static void process_msg(IVShmemState *s, int64_t msg, int fd, Error **errp)
{
IVSHMEM_DPRINTF("posn is %" PRId64 ", fd is %d\n", msg, fd);
if (msg < -1 || msg > IVSHMEM_MAX_PEERS) {
error_setg(errp, "server sent invalid message %" PRId64, msg);
close(fd);
return;
}
if (msg == -1) {
process_msg_shmem(s, fd, errp);
return;
}
if (msg >= s->nb_peers) {
resize_peers(s, msg + 1);
}
if (fd >= 0) {
process_msg_connect(s, msg, fd, errp);
} else {
process_msg_disconnect(s, msg, errp);
}
}
static void ivshmem_common_realize(PCIDevice *dev, Error **errp)
{
IVShmemState *s = IVSHMEM_COMMON(dev);
Error *err = NULL;
uint8_t *pci_conf;
uint8_t attr = PCI_BASE_ADDRESS_SPACE_MEMORY |
PCI_BASE_ADDRESS_MEM_PREFETCH;
/* IRQFD requires MSI */
if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD) &&
!ivshmem_has_feature(s, IVSHMEM_MSI)) {
error_setg(errp, "ioeventfd/irqfd requires MSI");
return;
}
pci_conf = dev->config;
pci_conf[PCI_COMMAND] = PCI_COMMAND_IO | PCI_COMMAND_MEMORY;
memory_region_init_io(&s->ivshmem_mmio, OBJECT(s), &ivshmem_mmio_ops, s,
"ivshmem-mmio", IVSHMEM_REG_BAR_SIZE);
/* region for registers*/
pci_register_bar(dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY,
&s->ivshmem_mmio);
if (!s->not_legacy_32bit) {
attr |= PCI_BASE_ADDRESS_MEM_TYPE_64;
}
if (s->hostmem != NULL) {
IVSHMEM_DPRINTF("using hostmem\n");
s->ivshmem_bar2 = host_memory_backend_get_memory(s->hostmem,
&error_abort);
} else {
assert(s->server_chr);
IVSHMEM_DPRINTF("using shared memory server (socket = %s)\n",
s->server_chr->filename);
/* we allocate enough space for 16 peers and grow as needed */
resize_peers(s, 16);
/*
* Receive setup messages from server synchronously.
* Older versions did it asynchronously, but that creates a
* number of entertaining race conditions.
*/
ivshmem_recv_setup(s, &err);
if (err) {
error_propagate(errp, err);
return;
}
if (s->master == ON_OFF_AUTO_ON && s->vm_id != 0) {
error_setg(errp,
"master must connect to the server before any peers");
return;
}
qemu_chr_add_handlers(s->server_chr, ivshmem_can_receive,
ivshmem_read, NULL, s);
if (ivshmem_setup_interrupts(s) < 0) {
error_setg(errp, "failed to initialize interrupts");
return;
}
}
vmstate_register_ram(s->ivshmem_bar2, DEVICE(s));
pci_register_bar(PCI_DEVICE(s), 2, attr, s->ivshmem_bar2);
if (s->master == ON_OFF_AUTO_AUTO) {
s->master = s->vm_id == 0 ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF;
}
if (!ivshmem_is_master(s)) {
error_setg(&s->migration_blocker,
"Migration is disabled when using feature 'peer mode' in device 'ivshmem'");
migrate_add_blocker(s->migration_blocker);
}
}
static void pci_ivshmem_realize(PCIDevice *dev, Error **errp)
{
IVShmemState *s = IVSHMEM(dev);
uint8_t *pci_conf;
uint8_t attr = PCI_BASE_ADDRESS_SPACE_MEMORY |
PCI_BASE_ADDRESS_MEM_PREFETCH;
if (!!s->server_chr + !!s->shmobj + !!s->hostmem != 1) {
error_setg(errp,
"You must specify either 'shm', 'chardev' or 'x-memdev'");
return;
}
if (s->hostmem) {
MemoryRegion *mr;
if (s->sizearg) {
g_warning("size argument ignored with hostmem");
}
mr = host_memory_backend_get_memory(s->hostmem, errp);
s->ivshmem_size = memory_region_size(mr);
} else if (s->sizearg == NULL) {
s->ivshmem_size = 4 << 20; /* 4 MB default */
} else {
char *end;
int64_t size = qemu_strtosz(s->sizearg, &end);
if (size < 0 || *end != '\0' || !is_power_of_2(size)) {
error_setg(errp, "Invalid size %s", s->sizearg);
return;
}
s->ivshmem_size = size;
}
fifo8_create(&s->incoming_fifo, sizeof(int64_t));
/* IRQFD requires MSI */
if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD) &&
!ivshmem_has_feature(s, IVSHMEM_MSI)) {
error_setg(errp, "ioeventfd/irqfd requires MSI");
return;
}
/* 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 {
error_setg(errp, "'role' must be 'peer' or 'master'");
return;
}
} else {
s->role_val = IVSHMEM_MASTER; /* default */
}
if (s->role_val == IVSHMEM_PEER) {
error_setg(&s->migration_blocker,
"Migration is disabled when using feature 'peer mode' in device 'ivshmem'");
migrate_add_blocker(s->migration_blocker);
}
pci_conf = dev->config;
pci_conf[PCI_COMMAND] = PCI_COMMAND_IO | PCI_COMMAND_MEMORY;
pci_config_set_interrupt_pin(pci_conf, 1);
memory_region_init_io(&s->ivshmem_mmio, OBJECT(s), &ivshmem_mmio_ops, s,
"ivshmem-mmio", IVSHMEM_REG_BAR_SIZE);
/* region for registers*/
pci_register_bar(dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY,
&s->ivshmem_mmio);
memory_region_init(&s->bar, OBJECT(s), "ivshmem-bar2-container", s->ivshmem_size);
if (s->ivshmem_64bit) {
attr |= PCI_BASE_ADDRESS_MEM_TYPE_64;
}
if (s->hostmem != NULL) {
MemoryRegion *mr;
IVSHMEM_DPRINTF("using hostmem\n");
mr = host_memory_backend_get_memory(MEMORY_BACKEND(s->hostmem), errp);
vmstate_register_ram(mr, DEVICE(s));
memory_region_add_subregion(&s->bar, 0, mr);
pci_register_bar(PCI_DEVICE(s), 2, attr, &s->bar);
} else if (s->server_chr != NULL) {
/* FIXME do not rely on what chr drivers put into filename */
if (strncmp(s->server_chr->filename, "unix:", 5)) {
error_setg(errp, "chardev is not a unix client socket");
return;
}
/* if we get a UNIX socket as the parameter we will talk
* to the ivshmem server to receive the memory region */
IVSHMEM_DPRINTF("using shared memory server (socket = %s)\n",
s->server_chr->filename);
if (ivshmem_has_feature(s, IVSHMEM_MSI) &&
ivshmem_setup_msi(s)) {
error_setg(errp, "msix initialization failed");
return;
}
/* we allocate enough space for 16 peers and grow as needed */
resize_peers(s, 16);
s->vm_id = -1;
pci_register_bar(dev, 2, attr, &s->bar);
s->eventfd_chr = g_malloc0(s->vectors * sizeof(CharDriverState *));
qemu_chr_add_handlers(s->server_chr, ivshmem_can_receive,
ivshmem_check_version, ivshmem_event, s);
} else {
/* just map the file immediately, we're not using a server */
int fd;
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) {
error_report("could not truncate shared file");
}
} else if ((fd = shm_open(s->shmobj, O_CREAT|O_RDWR,
S_IRWXU|S_IRWXG|S_IRWXO)) < 0) {
error_setg(errp, "could not open shared file");
return;
}
if (check_shm_size(s, fd, errp) == -1) {
return;
}
create_shared_memory_BAR(s, fd, attr, errp);
}
}
static void ivshmem_read(void *opaque, const uint8_t *buf, int size)
{
IVShmemState *s = opaque;
int incoming_fd;
int new_eventfd;
int64_t incoming_posn;
Error *err = NULL;
Peer *peer;
if (!fifo_update_and_get_i64(s, buf, size, &incoming_posn)) {
return;
}
if (incoming_posn < -1) {
IVSHMEM_DPRINTF("invalid incoming_posn %" PRId64 "\n", incoming_posn);
return;
}
/* pick off s->server_chr->msgfd and store it, posn should accompany msg */
incoming_fd = qemu_chr_fe_get_msgfd(s->server_chr);
IVSHMEM_DPRINTF("posn is %" PRId64 ", fd is %d\n",
incoming_posn, incoming_fd);
/* make sure we have enough space for this peer */
if (incoming_posn >= s->nb_peers) {
if (resize_peers(s, incoming_posn + 1) < 0) {
error_report("failed to resize peers array");
if (incoming_fd != -1) {
close(incoming_fd);
}
return;
}
}
peer = &s->peers[incoming_posn];
if (incoming_fd == -1) {
/* if posn is positive and unseen before then this is our posn*/
if (incoming_posn >= 0 && s->vm_id == -1) {
/* receive our posn */
s->vm_id = incoming_posn;
} else {
/* otherwise an fd == -1 means an existing peer has gone away */
IVSHMEM_DPRINTF("posn %" PRId64 " has gone away\n", incoming_posn);
close_peer_eventfds(s, incoming_posn);
}
return;
}
/* if the position is -1, then it's shared memory region fd */
if (incoming_posn == -1) {
void * map_ptr;
if (memory_region_is_mapped(&s->ivshmem)) {
error_report("shm already initialized");
close(incoming_fd);
return;
}
if (check_shm_size(s, incoming_fd, &err) == -1) {
error_report_err(err);
close(incoming_fd);
return;
}
/* mmap the region and map into the BAR2 */
map_ptr = mmap(0, s->ivshmem_size, PROT_READ|PROT_WRITE, MAP_SHARED,
incoming_fd, 0);
if (map_ptr == MAP_FAILED) {
error_report("Failed to mmap shared memory %s", strerror(errno));
close(incoming_fd);
return;
}
memory_region_init_ram_ptr(&s->ivshmem, OBJECT(s),
"ivshmem.bar2", s->ivshmem_size, map_ptr);
qemu_set_ram_fd(s->ivshmem.ram_addr, incoming_fd);
vmstate_register_ram(&s->ivshmem, DEVICE(s));
IVSHMEM_DPRINTF("guest h/w addr = %p, size = %" PRIu64 "\n",
map_ptr, s->ivshmem_size);
memory_region_add_subregion(&s->bar, 0, &s->ivshmem);
return;
}
/* each peer has an associated array of eventfds, and we keep
* track of how many eventfds received so far */
/* get a new eventfd: */
if (peer->nb_eventfds >= s->vectors) {
error_report("Too many eventfd received, device has %d vectors",
s->vectors);
close(incoming_fd);
return;
}
new_eventfd = peer->nb_eventfds++;
/* this is an eventfd for a particular peer VM */
IVSHMEM_DPRINTF("eventfds[%" PRId64 "][%d] = %d\n", incoming_posn,
new_eventfd, incoming_fd);
event_notifier_init_fd(&peer->eventfds[new_eventfd], incoming_fd);
fcntl_setfl(incoming_fd, O_NONBLOCK); /* msix/irqfd poll non block */
if (incoming_posn == s->vm_id) {
setup_interrupt(s, new_eventfd);
}
if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) {
ivshmem_add_eventfd(s, incoming_posn, new_eventfd);
}
}