_addr %llx, uaddr: %llx\n",
            d.slot, mem->start_addr, mem->phys_offset);

    if (kvm_vm_ioctl(s, KVM_GET_DIRTY_LOG, &d) == -1) {
        dprintf("ioctl failed %d\n", errno);
        goto out;
    }

    phys_addr = start_addr;
    for (addr = mem->phys_offset; phys_addr < end_addr; phys_addr+= TARGET_PAGE_SIZE, addr += TARGET_PAGE_SIZE) {
        unsigned long *bitmap = (unsigned long *)d.dirty_bitmap;
        unsigned nr = (phys_addr - start_addr) >> TARGET_PAGE_BITS;
        unsigned word = nr / (sizeof(*bitmap) * 8);
        unsigned bit = nr % (sizeof(*bitmap) * 8);
        if ((bitmap[word] >> bit) & 1)
            cpu_physical_memory_set_dirty(addr);
    }
out:
    qemu_free(d.dirty_bitmap);
}
aliguori authored
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
int kvm_coalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
{
    int ret = -ENOSYS;
#ifdef KVM_CAP_COALESCED_MMIO
    KVMState *s = kvm_state;

    if (s->coalesced_mmio) {
        struct kvm_coalesced_mmio_zone zone;

        zone.addr = start;
        zone.size = size;

        ret = kvm_vm_ioctl(s, KVM_REGISTER_COALESCED_MMIO, &zone);
    }
#endif

    return ret;
}

int kvm_uncoalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
{
    int ret = -ENOSYS;
#ifdef KVM_CAP_COALESCED_MMIO
    KVMState *s = kvm_state;

    if (s->coalesced_mmio) {
        struct kvm_coalesced_mmio_zone zone;

        zone.addr = start;
        zone.size = size;

        ret = kvm_vm_ioctl(s, KVM_UNREGISTER_COALESCED_MMIO, &zone);
    }
#endif

    return ret;
}
323
324
325
326
327
328
329
330
331
332
333
334
int kvm_check_extension(KVMState *s, unsigned int extension)
{
    int ret;

    ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, extension);
    if (ret < 0) {
        ret = 0;
    }

    return ret;
}
335
336
337
338
339
340
341
342
343
344
345
int kvm_init(int smp_cpus)
{
    KVMState *s;
    int ret;
    int i;

    if (smp_cpus > 1)
        return -EINVAL;

    s = qemu_mallocz(sizeof(KVMState));
346
347
348
#ifdef KVM_CAP_SET_GUEST_DEBUG
    TAILQ_INIT(&s->kvm_sw_breakpoints);
#endif
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
    for (i = 0; i < ARRAY_SIZE(s->slots); i++)
        s->slots[i].slot = i;

    s->vmfd = -1;
    s->fd = open("/dev/kvm", O_RDWR);
    if (s->fd == -1) {
        fprintf(stderr, "Could not access KVM kernel module: %m\n");
        ret = -errno;
        goto err;
    }

    ret = kvm_ioctl(s, KVM_GET_API_VERSION, 0);
    if (ret < KVM_API_VERSION) {
        if (ret > 0)
            ret = -EINVAL;
        fprintf(stderr, "kvm version too old\n");
        goto err;
    }

    if (ret > KVM_API_VERSION) {
        ret = -EINVAL;
        fprintf(stderr, "kvm version not supported\n");
        goto err;
    }

    s->vmfd = kvm_ioctl(s, KVM_CREATE_VM, 0);
    if (s->vmfd < 0)
        goto err;

    /* initially, KVM allocated its own memory and we had to jump through
     * hooks to make phys_ram_base point to this.  Modern versions of KVM
380
     * just use a user allocated buffer so we can use regular pages
381
382
     * unmodified.  Make sure we have a sufficiently modern version of KVM.
     */
383
384
    if (!kvm_check_extension(s, KVM_CAP_USER_MEMORY)) {
        ret = -EINVAL;
385
386
387
388
        fprintf(stderr, "kvm does not support KVM_CAP_USER_MEMORY\n");
        goto err;
    }
389
390
391
    /* There was a nasty bug in < kvm-80 that prevents memory slots from being
     * destroyed properly.  Since we rely on this capability, refuse to work
     * with any kernel without this capability. */
392
393
    if (!kvm_check_extension(s, KVM_CAP_DESTROY_MEMORY_REGION_WORKS)) {
        ret = -EINVAL;
394
395
396
397
398
399
400

        fprintf(stderr,
                "KVM kernel module broken (DESTROY_MEMORY_REGION)\n"
                "Please upgrade to at least kvm-81.\n");
        goto err;
    }
aliguori authored
401
#ifdef KVM_CAP_COALESCED_MMIO
402
403
404
    s->coalesced_mmio = kvm_check_extension(s, KVM_CAP_COALESCED_MMIO);
#else
    s->coalesced_mmio = 0;
aliguori authored
405
406
#endif
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
    ret = kvm_arch_init(s, smp_cpus);
    if (ret < 0)
        goto err;

    kvm_state = s;

    return 0;

err:
    if (s) {
        if (s->vmfd != -1)
            close(s->vmfd);
        if (s->fd != -1)
            close(s->fd);
    }
    qemu_free(s);

    return ret;
}

static int kvm_handle_io(CPUState *env, uint16_t port, void *data,
                         int direction, int size, uint32_t count)
{
    int i;
    uint8_t *ptr = data;

    for (i = 0; i < count; i++) {
        if (direction == KVM_EXIT_IO_IN) {
            switch (size) {
            case 1:
                stb_p(ptr, cpu_inb(env, port));
                break;
            case 2:
                stw_p(ptr, cpu_inw(env, port));
                break;
            case 4:
                stl_p(ptr, cpu_inl(env, port));
                break;
            }
        } else {
            switch (size) {
            case 1:
                cpu_outb(env, port, ldub_p(ptr));
                break;
            case 2:
                cpu_outw(env, port, lduw_p(ptr));
                break;
            case 4:
                cpu_outl(env, port, ldl_p(ptr));
                break;
            }
        }

        ptr += size;
    }

    return 1;
}
aliguori authored
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
static void kvm_run_coalesced_mmio(CPUState *env, struct kvm_run *run)
{
#ifdef KVM_CAP_COALESCED_MMIO
    KVMState *s = kvm_state;
    if (s->coalesced_mmio) {
        struct kvm_coalesced_mmio_ring *ring;

        ring = (void *)run + (s->coalesced_mmio * TARGET_PAGE_SIZE);
        while (ring->first != ring->last) {
            struct kvm_coalesced_mmio *ent;

            ent = &ring->coalesced_mmio[ring->first];

            cpu_physical_memory_write(ent->phys_addr, ent->data, ent->len);
            /* FIXME smp_wmb() */
            ring->first = (ring->first + 1) % KVM_COALESCED_MMIO_MAX;
        }
    }
#endif
}
487
488
489
490
491
492
493
494
495
496
int kvm_cpu_exec(CPUState *env)
{
    struct kvm_run *run = env->kvm_run;
    int ret;

    dprintf("kvm_cpu_exec()\n");

    do {
        kvm_arch_pre_run(env, run);
497
        if (env->exit_request) {
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
            dprintf("interrupt exit requested\n");
            ret = 0;
            break;
        }

        ret = kvm_vcpu_ioctl(env, KVM_RUN, 0);
        kvm_arch_post_run(env, run);

        if (ret == -EINTR || ret == -EAGAIN) {
            dprintf("io window exit\n");
            ret = 0;
            break;
        }

        if (ret < 0) {
            dprintf("kvm run failed %s\n", strerror(-ret));
            abort();
        }
aliguori authored
517
518
        kvm_run_coalesced_mmio(env, run);
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
        ret = 0; /* exit loop */
        switch (run->exit_reason) {
        case KVM_EXIT_IO:
            dprintf("handle_io\n");
            ret = kvm_handle_io(env, run->io.port,
                                (uint8_t *)run + run->io.data_offset,
                                run->io.direction,
                                run->io.size,
                                run->io.count);
            break;
        case KVM_EXIT_MMIO:
            dprintf("handle_mmio\n");
            cpu_physical_memory_rw(run->mmio.phys_addr,
                                   run->mmio.data,
                                   run->mmio.len,
                                   run->mmio.is_write);
            ret = 1;
            break;
        case KVM_EXIT_IRQ_WINDOW_OPEN:
            dprintf("irq_window_open\n");
            break;
        case KVM_EXIT_SHUTDOWN:
            dprintf("shutdown\n");
            qemu_system_reset_request();
            ret = 1;
            break;
        case KVM_EXIT_UNKNOWN:
            dprintf("kvm_exit_unknown\n");
            break;
        case KVM_EXIT_FAIL_ENTRY:
            dprintf("kvm_exit_fail_entry\n");
            break;
        case KVM_EXIT_EXCEPTION:
            dprintf("kvm_exit_exception\n");
            break;
        case KVM_EXIT_DEBUG:
            dprintf("kvm_exit_debug\n");
556
557
558
559
560
561
562
563
564
565
#ifdef KVM_CAP_SET_GUEST_DEBUG
            if (kvm_arch_debug(&run->debug.arch)) {
                gdb_set_stop_cpu(env);
                vm_stop(EXCP_DEBUG);
                env->exception_index = EXCP_DEBUG;
                return 0;
            }
            /* re-enter, this exception was guest-internal */
            ret = 1;
#endif /* KVM_CAP_SET_GUEST_DEBUG */
566
567
568
569
570
571
572
573
            break;
        default:
            dprintf("kvm_arch_handle_exit\n");
            ret = kvm_arch_handle_exit(env, run);
            break;
        }
    } while (ret > 0);
574
575
    if (env->exit_request) {
        env->exit_request = 0;
576
577
578
        env->exception_index = EXCP_INTERRUPT;
    }
579
580
581
582
583
584
585
586
587
    return ret;
}

void kvm_set_phys_mem(target_phys_addr_t start_addr,
                      ram_addr_t size,
                      ram_addr_t phys_offset)
{
    KVMState *s = kvm_state;
    ram_addr_t flags = phys_offset & ~TARGET_PAGE_MASK;
588
589
    KVMSlot *mem, old;
    int err;
590
591
    if (start_addr & ~TARGET_PAGE_MASK) {
592
593
594
595
596
597
598
599
600
        if (flags >= IO_MEM_UNASSIGNED) {
            if (!kvm_lookup_overlapping_slot(s, start_addr,
                                             start_addr + size)) {
                return;
            }
            fprintf(stderr, "Unaligned split of a KVM memory slot\n");
        } else {
            fprintf(stderr, "Only page-aligned memory slots supported\n");
        }
601
602
603
        abort();
    }
604
605
606
    /* KVM does not support read-only slots */
    phys_offset &= ~IO_MEM_ROM;
607
608
609
610
611
    while (1) {
        mem = kvm_lookup_overlapping_slot(s, start_addr, start_addr + size);
        if (!mem) {
            break;
        }
612
613
614
615
616
617
        if (flags < IO_MEM_UNASSIGNED && start_addr >= mem->start_addr &&
            (start_addr + size <= mem->start_addr + mem->memory_size) &&
            (phys_offset - start_addr == mem->phys_offset - mem->start_addr)) {
            /* The new slot fits into the existing one and comes with
             * identical parameters - nothing to be done. */
618
            return;
619
620
621
622
623
624
625
626
627
628
        }

        old = *mem;

        /* unregister the overlapping slot */
        mem->memory_size = 0;
        err = kvm_set_user_memory_region(s, mem);
        if (err) {
            fprintf(stderr, "%s: error unregistering overlapping slot: %s\n",
                    __func__, strerror(-err));
629
630
            abort();
        }
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

        /* Workaround for older KVM versions: we can't join slots, even not by
         * unregistering the previous ones and then registering the larger
         * slot. We have to maintain the existing fragmentation. Sigh.
         *
         * This workaround assumes that the new slot starts at the same
         * address as the first existing one. If not or if some overlapping
         * slot comes around later, we will fail (not seen in practice so far)
         * - and actually require a recent KVM version. */
        if (old.start_addr == start_addr && old.memory_size < size &&
            flags < IO_MEM_UNASSIGNED) {
            mem = kvm_alloc_slot(s);
            mem->memory_size = old.memory_size;
            mem->start_addr = old.start_addr;
            mem->phys_offset = old.phys_offset;
            mem->flags = 0;

            err = kvm_set_user_memory_region(s, mem);
            if (err) {
                fprintf(stderr, "%s: error updating slot: %s\n", __func__,
                        strerror(-err));
                abort();
            }

            start_addr += old.memory_size;
            phys_offset += old.memory_size;
            size -= old.memory_size;
            continue;
        }

        /* register prefix slot */
        if (old.start_addr < start_addr) {
            mem = kvm_alloc_slot(s);
            mem->memory_size = start_addr - old.start_addr;
            mem->start_addr = old.start_addr;
            mem->phys_offset = old.phys_offset;
            mem->flags = 0;

            err = kvm_set_user_memory_region(s, mem);
            if (err) {
                fprintf(stderr, "%s: error registering prefix slot: %s\n",
                        __func__, strerror(-err));
                abort();
            }
        }

        /* register suffix slot */
        if (old.start_addr + old.memory_size > start_addr + size) {
            ram_addr_t size_delta;

            mem = kvm_alloc_slot(s);
            mem->start_addr = start_addr + size;
            size_delta = mem->start_addr - old.start_addr;
            mem->memory_size = old.memory_size - size_delta;
            mem->phys_offset = old.phys_offset + size_delta;
            mem->flags = 0;

            err = kvm_set_user_memory_region(s, mem);
            if (err) {
                fprintf(stderr, "%s: error registering suffix slot: %s\n",
                        __func__, strerror(-err));
                abort();
            }
        }
695
    }
696
697
698
699
700

    /* in case the KVM bug workaround already "consumed" the new slot */
    if (!size)
        return;
701
702
703
704
705
706
    /* KVM does not need to know about this memory */
    if (flags >= IO_MEM_UNASSIGNED)
        return;

    mem = kvm_alloc_slot(s);
    mem->memory_size = size;
707
708
    mem->start_addr = start_addr;
    mem->phys_offset = phys_offset;
709
710
    mem->flags = 0;
711
712
713
714
715
716
    err = kvm_set_user_memory_region(s, mem);
    if (err) {
        fprintf(stderr, "%s: error registering slot: %s\n", __func__,
                strerror(-err));
        abort();
    }
717
718
}
719
int kvm_ioctl(KVMState *s, int type, ...)
720
721
{
    int ret;
722
723
    void *arg;
    va_list ap;
724
725
726
727
728
729
    va_start(ap, type);
    arg = va_arg(ap, void *);
    va_end(ap);

    ret = ioctl(s->fd, type, arg);
730
731
732
733
734
735
    if (ret == -1)
        ret = -errno;

    return ret;
}
736
int kvm_vm_ioctl(KVMState *s, int type, ...)
737
738
{
    int ret;
739
740
741
742
743
744
    void *arg;
    va_list ap;

    va_start(ap, type);
    arg = va_arg(ap, void *);
    va_end(ap);
745
746
    ret = ioctl(s->vmfd, type, arg);
747
748
749
750
751
752
    if (ret == -1)
        ret = -errno;

    return ret;
}
753
int kvm_vcpu_ioctl(CPUState *env, int type, ...)
754
755
{
    int ret;
756
757
758
759
760
761
    void *arg;
    va_list ap;

    va_start(ap, type);
    arg = va_arg(ap, void *);
    va_end(ap);
762
763
    ret = ioctl(env->kvm_fd, type, arg);
764
765
766
767
768
    if (ret == -1)
        ret = -errno;

    return ret;
}
aliguori authored
769
770
771

int kvm_has_sync_mmu(void)
{
772
#ifdef KVM_CAP_SYNC_MMU
aliguori authored
773
774
    KVMState *s = kvm_state;
775
776
    return kvm_check_extension(s, KVM_CAP_SYNC_MMU);
#else
aliguori authored
777
    return 0;
778
#endif
aliguori authored
779
}
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
void kvm_setup_guest_memory(void *start, size_t size)
{
    if (!kvm_has_sync_mmu()) {
#ifdef MADV_DONTFORK
        int ret = madvise(start, size, MADV_DONTFORK);

        if (ret) {
            perror("madvice");
            exit(1);
        }
#else
        fprintf(stderr,
                "Need MADV_DONTFORK in absence of synchronous KVM MMU\n");
        exit(1);
#endif
    }
}
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
#ifdef KVM_CAP_SET_GUEST_DEBUG
struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUState *env,
                                                 target_ulong pc)
{
    struct kvm_sw_breakpoint *bp;

    TAILQ_FOREACH(bp, &env->kvm_state->kvm_sw_breakpoints, entry) {
        if (bp->pc == pc)
            return bp;
    }
    return NULL;
}

int kvm_sw_breakpoints_active(CPUState *env)
{
    return !TAILQ_EMPTY(&env->kvm_state->kvm_sw_breakpoints);
}

int kvm_update_guest_debug(CPUState *env, unsigned long reinject_trap)
{
    struct kvm_guest_debug dbg;

    dbg.control = 0;
    if (env->singlestep_enabled)
        dbg.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP;

    kvm_arch_update_guest_debug(env, &dbg);
    dbg.control |= reinject_trap;

    return kvm_vcpu_ioctl(env, KVM_SET_GUEST_DEBUG, &dbg);
}

int kvm_insert_breakpoint(CPUState *current_env, target_ulong addr,
                          target_ulong len, int type)
{
    struct kvm_sw_breakpoint *bp;
    CPUState *env;
    int err;

    if (type == GDB_BREAKPOINT_SW) {
        bp = kvm_find_sw_breakpoint(current_env, addr);
        if (bp) {
            bp->use_count++;
            return 0;
        }

        bp = qemu_malloc(sizeof(struct kvm_sw_breakpoint));
        if (!bp)
            return -ENOMEM;

        bp->pc = addr;
        bp->use_count = 1;
        err = kvm_arch_insert_sw_breakpoint(current_env, bp);
        if (err) {
            free(bp);
            return err;
        }

        TAILQ_INSERT_HEAD(&current_env->kvm_state->kvm_sw_breakpoints,
                          bp, entry);
    } else {
        err = kvm_arch_insert_hw_breakpoint(addr, len, type);
        if (err)
            return err;
    }

    for (env = first_cpu; env != NULL; env = env->next_cpu) {
        err = kvm_update_guest_debug(env, 0);
        if (err)
            return err;
    }
    return 0;
}

int kvm_remove_breakpoint(CPUState *current_env, target_ulong addr,
                          target_ulong len, int type)
{
    struct kvm_sw_breakpoint *bp;
    CPUState *env;
    int err;

    if (type == GDB_BREAKPOINT_SW) {
        bp = kvm_find_sw_breakpoint(current_env, addr);
        if (!bp)
            return -ENOENT;

        if (bp->use_count > 1) {
            bp->use_count--;
            return 0;
        }

        err = kvm_arch_remove_sw_breakpoint(current_env, bp);
        if (err)
            return err;

        TAILQ_REMOVE(&current_env->kvm_state->kvm_sw_breakpoints, bp, entry);
        qemu_free(bp);
    } else {
        err = kvm_arch_remove_hw_breakpoint(addr, len, type);
        if (err)
            return err;
    }

    for (env = first_cpu; env != NULL; env = env->next_cpu) {
        err = kvm_update_guest_debug(env, 0);
        if (err)
            return err;
    }
    return 0;
}

void kvm_remove_all_breakpoints(CPUState *current_env)
{
    struct kvm_sw_breakpoint *bp, *next;
    KVMState *s = current_env->kvm_state;
    CPUState *env;

    TAILQ_FOREACH_SAFE(bp, &s->kvm_sw_breakpoints, entry, next) {
        if (kvm_arch_remove_sw_breakpoint(current_env, bp) != 0) {
            /* Try harder to find a CPU that currently sees the breakpoint. */
            for (env = first_cpu; env != NULL; env = env->next_cpu) {
                if (kvm_arch_remove_sw_breakpoint(env, bp) == 0)
                    break;
            }
        }
    }
    kvm_arch_remove_all_hw_breakpoints();

    for (env = first_cpu; env != NULL; env = env->next_cpu)
        kvm_update_guest_debug(env, 0);
}

#else /* !KVM_CAP_SET_GUEST_DEBUG */

int kvm_update_guest_debug(CPUState *env, unsigned long reinject_trap)
{
    return -EINVAL;
}

int kvm_insert_breakpoint(CPUState *current_env, target_ulong addr,
                          target_ulong len, int type)
{
    return -EINVAL;
}

int kvm_remove_breakpoint(CPUState *current_env, target_ulong addr,
                          target_ulong len, int type)
{
    return -EINVAL;
}

void kvm_remove_all_breakpoints(CPUState *current_env)
{
}
#endif /* !KVM_CAP_SET_GUEST_DEBUG */