ivshmem.c 22.7 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 20 21 22 23
 */
#include "hw.h"
#include "pc.h"
#include "pci.h"
#include "msix.h"
#include "kvm.h"
24 25
#include "migration.h"
#include "qerror.h"
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

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

#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

typedef struct Peer {
    int nb_eventfds;
    int *eventfds;
} Peer;

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

typedef struct IVShmemState {
    PCIDevice dev;
    uint32_t intrmask;
    uint32_t intrstatus;
    uint32_t doorbell;

    CharDriverState **eventfd_chr;
    CharDriverState *server_chr;
A
Avi Kivity 已提交
64
    MemoryRegion ivshmem_mmio;
65 66

    pcibus_t mmio_addr;
A
Avi Kivity 已提交
67 68 69 70 71 72
    /* 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;
A
Avi Kivity 已提交
73
    MemoryRegion msix_bar;
74 75 76 77 78 79 80 81 82 83 84 85
    uint64_t ivshmem_size; /* size of shared memory region */
    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;

86 87
    Error *migration_blocker;

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
    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)
{
    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);
    }

    qemu_set_irq(s->dev.irq[0], (isr != 0));
}

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);
    return;
}

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
166 167
static void ivshmem_io_write(void *opaque, target_phys_addr_t addr,
                             uint64_t val, unsigned size)
168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189
{
    IVShmemState *s = opaque;

    uint64_t write_one = 1;
    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 */
190
            if (dest > s->max_peer) {
191 192 193 194 195
                IVSHMEM_DPRINTF("Invalid destination VM ID (%d)\n", dest);
                break;
            }

            /* check doorbell range */
196
            if (vector < s->peers[dest].nb_eventfds) {
197 198 199 200 201 202 203 204 205 206 207 208 209
                IVSHMEM_DPRINTF("Writing %" PRId64 " to VM %d on vector %d\n",
                                                    write_one, dest, vector);
                if (write(s->peers[dest].eventfds[vector],
                                                    &(write_one), 8) != 8) {
                    IVSHMEM_DPRINTF("error writing to eventfd\n");
                }
            }
            break;
        default:
            IVSHMEM_DPRINTF("Invalid VM Doorbell VM %d\n", dest);
    }
}

A
Avi Kivity 已提交
210 211
static uint64_t ivshmem_io_read(void *opaque, target_phys_addr_t addr,
                                unsigned size)
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
{

    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
244 245 246 247 248 249 250 251
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,
    },
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
};

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);
}

static CharDriverState* create_eventfd_chr_device(void * opaque, int eventfd,
                                                                    int vector)
{
    /* create a event character device based on the passed eventfd */
    IVShmemState *s = opaque;
    CharDriverState * chr;

    chr = qemu_chr_open_eventfd(eventfd);

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

    /* if MSI is supported we need multiple interrupts */
    if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
        s->eventfd_table[vector].pdev = &s->dev;
        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
321 322 323 324
        fprintf(stderr,
                "IVSHMEM ERROR: Requested memory size greater"
                " than shared object size (%" PRIu64 " > %" PRIu64")\n",
                s->ivshmem_size, (uint64_t)buf.st_size);
325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340
        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);

341
    memory_region_init_ram_ptr(&s->ivshmem, "ivshmem.bar2",
A
Avi Kivity 已提交
342
                               s->ivshmem_size, ptr);
343
    vmstate_register_ram(&s->ivshmem, &s->dev.qdev);
A
Avi Kivity 已提交
344
    memory_region_add_subregion(&s->bar, 0, &s->ivshmem);
345 346

    /* region for shared memory */
347
    pci_register_bar(&s->dev, 2, PCI_BASE_ADDRESS_SPACE_MEMORY, &s->bar);
348 349 350 351 352 353 354 355 356
}

static void close_guest_eventfds(IVShmemState *s, int posn)
{
    int i, guest_curr_max;

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

    for (i = 0; i < guest_curr_max; i++) {
357 358
        kvm_set_ioeventfd_mmio(s->peers[posn].eventfds[i],
                    s->mmio_addr + DOORBELL, (posn << 16) | i, 0, 4);
359 360 361
        close(s->peers[posn].eventfds[i]);
    }

362
    g_free(s->peers[posn].eventfds);
363 364 365 366 367 368 369 370 371
    s->peers[posn].nb_eventfds = 0;
}

static void setup_ioeventfds(IVShmemState *s) {

    int i, j;

    for (i = 0; i <= s->max_peer; i++) {
        for (j = 0; j < s->peers[i].nb_eventfds; j++) {
A
Avi Kivity 已提交
372 373 374 375 376 377
            memory_region_add_eventfd(&s->ivshmem_mmio,
                                      DOORBELL,
                                      4,
                                      true,
                                      (i << 16) | j,
                                      s->peers[i].eventfds[j]);
378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393
        }
    }
}

/* 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);
394
    s->peers = g_realloc(s->peers, s->nb_peers * sizeof(Peer));
395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411

    /* 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 */
412
    tmp_fd = qemu_chr_fe_get_msgfd(s->server_chr);
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
    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);
458
        memory_region_init_ram_ptr(&s->ivshmem,
A
Avi Kivity 已提交
459
                                   "ivshmem.bar2", s->ivshmem_size, map_ptr);
460
        vmstate_register_ram(&s->ivshmem, &s->dev.qdev);
461

A
Avi Kivity 已提交
462
        IVSHMEM_DPRINTF("guest h/w addr = %" PRIu64 ", size = %" PRIu64 "\n",
463 464
                         s->ivshmem_offset, s->ivshmem_size);

A
Avi Kivity 已提交
465
        memory_region_add_subregion(&s->bar, 0, &s->ivshmem);
466 467 468 469 470 471 472 473 474 475 476 477 478

        /* 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 */
479
        s->peers[incoming_posn].eventfds = (int *) g_malloc(s->vectors *
480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502
                                                                sizeof(int));
    }

    /* this is an eventfd for a particular guest VM */
    IVSHMEM_DPRINTF("eventfds[%ld][%d] = %d\n", incoming_posn,
                                            guest_max_eventfd, incoming_fd);
    s->peers[incoming_posn].eventfds[guest_max_eventfd] = incoming_fd;

    /* 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,
                   s->peers[s->vm_id].eventfds[guest_max_eventfd],
                   guest_max_eventfd);
    }

    if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) {
503 504
        if (kvm_set_ioeventfd_mmio(incoming_fd, s->mmio_addr + DOORBELL,
                        (incoming_posn << 16) | guest_max_eventfd, 1, 4) < 0) {
505 506 507 508 509 510 511
            fprintf(stderr, "ivshmem: ioeventfd not available\n");
        }
    }

    return;
}

512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527
/* 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)
{
    int i;

    if (!msix_present(&s->dev)) {
        return;
    }

    for (i = 0; i < s->vectors; i++) {
        msix_vector_use(&s->dev, i);
    }
}

528 529 530 531 532
static void ivshmem_reset(DeviceState *d)
{
    IVShmemState *s = DO_UPCAST(IVShmemState, dev.qdev, d);

    s->intrstatus = 0;
533 534
    msix_reset(&s->dev);
    ivshmem_use_msix(s);
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
    return;
}

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;
}

565 566
static void ivshmem_setup_msi(IVShmemState * s)
{
A
Avi Kivity 已提交
567 568
    memory_region_init(&s->msix_bar, "ivshmem-msix", 4096);
    if (!msix_init(&s->dev, s->vectors, &s->msix_bar, 1, 0)) {
569 570
        pci_register_bar(&s->dev, 1, PCI_BASE_ADDRESS_SPACE_MEMORY,
                         &s->msix_bar);
571 572 573 574 575 576
        IVSHMEM_DPRINTF("msix initialized (%d vectors)\n", s->vectors);
    } else {
        IVSHMEM_DPRINTF("msix initialization failed\n");
        exit(1);
    }

S
Stefan Weil 已提交
577
    /* allocate QEMU char devices for receiving interrupts */
578
    s->eventfd_table = g_malloc0(s->vectors * sizeof(EventfdEntry));
579 580

    ivshmem_use_msix(s);
581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603
}

static void ivshmem_save(QEMUFile* f, void *opaque)
{
    IVShmemState *proxy = opaque;

    IVSHMEM_DPRINTF("ivshmem_save\n");
    pci_device_save(&proxy->dev, f);

    if (ivshmem_has_feature(proxy, IVSHMEM_MSI)) {
        msix_save(&proxy->dev, f);
    } 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;
604
    int ret;
605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621

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

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

    ret = pci_device_load(&proxy->dev, f);
    if (ret) {
        return ret;
    }

    if (ivshmem_has_feature(proxy, IVSHMEM_MSI)) {
        msix_load(&proxy->dev, f);
622
	ivshmem_use_msix(proxy);
623 624 625 626 627 628 629 630
    } else {
        proxy->intrstatus = qemu_get_be32(f);
        proxy->intrmask = qemu_get_be32(f);
    }

    return 0;
}

631 632 633 634 635 636 637
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);
}

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
static int pci_ivshmem_init(PCIDevice *dev)
{
    IVShmemState *s = DO_UPCAST(IVShmemState, dev, dev);
    uint8_t *pci_conf;

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

    register_savevm(&s->dev.qdev, "ivshmem", 0, 0, ivshmem_save, ivshmem_load,
                                                                        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) {
674 675
        error_set(&s->migration_blocker, QERR_DEVICE_FEATURE_BLOCKS_MIGRATION, "ivshmem", "peer mode");
        migrate_add_blocker(s->migration_blocker);
676 677 678 679 680 681 682 683 684
    }

    pci_conf = s->dev.config;
    pci_conf[PCI_COMMAND] = PCI_COMMAND_IO | PCI_COMMAND_MEMORY;

    pci_config_set_interrupt_pin(pci_conf, 1);

    s->shm_fd = 0;

A
Avi Kivity 已提交
685 686 687 688 689 690 691
    memory_region_init_io(&s->ivshmem_mmio, &ivshmem_mmio_ops, s,
                          "ivshmem-mmio", IVSHMEM_REG_BAR_SIZE);

    if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) {
        setup_ioeventfds(s);
    }

692
    /* region for registers*/
693 694
    pci_register_bar(&s->dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY,
                     &s->ivshmem_mmio);
A
Avi Kivity 已提交
695 696

    memory_region_init(&s->bar, "ivshmem-bar2-container", s->ivshmem_size);
697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719

    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 */
720
        s->peers = g_malloc0(s->nb_peers * sizeof(Peer));
721

722
        pci_register_bar(&s->dev, 2,
723
                         PCI_BASE_ADDRESS_SPACE_MEMORY, &s->bar);
724

725
        s->eventfd_chr = g_malloc0(s->vectors * sizeof(CharDriverState *));
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

        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");
        }

        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);

    }

763 764
    s->dev.config_write = ivshmem_write_config;

765 766 767 768 769 770 771
    return 0;
}

static int pci_ivshmem_uninit(PCIDevice *dev)
{
    IVShmemState *s = DO_UPCAST(IVShmemState, dev, dev);

772 773 774 775 776
    if (s->migration_blocker) {
        migrate_del_blocker(s->migration_blocker);
        error_free(s->migration_blocker);
    }

A
Avi Kivity 已提交
777 778
    memory_region_destroy(&s->ivshmem_mmio);
    memory_region_del_subregion(&s->bar, &s->ivshmem);
779
    vmstate_unregister_ram(&s->ivshmem, &s->dev.qdev);
A
Avi Kivity 已提交
780 781
    memory_region_destroy(&s->ivshmem);
    memory_region_destroy(&s->bar);
782 783 784 785 786
    unregister_savevm(&dev->qdev, "ivshmem", s);

    return 0;
}

787 788 789 790 791 792 793 794 795 796 797 798 799
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),
    DEFINE_PROP_END_OF_LIST(),
};

static void ivshmem_class_init(ObjectClass *klass, void *data)
{
800
    DeviceClass *dc = DEVICE_CLASS(klass);
801 802 803 804 805 806 807
    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);

    k->init = pci_ivshmem_init;
    k->exit = pci_ivshmem_uninit;
    k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET;
    k->device_id = 0x1110;
    k->class_id = PCI_CLASS_MEMORY_RAM;
808 809
    dc->reset = ivshmem_reset;
    dc->props = ivshmem_properties;
810 811
}

812 813 814 815 816
static TypeInfo ivshmem_info = {
    .name          = "ivshmem",
    .parent        = TYPE_PCI_DEVICE,
    .instance_size = sizeof(IVShmemState),
    .class_init    = ivshmem_class_init,
817 818
};

A
Andreas Färber 已提交
819
static void ivshmem_register_types(void)
820
{
821
    type_register_static(&ivshmem_info);
822 823
}

A
Andreas Färber 已提交
824
type_init(ivshmem_register_types)