static void update_cr8_intercept(struct kvm_vcpu *vcpu);
static void process_nmi(struct kvm_vcpu *vcpu);
+static void enter_smm(struct kvm_vcpu *vcpu);
static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
struct kvm_x86_ops *kvm_x86_ops __read_mostly;
{ "halt_exits", VCPU_STAT(halt_exits) },
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
+ { "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "hypercalls", VCPU_STAT(hypercalls) },
{ "request_irq", VCPU_STAT(request_irq_exits) },
vcpu->arch.pv_time_enabled = false;
}
-static void accumulate_steal_time(struct kvm_vcpu *vcpu)
-{
- u64 delta;
-
- if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
- return;
-
- delta = current->sched_info.run_delay - vcpu->arch.st.last_steal;
- vcpu->arch.st.last_steal = current->sched_info.run_delay;
- vcpu->arch.st.accum_steal = delta;
-}
-
static void record_steal_time(struct kvm_vcpu *vcpu)
{
- accumulate_steal_time(vcpu);
-
if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
return;
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
return;
- vcpu->arch.st.steal.steal += vcpu->arch.st.accum_steal;
- vcpu->arch.st.steal.version += 2;
- vcpu->arch.st.accum_steal = 0;
+ if (vcpu->arch.st.steal.version & 1)
+ vcpu->arch.st.steal.version += 1; /* first time write, random junk */
+
+ vcpu->arch.st.steal.version += 1;
+
+ kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
+ &vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+
+ smp_wmb();
+
+ vcpu->arch.st.steal.steal += current->sched_info.run_delay -
+ vcpu->arch.st.last_steal;
+ vcpu->arch.st.last_steal = current->sched_info.run_delay;
+
+ kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
+ &vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+
+ smp_wmb();
+
+ vcpu->arch.st.steal.version += 1;
kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
case MSR_AMD64_NB_CFG:
case MSR_FAM10H_MMIO_CONF_BASE:
case MSR_AMD64_BU_CFG2:
+ case MSR_IA32_PERF_CTL:
msr_info->data = 0;
break;
case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
r = KVM_MAX_MCE_BANKS;
break;
case KVM_CAP_XCRS:
- r = cpu_has_xsave;
+ r = boot_cpu_has(X86_FEATURE_XSAVE);
break;
case KVM_CAP_TSC_CONTROL:
r = kvm_has_tsc_control;
| KVM_VCPUEVENT_VALID_SMM))
return -EINVAL;
+ if (events->exception.injected &&
+ (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
+ return -EINVAL;
+
process_nmi(vcpu);
vcpu->arch.exception.pending = events->exception.injected;
vcpu->arch.exception.nr = events->exception.nr;
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;
/* Set XSTATE_BV and possibly XCOMP_BV. */
xsave->header.xfeatures = xstate_bv;
- if (cpu_has_xsaves)
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
/*
static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
struct kvm_xsave *guest_xsave)
{
- if (cpu_has_xsave) {
+ if (boot_cpu_has(X86_FEATURE_XSAVE)) {
memset(guest_xsave, 0, sizeof(struct kvm_xsave));
fill_xsave((u8 *) guest_xsave->region, vcpu);
} else {
u64 xstate_bv =
*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
- if (cpu_has_xsave) {
+ if (boot_cpu_has(X86_FEATURE_XSAVE)) {
/*
* Here we allow setting states that are not present in
* CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility
static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu,
struct kvm_xcrs *guest_xcrs)
{
- if (!cpu_has_xsave) {
+ if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
guest_xcrs->nr_xcrs = 0;
return;
}
{
int i, r = 0;
- if (!cpu_has_xsave)
+ if (!boot_cpu_has(X86_FEATURE_XSAVE))
return -EINVAL;
if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags)
/* This is a good place to trace that we are exiting SMM. */
trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, false);
- if (unlikely(vcpu->arch.smi_pending)) {
- kvm_make_request(KVM_REQ_SMI, vcpu);
- vcpu->arch.smi_pending = 0;
- } else {
- /* Process a latched INIT, if any. */
- kvm_make_request(KVM_REQ_EVENT, vcpu);
- }
+ /* Process a latched INIT or SMI, if any. */
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
}
kvm_mmu_reset_context(vcpu);
perf_register_guest_info_callbacks(&kvm_guest_cbs);
- if (cpu_has_xsave)
+ if (boot_cpu_has(X86_FEATURE_XSAVE))
host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
kvm_lapic_init();
}
/* try to inject new event if pending */
- if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
+ if (vcpu->arch.smi_pending && !is_smm(vcpu)) {
+ vcpu->arch.smi_pending = false;
+ enter_smm(vcpu);
+ } else 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);
kvm_x86_ops->set_irq(vcpu);
}
}
+
return 0;
}
#define put_smstate(type, buf, offset, val) \
*(type *)((buf) + (offset) - 0x7e00) = val
-static u32 process_smi_get_segment_flags(struct kvm_segment *seg)
+static u32 enter_smm_get_segment_flags(struct kvm_segment *seg)
{
u32 flags = 0;
flags |= seg->g << 23;
return flags;
}
-static void process_smi_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
+static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
{
struct kvm_segment seg;
int offset;
put_smstate(u32, buf, offset + 8, seg.base);
put_smstate(u32, buf, offset + 4, seg.limit);
- put_smstate(u32, buf, offset, process_smi_get_segment_flags(&seg));
+ put_smstate(u32, buf, offset, enter_smm_get_segment_flags(&seg));
}
#ifdef CONFIG_X86_64
-static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
+static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
{
struct kvm_segment seg;
int offset;
kvm_get_segment(vcpu, &seg, n);
offset = 0x7e00 + n * 16;
- flags = process_smi_get_segment_flags(&seg) >> 8;
+ flags = enter_smm_get_segment_flags(&seg) >> 8;
put_smstate(u16, buf, offset, seg.selector);
put_smstate(u16, buf, offset + 2, flags);
put_smstate(u32, buf, offset + 4, seg.limit);
}
#endif
-static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf)
+static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
{
struct desc_ptr dt;
struct kvm_segment seg;
put_smstate(u32, buf, 0x7fc4, seg.selector);
put_smstate(u32, buf, 0x7f64, seg.base);
put_smstate(u32, buf, 0x7f60, seg.limit);
- put_smstate(u32, buf, 0x7f5c, process_smi_get_segment_flags(&seg));
+ put_smstate(u32, buf, 0x7f5c, enter_smm_get_segment_flags(&seg));
kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
put_smstate(u32, buf, 0x7fc0, seg.selector);
put_smstate(u32, buf, 0x7f80, seg.base);
put_smstate(u32, buf, 0x7f7c, seg.limit);
- put_smstate(u32, buf, 0x7f78, process_smi_get_segment_flags(&seg));
+ put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg));
kvm_x86_ops->get_gdt(vcpu, &dt);
put_smstate(u32, buf, 0x7f74, dt.address);
put_smstate(u32, buf, 0x7f54, dt.size);
for (i = 0; i < 6; i++)
- process_smi_save_seg_32(vcpu, buf, i);
+ enter_smm_save_seg_32(vcpu, buf, i);
put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu));
put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
}
-static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf)
+static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
{
#ifdef CONFIG_X86_64
struct desc_ptr dt;
kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
put_smstate(u16, buf, 0x7e90, seg.selector);
- put_smstate(u16, buf, 0x7e92, process_smi_get_segment_flags(&seg) >> 8);
+ put_smstate(u16, buf, 0x7e92, enter_smm_get_segment_flags(&seg) >> 8);
put_smstate(u32, buf, 0x7e94, seg.limit);
put_smstate(u64, buf, 0x7e98, seg.base);
kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
put_smstate(u16, buf, 0x7e70, seg.selector);
- put_smstate(u16, buf, 0x7e72, process_smi_get_segment_flags(&seg) >> 8);
+ put_smstate(u16, buf, 0x7e72, enter_smm_get_segment_flags(&seg) >> 8);
put_smstate(u32, buf, 0x7e74, seg.limit);
put_smstate(u64, buf, 0x7e78, seg.base);
put_smstate(u64, buf, 0x7e68, dt.address);
for (i = 0; i < 6; i++)
- process_smi_save_seg_64(vcpu, buf, i);
+ enter_smm_save_seg_64(vcpu, buf, i);
#else
WARN_ON_ONCE(1);
#endif
}
-static void process_smi(struct kvm_vcpu *vcpu)
+static void enter_smm(struct kvm_vcpu *vcpu)
{
struct kvm_segment cs, ds;
struct desc_ptr dt;
char buf[512];
u32 cr0;
- if (is_smm(vcpu)) {
- vcpu->arch.smi_pending = true;
- return;
- }
-
trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
vcpu->arch.hflags |= HF_SMM_MASK;
memset(buf, 0, 512);
if (guest_cpuid_has_longmode(vcpu))
- process_smi_save_state_64(vcpu, buf);
+ enter_smm_save_state_64(vcpu, buf);
else
- process_smi_save_state_32(vcpu, buf);
+ enter_smm_save_state_32(vcpu, buf);
kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf));
kvm_mmu_reset_context(vcpu);
}
+static void process_smi(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.smi_pending = true;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+}
+
void kvm_make_scan_ioapic_request(struct kvm *kvm)
{
kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
if (inject_pending_event(vcpu, req_int_win) != 0)
req_immediate_exit = true;
- /* enable NMI/IRQ window open exits if needed */
else {
+ /* Enable NMI/IRQ window open exits if needed.
+ *
+ * SMIs have two cases: 1) they can be nested, and
+ * then there is nothing to do here because RSM will
+ * cause a vmexit anyway; 2) or the SMI can be pending
+ * because inject_pending_event has completed the
+ * injection of an IRQ or NMI from the previous vmexit,
+ * and then we request an immediate exit to inject the SMI.
+ */
+ if (vcpu->arch.smi_pending && !is_smm(vcpu))
+ req_immediate_exit = true;
if (vcpu->arch.nmi_pending)
kvm_x86_ops->enable_nmi_window(vcpu);
if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
kvm_load_guest_xcr0(vcpu);
- if (req_immediate_exit)
+ if (req_immediate_exit) {
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
smp_send_reschedule(vcpu->cpu);
+ }
trace_kvm_entry(vcpu->vcpu_id);
wait_lapic_expire(vcpu);
static void fx_init(struct kvm_vcpu *vcpu)
{
fpstate_init(&vcpu->arch.guest_fpu.state);
- if (cpu_has_xsaves)
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
vcpu->arch.guest_fpu.state.xsave.header.xcomp_bv =
host_xcr0 | XSTATE_COMPACTION_ENABLED;
{
vcpu->arch.hflags = 0;
+ vcpu->arch.smi_pending = 0;
atomic_set(&vcpu->arch.nmi_queued, 0);
vcpu->arch.nmi_pending = 0;
vcpu->arch.nmi_injected = false;
kvm_page_track_init(kvm);
kvm_mmu_init_vm(kvm);
+ if (kvm_x86_ops->vm_init)
+ return kvm_x86_ops->vm_init(kvm);
+
return 0;
}
slot = id_to_memslot(slots, id);
if (size) {
- if (WARN_ON(slot->npages))
+ if (slot->npages)
return -EEXIST;
/*
x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0);
x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0);
}
+ if (kvm_x86_ops->vm_destroy)
+ kvm_x86_ops->vm_destroy(kvm);
kvm_iommu_unmap_guest(kvm);
kfree(kvm->arch.vpic);
kfree(kvm->arch.vioapic);
}
EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
+bool kvm_arch_has_irq_bypass(void)
+{
+ return kvm_x86_ops->update_pi_irte != NULL;
+}
+
int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
struct irq_bypass_producer *prod)
{
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
- if (kvm_x86_ops->update_pi_irte) {
- irqfd->producer = prod;
- return kvm_x86_ops->update_pi_irte(irqfd->kvm,
- prod->irq, irqfd->gsi, 1);
- }
+ irqfd->producer = prod;
- return -EINVAL;
+ return kvm_x86_ops->update_pi_irte(irqfd->kvm,
+ prod->irq, irqfd->gsi, 1);
}
void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
- if (!kvm_x86_ops->update_pi_irte) {
- WARN_ON(irqfd->producer != NULL);
- return;
- }
-
WARN_ON(irqfd->producer != prod);
irqfd->producer = NULL;
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi);
projects / linux-2.6-block.git / blobdiff