static void ivshmem_reset(DeviceState *d)
{
IVShmemState *s = IVSHMEM(d);
s->intrstatus = 0;
ivshmem_use_msix(s);
}
static void fake_irqfd(void *opaque, const uint8_t *buf, int size) {
MSIVector *entry = opaque;
PCIDevice *pdev = entry->pdev;
IVShmemState *s = IVSHMEM(pdev);
int vector = entry - s->msi_vectors;
IVSHMEM_DPRINTF("interrupt on vector %p %d\n", pdev, vector);
msix_notify(pdev, vector);
}
static void ivshmem_init(Object *obj)
{
IVShmemState *s = IVSHMEM(obj);
object_property_add_link(obj, "x-memdev", TYPE_MEMORY_BACKEND,
(Object **)&s->hostmem,
ivshmem_check_memdev_is_busy,
OBJ_PROP_LINK_UNREF_ON_RELEASE,
&error_abort);
}
static void pci_ivshmem_exit(PCIDevice *dev)
{
IVShmemState *s = IVSHMEM(dev);
int i;
fifo8_destroy(&s->incoming_fifo);
if (s->migration_blocker) {
migrate_del_blocker(s->migration_blocker);
error_free(s->migration_blocker);
}
if (memory_region_is_mapped(&s->ivshmem)) {
if (!s->hostmem) {
void *addr = memory_region_get_ram_ptr(&s->ivshmem);
int fd;
if (munmap(addr, s->ivshmem_size) == -1) {
error_report("Failed to munmap shared memory %s",
strerror(errno));
}
fd = qemu_get_ram_fd(memory_region_get_ram_addr(&s->ivshmem));
if (fd != -1) {
close(fd);
}
}
vmstate_unregister_ram(&s->ivshmem, DEVICE(dev));
memory_region_del_subregion(&s->bar, &s->ivshmem);
}
if (s->eventfd_chr) {
for (i = 0; i < s->vectors; i++) {
if (s->eventfd_chr[i]) {
qemu_chr_free(s->eventfd_chr[i]);
}
}
g_free(s->eventfd_chr);
}
if (s->peers) {
for (i = 0; i < s->nb_peers; i++) {
close_peer_eventfds(s, i);
}
g_free(s->peers);
}
if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
msix_uninit_exclusive_bar(dev);
}
g_free(s->msi_vectors);
}
static void pci_ivshmem_uninit(PCIDevice *dev)
{
IVShmemState *s = IVSHMEM(dev);
if (s->migration_blocker) {
migrate_del_blocker(s->migration_blocker);
error_free(s->migration_blocker);
}
memory_region_del_subregion(&s->bar, &s->ivshmem);
vmstate_unregister_ram(&s->ivshmem, DEVICE(dev));
unregister_savevm(DEVICE(dev), "ivshmem", s);
}
static void ivshmem_vector_mask(PCIDevice *dev, unsigned vector)
{
IVShmemState *s = IVSHMEM(dev);
EventNotifier *n = &s->peers[s->vm_id].eventfds[vector];
int ret;
IVSHMEM_DPRINTF("vector mask %p %d\n", dev, vector);
ret = kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, n,
s->msi_vectors[vector].virq);
if (ret != 0) {
error_report("remove_irqfd_notifier_gsi failed");
}
}
static void ivshmem_write_config(PCIDevice *pdev, uint32_t address,
uint32_t val, int len)
{
IVShmemState *s = IVSHMEM(pdev);
int is_enabled, was_enabled = msix_enabled(pdev);
pci_default_write_config(pdev, address, val, len);
is_enabled = msix_enabled(pdev);
if (kvm_msi_via_irqfd_enabled() && s->vm_id != -1) {
if (!was_enabled && is_enabled) {
ivshmem_enable_irqfd(s);
} else if (was_enabled && !is_enabled) {
ivshmem_disable_irqfd(s);
}
}
}
static int ivshmem_vector_unmask(PCIDevice *dev, unsigned vector,
MSIMessage msg)
{
IVShmemState *s = IVSHMEM(dev);
EventNotifier *n = &s->peers[s->vm_id].eventfds[vector];
MSIVector *v = &s->msi_vectors[vector];
int ret;
IVSHMEM_DPRINTF("vector unmask %p %d\n", dev, vector);
ret = kvm_irqchip_update_msi_route(kvm_state, v->virq, msg, dev);
if (ret < 0) {
return ret;
}
return kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, n, NULL, v->virq);
}
static void ivshmem_vector_notify(void *opaque)
{
MSIVector *entry = opaque;
PCIDevice *pdev = entry->pdev;
IVShmemState *s = IVSHMEM(pdev);
int vector = entry - s->msi_vectors;
EventNotifier *n = &s->peers[s->vm_id].eventfds[vector];
if (!event_notifier_test_and_clear(n)) {
return;
}
IVSHMEM_DPRINTF("interrupt on vector %p %d\n", pdev, vector);
if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
msix_notify(pdev, vector);
} else {
ivshmem_IntrStatus_write(s, 1);
}
}
static void ivshmem_vector_poll(PCIDevice *dev,
unsigned int vector_start,
unsigned int vector_end)
{
IVShmemState *s = IVSHMEM(dev);
unsigned int vector;
IVSHMEM_DPRINTF("vector poll %p %d-%d\n", dev, vector_start, vector_end);
vector_end = MIN(vector_end, s->vectors);
for (vector = vector_start; vector < vector_end; vector++) {
EventNotifier *notifier = &s->peers[s->vm_id].eventfds[vector];
if (!msix_is_masked(dev, vector)) {
continue;
}
if (event_notifier_test_and_clear(notifier)) {
msix_set_pending(dev, vector);
}
}
}
static int pci_ivshmem_init(PCIDevice *dev)
{
IVShmemState *s = IVSHMEM(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);
}
fifo8_create(&s->incoming_fifo, sizeof(long));
register_savevm(DEVICE(dev), "ivshmem", 0, 0, ivshmem_save, ivshmem_load,
dev);
/* IRQFD requires MSI */
if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD) &&
!ivshmem_has_feature(s, IVSHMEM_MSI)) {
error_report("ioeventfd/irqfd requires MSI");
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 {
error_report("'role' must be 'peer' or 'master'");
exit(1);
}
} 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);
s->shm_fd = 0;
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);
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;
}
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) {
error_report("WARNING: do not specify both 'chardev' "
"and 'shm' with ivshmem");
}
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 */
s->peers = g_malloc0(s->nb_peers * sizeof(Peer));
pci_register_bar(dev, 2, s->ivshmem_attr, &s->bar);
s->eventfd_chr = g_malloc0(s->vectors * sizeof(CharDriverState *));
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) {
error_report("Must specify 'chardev' or 'shm' to ivshmem");
exit(1);
}
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_report("could not open shared file");
exit(1);
}
if (check_shm_size(s, fd) == -1) {
exit(1);
}
create_shared_memory_BAR(s, fd);
}
dev->config_write = ivshmem_write_config;
return 0;
}
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);
}
}
