/* The guest-physical address of the current VMCS L1 keeps for L2 */
gpa_t current_vmptr;
- /* The host-usable pointer to the above */
- struct page *current_vmcs12_page;
- struct vmcs12 *current_vmcs12;
/*
* Cache of the guest's VMCS, existing outside of guest memory.
* Loaded from guest memory during VMPTRLD. Flushed to guest
- * memory during VMXOFF, VMCLEAR, VMPTRLD.
+ * memory during VMCLEAR and VMPTRLD.
*/
struct vmcs12 *cached_vmcs12;
/*
struct kvm_vcpu vcpu;
unsigned long host_rsp;
u8 fail;
- bool nmi_known_unmasked;
u32 exit_intr_info;
u32 idt_vectoring_info;
ulong rflags;
static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
static int alloc_identity_pagetable(struct kvm *kvm);
+static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
+static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
+static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
+ u16 error_code);
static DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
vmx_set_interrupt_shadow(vcpu, 0);
}
+static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
+ unsigned long exit_qual)
+{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ unsigned int nr = vcpu->arch.exception.nr;
+ u32 intr_info = nr | INTR_INFO_VALID_MASK;
+
+ if (vcpu->arch.exception.has_error_code) {
+ vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code;
+ intr_info |= INTR_INFO_DELIVER_CODE_MASK;
+ }
+
+ if (kvm_exception_is_soft(nr))
+ intr_info |= INTR_TYPE_SOFT_EXCEPTION;
+ else
+ intr_info |= INTR_TYPE_HARD_EXCEPTION;
+
+ if (!(vmcs12->idt_vectoring_info_field & VECTORING_INFO_VALID_MASK) &&
+ vmx_get_nmi_mask(vcpu))
+ intr_info |= INTR_INFO_UNBLOCK_NMI;
+
+ nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual);
+}
+
/*
* KVM wants to inject page-faults which it got to the guest. This function
* checks whether in a nested guest, we need to inject them to L1 or L2.
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
unsigned int nr = vcpu->arch.exception.nr;
- if (!((vmcs12->exception_bitmap & (1u << nr)) ||
- (nr == PF_VECTOR && vcpu->arch.exception.nested_apf)))
- return 0;
+ if (nr == PF_VECTOR) {
+ if (vcpu->arch.exception.nested_apf) {
+ nested_vmx_inject_exception_vmexit(vcpu,
+ vcpu->arch.apf.nested_apf_token);
+ return 1;
+ }
+ /*
+ * FIXME: we must not write CR2 when L1 intercepts an L2 #PF exception.
+ * The fix is to add the ancillary datum (CR2 or DR6) to structs
+ * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6
+ * can be written only when inject_pending_event runs. This should be
+ * conditional on a new capability---if the capability is disabled,
+ * kvm_multiple_exception would write the ancillary information to
+ * CR2 or DR6, for backwards ABI-compatibility.
+ */
+ if (nested_vmx_is_page_fault_vmexit(vmcs12,
+ vcpu->arch.exception.error_code)) {
+ nested_vmx_inject_exception_vmexit(vcpu, vcpu->arch.cr2);
+ return 1;
+ }
+ } else {
+ unsigned long exit_qual = 0;
+ if (nr == DB_VECTOR)
+ exit_qual = vcpu->arch.dr6;
- if (vcpu->arch.exception.nested_apf) {
- vmcs_write32(VM_EXIT_INTR_ERROR_CODE, vcpu->arch.exception.error_code);
- nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
- PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
- INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
- vcpu->arch.apf.nested_apf_token);
- return 1;
+ if (vmcs12->exception_bitmap & (1u << nr)) {
+ nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+ return 1;
+ }
}
- nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
- vmcs_read32(VM_EXIT_INTR_INFO),
- vmcs_readl(EXIT_QUALIFICATION));
- return 1;
+ return 0;
}
static void vmx_queue_exception(struct kvm_vcpu *vcpu)
* reason is that if one of these bits is necessary, it will appear
* in vmcs01 and prepare_vmcs02, when it bitwise-or's the control
* fields of vmcs01 and vmcs02, will turn these bits off - and
- * nested_vmx_exit_handled() will not pass related exits to L1.
+ * nested_vmx_exit_reflected() will not pass related exits to L1.
* These rules have exceptions below.
*/
return enable_apicv;
}
+static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
+{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ gfn_t gfn;
+
+ /*
+ * Don't need to mark the APIC access page dirty; it is never
+ * written to by the CPU during APIC virtualization.
+ */
+
+ if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
+ gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT;
+ kvm_vcpu_mark_page_dirty(vcpu, gfn);
+ }
+
+ if (nested_cpu_has_posted_intr(vmcs12)) {
+ gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT;
+ kvm_vcpu_mark_page_dirty(vcpu, gfn);
+ }
+}
+
+
static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
void *vapic_page;
u16 status;
- if (vmx->nested.pi_desc &&
- vmx->nested.pi_pending) {
- vmx->nested.pi_pending = false;
- if (!pi_test_and_clear_on(vmx->nested.pi_desc))
- return;
-
- max_irr = find_last_bit(
- (unsigned long *)vmx->nested.pi_desc->pir, 256);
+ if (!vmx->nested.pi_desc || !vmx->nested.pi_pending)
+ return;
- if (max_irr == 256)
- return;
+ vmx->nested.pi_pending = false;
+ if (!pi_test_and_clear_on(vmx->nested.pi_desc))
+ return;
+ max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
+ if (max_irr != 256) {
vapic_page = kmap(vmx->nested.virtual_apic_page);
__kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page);
kunmap(vmx->nested.virtual_apic_page);
vmcs_write16(GUEST_INTR_STATUS, status);
}
}
+
+ nested_mark_vmcs12_pages_dirty(vcpu);
}
-static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
+static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
+ bool nested)
{
#ifdef CONFIG_SMP
+ int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR;
+
if (vcpu->mode == IN_GUEST_MODE) {
struct vcpu_vmx *vmx = to_vmx(vcpu);
*/
WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc));
- apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
- POSTED_INTR_VECTOR);
+ apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
return true;
}
#endif
if (is_guest_mode(vcpu) &&
vector == vmx->nested.posted_intr_nv) {
/* the PIR and ON have been set by L1. */
- kvm_vcpu_trigger_posted_interrupt(vcpu);
+ kvm_vcpu_trigger_posted_interrupt(vcpu, true);
/*
* If a posted intr is not recognized by hardware,
* we will accomplish it in the next vmentry.
if (pi_test_and_set_on(&vmx->pi_desc))
return;
- if (!kvm_vcpu_trigger_posted_interrupt(vcpu))
+ if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
kvm_vcpu_kick(vcpu);
}
return 1;
}
+static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
+{
+ vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS);
+ vmcs_write64(VMCS_LINK_POINTER, -1ull);
+}
+
static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
{
if (vmx->nested.current_vmptr == -1ull)
return;
- /* current_vmptr and current_vmcs12 are always set/reset together */
- if (WARN_ON(vmx->nested.current_vmcs12 == NULL))
- return;
-
if (enable_shadow_vmcs) {
/* copy to memory all shadowed fields in case
they were modified */
copy_shadow_to_vmcs12(vmx);
vmx->nested.sync_shadow_vmcs = false;
- vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
- SECONDARY_EXEC_SHADOW_VMCS);
- vmcs_write64(VMCS_LINK_POINTER, -1ull);
+ vmx_disable_shadow_vmcs(vmx);
}
vmx->nested.posted_intr_nv = -1;
/* Flush VMCS12 to guest memory */
- memcpy(vmx->nested.current_vmcs12, vmx->nested.cached_vmcs12,
- VMCS12_SIZE);
+ kvm_vcpu_write_guest_page(&vmx->vcpu,
+ vmx->nested.current_vmptr >> PAGE_SHIFT,
+ vmx->nested.cached_vmcs12, 0, VMCS12_SIZE);
- kunmap(vmx->nested.current_vmcs12_page);
- nested_release_page(vmx->nested.current_vmcs12_page);
vmx->nested.current_vmptr = -1ull;
- vmx->nested.current_vmcs12 = NULL;
}
/*
vmx->nested.vmxon = false;
free_vpid(vmx->nested.vpid02);
- nested_release_vmcs12(vmx);
+ vmx->nested.posted_intr_nv = -1;
+ vmx->nested.current_vmptr = -1ull;
if (vmx->nested.msr_bitmap) {
free_page((unsigned long)vmx->nested.msr_bitmap);
vmx->nested.msr_bitmap = NULL;
}
if (enable_shadow_vmcs) {
+ vmx_disable_shadow_vmcs(vmx);
vmcs_clear(vmx->vmcs01.shadow_vmcs);
free_vmcs(vmx->vmcs01.shadow_vmcs);
vmx->vmcs01.shadow_vmcs = NULL;
}
nested_release_vmcs12(vmx);
- vmx->nested.current_vmcs12 = new_vmcs12;
- vmx->nested.current_vmcs12_page = page;
/*
* Load VMCS12 from guest memory since it is not already
* cached.
*/
- memcpy(vmx->nested.cached_vmcs12,
- vmx->nested.current_vmcs12, VMCS12_SIZE);
+ memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE);
+ kunmap(page);
+ nested_release_page_clean(page);
+
set_current_vmptr(vmx, vmptr);
}
* should handle it ourselves in L0 (and then continue L2). Only call this
* when in is_guest_mode (L2).
*/
-static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
+static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
{
u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- u32 exit_reason = vmx->exit_reason;
trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason,
vmcs_readl(EXIT_QUALIFICATION),
vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
KVM_ISA_VMX);
+ /*
+ * The host physical addresses of some pages of guest memory
+ * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU
+ * may write to these pages via their host physical address while
+ * L2 is running, bypassing any address-translation-based dirty
+ * tracking (e.g. EPT write protection).
+ *
+ * Mark them dirty on every exit from L2 to prevent them from
+ * getting out of sync with dirty tracking.
+ */
+ nested_mark_vmcs12_pages_dirty(vcpu);
+
if (vmx->nested.nested_run_pending)
return false;
}
}
+static int nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason)
+{
+ u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+
+ /*
+ * At this point, the exit interruption info in exit_intr_info
+ * is only valid for EXCEPTION_NMI exits. For EXTERNAL_INTERRUPT
+ * we need to query the in-kernel LAPIC.
+ */
+ WARN_ON(exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT);
+ if ((exit_intr_info &
+ (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) ==
+ (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) {
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ vmcs12->vm_exit_intr_error_code =
+ vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+ }
+
+ nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info,
+ vmcs_readl(EXIT_QUALIFICATION));
+ return 1;
+}
+
static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
{
*info1 = vmcs_readl(EXIT_QUALIFICATION);
if (vmx->emulation_required)
return handle_invalid_guest_state(vcpu);
- if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) {
- nested_vmx_vmexit(vcpu, exit_reason,
- vmcs_read32(VM_EXIT_INTR_INFO),
- vmcs_readl(EXIT_QUALIFICATION));
- return 1;
- }
+ if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason))
+ return nested_vmx_reflect_vmexit(vcpu, exit_reason);
if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
dump_vmcs();
vmx->nested.posted_intr_nv = -1;
vmx->nested.current_vmptr = -1ull;
- vmx->nested.current_vmcs12 = NULL;
vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
WARN_ON(!is_guest_mode(vcpu));
- if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code))
- nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason,
- vmcs_read32(VM_EXIT_INTR_INFO),
- vmcs_readl(EXIT_QUALIFICATION));
- else
+ if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) {
+ vmcs12->vm_exit_intr_error_code = fault->error_code;
+ nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
+ PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
+ INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
+ fault->address);
+ } else {
kvm_inject_page_fault(vcpu, fault);
+ }
}
static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
vmcs12->vm_entry_instruction_len);
vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
vmcs12->guest_interruptibility_info);
+ vmx->loaded_vmcs->nmi_known_unmasked =
+ !(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI);
} else {
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
}
/* Posted interrupts setting is only taken from vmcs12. */
if (nested_cpu_has_posted_intr(vmcs12)) {
- /*
- * Note that we use L0's vector here and in
- * vmx_deliver_nested_posted_interrupt.
- */
vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
vmx->nested.pi_pending = false;
- vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
+ vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);
} else {
exec_control &= ~PIN_BASED_POSTED_INTR;
}
* "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
* vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
* !enable_ept, EB.PF is 1, so the "or" will always be 1.
- *
- * A problem with this approach (when !enable_ept) is that L1 may be
- * injected with more page faults than it asked for. This could have
- * caused problems, but in practice existing hypervisors don't care.
- * To fix this, we will need to emulate the PFEC checking (on the L1
- * page tables), using walk_addr(), when injecting PFs to L1.
*/
vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
enable_ept ? vmcs12->page_fault_error_code_mask : 0);
vmcs12->vm_exit_reason = exit_reason;
vmcs12->exit_qualification = exit_qualification;
-
vmcs12->vm_exit_intr_info = exit_intr_info;
- if ((vmcs12->vm_exit_intr_info &
- (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) ==
- (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK))
- vmcs12->vm_exit_intr_error_code =
- vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+
vmcs12->idt_vectoring_info_field = 0;
vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
*/
vmx_flush_tlb(vcpu);
}
-
+ /* Restore posted intr vector. */
+ if (nested_cpu_has_posted_intr(vmcs12))
+ vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs);
vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp);
git.samba.org / sfrench / cifs-2.6.git / blobdiff