ivshmem.c 23.0 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14
/*
 * Inter-VM Shared Memory PCI device.
 *
 * Author:
 *      Cam Macdonell <cam@cs.ualberta.ca>
 *
 * Based On: cirrus_vga.c
 *          Copyright (c) 2004 Fabrice Bellard
 *          Copyright (c) 2004 Makoto Suzuki (suzu)
 *
 *      and rtl8139.c
 *          Copyright (c) 2006 Igor Kovalenko
 *
 * This code is licensed under the GNU GPL v2.
15 16 17
 *
 * Contributions after 2012-01-13 are licensed under the terms of the
 * GNU GPL, version 2 or (at your option) any later version.
18
 */
19
#include "hw/hw.h"
P
Paolo Bonzini 已提交
20
#include "hw/i386/pc.h"
21 22
#include "hw/pci/pci.h"
#include "hw/pci/msix.h"
23
#include "sysemu/kvm.h"
24
#include "migration/migration.h"
25
#include "qapi/qmp/qerror.h"
26
#include "qemu/event_notifier.h"
27
#include "sysemu/char.h"
28 29 30 31

#include <sys/mman.h>
#include <sys/types.h>

32 33 34
#define PCI_VENDOR_ID_IVSHMEM   PCI_VENDOR_ID_REDHAT_QUMRANET
#define PCI_DEVICE_ID_IVSHMEM   0x1110

35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50
#define IVSHMEM_IOEVENTFD   0
#define IVSHMEM_MSI     1

#define IVSHMEM_PEER    0
#define IVSHMEM_MASTER  1

#define IVSHMEM_REG_BAR_SIZE 0x100

//#define DEBUG_IVSHMEM
#ifdef DEBUG_IVSHMEM
#define IVSHMEM_DPRINTF(fmt, ...)        \
    do {printf("IVSHMEM: " fmt, ## __VA_ARGS__); } while (0)
#else
#define IVSHMEM_DPRINTF(fmt, ...)
#endif

51 52 53 54
#define TYPE_IVSHMEM "ivshmem"
#define IVSHMEM(obj) \
    OBJECT_CHECK(IVShmemState, (obj), TYPE_IVSHMEM)

55 56
typedef struct Peer {
    int nb_eventfds;
57
    EventNotifier *eventfds;
58 59 60 61 62 63 64 65
} Peer;

typedef struct EventfdEntry {
    PCIDevice *pdev;
    int vector;
} EventfdEntry;

typedef struct IVShmemState {
66 67 68 69
    /*< private >*/
    PCIDevice parent_obj;
    /*< public >*/

70 71 72 73 74 75
    uint32_t intrmask;
    uint32_t intrstatus;
    uint32_t doorbell;

    CharDriverState **eventfd_chr;
    CharDriverState *server_chr;
A
Avi Kivity 已提交
76
    MemoryRegion ivshmem_mmio;
77

A
Avi Kivity 已提交
78 79 80 81 82 83
    /* We might need to register the BAR before we actually have the memory.
     * So prepare a container MemoryRegion for the BAR immediately and
     * add a subregion when we have the memory.
     */
    MemoryRegion bar;
    MemoryRegion ivshmem;
84
    uint64_t ivshmem_size; /* size of shared memory region */
G
Gerd Hoffmann 已提交
85 86
    uint32_t ivshmem_attr;
    uint32_t ivshmem_64bit;
87 88 89 90 91 92 93 94 95 96 97
    int shm_fd; /* shared memory file descriptor */

    Peer *peers;
    int nb_peers; /* how many guests we have space for */
    int max_peer; /* maximum numbered peer */

    int vm_id;
    uint32_t vectors;
    uint32_t features;
    EventfdEntry *eventfd_table;

98 99
    Error *migration_blocker;

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
    char * shmobj;
    char * sizearg;
    char * role;
    int role_val;   /* scalar to avoid multiple string comparisons */
} IVShmemState;

/* registers for the Inter-VM shared memory device */
enum ivshmem_registers {
    INTRMASK = 0,
    INTRSTATUS = 4,
    IVPOSITION = 8,
    DOORBELL = 12,
};

static inline uint32_t ivshmem_has_feature(IVShmemState *ivs,
                                                    unsigned int feature) {
    return (ivs->features & (1 << feature));
}

static inline bool is_power_of_two(uint64_t x) {
    return (x & (x - 1)) == 0;
}

/* accessing registers - based on rtl8139 */
static void ivshmem_update_irq(IVShmemState *s, int val)
{
126
    PCIDevice *d = PCI_DEVICE(s);
127 128 129 130 131 132 133 134 135
    int isr;
    isr = (s->intrstatus & s->intrmask) & 0xffffffff;

    /* don't print ISR resets */
    if (isr) {
        IVSHMEM_DPRINTF("Set IRQ to %d (%04x %04x)\n",
           isr ? 1 : 0, s->intrstatus, s->intrmask);
    }

136
    qemu_set_irq(d->irq[0], (isr != 0));
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
}

static void ivshmem_IntrMask_write(IVShmemState *s, uint32_t val)
{
    IVSHMEM_DPRINTF("IntrMask write(w) val = 0x%04x\n", val);

    s->intrmask = val;

    ivshmem_update_irq(s, val);
}

static uint32_t ivshmem_IntrMask_read(IVShmemState *s)
{
    uint32_t ret = s->intrmask;

    IVSHMEM_DPRINTF("intrmask read(w) val = 0x%04x\n", ret);

    return ret;
}

static void ivshmem_IntrStatus_write(IVShmemState *s, uint32_t val)
{
    IVSHMEM_DPRINTF("IntrStatus write(w) val = 0x%04x\n", val);

    s->intrstatus = val;

    ivshmem_update_irq(s, val);
}

static uint32_t ivshmem_IntrStatus_read(IVShmemState *s)
{
    uint32_t ret = s->intrstatus;

    /* reading ISR clears all interrupts */
    s->intrstatus = 0;

    ivshmem_update_irq(s, 0);

    return ret;
}

A
Avi Kivity 已提交
178
static void ivshmem_io_write(void *opaque, hwaddr addr,
A
Avi Kivity 已提交
179
                             uint64_t val, unsigned size)
180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200
{
    IVShmemState *s = opaque;

    uint16_t dest = val >> 16;
    uint16_t vector = val & 0xff;

    addr &= 0xfc;

    IVSHMEM_DPRINTF("writing to addr " TARGET_FMT_plx "\n", addr);
    switch (addr)
    {
        case INTRMASK:
            ivshmem_IntrMask_write(s, val);
            break;

        case INTRSTATUS:
            ivshmem_IntrStatus_write(s, val);
            break;

        case DOORBELL:
            /* check that dest VM ID is reasonable */
201
            if (dest > s->max_peer) {
202 203 204 205 206
                IVSHMEM_DPRINTF("Invalid destination VM ID (%d)\n", dest);
                break;
            }

            /* check doorbell range */
207
            if (vector < s->peers[dest].nb_eventfds) {
208 209
                IVSHMEM_DPRINTF("Notifying VM %d on vector %d\n", dest, vector);
                event_notifier_set(&s->peers[dest].eventfds[vector]);
210 211 212 213 214 215 216
            }
            break;
        default:
            IVSHMEM_DPRINTF("Invalid VM Doorbell VM %d\n", dest);
    }
}

A
Avi Kivity 已提交
217
static uint64_t ivshmem_io_read(void *opaque, hwaddr addr,
A
Avi Kivity 已提交
218
                                unsigned size)
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
{

    IVShmemState *s = opaque;
    uint32_t ret;

    switch (addr)
    {
        case INTRMASK:
            ret = ivshmem_IntrMask_read(s);
            break;

        case INTRSTATUS:
            ret = ivshmem_IntrStatus_read(s);
            break;

        case IVPOSITION:
            /* return my VM ID if the memory is mapped */
            if (s->shm_fd > 0) {
                ret = s->vm_id;
            } else {
                ret = -1;
            }
            break;

        default:
            IVSHMEM_DPRINTF("why are we reading " TARGET_FMT_plx "\n", addr);
            ret = 0;
    }

    return ret;
}

A
Avi Kivity 已提交
251 252 253 254 255 256 257 258
static const MemoryRegionOps ivshmem_mmio_ops = {
    .read = ivshmem_io_read,
    .write = ivshmem_io_write,
    .endianness = DEVICE_NATIVE_ENDIAN,
    .impl = {
        .min_access_size = 4,
        .max_access_size = 4,
    },
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
};

static void ivshmem_receive(void *opaque, const uint8_t *buf, int size)
{
    IVShmemState *s = opaque;

    ivshmem_IntrStatus_write(s, *buf);

    IVSHMEM_DPRINTF("ivshmem_receive 0x%02x\n", *buf);
}

static int ivshmem_can_receive(void * opaque)
{
    return 8;
}

static void ivshmem_event(void *opaque, int event)
{
    IVSHMEM_DPRINTF("ivshmem_event %d\n", event);
}

static void fake_irqfd(void *opaque, const uint8_t *buf, int size) {

    EventfdEntry *entry = opaque;
    PCIDevice *pdev = entry->pdev;

    IVSHMEM_DPRINTF("interrupt on vector %p %d\n", pdev, entry->vector);
    msix_notify(pdev, entry->vector);
}

289 290
static CharDriverState* create_eventfd_chr_device(void * opaque, EventNotifier *n,
                                                  int vector)
291 292 293 294
{
    /* create a event character device based on the passed eventfd */
    IVShmemState *s = opaque;
    CharDriverState * chr;
295
    int eventfd = event_notifier_get_fd(n);
296 297 298 299 300 301 302

    chr = qemu_chr_open_eventfd(eventfd);

    if (chr == NULL) {
        fprintf(stderr, "creating eventfd for eventfd %d failed\n", eventfd);
        exit(-1);
    }
303
    qemu_chr_fe_claim_no_fail(chr);
304 305 306

    /* if MSI is supported we need multiple interrupts */
    if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
307
        s->eventfd_table[vector].pdev = PCI_DEVICE(s);
308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329
        s->eventfd_table[vector].vector = vector;

        qemu_chr_add_handlers(chr, ivshmem_can_receive, fake_irqfd,
                      ivshmem_event, &s->eventfd_table[vector]);
    } else {
        qemu_chr_add_handlers(chr, ivshmem_can_receive, ivshmem_receive,
                      ivshmem_event, s);
    }

    return chr;

}

static int check_shm_size(IVShmemState *s, int fd) {
    /* check that the guest isn't going to try and map more memory than the
     * the object has allocated return -1 to indicate error */

    struct stat buf;

    fstat(fd, &buf);

    if (s->ivshmem_size > buf.st_size) {
A
Avi Kivity 已提交
330 331 332 333
        fprintf(stderr,
                "IVSHMEM ERROR: Requested memory size greater"
                " than shared object size (%" PRIu64 " > %" PRIu64")\n",
                s->ivshmem_size, (uint64_t)buf.st_size);
334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349
        return -1;
    } else {
        return 0;
    }
}

/* create the shared memory BAR when we are not using the server, so we can
 * create the BAR and map the memory immediately */
static void create_shared_memory_BAR(IVShmemState *s, int fd) {

    void * ptr;

    s->shm_fd = fd;

    ptr = mmap(0, s->ivshmem_size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);

350
    memory_region_init_ram_ptr(&s->ivshmem, OBJECT(s), "ivshmem.bar2",
A
Avi Kivity 已提交
351
                               s->ivshmem_size, ptr);
352
    vmstate_register_ram(&s->ivshmem, DEVICE(s));
A
Avi Kivity 已提交
353
    memory_region_add_subregion(&s->bar, 0, &s->ivshmem);
354 355

    /* region for shared memory */
356
    pci_register_bar(PCI_DEVICE(s), 2, s->ivshmem_attr, &s->bar);
357 358
}

359 360 361 362 363 364 365
static void ivshmem_add_eventfd(IVShmemState *s, int posn, int i)
{
    memory_region_add_eventfd(&s->ivshmem_mmio,
                              DOORBELL,
                              4,
                              true,
                              (posn << 16) | i,
366
                              &s->peers[posn].eventfds[i]);
367 368 369 370 371 372 373 374 375
}

static void ivshmem_del_eventfd(IVShmemState *s, int posn, int i)
{
    memory_region_del_eventfd(&s->ivshmem_mmio,
                              DOORBELL,
                              4,
                              true,
                              (posn << 16) | i,
376
                              &s->peers[posn].eventfds[i]);
377 378
}

379 380 381 382
static void close_guest_eventfds(IVShmemState *s, int posn)
{
    int i, guest_curr_max;

383 384 385 386
    if (!ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) {
        return;
    }

387 388
    guest_curr_max = s->peers[posn].nb_eventfds;

389
    memory_region_transaction_begin();
390
    for (i = 0; i < guest_curr_max; i++) {
391
        ivshmem_del_eventfd(s, posn, i);
392 393 394
    }
    memory_region_transaction_commit();
    for (i = 0; i < guest_curr_max; i++) {
395
        event_notifier_cleanup(&s->peers[posn].eventfds[i]);
396 397
    }

398
    g_free(s->peers[posn].eventfds);
399 400 401 402 403 404 405 406 407 408 409 410 411 412 413
    s->peers[posn].nb_eventfds = 0;
}

/* this function increase the dynamic storage need to store data about other
 * guests */
static void increase_dynamic_storage(IVShmemState *s, int new_min_size) {

    int j, old_nb_alloc;

    old_nb_alloc = s->nb_peers;

    while (new_min_size >= s->nb_peers)
        s->nb_peers = s->nb_peers * 2;

    IVSHMEM_DPRINTF("bumping storage to %d guests\n", s->nb_peers);
414
    s->peers = g_realloc(s->peers, s->nb_peers * sizeof(Peer));
415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431

    /* zero out new pointers */
    for (j = old_nb_alloc; j < s->nb_peers; j++) {
        s->peers[j].eventfds = NULL;
        s->peers[j].nb_eventfds = 0;
    }
}

static void ivshmem_read(void *opaque, const uint8_t * buf, int flags)
{
    IVShmemState *s = opaque;
    int incoming_fd, tmp_fd;
    int guest_max_eventfd;
    long incoming_posn;

    memcpy(&incoming_posn, buf, sizeof(long));
    /* pick off s->server_chr->msgfd and store it, posn should accompany msg */
432
    tmp_fd = qemu_chr_fe_get_msgfd(s->server_chr);
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
    IVSHMEM_DPRINTF("posn is %ld, fd is %d\n", incoming_posn, tmp_fd);

    /* make sure we have enough space for this guest */
    if (incoming_posn >= s->nb_peers) {
        increase_dynamic_storage(s, incoming_posn);
    }

    if (tmp_fd == -1) {
        /* if posn is positive and unseen before then this is our posn*/
        if ((incoming_posn >= 0) &&
                            (s->peers[incoming_posn].eventfds == NULL)) {
            /* receive our posn */
            s->vm_id = incoming_posn;
            return;
        } else {
            /* otherwise an fd == -1 means an existing guest has gone away */
            IVSHMEM_DPRINTF("posn %ld has gone away\n", incoming_posn);
            close_guest_eventfds(s, incoming_posn);
            return;
        }
    }

    /* because of the implementation of get_msgfd, we need a dup */
    incoming_fd = dup(tmp_fd);

    if (incoming_fd == -1) {
        fprintf(stderr, "could not allocate file descriptor %s\n",
                                                            strerror(errno));
        return;
    }

    /* if the position is -1, then it's shared memory region fd */
    if (incoming_posn == -1) {

        void * map_ptr;

        s->max_peer = 0;

        if (check_shm_size(s, incoming_fd) == -1) {
            exit(-1);
        }

        /* mmap the region and map into the BAR2 */
        map_ptr = mmap(0, s->ivshmem_size, PROT_READ|PROT_WRITE, MAP_SHARED,
                                                            incoming_fd, 0);
478
        memory_region_init_ram_ptr(&s->ivshmem, OBJECT(s),
A
Avi Kivity 已提交
479
                                   "ivshmem.bar2", s->ivshmem_size, map_ptr);
480
        vmstate_register_ram(&s->ivshmem, DEVICE(s));
481

A
Avi Kivity 已提交
482
        IVSHMEM_DPRINTF("guest h/w addr = %" PRIu64 ", size = %" PRIu64 "\n",
483 484
                         s->ivshmem_offset, s->ivshmem_size);

A
Avi Kivity 已提交
485
        memory_region_add_subregion(&s->bar, 0, &s->ivshmem);
486 487 488 489 490 491 492 493 494 495 496 497 498

        /* only store the fd if it is successfully mapped */
        s->shm_fd = incoming_fd;

        return;
    }

    /* each guest has an array of eventfds, and we keep track of how many
     * guests for each VM */
    guest_max_eventfd = s->peers[incoming_posn].nb_eventfds;

    if (guest_max_eventfd == 0) {
        /* one eventfd per MSI vector */
499
        s->peers[incoming_posn].eventfds = g_new(EventNotifier, s->vectors);
500 501 502 503 504
    }

    /* this is an eventfd for a particular guest VM */
    IVSHMEM_DPRINTF("eventfds[%ld][%d] = %d\n", incoming_posn,
                                            guest_max_eventfd, incoming_fd);
505 506
    event_notifier_init_fd(&s->peers[incoming_posn].eventfds[guest_max_eventfd],
                           incoming_fd);
507 508 509 510 511 512 513 514 515 516 517

    /* increment count for particular guest */
    s->peers[incoming_posn].nb_eventfds++;

    /* keep track of the maximum VM ID */
    if (incoming_posn > s->max_peer) {
        s->max_peer = incoming_posn;
    }

    if (incoming_posn == s->vm_id) {
        s->eventfd_chr[guest_max_eventfd] = create_eventfd_chr_device(s,
518
                   &s->peers[s->vm_id].eventfds[guest_max_eventfd],
519 520 521 522
                   guest_max_eventfd);
    }

    if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) {
523
        ivshmem_add_eventfd(s, incoming_posn, guest_max_eventfd);
524 525 526
    }
}

527 528 529 530 531
/* Select the MSI-X vectors used by device.
 * ivshmem maps events to vectors statically, so
 * we just enable all vectors on init and after reset. */
static void ivshmem_use_msix(IVShmemState * s)
{
532
    PCIDevice *d = PCI_DEVICE(s);
533 534
    int i;

535
    if (!msix_present(d)) {
536 537 538 539
        return;
    }

    for (i = 0; i < s->vectors; i++) {
540
        msix_vector_use(d, i);
541 542 543
    }
}

544 545
static void ivshmem_reset(DeviceState *d)
{
546
    IVShmemState *s = IVSHMEM(d);
547 548

    s->intrstatus = 0;
549
    ivshmem_use_msix(s);
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
}

static uint64_t ivshmem_get_size(IVShmemState * s) {

    uint64_t value;
    char *ptr;

    value = strtoull(s->sizearg, &ptr, 10);
    switch (*ptr) {
        case 0: case 'M': case 'm':
            value <<= 20;
            break;
        case 'G': case 'g':
            value <<= 30;
            break;
        default:
            fprintf(stderr, "qemu: invalid ram size: %s\n", s->sizearg);
            exit(1);
    }

    /* BARs must be a power of 2 */
    if (!is_power_of_two(value)) {
        fprintf(stderr, "ivshmem: size must be power of 2\n");
        exit(1);
    }

    return value;
}

579 580
static void ivshmem_setup_msi(IVShmemState * s)
{
581
    if (msix_init_exclusive_bar(PCI_DEVICE(s), s->vectors, 1)) {
582 583 584 585
        IVSHMEM_DPRINTF("msix initialization failed\n");
        exit(1);
    }

586 587
    IVSHMEM_DPRINTF("msix initialized (%d vectors)\n", s->vectors);

S
Stefan Weil 已提交
588
    /* allocate QEMU char devices for receiving interrupts */
589
    s->eventfd_table = g_malloc0(s->vectors * sizeof(EventfdEntry));
590 591

    ivshmem_use_msix(s);
592 593 594 595 596
}

static void ivshmem_save(QEMUFile* f, void *opaque)
{
    IVShmemState *proxy = opaque;
597
    PCIDevice *pci_dev = PCI_DEVICE(proxy);
598 599

    IVSHMEM_DPRINTF("ivshmem_save\n");
600
    pci_device_save(pci_dev, f);
601 602

    if (ivshmem_has_feature(proxy, IVSHMEM_MSI)) {
603
        msix_save(pci_dev, f);
604 605 606 607 608 609 610 611 612 613 614 615
    } else {
        qemu_put_be32(f, proxy->intrstatus);
        qemu_put_be32(f, proxy->intrmask);
    }

}

static int ivshmem_load(QEMUFile* f, void *opaque, int version_id)
{
    IVSHMEM_DPRINTF("ivshmem_load\n");

    IVShmemState *proxy = opaque;
616
    PCIDevice *pci_dev = PCI_DEVICE(proxy);
617
    int ret;
618 619 620 621 622 623 624 625 626 627

    if (version_id > 0) {
        return -EINVAL;
    }

    if (proxy->role_val == IVSHMEM_PEER) {
        fprintf(stderr, "ivshmem: 'peer' devices are not migratable\n");
        return -EINVAL;
    }

628
    ret = pci_device_load(pci_dev, f);
629 630 631 632 633
    if (ret) {
        return ret;
    }

    if (ivshmem_has_feature(proxy, IVSHMEM_MSI)) {
634
        msix_load(pci_dev, f);
635
	ivshmem_use_msix(proxy);
636 637 638 639 640 641 642 643
    } else {
        proxy->intrstatus = qemu_get_be32(f);
        proxy->intrmask = qemu_get_be32(f);
    }

    return 0;
}

644 645 646 647 648 649 650
static void ivshmem_write_config(PCIDevice *pci_dev, uint32_t address,
				 uint32_t val, int len)
{
    pci_default_write_config(pci_dev, address, val, len);
    msix_write_config(pci_dev, address, val, len);
}

651 652
static int pci_ivshmem_init(PCIDevice *dev)
{
653
    IVShmemState *s = IVSHMEM(dev);
654 655 656 657 658 659 660 661
    uint8_t *pci_conf;

    if (s->sizearg == NULL)
        s->ivshmem_size = 4 << 20; /* 4 MB default */
    else {
        s->ivshmem_size = ivshmem_get_size(s);
    }

662
    register_savevm(DEVICE(dev), "ivshmem", 0, 0, ivshmem_save, ivshmem_load,
663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686
                                                                        dev);

    /* IRQFD requires MSI */
    if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD) &&
        !ivshmem_has_feature(s, IVSHMEM_MSI)) {
        fprintf(stderr, "ivshmem: ioeventfd/irqfd requires MSI\n");
        exit(1);
    }

    /* check that role is reasonable */
    if (s->role) {
        if (strncmp(s->role, "peer", 5) == 0) {
            s->role_val = IVSHMEM_PEER;
        } else if (strncmp(s->role, "master", 7) == 0) {
            s->role_val = IVSHMEM_MASTER;
        } else {
            fprintf(stderr, "ivshmem: 'role' must be 'peer' or 'master'\n");
            exit(1);
        }
    } else {
        s->role_val = IVSHMEM_MASTER; /* default */
    }

    if (s->role_val == IVSHMEM_PEER) {
687 688
        error_set(&s->migration_blocker, QERR_DEVICE_FEATURE_BLOCKS_MIGRATION,
                  "peer mode", "ivshmem");
689
        migrate_add_blocker(s->migration_blocker);
690 691
    }

692
    pci_conf = dev->config;
693 694 695 696 697 698
    pci_conf[PCI_COMMAND] = PCI_COMMAND_IO | PCI_COMMAND_MEMORY;

    pci_config_set_interrupt_pin(pci_conf, 1);

    s->shm_fd = 0;

699
    memory_region_init_io(&s->ivshmem_mmio, OBJECT(s), &ivshmem_mmio_ops, s,
A
Avi Kivity 已提交
700 701
                          "ivshmem-mmio", IVSHMEM_REG_BAR_SIZE);

702
    /* region for registers*/
703
    pci_register_bar(dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY,
704
                     &s->ivshmem_mmio);
A
Avi Kivity 已提交
705

706
    memory_region_init(&s->bar, OBJECT(s), "ivshmem-bar2-container", s->ivshmem_size);
G
Gerd Hoffmann 已提交
707 708 709 710 711
    s->ivshmem_attr = PCI_BASE_ADDRESS_SPACE_MEMORY |
        PCI_BASE_ADDRESS_MEM_PREFETCH;
    if (s->ivshmem_64bit) {
        s->ivshmem_attr |= PCI_BASE_ADDRESS_MEM_TYPE_64;
    }
712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734

    if ((s->server_chr != NULL) &&
                        (strncmp(s->server_chr->filename, "unix:", 5) == 0)) {
        /* if we get a UNIX socket as the parameter we will talk
         * to the ivshmem server to receive the memory region */

        if (s->shmobj != NULL) {
            fprintf(stderr, "WARNING: do not specify both 'chardev' "
                                                "and 'shm' with ivshmem\n");
        }

        IVSHMEM_DPRINTF("using shared memory server (socket = %s)\n",
                                                    s->server_chr->filename);

        if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
            ivshmem_setup_msi(s);
        }

        /* we allocate enough space for 16 guests and grow as needed */
        s->nb_peers = 16;
        s->vm_id = -1;

        /* allocate/initialize space for interrupt handling */
735
        s->peers = g_malloc0(s->nb_peers * sizeof(Peer));
736

737
        pci_register_bar(dev, 2, s->ivshmem_attr, &s->bar);
738

739
        s->eventfd_chr = g_malloc0(s->vectors * sizeof(CharDriverState *));
740 741 742 743 744 745 746 747 748

        qemu_chr_add_handlers(s->server_chr, ivshmem_can_receive, ivshmem_read,
                     ivshmem_event, s);
    } else {
        /* just map the file immediately, we're not using a server */
        int fd;

        if (s->shmobj == NULL) {
            fprintf(stderr, "Must specify 'chardev' or 'shm' to ivshmem\n");
749
            exit(1);
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
        }

        IVSHMEM_DPRINTF("using shm_open (shm object = %s)\n", s->shmobj);

        /* try opening with O_EXCL and if it succeeds zero the memory
         * by truncating to 0 */
        if ((fd = shm_open(s->shmobj, O_CREAT|O_RDWR|O_EXCL,
                        S_IRWXU|S_IRWXG|S_IRWXO)) > 0) {
           /* truncate file to length PCI device's memory */
            if (ftruncate(fd, s->ivshmem_size) != 0) {
                fprintf(stderr, "ivshmem: could not truncate shared file\n");
            }

        } else if ((fd = shm_open(s->shmobj, O_CREAT|O_RDWR,
                        S_IRWXU|S_IRWXG|S_IRWXO)) < 0) {
            fprintf(stderr, "ivshmem: could not open shared file\n");
            exit(-1);

        }

        if (check_shm_size(s, fd) == -1) {
            exit(-1);
        }

        create_shared_memory_BAR(s, fd);

    }

778
    dev->config_write = ivshmem_write_config;
779

780 781 782
    return 0;
}

783
static void pci_ivshmem_uninit(PCIDevice *dev)
784
{
785
    IVShmemState *s = IVSHMEM(dev);
786

787 788 789 790 791
    if (s->migration_blocker) {
        migrate_del_blocker(s->migration_blocker);
        error_free(s->migration_blocker);
    }

A
Avi Kivity 已提交
792 793
    memory_region_destroy(&s->ivshmem_mmio);
    memory_region_del_subregion(&s->bar, &s->ivshmem);
794
    vmstate_unregister_ram(&s->ivshmem, DEVICE(dev));
A
Avi Kivity 已提交
795 796
    memory_region_destroy(&s->ivshmem);
    memory_region_destroy(&s->bar);
797
    unregister_savevm(DEVICE(dev), "ivshmem", s);
798 799
}

800 801 802 803 804 805 806 807
static Property ivshmem_properties[] = {
    DEFINE_PROP_CHR("chardev", IVShmemState, server_chr),
    DEFINE_PROP_STRING("size", IVShmemState, sizearg),
    DEFINE_PROP_UINT32("vectors", IVShmemState, vectors, 1),
    DEFINE_PROP_BIT("ioeventfd", IVShmemState, features, IVSHMEM_IOEVENTFD, false),
    DEFINE_PROP_BIT("msi", IVShmemState, features, IVSHMEM_MSI, true),
    DEFINE_PROP_STRING("shm", IVShmemState, shmobj),
    DEFINE_PROP_STRING("role", IVShmemState, role),
G
Gerd Hoffmann 已提交
808
    DEFINE_PROP_UINT32("use64", IVShmemState, ivshmem_64bit, 1),
809 810 811 812 813
    DEFINE_PROP_END_OF_LIST(),
};

static void ivshmem_class_init(ObjectClass *klass, void *data)
{
814
    DeviceClass *dc = DEVICE_CLASS(klass);
815 816 817 818
    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);

    k->init = pci_ivshmem_init;
    k->exit = pci_ivshmem_uninit;
819 820
    k->vendor_id = PCI_VENDOR_ID_IVSHMEM;
    k->device_id = PCI_DEVICE_ID_IVSHMEM;
821
    k->class_id = PCI_CLASS_MEMORY_RAM;
822 823
    dc->reset = ivshmem_reset;
    dc->props = ivshmem_properties;
824 825
}

826
static const TypeInfo ivshmem_info = {
827
    .name          = TYPE_IVSHMEM,
828 829 830
    .parent        = TYPE_PCI_DEVICE,
    .instance_size = sizeof(IVShmemState),
    .class_init    = ivshmem_class_init,
831 832
};

A
Andreas Färber 已提交
833
static void ivshmem_register_types(void)
834
{
835
    type_register_static(&ivshmem_info);
836 837
}

A
Andreas Färber 已提交
838
type_init(ivshmem_register_types)