struct kvm_shared_msrs *locals
= container_of(urn, struct kvm_shared_msrs, urn);
struct kvm_shared_msr_values *values;
+ unsigned long flags;
+ /*
+ * Disabling irqs at this point since the following code could be
+ * interrupted and executed through kvm_arch_hardware_disable()
+ */
+ local_irq_save(flags);
+ if (locals->registered) {
+ locals->registered = false;
+ user_return_notifier_unregister(urn);
+ }
+ local_irq_restore(flags);
for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
values = &locals->values[slot];
if (values->host != values->curr) {
values->curr = values->host;
}
}
- locals->registered = false;
- user_return_notifier_unregister(urn);
}
static void shared_msr_update(unsigned slot, u32 msr)
if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512)
return 1;
}
- kvm_put_guest_xcr0(vcpu);
vcpu->arch.xcr0 = xcr0;
if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND)
MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
#endif
MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
- MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS
+ MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
};
static unsigned num_msrs_to_save;
memset(&events->reserved, 0, sizeof(events->reserved));
}
+static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+
static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
{
| KVM_VCPUEVENT_VALID_SMM))
return -EINVAL;
+ /* INITs are latched while in SMM */
+ if (events->flags & KVM_VCPUEVENT_VALID_SMM &&
+ (events->smi.smm || events->smi.pending) &&
+ vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED)
+ return -EINVAL;
+
process_nmi(vcpu);
vcpu->arch.exception.pending = events->exception.injected;
vcpu->arch.exception.nr = events->exception.nr;
vcpu->arch.apic->sipi_vector = events->sipi_vector;
if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
+ u32 hflags = vcpu->arch.hflags;
if (events->smi.smm)
- vcpu->arch.hflags |= HF_SMM_MASK;
+ hflags |= HF_SMM_MASK;
else
- vcpu->arch.hflags &= ~HF_SMM_MASK;
+ hflags &= ~HF_SMM_MASK;
+ kvm_set_hflags(vcpu, hflags);
+
vcpu->arch.smi_pending = events->smi.pending;
if (events->smi.smm_inside_nmi)
vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
if (dbgregs->flags)
return -EINVAL;
+ if (dbgregs->dr6 & ~0xffffffffull)
+ return -EINVAL;
+ if (dbgregs->dr7 & ~0xffffffffull)
+ return -EINVAL;
+
memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
kvm_update_dr0123(vcpu);
vcpu->arch.dr6 = dbgregs->dr6;
memcpy(dest, xsave, XSAVE_HDR_OFFSET);
/* Set XSTATE_BV */
+ xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE;
*(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
/*
}
}
+#define XSAVE_MXCSR_OFFSET 24
+
static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
struct kvm_xsave *guest_xsave)
{
u64 xstate_bv =
*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
+ u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
if (cpu_has_xsave) {
/*
* CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility
* with old userspace.
*/
- if (xstate_bv & ~kvm_supported_xcr0())
+ if (xstate_bv & ~kvm_supported_xcr0() ||
+ mxcsr & ~mxcsr_feature_mask)
return -EINVAL;
load_xsave(vcpu, (u8 *)guest_xsave->region);
} else {
- if (xstate_bv & ~XFEATURE_MASK_FPSSE)
+ if (xstate_bv & ~XFEATURE_MASK_FPSSE ||
+ mxcsr & ~mxcsr_feature_mask)
return -EINVAL;
memcpy(&vcpu->arch.guest_fpu.state.fxsave,
guest_xsave->region, sizeof(struct fxregs_state));
};
case KVM_SET_VAPIC_ADDR: {
struct kvm_vapic_addr va;
+ int idx;
r = -EINVAL;
if (!lapic_in_kernel(vcpu))
r = -EFAULT;
if (copy_from_user(&va, argp, sizeof va))
goto out;
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
break;
}
case KVM_X86_SETUP_MCE: {
static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
{
+ int i;
mutex_lock(&kvm->arch.vpit->pit_state.lock);
memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
- kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0);
+ for (i = 0; i < 3; i++)
+ kvm_pit_load_count(kvm, i, ps->channels[i].count, 0);
mutex_unlock(&kvm->arch.vpit->pit_state.lock);
return 0;
}
static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
{
int start = 0;
+ int i;
u32 prev_legacy, cur_legacy;
mutex_lock(&kvm->arch.vpit->pit_state.lock);
prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels,
sizeof(kvm->arch.vpit->pit_state.channels));
kvm->arch.vpit->pit_state.flags = ps->flags;
- kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start);
+ for (i = 0; i < 3; i++)
+ kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count,
+ start && i == 0);
mutex_unlock(&kvm->arch.vpit->pit_state.lock);
return 0;
}
/*
* Even MSRs that are valid in the host may not be exposed
- * to the guests in some cases. We could work around this
- * in VMX with the generic MSR save/load machinery, but it
- * is not really worthwhile since it will really only
- * happen with nested virtualization.
+ * to the guests in some cases.
*/
switch (msrs_to_save[i]) {
case MSR_IA32_BNDCFGS:
if (!kvm_x86_ops->mpx_supported())
continue;
break;
+ case MSR_TSC_AUX:
+ if (!kvm_x86_ops->rdtscp_supported())
+ continue;
+ break;
default:
break;
}
static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
{
- /* TODO: String I/O for in kernel device */
- int r;
+ int r = 0, i;
- if (vcpu->arch.pio.in)
- r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
- vcpu->arch.pio.size, pd);
- else
- r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
- vcpu->arch.pio.port, vcpu->arch.pio.size,
- pd);
+ for (i = 0; i < vcpu->arch.pio.count; i++) {
+ if (vcpu->arch.pio.in)
+ r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
+ vcpu->arch.pio.size, pd);
+ else
+ r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
+ vcpu->arch.pio.port, vcpu->arch.pio.size,
+ pd);
+ if (r)
+ break;
+ pd += vcpu->arch.pio.size;
+ }
return r;
}
if (vcpu->arch.pio.count)
goto data_avail;
+ memset(vcpu->arch.pio_data, 0, size * count);
+
ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
if (ret) {
data_avail:
if (var.unusable) {
memset(desc, 0, sizeof(*desc));
+ if (base3)
+ *base3 = 0;
return false;
}
kvm_x86_ops->set_nmi_mask(emul_to_vcpu(ctxt), masked);
}
+static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
+{
+ return emul_to_vcpu(ctxt)->arch.hflags;
+}
+
+static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
+{
+ kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags);
+}
+
static const struct x86_emulate_ops emulate_ops = {
.read_gpr = emulator_read_gpr,
.write_gpr = emulator_write_gpr,
.intercept = emulator_intercept,
.get_cpuid = emulator_get_cpuid,
.set_nmi_mask = emulator_set_nmi_mask,
+ .get_hflags = emulator_get_hflags,
+ .set_hflags = emulator_set_hflags,
};
static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
ctxt->eflags = kvm_get_rflags(vcpu);
+ ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0;
+
ctxt->eip = kvm_rip_read(vcpu);
ctxt->mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL :
(ctxt->eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_VM86 :
BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK);
BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK);
- ctxt->emul_flags = vcpu->arch.hflags;
init_decode_cache(ctxt);
vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
return dr6;
}
-static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflags, int *r)
+static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r)
{
struct kvm_run *kvm_run = vcpu->run;
- /*
- * rflags is the old, "raw" value of the flags. The new value has
- * not been saved yet.
- *
- * This is correct even for TF set by the guest, because "the
- * processor will not generate this exception after the instruction
- * that sets the TF flag".
- */
- if (unlikely(rflags & X86_EFLAGS_TF)) {
- if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
- kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 |
- DR6_RTM;
- kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
- kvm_run->debug.arch.exception = DB_VECTOR;
- kvm_run->exit_reason = KVM_EXIT_DEBUG;
- *r = EMULATE_USER_EXIT;
- } else {
- vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF;
- /*
- * "Certain debug exceptions may clear bit 0-3. The
- * remaining contents of the DR6 register are never
- * cleared by the processor".
- */
- vcpu->arch.dr6 &= ~15;
- vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
- kvm_queue_exception(vcpu, DB_VECTOR);
- }
+ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+ kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM;
+ kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
+ kvm_run->debug.arch.exception = DB_VECTOR;
+ kvm_run->exit_reason = KVM_EXIT_DEBUG;
+ *r = EMULATE_USER_EXIT;
+ } else {
+ vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF;
+ /*
+ * "Certain debug exceptions may clear bit 0-3. The
+ * remaining contents of the DR6 register are never
+ * cleared by the processor".
+ */
+ vcpu->arch.dr6 &= ~15;
+ vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
+ kvm_queue_exception(vcpu, DB_VECTOR);
}
}
unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
toggle_interruptibility(vcpu, ctxt->interruptibility);
vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
- if (vcpu->arch.hflags != ctxt->emul_flags)
- kvm_set_hflags(vcpu, ctxt->emul_flags);
kvm_rip_write(vcpu, ctxt->eip);
- if (r == EMULATE_DONE)
- kvm_vcpu_check_singlestep(vcpu, rflags, &r);
+ if (r == EMULATE_DONE &&
+ (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
+ kvm_vcpu_do_singlestep(vcpu, &r);
if (!ctxt->have_exception ||
exception_type(ctxt->exception.vector) == EXCPT_TRAP)
__kvm_set_rflags(vcpu, ctxt->eflags);
void kvm_arch_exit(void)
{
+ kvm_lapic_exit();
perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
kvm_x86_ops->patch_hypercall(vcpu, instruction);
- return emulator_write_emulated(ctxt, rip, instruction, 3, NULL);
+ return emulator_write_emulated(ctxt, rip, instruction, 3,
+ &ctxt->exception);
}
static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
}
/* try to inject new event if pending */
- if (vcpu->arch.nmi_pending) {
- if (kvm_x86_ops->nmi_allowed(vcpu)) {
- --vcpu->arch.nmi_pending;
- vcpu->arch.nmi_injected = true;
- kvm_x86_ops->set_nmi(vcpu);
- }
+ if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
+ --vcpu->arch.nmi_pending;
+ vcpu->arch.nmi_injected = true;
+ kvm_x86_ops->set_nmi(vcpu);
} else if (kvm_cpu_has_injectable_intr(vcpu)) {
/*
* Because interrupts can be injected asynchronously, we are
if (inject_pending_event(vcpu, req_int_win) != 0)
req_immediate_exit = true;
/* enable NMI/IRQ window open exits if needed */
- else if (vcpu->arch.nmi_pending)
- kvm_x86_ops->enable_nmi_window(vcpu);
- else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
- kvm_x86_ops->enable_irq_window(vcpu);
+ else {
+ if (vcpu->arch.nmi_pending)
+ kvm_x86_ops->enable_nmi_window(vcpu);
+ if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
+ kvm_x86_ops->enable_irq_window(vcpu);
+ }
if (kvm_lapic_enabled(vcpu)) {
update_cr8_intercept(vcpu);
kvm_x86_ops->prepare_guest_switch(vcpu);
if (vcpu->fpu_active)
kvm_load_guest_fpu(vcpu);
- kvm_load_guest_xcr0(vcpu);
-
vcpu->mode = IN_GUEST_MODE;
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
goto cancel_injection;
}
+ kvm_load_guest_xcr0(vcpu);
+
if (req_immediate_exit)
smp_send_reschedule(vcpu->cpu);
+ trace_kvm_entry(vcpu->vcpu_id);
+ wait_lapic_expire(vcpu);
__kvm_guest_enter();
if (unlikely(vcpu->arch.switch_db_regs)) {
vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
}
- trace_kvm_entry(vcpu->vcpu_id);
- wait_lapic_expire(vcpu);
kvm_x86_ops->run(vcpu);
/*
* KVM_DEBUGREG_WONT_EXIT again.
*/
if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) {
- int i;
-
WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
kvm_x86_ops->sync_dirty_debug_regs(vcpu);
- for (i = 0; i < KVM_NR_DB_REGS; i++)
- vcpu->arch.eff_db[i] = vcpu->arch.db[i];
+ kvm_update_dr0123(vcpu);
+ kvm_update_dr6(vcpu);
+ kvm_update_dr7(vcpu);
+ vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
}
/*
vcpu->mode = OUTSIDE_GUEST_MODE;
smp_wmb();
+ kvm_put_guest_xcr0(vcpu);
+
/* Interrupt is enabled by handle_external_intr() */
kvm_x86_ops->handle_external_intr(vcpu);
mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
return -EINVAL;
+ /* INITs are latched while in SMM */
+ if ((is_smm(vcpu) || vcpu->arch.smi_pending) &&
+ (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED ||
+ mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED))
+ 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);
* and assume host would use all available bits.
* Guest xcr0 would be loaded later.
*/
- kvm_put_guest_xcr0(vcpu);
vcpu->guest_fpu_loaded = 1;
__kernel_fpu_begin();
__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
{
- kvm_put_guest_xcr0(vcpu);
-
if (!vcpu->guest_fpu_loaded) {
vcpu->fpu_counter = 0;
return;
void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
{
+ void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
+
kvmclock_reset(vcpu);
- free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
kvm_x86_ops->vcpu_free(vcpu);
+ free_cpumask_var(wbinvd_dirty_mask);
}
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED))
return true;
else
- return !kvm_event_needs_reinjection(vcpu) &&
- kvm_x86_ops->interrupt_allowed(vcpu);
+ return kvm_can_do_async_pf(vcpu);
}
void kvm_arch_start_assignment(struct kvm *kvm)