void kvm_create_irqchip(kvm_context_t kvm)
{
int r;
kvm->irqchip_in_kernel = 0;
#ifdef KVM_CAP_IRQCHIP
if (!kvm->no_irqchip_creation) {
r = kvm_ioctl(kvm_state, KVM_CHECK_EXTENSION, KVM_CAP_IRQCHIP);
if (r > 0) { /* kernel irqchip supported */
r = kvm_vm_ioctl(kvm_state, KVM_CREATE_IRQCHIP);
if (r >= 0) {
kvm->irqchip_inject_ioctl = KVM_IRQ_LINE;
#if defined(KVM_CAP_IRQ_INJECT_STATUS) && defined(KVM_IRQ_LINE_STATUS)
r = kvm_ioctl(kvm_state, KVM_CHECK_EXTENSION,
KVM_CAP_IRQ_INJECT_STATUS);
if (r > 0) {
kvm->irqchip_inject_ioctl = KVM_IRQ_LINE_STATUS;
}
#endif
kvm->irqchip_in_kernel = 1;
} else
fprintf(stderr, "Create kernel PIC irqchip failed\n");
}
}
#endif
kvm_state->irqchip_in_kernel = kvm->irqchip_in_kernel;
}
int kvm_get_mce_cap_supported(kvm_context_t kvm, uint64_t *mce_cap,
int *max_banks)
{
#ifdef KVM_CAP_MCE
int r;
r = kvm_ioctl(kvm_state, KVM_CHECK_EXTENSION, KVM_CAP_MCE);
if (r > 0) {
*max_banks = r;
return kvm_ioctl(kvm_state, KVM_X86_GET_MCE_CAP_SUPPORTED, mce_cap);
}
#endif
return -ENOSYS;
}
int main(int argc, char *argv[]) {
int kvm_fd = open("/dev/kvm", O_RDWR);
if (kvm_fd < 0) {
perror("kvm_open");
return -1;
}
printf("sending ioctl %X\n", KVM_GET_API_VERSION);
int version = kvm_ioctl(kvm_fd, KVM_GET_API_VERSION, 0);
printf("got version %d\n", version);
if (version != KVM_API_VERSION) {
perror("ioctl");
}
int vm_fd = kvm_ioctl(kvm_fd, KVM_CREATE_VM, 0);
printf("got vm %d\n", vm_fd);
return 0;
}
int kvm_init_vcpu(CPUArchState *env)
{
KVMState *s = kvm_state;
long mmap_size;
int ret;
DPRINTF("kvm_init_vcpu\n");
#ifdef CONFIG_SOLARIS
ret = kvm_vm_clone(kvm_state);
if (ret < 0) {
fprintf(stderr, "kvm_init_vcpu could not clone fd: %m\n");
goto err;
}
env->kvm_fd = ret;
ret = ioctl(env->kvm_fd, KVM_CREATE_VCPU, env->cpu_index);
#else
ret = kvm_vm_ioctl(s, KVM_CREATE_VCPU, env->cpu_index);
#endif
if (ret < 0) {
DPRINTF("kvm_create_vcpu failed\n");
goto err;
}
#ifndef CONFIG_SOLARIS
env->kvm_fd = ret;
#endif
env->kvm_state = s;
env->kvm_vcpu_dirty = 1;
mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0);
if (mmap_size < 0) {
ret = mmap_size;
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;
}
if (s->coalesced_mmio && !s->coalesced_mmio_ring) {
s->coalesced_mmio_ring =
(void *)env->kvm_run + s->coalesced_mmio * PAGE_SIZE;
}
ret = kvm_arch_init_vcpu(env);
if (ret == 0) {
qemu_register_reset(kvm_reset_vcpu, env);
kvm_arch_reset_vcpu(env);
}
err:
return ret;
}
int kvm_init(void)
{
long mmap_size;
struct kvm_enable_cap cap;
int r;
kvm_fd = open("/dev/kvm", O_RDWR);
if (kvm_fd < 0) {
fprintf(stderr, "KVM: Couldn't open /dev/kvm\n");
return -1;
}
vm_fd = kvm_ioctl(KVM_CREATE_VM, 0);
if (vm_fd < 0) {
fprintf(stderr, "KVM: Couldn't create VM\n");
return -1;
}
vcpu_fd = kvm_vm_ioctl(KVM_CREATE_VCPU, 0);
if (vcpu_fd < 0) {
fprintf(stderr, "kvm_create_vcpu failed\n");
return -1;
}
memset(&cap, 0, sizeof(cap));
cap.cap = KVM_CAP_PPC_OSI;
r = kvm_vcpu_ioctl(KVM_ENABLE_CAP, &cap);
if (r < 0) {
fprintf(stderr, "kvm_enable_cap failed\n");
return -1;
}
mmap_size = kvm_ioctl(KVM_GET_VCPU_MMAP_SIZE, 0);
if (mmap_size < 0) {
fprintf(stderr, "KVM_GET_VCPU_MMAP_SIZE failed\n");
return -1;
}
kvm_run = (struct kvm_run *)mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
MAP_SHARED, vcpu_fd, 0);
if (kvm_run == MAP_FAILED) {
fprintf(stderr, "mmap'ing vcpu state failed\n");
return -1;
}
return 0;
}
int kvm_set_mpstate(CPUState *env, struct kvm_mp_state *mp_state)
{
int r;
r = kvm_ioctl(kvm_state, KVM_CHECK_EXTENSION, KVM_CAP_MP_STATE);
if (r > 0) {
return kvm_vcpu_ioctl(env, KVM_SET_MP_STATE, mp_state);
}
return -ENOSYS;
}
int kvm_assign_irq(KVMState *s, struct kvm_assigned_irq *assigned_irq)
{
int ret;
ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_ASSIGN_DEV_IRQ);
if (ret > 0) {
return kvm_vm_ioctl(s, KVM_ASSIGN_DEV_IRQ, assigned_irq);
}
return kvm_old_assign_irq(s, assigned_irq);
}
int kvm_assign_irq(kvm_context_t kvm, struct kvm_assigned_irq *assigned_irq)
{
int ret;
ret = kvm_ioctl(kvm_state, KVM_CHECK_EXTENSION, KVM_CAP_ASSIGN_DEV_IRQ);
if (ret > 0) {
return kvm_vm_ioctl(kvm_state, KVM_ASSIGN_DEV_IRQ, assigned_irq);
}
return kvm_old_assign_irq(kvm, assigned_irq);
}
int kvm_check_extension(KVMState *s, unsigned int extension)
{
int ret;
ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, extension);
if (ret < 0) {
ret = 0;
}
return ret;
}
static int kvm_set_boot_vcpu_id(kvm_context_t kvm, uint32_t id)
{
#ifdef KVM_CAP_SET_BOOT_CPU_ID
int r = kvm_ioctl(kvm_state, KVM_CHECK_EXTENSION, KVM_CAP_SET_BOOT_CPU_ID);
if (r > 0) {
return kvm_vm_ioctl(kvm_state, KVM_SET_BOOT_CPU_ID, id);
}
return -ENOSYS;
#else
return -ENOSYS;
#endif
}
int kvm_init_coalesced_mmio(kvm_context_t kvm)
{
int r = 0;
kvm_state->coalesced_mmio = 0;
#ifdef KVM_CAP_COALESCED_MMIO
r = kvm_ioctl(kvm_state, KVM_CHECK_EXTENSION, KVM_CAP_COALESCED_MMIO);
if (r > 0) {
kvm_state->coalesced_mmio = r;
return 0;
}
#endif
return r;
}
int kvm_get_shadow_pages(kvm_context_t kvm, unsigned int *nrshadow_pages)
{
#ifdef KVM_CAP_MMU_SHADOW_CACHE_CONTROL
int r;
r = kvm_ioctl(kvm_state, KVM_CHECK_EXTENSION,
KVM_CAP_MMU_SHADOW_CACHE_CONTROL);
if (r > 0) {
*nrshadow_pages = kvm_vm_ioctl(kvm_state, KVM_GET_NR_MMU_PAGES);
return 0;
}
#endif
return -1;
}
/*
* Returns available msr list. User must free.
*/
static struct kvm_msr_list *kvm_get_msr_list(void)
{
struct kvm_msr_list sizer, *msrs;
int r;
sizer.nmsrs = 0;
r = kvm_ioctl(kvm_state, KVM_GET_MSR_INDEX_LIST, &sizer);
if (r < 0 && r != -E2BIG)
return NULL;
/* Old kernel modules had a bug and could write beyond the provided
memory. Allocate at least a safe amount of 1K. */
msrs = qemu_malloc(MAX(1024, sizeof(*msrs) +
sizer.nmsrs * sizeof(*msrs->indices)));
msrs->nmsrs = sizer.nmsrs;
r = kvm_ioctl(kvm_state, KVM_GET_MSR_INDEX_LIST, msrs);
if (r < 0) {
free(msrs);
errno = r;
return NULL;
}
return msrs;
}
int kvm_reinject_control(KVMState *s, int pit_reinject)
{
#ifdef KVM_CAP_REINJECT_CONTROL
int r;
struct kvm_reinject_control control;
control.pit_reinject = pit_reinject;
r = kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_REINJECT_CONTROL);
if (r > 0) {
return kvm_vm_ioctl(s, KVM_REINJECT_CONTROL, &control);
}
#endif
return -ENOSYS;
}
static int kvm_create_default_phys_mem(kvm_context_t kvm,
unsigned long phys_mem_bytes,
void **vm_mem)
{
#ifdef KVM_CAP_USER_MEMORY
int r = kvm_ioctl(kvm_state, KVM_CHECK_EXTENSION, KVM_CAP_USER_MEMORY);
if (r > 0)
return 0;
fprintf(stderr,
"Hypervisor too old: KVM_CAP_USER_MEMORY extension not supported\n");
#else
#error Hypervisor too old: KVM_CAP_USER_MEMORY extension not supported
#endif
return -1;
}
int kvm_create_vm(kvm_context_t kvm)
{
int fd;
#ifdef KVM_CAP_IRQ_ROUTING
kvm->irq_routes = qemu_mallocz(sizeof(*kvm->irq_routes));
kvm->nr_allocated_irq_routes = 0;
#endif
fd = kvm_ioctl(kvm_state, KVM_CREATE_VM, 0);
if (fd < 0) {
fprintf(stderr, "kvm_create_vm: %m\n");
return -1;
}
kvm_state->vmfd = fd;
return 0;
}
static void kvm_create_vcpu(CPUState *env, int id)
{
long mmap_size;
int r;
KVMState *s = kvm_state;
r = kvm_vm_ioctl(kvm_state, KVM_CREATE_VCPU, id);
if (r < 0) {
fprintf(stderr, "kvm_create_vcpu: %m\n");
fprintf(stderr, "Failed to create vCPU. Check the -smp parameter.\n");
goto err;
}
env->kvm_fd = r;
env->kvm_state = kvm_state;
mmap_size = kvm_ioctl(kvm_state, KVM_GET_VCPU_MMAP_SIZE, 0);
if (mmap_size < 0) {
fprintf(stderr, "get vcpu mmap size: %m\n");
goto err_fd;
}
env->kvm_run =
mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, env->kvm_fd,
0);
if (env->kvm_run == MAP_FAILED) {
fprintf(stderr, "mmap vcpu area: %m\n");
goto err_fd;
}
#ifdef KVM_CAP_COALESCED_MMIO
if (s->coalesced_mmio && !s->coalesced_mmio_ring)
s->coalesced_mmio_ring = (void *) env->kvm_run +
s->coalesced_mmio * PAGE_SIZE;
#endif
r = kvm_arch_init_vcpu(env);
if (r == 0) {
qemu_register_reset(kvm_reset_vcpu, env);
}
return;
err_fd:
close(env->kvm_fd);
err:
/* We're no good with semi-broken states. */
abort();
}
static int kvm_set_identity_map_addr(kvm_context_t kvm, uint64_t addr)
{
#ifdef KVM_CAP_SET_IDENTITY_MAP_ADDR
int r;
r = kvm_ioctl(kvm_state, KVM_CHECK_EXTENSION, KVM_CAP_SET_IDENTITY_MAP_ADDR);
if (r > 0) {
r = kvm_vm_ioctl(kvm_state, KVM_SET_IDENTITY_MAP_ADDR, &addr);
if (r == -1) {
fprintf(stderr, "kvm_set_identity_map_addr: %m\n");
return -errno;
}
return 0;
}
#endif
return -ENOSYS;
}
int kvm_set_shadow_pages(kvm_context_t kvm, unsigned int nrshadow_pages)
{
#ifdef KVM_CAP_MMU_SHADOW_CACHE_CONTROL
int r;
r = kvm_ioctl(kvm_state, KVM_CHECK_EXTENSION,
KVM_CAP_MMU_SHADOW_CACHE_CONTROL);
if (r > 0) {
r = kvm_vm_ioctl(kvm_state, KVM_SET_NR_MMU_PAGES, nrshadow_pages);
if (r < 0) {
fprintf(stderr, "kvm_set_shadow_pages: %m\n");
return r;
}
return 0;
}
#endif
return -1;
}
static int kvm_init_tss(kvm_context_t kvm)
{
int r;
r = kvm_ioctl(kvm_state, KVM_CHECK_EXTENSION, KVM_CAP_SET_TSS_ADDR);
if (r > 0) {
/*
* this address is 3 pages before the bios, and the bios should present
* as unavaible memory
*/
r = kvm_set_tss_addr(kvm, 0xfeffd000);
if (r < 0) {
fprintf(stderr, "kvm_init_tss: unable to set tss addr\n");
return r;
}
} else {
fprintf(stderr, "kvm does not support KVM_CAP_SET_TSS_ADDR\n");
}
return 0;
}
static int kvm_enable_tpr_access_reporting(CPUState *env)
{
int r;
struct kvm_tpr_access_ctl tac = { .enabled = 1 };
r = kvm_ioctl(env->kvm_state, KVM_CHECK_EXTENSION, KVM_CAP_VAPIC);
if (r <= 0)
return -ENOSYS;
return kvm_vcpu_ioctl(env, KVM_TPR_ACCESS_REPORTING, &tac);
}
#endif
#ifdef KVM_CAP_ADJUST_CLOCK
static struct kvm_clock_data kvmclock_data;
static void kvmclock_pre_save(void *opaque)
{
struct kvm_clock_data *cl = opaque;
kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, cl);
}
static int kvmclock_post_load(void *opaque, int version_id)
{
struct kvm_clock_data *cl = opaque;
return kvm_vm_ioctl(kvm_state, KVM_SET_CLOCK, cl);
}
static const VMStateDescription vmstate_kvmclock= {
.name = "kvmclock",
.version_id = 1,
.minimum_version_id = 1,
.minimum_version_id_old = 1,
.pre_save = kvmclock_pre_save,
.post_load = kvmclock_post_load,
.fields = (VMStateField []) {
VMSTATE_U64(clock, struct kvm_clock_data),
VMSTATE_END_OF_LIST()
}
};
static int kvm_create_pit(kvm_context_t kvm)
{
#ifdef KVM_CAP_PIT
int r;
kvm_state->pit_in_kernel = 0;
if (!kvm->no_pit_creation) {
r = kvm_ioctl(kvm_state, KVM_CHECK_EXTENSION, KVM_CAP_PIT);
if (r > 0) {
r = kvm_vm_ioctl(kvm_state, KVM_CREATE_PIT);
if (r >= 0)
kvm_state->pit_in_kernel = 1;
else {
fprintf(stderr, "Create kernel PIC irqchip failed\n");
return r;
}
}
}
#endif
return 0;
}
static int kvm_init_identity_map_page(kvm_context_t kvm)
{
#ifdef KVM_CAP_SET_IDENTITY_MAP_ADDR
int r;
r = kvm_ioctl(kvm_state, KVM_CHECK_EXTENSION, KVM_CAP_SET_IDENTITY_MAP_ADDR);
if (r > 0) {
/*
* this address is 4 pages before the bios, and the bios should present
* as unavaible memory
*/
r = kvm_set_identity_map_addr(kvm, 0xfeffc000);
if (r < 0) {
fprintf(stderr, "kvm_init_identity_map_page: "
"unable to set identity mapping addr\n");
return r;
}
}
#endif
return 0;
}