aboutsummaryrefslogtreecommitdiff
path: root/kvm-all.c
blob: 0b1742709b82b09fedaa2c8177e6315c30d3babb (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
/*
 * QEMU KVM support
 *
 * Copyright IBM, Corp. 2008
 *           Red Hat, Inc. 2008
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
 *  Glauber Costa     <gcosta@redhat.com>
 *
 * 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>
#include <stdarg.h>

#include <linux/kvm.h>

#include "qemu-common.h"
#include "sysemu.h"
#include "kvm.h"

/* KVM uses PAGE_SIZE in it's definition of COALESCED_MMIO_MAX */
#define PAGE_SIZE TARGET_PAGE_SIZE

//#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

typedef struct KVMSlot
{
    target_phys_addr_t start_addr;
    ram_addr_t memory_size;
    ram_addr_t phys_offset;
    int slot;
    int flags;
} KVMSlot;

typedef struct kvm_dirty_log KVMDirtyLog;

int kvm_allowed = 0;

struct KVMState
{
    KVMSlot slots[32];
    int fd;
    int vmfd;
    int coalesced_mmio;
};

static KVMState *kvm_state;

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

    for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
        /* KVM private memory slots */
        if (i >= 8 && i < 12)
            continue;
        if (s->slots[i].memory_size == 0)
            return &s->slots[i];
    }

    return NULL;
}

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

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

        if (start_addr >= mem->start_addr &&
            start_addr < (mem->start_addr + mem->memory_size))
            return mem;
    }

    return NULL;
}

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;
    mem.userspace_addr = (unsigned long)phys_ram_base + slot->phys_offset;
    mem.flags = slot->flags;

    return kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
}


int kvm_init_vcpu(CPUState *env)
{
    KVMState *s = kvm_state;
    long mmap_size;
    int ret;

    dprintf("kvm_init_vcpu\n");

    ret = kvm_vm_ioctl(s, KVM_CREATE_VCPU, env->cpu_index);
    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;
}

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;
}

/*
 * dirty pages logging control
 */
static int kvm_dirty_pages_log_change(target_phys_addr_t phys_addr, target_phys_addr_t end_addr,
                                      unsigned flags,
                                      unsigned mask)
{
    KVMState *s = kvm_state;
    KVMSlot *mem = kvm_lookup_slot(s, phys_addr);
    if (mem == NULL)  {
            dprintf("invalid parameters %llx-%llx\n", phys_addr, end_addr);
            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);
}

int kvm_log_start(target_phys_addr_t phys_addr, target_phys_addr_t end_addr)
{
        return kvm_dirty_pages_log_change(phys_addr, end_addr,
                                          KVM_MEM_LOG_DIRTY_PAGES,
                                          KVM_MEM_LOG_DIRTY_PAGES);
}

int kvm_log_stop(target_phys_addr_t phys_addr, target_phys_addr_t end_addr)
{
        return kvm_dirty_pages_log_change(phys_addr, end_addr,
                                          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.
 *
 * @start_add: start of logged region. This is what we use to search the memslot
 * @end_addr: end of logged region.
 */
void kvm_physical_sync_dirty_bitmap(target_phys_addr_t start_addr, target_phys_addr_t end_addr)
{
    KVMState *s = kvm_state;
    KVMDirtyLog d;
    KVMSlot *mem = kvm_lookup_slot(s, start_addr);
    unsigned long alloc_size;
    ram_addr_t addr;
    target_phys_addr_t phys_addr = start_addr;

    dprintf("sync addr: %llx into %lx\n", start_addr, mem->phys_offset);
    if (mem == NULL) {
            fprintf(stderr, "BUG: %s: invalid parameters\n", __func__);
            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);
}

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;
}

int kvm_init(int smp_cpus)
{
    KVMState *s;
    int ret;
    int i;

    if (smp_cpus > 1)
        return -EINVAL;

    s = qemu_mallocz(sizeof(KVMState));

    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
     * just use a user allocated buffer so we can use phys_ram_base
     * unmodified.  Make sure we have a sufficiently modern version of KVM.
     */
    ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_USER_MEMORY);
    if (ret <= 0) {
        if (ret == 0)
            ret = -EINVAL;
        fprintf(stderr, "kvm does not support KVM_CAP_USER_MEMORY\n");
        goto err;
    }

    /* 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. */
    ret = kvm_ioctl(s, KVM_CHECK_EXTENSION,
                    KVM_CAP_DESTROY_MEMORY_REGION_WORKS);
    if (ret <= 0) {
        if (ret == 0)
            ret = -EINVAL;

        fprintf(stderr,
                "KVM kernel module broken (DESTROY_MEMORY_REGION)\n"
                "Please upgrade to at least kvm-81.\n");
        goto err;
    }

    s->coalesced_mmio = 0;
#ifdef KVM_CAP_COALESCED_MMIO
    ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_COALESCED_MMIO);
    if (ret > 0)
        s->coalesced_mmio = ret;
#endif

    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;
}

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
}

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);

        if ((env->interrupt_request & CPU_INTERRUPT_EXIT)) {
            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();
        }

        kvm_run_coalesced_mmio(env, run);

        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");
            break;
        default:
            dprintf("kvm_arch_handle_exit\n");
            ret = kvm_arch_handle_exit(env, run);
            break;
        }
    } while (ret > 0);

    if ((env->interrupt_request & CPU_INTERRUPT_EXIT)) {
        env->interrupt_request &= ~CPU_INTERRUPT_EXIT;
        env->exception_index = EXCP_INTERRUPT;
    }

    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;
    KVMSlot *mem;

    /* KVM does not support read-only slots */
    phys_offset &= ~IO_MEM_ROM;

    mem = kvm_lookup_slot(s, start_addr);
    if (mem) {
        if ((flags == IO_MEM_UNASSIGNED) || (flags >= TLB_MMIO)) {
            mem->memory_size = 0;
            mem->start_addr = start_addr;
            mem->phys_offset = 0;
            mem->flags = 0;

            kvm_set_user_memory_region(s, mem);
        } else if (start_addr >= mem->start_addr &&
                   (start_addr + size) <= (mem->start_addr +
                                           mem->memory_size)) {
            KVMSlot slot;
            target_phys_addr_t mem_start;
            ram_addr_t mem_size, mem_offset;

            /* Not splitting */
            if ((phys_offset - (start_addr - mem->start_addr)) == 
                mem->phys_offset)
                return;

            /* unregister whole slot */
            memcpy(&slot, mem, sizeof(slot));
            mem->memory_size = 0;
            kvm_set_user_memory_region(s, mem);

            /* register prefix slot */
            mem_start = slot.start_addr;
            mem_size = start_addr - slot.start_addr;
            mem_offset = slot.phys_offset;
            if (mem_size)
                kvm_set_phys_mem(mem_start, mem_size, mem_offset);

            /* register new slot */
            kvm_set_phys_mem(start_addr, size, phys_offset);

            /* register suffix slot */
            mem_start = start_addr + size;
            mem_offset += mem_size + size;
            mem_size = slot.memory_size - mem_size - size;
            if (mem_size)
                kvm_set_phys_mem(mem_start, mem_size, mem_offset);

            return;
        } else {
            printf("Registering overlapping slot\n");
            abort();
        }
    }
    /* KVM does not need to know about this memory */
    if (flags >= IO_MEM_UNASSIGNED)
        return;

    mem = kvm_alloc_slot(s);
    mem->memory_size = size;
    mem->start_addr = start_addr;
    mem->phys_offset = phys_offset;
    mem->flags = 0;

    kvm_set_user_memory_region(s, mem);
    /* FIXME deal with errors */
}

int kvm_ioctl(KVMState *s, int type, ...)
{
    int ret;
    void *arg;
    va_list ap;

    va_start(ap, type);
    arg = va_arg(ap, void *);
    va_end(ap);

    ret = ioctl(s->fd, type, arg);
    if (ret == -1)
        ret = -errno;

    return ret;
}

int kvm_vm_ioctl(KVMState *s, int type, ...)
{
    int ret;
    void *arg;
    va_list ap;

    va_start(ap, type);
    arg = va_arg(ap, void *);
    va_end(ap);

    ret = ioctl(s->vmfd, type, arg);
    if (ret == -1)
        ret = -errno;

    return ret;
}

int kvm_vcpu_ioctl(CPUState *env, int type, ...)
{
    int ret;
    void *arg;
    va_list ap;

    va_start(ap, type);
    arg = va_arg(ap, void *);
    va_end(ap);

    ret = ioctl(env->kvm_fd, type, arg);
    if (ret == -1)
        ret = -errno;

    return ret;
}

int kvm_has_sync_mmu(void)
{
#ifdef KVM_CAP_SYNC_MMU
    KVMState *s = kvm_state;

    if (kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_SYNC_MMU) > 0)
        return 1;
#endif

    return 0;
}