Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM changes from Paolo Bonzini:
 "Here are the 3.13 KVM changes.  There was a lot of work on the PPC
  side: the HV and emulation flavors can now coexist in a single kernel
  is probably the most interesting change from a user point of view.

  On the x86 side there are nested virtualization improvements and a few
  bugfixes.

  ARM got transparent huge page support, improved overcommit, and
  support for big endian guests.

  Finally, there is a new interface to connect KVM with VFIO.  This
  helps with devices that use NoSnoop PCI transactions, letting the
  driver in the guest execute WBINVD instructions.  This includes some
  nVidia cards on Windows, that fail to start without these patches and
  the corresponding userspace changes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (146 commits)
  kvm, vmx: Fix lazy FPU on nested guest
  arm/arm64: KVM: PSCI: propagate caller endianness to the incoming vcpu
  arm/arm64: KVM: MMIO support for BE guest
  kvm, cpuid: Fix sparse warning
  kvm: Delete prototype for non-existent function kvm_check_iopl
  kvm: Delete prototype for non-existent function complete_pio
  hung_task: add method to reset detector
  pvclock: detect watchdog reset at pvclock read
  kvm: optimize out smp_mb after srcu_read_unlock
  srcu: API for barrier after srcu read unlock
  KVM: remove vm mmap method
  KVM: IOMMU: hva align mapping page size
  KVM: x86: trace cpuid emulation when called from emulator
  KVM: emulator: cleanup decode_register_operand() a bit
  KVM: emulator: check rex prefix inside decode_register()
  KVM: x86: fix emulation of "movzbl %bpl, %eax"
  kvm_host: typo fix
  KVM: x86: emulate SAHF instruction
  MAINTAINERS: add tree for kvm.git
  Documentation/kvm: add a 00-INDEX file
  ...

1 files changed, 113 insertions, 45 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2b2fce1b2009..b2fe1c252f35 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1498,7 +1498,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 			break;
 
 	if (i == NR_AUTOLOAD_MSRS) {
-		printk_once(KERN_WARNING"Not enough mst switch entries. "
+		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
 	} else if (i == m->nr) {
@@ -1898,16 +1898,12 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 /*
  * 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.
- * This function assumes it is called with the exit reason in vmcs02 being
- * a #PF exception (this is the only case in which KVM injects a #PF when L2
- * is running).
  */
-static int nested_pf_handled(struct kvm_vcpu *vcpu)
+static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
-	/* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */
-	if (!(vmcs12->exception_bitmap & (1u << PF_VECTOR)))
+	if (!(vmcs12->exception_bitmap & (1u << nr)))
 		return 0;
 
 	nested_vmx_vmexit(vcpu);
@@ -1921,8 +1917,8 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 intr_info = nr | INTR_INFO_VALID_MASK;
 
-	if (nr == PF_VECTOR && is_guest_mode(vcpu) &&
-	    !vmx->nested.nested_run_pending && nested_pf_handled(vcpu))
+	if (!reinject && is_guest_mode(vcpu) &&
+	    nested_vmx_check_exception(vcpu, nr))
 		return;
 
 	if (has_error_code) {
@@ -2204,9 +2200,15 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 #ifdef CONFIG_X86_64
 		VM_EXIT_HOST_ADDR_SPACE_SIZE |
 #endif
-		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
+		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT |
+		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
+	if (!(nested_vmx_pinbased_ctls_high & PIN_BASED_VMX_PREEMPTION_TIMER) ||
+	    !(nested_vmx_exit_ctls_high & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)) {
+		nested_vmx_exit_ctls_high &= ~VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
+		nested_vmx_pinbased_ctls_high &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+	}
 	nested_vmx_exit_ctls_high |= (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
-				      VM_EXIT_LOAD_IA32_EFER);
+		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER);
 
 	/* entry controls */
 	rdmsr(MSR_IA32_VMX_ENTRY_CTLS,
@@ -2226,7 +2228,8 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 		nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high);
 	nested_vmx_procbased_ctls_low = 0;
 	nested_vmx_procbased_ctls_high &=
-		CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_USE_TSC_OFFSETING |
+		CPU_BASED_VIRTUAL_INTR_PENDING |
+		CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING |
 		CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING |
 		CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING |
 		CPU_BASED_CR3_STORE_EXITING |
@@ -2252,13 +2255,15 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	nested_vmx_secondary_ctls_low = 0;
 	nested_vmx_secondary_ctls_high &=
 		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+		SECONDARY_EXEC_UNRESTRICTED_GUEST |
 		SECONDARY_EXEC_WBINVD_EXITING;
 
 	if (enable_ept) {
 		/* nested EPT: emulate EPT also to L1 */
 		nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT;
 		nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
-			 VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT;
+			 VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT |
+			 VMX_EPT_INVEPT_BIT;
 		nested_vmx_ept_caps &= vmx_capability.ept;
 		/*
 		 * Since invept is completely emulated we support both global
@@ -3380,8 +3385,10 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	if (enable_ept) {
 		eptp = construct_eptp(cr3);
 		vmcs_write64(EPT_POINTER, eptp);
-		guest_cr3 = is_paging(vcpu) ? kvm_read_cr3(vcpu) :
-			vcpu->kvm->arch.ept_identity_map_addr;
+		if (is_paging(vcpu) || is_guest_mode(vcpu))
+			guest_cr3 = kvm_read_cr3(vcpu);
+		else
+			guest_cr3 = vcpu->kvm->arch.ept_identity_map_addr;
 		ept_load_pdptrs(vcpu);
 	}
 
@@ -4879,6 +4886,17 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
 	hypercall[2] = 0xc1;
 }
 
+static bool nested_cr0_valid(struct vmcs12 *vmcs12, unsigned long val)
+{
+	unsigned long always_on = VMXON_CR0_ALWAYSON;
+
+	if (nested_vmx_secondary_ctls_high &
+		SECONDARY_EXEC_UNRESTRICTED_GUEST &&
+	    nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST))
+		always_on &= ~(X86_CR0_PE | X86_CR0_PG);
+	return (val & always_on) == always_on;
+}
+
 /* called to set cr0 as appropriate for a mov-to-cr0 exit. */
 static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
 {
@@ -4897,9 +4915,7 @@ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
 		val = (val & ~vmcs12->cr0_guest_host_mask) |
 			(vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask);
 
-		/* TODO: will have to take unrestricted guest mode into
-		 * account */
-		if ((val & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON)
+		if (!nested_cr0_valid(vmcs12, val))
 			return 1;
 
 		if (kvm_set_cr0(vcpu, val))
@@ -6627,6 +6643,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 			return 0;
 		else if (is_page_fault(intr_info))
 			return enable_ept;
+		else if (is_no_device(intr_info) &&
+			 !(nested_read_cr0(vmcs12) & X86_CR0_TS))
+			return 0;
 		return vmcs12->exception_bitmap &
 				(1u << (intr_info & INTR_INFO_VECTOR_MASK));
 	case EXIT_REASON_EXTERNAL_INTERRUPT:
@@ -6722,6 +6741,27 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
 	*info2 = vmcs_read32(VM_EXIT_INTR_INFO);
 }
 
+static void nested_adjust_preemption_timer(struct kvm_vcpu *vcpu)
+{
+	u64 delta_tsc_l1;
+	u32 preempt_val_l1, preempt_val_l2, preempt_scale;
+
+	if (!(get_vmcs12(vcpu)->pin_based_vm_exec_control &
+			PIN_BASED_VMX_PREEMPTION_TIMER))
+		return;
+	preempt_scale = native_read_msr(MSR_IA32_VMX_MISC) &
+			MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE;
+	preempt_val_l2 = vmcs_read32(VMX_PREEMPTION_TIMER_VALUE);
+	delta_tsc_l1 = vmx_read_l1_tsc(vcpu, native_read_tsc())
+		- vcpu->arch.last_guest_tsc;
+	preempt_val_l1 = delta_tsc_l1 >> preempt_scale;
+	if (preempt_val_l2 <= preempt_val_l1)
+		preempt_val_l2 = 0;
+	else
+		preempt_val_l2 -= preempt_val_l1;
+	vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, preempt_val_l2);
+}
+
 /*
  * The guest has exited.  See if we can fix it or if we need userspace
  * assistance.
@@ -6736,20 +6776,6 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	if (vmx->emulation_required)
 		return handle_invalid_guest_state(vcpu);
 
-	/*
-	 * the KVM_REQ_EVENT optimization bit is only on for one entry, and if
-	 * we did not inject a still-pending event to L1 now because of
-	 * nested_run_pending, we need to re-enable this bit.
-	 */
-	if (vmx->nested.nested_run_pending)
-		kvm_make_request(KVM_REQ_EVENT, vcpu);
-
-	if (!is_guest_mode(vcpu) && (exit_reason == EXIT_REASON_VMLAUNCH ||
-	    exit_reason == EXIT_REASON_VMRESUME))
-		vmx->nested.nested_run_pending = 1;
-	else
-		vmx->nested.nested_run_pending = 0;
-
 	if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) {
 		nested_vmx_vmexit(vcpu);
 		return 1;
@@ -7061,9 +7087,9 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu,
 	case INTR_TYPE_HARD_EXCEPTION:
 		if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) {
 			u32 err = vmcs_read32(error_code_field);
-			kvm_queue_exception_e(vcpu, vector, err);
+			kvm_requeue_exception_e(vcpu, vector, err);
 		} else
-			kvm_queue_exception(vcpu, vector);
+			kvm_requeue_exception(vcpu, vector);
 		break;
 	case INTR_TYPE_SOFT_INTR:
 		vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field);
@@ -7146,6 +7172,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	atomic_switch_perf_msrs(vmx);
 	debugctlmsr = get_debugctlmsr();
 
+	if (is_guest_mode(vcpu) && !vmx->nested.nested_run_pending)
+		nested_adjust_preemption_timer(vcpu);
 	vmx->__launched = vmx->loaded_vmcs->launched;
 	asm(
 		/* Store host registers */
@@ -7284,6 +7312,16 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
 	trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX);
 
+	/*
+	 * the KVM_REQ_EVENT optimization bit is only on for one entry, and if
+	 * we did not inject a still-pending event to L1 now because of
+	 * nested_run_pending, we need to re-enable this bit.
+	 */
+	if (vmx->nested.nested_run_pending)
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+	vmx->nested.nested_run_pending = 0;
+
 	vmx_complete_atomic_exit(vmx);
 	vmx_recover_nmi_blocking(vmx);
 	vmx_complete_interrupts(vmx);
@@ -7410,8 +7448,7 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	 */
 	if (is_mmio)
 		ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT;
-	else if (vcpu->kvm->arch.iommu_domain &&
-		!(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY))
+	else if (kvm_arch_has_noncoherent_dma(vcpu->kvm))
 		ret = kvm_get_guest_memory_type(vcpu, gfn) <<
 		      VMX_EPT_MT_EPTE_SHIFT;
 	else
@@ -7501,9 +7538,9 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
 	return get_vmcs12(vcpu)->ept_pointer;
 }
 
-static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
+static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
 {
-	int r = kvm_init_shadow_ept_mmu(vcpu, &vcpu->arch.mmu,
+	kvm_init_shadow_ept_mmu(vcpu, &vcpu->arch.mmu,
 			nested_vmx_ept_caps & VMX_EPT_EXECUTE_ONLY_BIT);
 
 	vcpu->arch.mmu.set_cr3           = vmx_set_cr3;
@@ -7511,8 +7548,6 @@ static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault;
 
 	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
-
-	return r;
 }
 
 static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
@@ -7520,6 +7555,20 @@ static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
 	vcpu->arch.walk_mmu = &vcpu->arch.mmu;
 }
 
+static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
+		struct x86_exception *fault)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	WARN_ON(!is_guest_mode(vcpu));
+
+	/* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */
+	if (vmcs12->exception_bitmap & (1u << PF_VECTOR))
+		nested_vmx_vmexit(vcpu);
+	else
+		kvm_inject_page_fault(vcpu, fault);
+}
+
 /*
  * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
  * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
@@ -7533,6 +7582,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 exec_control;
+	u32 exit_control;
 
 	vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
 	vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
@@ -7706,7 +7756,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	 * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER
 	 * bits are further modified by vmx_set_efer() below.
 	 */
-	vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl);
+	exit_control = vmcs_config.vmexit_ctrl;
+	if (vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER)
+		exit_control |= VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
+	vmcs_write32(VM_EXIT_CONTROLS, exit_control);
 
 	/* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are
 	 * emulated by vmx_set_efer(), below.
@@ -7773,6 +7826,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	kvm_set_cr3(vcpu, vmcs12->guest_cr3);
 	kvm_mmu_reset_context(vcpu);
 
+	if (!enable_ept)
+		vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
+
 	/*
 	 * L1 may access the L2's PDPTR, so save them to construct vmcs12
 	 */
@@ -7876,7 +7932,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		return 1;
 	}
 
-	if (((vmcs12->guest_cr0 & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON) ||
+	if (!nested_cr0_valid(vmcs12, vmcs12->guest_cr0) ||
 	    ((vmcs12->guest_cr4 & VMXON_CR4_ALWAYSON) != VMXON_CR4_ALWAYSON)) {
 		nested_vmx_entry_failure(vcpu, vmcs12,
 			EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT);
@@ -7938,6 +7994,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 
 	enter_guest_mode(vcpu);
 
+	vmx->nested.nested_run_pending = 1;
+
 	vmx->nested.vmcs01_tsc_offset = vmcs_read64(TSC_OFFSET);
 
 	cpu = get_cpu();
@@ -8005,7 +8063,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
 	u32 idt_vectoring;
 	unsigned int nr;
 
-	if (vcpu->arch.exception.pending) {
+	if (vcpu->arch.exception.pending && vcpu->arch.exception.reinject) {
 		nr = vcpu->arch.exception.nr;
 		idt_vectoring = nr | VECTORING_INFO_VALID_MASK;
 
@@ -8023,7 +8081,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
 		}
 
 		vmcs12->idt_vectoring_info_field = idt_vectoring;
-	} else if (vcpu->arch.nmi_pending) {
+	} else if (vcpu->arch.nmi_injected) {
 		vmcs12->idt_vectoring_info_field =
 			INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR;
 	} else if (vcpu->arch.interrupt.pending) {
@@ -8105,6 +8163,11 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	vmcs12->guest_pending_dbg_exceptions =
 		vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS);
 
+	if ((vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER) &&
+	    (vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER))
+		vmcs12->vmx_preemption_timer_value =
+			vmcs_read32(VMX_PREEMPTION_TIMER_VALUE);
+
 	/*
 	 * In some cases (usually, nested EPT), L2 is allowed to change its
 	 * own CR3 without exiting. If it has changed it, we must keep it.
@@ -8130,6 +8193,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	vmcs12->guest_ia32_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
 	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT)
 		vmcs12->guest_ia32_pat = vmcs_read64(GUEST_IA32_PAT);
+	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER)
+		vmcs12->guest_ia32_efer = vcpu->arch.efer;
 	vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
 	vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
 	vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
@@ -8201,7 +8266,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	 * fpu_active (which may have changed).
 	 * Note that vmx_set_cr0 refers to efer set above.
 	 */
-	kvm_set_cr0(vcpu, vmcs12->host_cr0);
+	vmx_set_cr0(vcpu, vmcs12->host_cr0);
 	/*
 	 * If we did fpu_activate()/fpu_deactivate() during L2's run, we need
 	 * to apply the same changes to L1's vmcs. We just set cr0 correctly,
@@ -8224,6 +8289,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	kvm_set_cr3(vcpu, vmcs12->host_cr3);
 	kvm_mmu_reset_context(vcpu);
 
+	if (!enable_ept)
+		vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
+
 	if (enable_vpid) {
 		/*
 		 * Trivially support vpid by letting L2s share their parent