static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt);
-static int kvm_vcpu_reset(struct kvm_vcpu *vcpu);
-
static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu)
{
int i;
}
EXPORT_SYMBOL_GPL(kvm_set_apic_base);
+asmlinkage void kvm_spurious_fault(void)
+{
+ /* Fault while not rebooting. We want the trace. */
+ BUG();
+}
+EXPORT_SYMBOL_GPL(kvm_spurious_fault);
+
#define EXCPT_BENIGN 0
#define EXCPT_CONTRIBUTORY 1
#define EXCPT_PF 2
u32 thresh_lo, thresh_hi;
int use_scaling = 0;
+ /* tsc_khz can be zero if TSC calibration fails */
+ if (this_tsc_khz == 0)
+ return;
+
/* Compute a scale to convert nanoseconds in TSC cycles */
kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000,
&vcpu->arch.virtual_tsc_shift,
ns = get_kernel_ns();
elapsed = ns - kvm->arch.last_tsc_nsec;
- /* n.b - signed multiplication and division required */
- usdiff = data - kvm->arch.last_tsc_write;
+ if (vcpu->arch.virtual_tsc_khz) {
+ /* n.b - signed multiplication and division required */
+ usdiff = data - kvm->arch.last_tsc_write;
#ifdef CONFIG_X86_64
- usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz;
+ usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz;
#else
- /* do_div() only does unsigned */
- asm("idivl %2; xor %%edx, %%edx"
- : "=A"(usdiff)
- : "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz));
+ /* do_div() only does unsigned */
+ asm("idivl %2; xor %%edx, %%edx"
+ : "=A"(usdiff)
+ : "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz));
#endif
- do_div(elapsed, 1000);
- usdiff -= elapsed;
- if (usdiff < 0)
- usdiff = -usdiff;
+ do_div(elapsed, 1000);
+ usdiff -= elapsed;
+ if (usdiff < 0)
+ usdiff = -usdiff;
+ } else
+ usdiff = USEC_PER_SEC; /* disable TSC match window below */
/*
* Special case: TSC write with a small delta (1 second) of virtual
unsigned long flags, this_tsc_khz;
struct kvm_vcpu_arch *vcpu = &v->arch;
struct kvm_arch *ka = &v->kvm->arch;
- void *shared_kaddr;
s64 kernel_ns, max_kernel_ns;
u64 tsc_timestamp, host_tsc;
- struct pvclock_vcpu_time_info *guest_hv_clock;
+ struct pvclock_vcpu_time_info guest_hv_clock;
u8 pvclock_flags;
bool use_master_clock;
kernel_ns = 0;
host_tsc = 0;
- /* Keep irq disabled to prevent changes to the clock */
- local_irq_save(flags);
- this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
- if (unlikely(this_tsc_khz == 0)) {
- local_irq_restore(flags);
- kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
- return 1;
- }
-
/*
* If the host uses TSC clock, then passthrough TSC as stable
* to the guest.
kernel_ns = ka->master_kernel_ns;
}
spin_unlock(&ka->pvclock_gtod_sync_lock);
+
+ /* Keep irq disabled to prevent changes to the clock */
+ local_irq_save(flags);
+ this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
+ if (unlikely(this_tsc_khz == 0)) {
+ local_irq_restore(flags);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
+ return 1;
+ }
if (!use_master_clock) {
host_tsc = native_read_tsc();
kernel_ns = get_kernel_ns();
local_irq_restore(flags);
- if (!vcpu->time_page)
+ if (!vcpu->pv_time_enabled)
return 0;
/*
*/
vcpu->hv_clock.version += 2;
- shared_kaddr = kmap_atomic(vcpu->time_page);
-
- guest_hv_clock = shared_kaddr + vcpu->time_offset;
+ if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
+ &guest_hv_clock, sizeof(guest_hv_clock))))
+ return 0;
/* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
- pvclock_flags = (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED);
+ pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
if (vcpu->pvclock_set_guest_stopped_request) {
pvclock_flags |= PVCLOCK_GUEST_STOPPED;
vcpu->hv_clock.flags = pvclock_flags;
- memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
- sizeof(vcpu->hv_clock));
-
- kunmap_atomic(shared_kaddr);
-
- mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock));
return 0;
}
static void kvmclock_reset(struct kvm_vcpu *vcpu)
{
- if (vcpu->arch.time_page) {
- kvm_release_page_dirty(vcpu->arch.time_page);
- vcpu->arch.time_page = NULL;
- }
+ vcpu->arch.pv_time_enabled = false;
}
static void accumulate_steal_time(struct kvm_vcpu *vcpu)
break;
case MSR_KVM_SYSTEM_TIME_NEW:
case MSR_KVM_SYSTEM_TIME: {
+ u64 gpa_offset;
kvmclock_reset(vcpu);
vcpu->arch.time = data;
if (!(data & 1))
break;
- /* ...but clean it before doing the actual write */
- vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
+ gpa_offset = data & ~(PAGE_MASK | 1);
- vcpu->arch.time_page =
- gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
+ /* Check that the address is 32-byte aligned. */
+ if (gpa_offset & (sizeof(struct pvclock_vcpu_time_info) - 1))
+ break;
- if (is_error_page(vcpu->arch.time_page))
- vcpu->arch.time_page = NULL;
+ if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+ &vcpu->arch.pv_time, data & ~1ULL))
+ vcpu->arch.pv_time_enabled = false;
+ else
+ vcpu->arch.pv_time_enabled = true;
break;
}
case MSR_P6_EVNTSEL0:
case MSR_P6_EVNTSEL1:
if (kvm_pmu_msr(vcpu, msr))
- return kvm_pmu_set_msr(vcpu, msr, data);
+ return kvm_pmu_set_msr(vcpu, msr_info);
if (pr || data != 0)
vcpu_unimpl(vcpu, "disabled perfctr wrmsr: "
if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
return xen_hvm_config(vcpu, data);
if (kvm_pmu_msr(vcpu, msr))
- return kvm_pmu_set_msr(vcpu, msr, data);
+ return kvm_pmu_set_msr(vcpu, msr_info);
if (!ignore_msrs) {
vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
msr, data);
static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
struct kvm_interrupt *irq)
{
- if (irq->irq < 0 || irq->irq >= KVM_NR_INTERRUPTS)
+ if (irq->irq >= KVM_NR_INTERRUPTS)
return -EINVAL;
if (irqchip_in_kernel(vcpu->kvm))
return -ENXIO;
events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu);
events->nmi.pad = 0;
- events->sipi_vector = vcpu->arch.sipi_vector;
+ events->sipi_vector = 0; /* never valid when reporting to user space */
events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
- | KVM_VCPUEVENT_VALID_SIPI_VECTOR
| KVM_VCPUEVENT_VALID_SHADOW);
memset(&events->reserved, 0, sizeof(events->reserved));
}
vcpu->arch.nmi_pending = events->nmi.pending;
kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked);
- if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR)
- vcpu->arch.sipi_vector = events->sipi_vector;
+ if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR &&
+ kvm_vcpu_has_lapic(vcpu))
+ vcpu->arch.apic->sipi_vector = events->sipi_vector;
kvm_make_request(KVM_REQ_EVENT, vcpu);
*/
static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
{
- if (!vcpu->arch.time_page)
+ if (!vcpu->arch.pv_time_enabled)
return -EINVAL;
vcpu->arch.pvclock_set_guest_stopped_request = true;
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
return r;
}
-int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event)
+int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event,
+ bool line_status)
{
if (!irqchip_in_kernel(kvm))
return -ENXIO;
irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
- irq_event->irq, irq_event->level);
+ irq_event->irq, irq_event->level,
+ line_status);
return 0;
}
}
static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
- bool write_fault_to_shadow_pgtable)
+ bool write_fault_to_shadow_pgtable,
+ int emulation_type)
{
gpa_t gpa = cr2;
pfn_t pfn;
+ if (emulation_type & EMULTYPE_NO_REEXECUTE)
+ return false;
+
if (!vcpu->arch.mmu.direct_map) {
/*
* Write permission should be allowed since only
if (r != EMULATION_OK) {
if (emulation_type & EMULTYPE_TRAP_UD)
return EMULATE_FAIL;
- if (reexecute_instruction(vcpu, cr2,
- write_fault_to_spt))
+ if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
+ emulation_type))
return EMULATE_DONE;
if (emulation_type & EMULTYPE_SKIP)
return EMULATE_FAIL;
return EMULATE_DONE;
if (r == EMULATION_FAILED) {
- if (reexecute_instruction(vcpu, cr2, write_fault_to_spt))
+ if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
+ emulation_type))
return EMULATE_DONE;
return handle_emulation_failure(vcpu);
}
if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
+ kvm_apic_accept_events(vcpu);
+ if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
+ r = 1;
+ goto out;
+ }
+
inject_pending_event(vcpu);
/* enable NMI/IRQ window open exits if needed */
int r;
struct kvm *kvm = vcpu->kvm;
- if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) {
- pr_debug("vcpu %d received sipi with vector # %x\n",
- vcpu->vcpu_id, vcpu->arch.sipi_vector);
- kvm_lapic_reset(vcpu);
- r = kvm_vcpu_reset(vcpu);
- if (r)
- return r;
- vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
- }
-
vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
r = vapic_enter(vcpu);
if (r) {
srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
kvm_vcpu_block(vcpu);
vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
- if (kvm_check_request(KVM_REQ_UNHALT, vcpu))
- {
+ if (kvm_check_request(KVM_REQ_UNHALT, vcpu)) {
+ kvm_apic_accept_events(vcpu);
switch(vcpu->arch.mp_state) {
case KVM_MP_STATE_HALTED:
vcpu->arch.mp_state =
case KVM_MP_STATE_RUNNABLE:
vcpu->arch.apf.halted = false;
break;
- case KVM_MP_STATE_SIPI_RECEIVED:
+ case KVM_MP_STATE_INIT_RECEIVED:
+ break;
default:
r = -EINTR;
break;
if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
kvm_vcpu_block(vcpu);
+ kvm_apic_accept_events(vcpu);
clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
r = -EAGAIN;
goto out;
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
+ kvm_apic_accept_events(vcpu);
mp_state->mp_state = vcpu->arch.mp_state;
return 0;
}
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
- vcpu->arch.mp_state = mp_state->mp_state;
+ if (!kvm_vcpu_has_lapic(vcpu) &&
+ mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
+ return -EINVAL;
+
+ if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) {
+ vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
+ set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events);
+ } else
+ vcpu->arch.mp_state = mp_state->mp_state;
kvm_make_request(KVM_REQ_EVENT, vcpu);
return 0;
}
r = vcpu_load(vcpu);
if (r)
return r;
- r = kvm_vcpu_reset(vcpu);
- if (r == 0)
- r = kvm_mmu_setup(vcpu);
+ kvm_vcpu_reset(vcpu);
+ r = kvm_mmu_setup(vcpu);
vcpu_put(vcpu);
return r;
kvm_x86_ops->vcpu_free(vcpu);
}
-static int kvm_vcpu_reset(struct kvm_vcpu *vcpu)
+void kvm_vcpu_reset(struct kvm_vcpu *vcpu)
{
atomic_set(&vcpu->arch.nmi_queued, 0);
vcpu->arch.nmi_pending = 0;
vcpu->arch.regs_avail = ~0;
vcpu->arch.regs_dirty = ~0;
- return kvm_x86_ops->vcpu_reset(vcpu);
+ kvm_x86_ops->vcpu_reset(vcpu);
+}
+
+void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector)
+{
+ struct kvm_segment cs;
+
+ kvm_get_segment(vcpu, &cs, VCPU_SREG_CS);
+ cs.selector = vector << 8;
+ cs.base = vector << 12;
+ kvm_set_segment(vcpu, &cs, VCPU_SREG_CS);
+ kvm_rip_write(vcpu, 0);
}
int kvm_arch_hardware_enable(void *garbage)
goto fail_free_wbinvd_dirty_mask;
vcpu->arch.ia32_tsc_adjust_msr = 0x0;
+ vcpu->arch.pv_time_enabled = false;
kvm_async_pf_hash_reset(vcpu);
kvm_pmu_init(vcpu);
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_memory_slot old,
struct kvm_userspace_memory_region *mem,
- bool user_alloc)
+ enum kvm_mr_change change)
{
- int npages = memslot->npages;
-
/*
* Only private memory slots need to be mapped here since
* KVM_SET_MEMORY_REGION ioctl is no longer supported.
*/
- if ((memslot->id >= KVM_USER_MEM_SLOTS) && npages && !old.npages) {
+ if ((memslot->id >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_CREATE)) {
unsigned long userspace_addr;
/*
* MAP_SHARED to prevent internal slot pages from being moved
* by fork()/COW.
*/
- userspace_addr = vm_mmap(NULL, 0, npages * PAGE_SIZE,
+ userspace_addr = vm_mmap(NULL, 0, memslot->npages * PAGE_SIZE,
PROT_READ | PROT_WRITE,
MAP_SHARED | MAP_ANONYMOUS, 0);
void kvm_arch_commit_memory_region(struct kvm *kvm,
struct kvm_userspace_memory_region *mem,
- struct kvm_memory_slot old,
- bool user_alloc)
+ const struct kvm_memory_slot *old,
+ enum kvm_mr_change change)
{
- int nr_mmu_pages = 0, npages = mem->memory_size >> PAGE_SHIFT;
+ int nr_mmu_pages = 0;
- if ((mem->slot >= KVM_USER_MEM_SLOTS) && old.npages && !npages) {
+ if ((mem->slot >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_DELETE)) {
int ret;
- ret = vm_munmap(old.userspace_addr,
- old.npages * PAGE_SIZE);
+ ret = vm_munmap(old->userspace_addr,
+ old->npages * PAGE_SIZE);
if (ret < 0)
printk(KERN_WARNING
"kvm_vm_ioctl_set_memory_region: "
* Existing largepage mappings are destroyed here and new ones will
* not be created until the end of the logging.
*/
- if (npages && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES))
+ if ((change != KVM_MR_DELETE) && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES))
kvm_mmu_slot_remove_write_access(kvm, mem->slot);
/*
* If memory slot is created, or moved, we need to clear all
* mmio sptes.
*/
- if (npages && old.base_gfn != mem->guest_phys_addr >> PAGE_SHIFT) {
- kvm_mmu_zap_all(kvm);
+ if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
+ kvm_mmu_zap_mmio_sptes(kvm);
kvm_reload_remote_mmus(kvm);
}
}
return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
!vcpu->arch.apf.halted)
|| !list_empty_careful(&vcpu->async_pf.done)
- || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED
+ || kvm_apic_has_events(vcpu)
|| atomic_read(&vcpu->arch.nmi_queued) ||
(kvm_arch_interrupt_allowed(vcpu) &&
kvm_cpu_has_interrupt(vcpu));