1 files changed, 210 insertions, 123 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 138ceffc6377..801332edefc3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -354,6 +354,7 @@ struct vmcs02_list {
 struct nested_vmx {
 	/* Has the level1 guest done vmxon? */
 	bool vmxon;
+	gpa_t vmxon_ptr;
 
 	/* The guest-physical address of the current VMCS L1 keeps for L2 */
 	gpa_t current_vmptr;
@@ -413,7 +414,6 @@ struct vcpu_vmx {
 	struct kvm_vcpu       vcpu;
 	unsigned long         host_rsp;
 	u8                    fail;
-	u8                    cpl;
 	bool                  nmi_known_unmasked;
 	u32                   exit_intr_info;
 	u32                   idt_vectoring_info;
@@ -2283,7 +2283,7 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	rdmsr(MSR_IA32_VMX_EXIT_CTLS,
 		nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high);
 	nested_vmx_exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
-	/* Note that guest use of VM_EXIT_ACK_INTR_ON_EXIT is not supported. */
+
 	nested_vmx_exit_ctls_high &=
 #ifdef CONFIG_X86_64
 		VM_EXIT_HOST_ADDR_SPACE_SIZE |
@@ -2291,7 +2291,8 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
 	nested_vmx_exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
 		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
-		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
+		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
+
 	if (vmx_mpx_supported())
 		nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
 
@@ -2353,12 +2354,11 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 			 VMX_EPT_INVEPT_BIT;
 		nested_vmx_ept_caps &= vmx_capability.ept;
 		/*
-		 * Since invept is completely emulated we support both global
-		 * and context invalidation independent of what host cpu
-		 * supports
+		 * For nested guests, we don't do anything specific
+		 * for single context invalidation. Hence, only advertise
+		 * support for global context invalidation.
 		 */
-		nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT |
-			VMX_EPT_EXTENT_CONTEXT_BIT;
+		nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT;
 	} else
 		nested_vmx_ept_caps = 0;
 
@@ -3186,10 +3186,6 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 	fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
 	fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
 	fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
-
-	/* CPL is always 0 when CPU enters protected mode */
-	__set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
-	vmx->cpl = 0;
 }
 
 static void fix_rmode_seg(int seg, struct kvm_segment *save)
@@ -3591,22 +3587,14 @@ static int vmx_get_cpl(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (!is_protmode(vcpu))
+	if (unlikely(vmx->rmode.vm86_active))
 		return 0;
-
-	if (!is_long_mode(vcpu)
-	    && (kvm_get_rflags(vcpu) & X86_EFLAGS_VM)) /* if virtual 8086 */
-		return 3;
-
-	if (!test_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail)) {
-		__set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
-		vmx->cpl = vmx_read_guest_seg_selector(vmx, VCPU_SREG_CS) & 3;
+	else {
+		int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS);
+		return AR_DPL(ar);
 	}
-
-	return vmx->cpl;
 }
 
-
 static u32 vmx_segment_access_rights(struct kvm_segment *var)
 {
 	u32 ar;
@@ -3634,8 +3622,6 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
 
 	vmx_segment_cache_clear(vmx);
-	if (seg == VCPU_SREG_CS)
-		__clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
 
 	if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) {
 		vmx->rmode.segs[seg] = *var;
@@ -4564,6 +4550,16 @@ static bool nested_exit_on_intr(struct kvm_vcpu *vcpu)
 		PIN_BASED_EXT_INTR_MASK;
 }
 
+/*
+ * In nested virtualization, check if L1 has set
+ * VM_EXIT_ACK_INTR_ON_EXIT
+ */
+static bool nested_exit_intr_ack_set(struct kvm_vcpu *vcpu)
+{
+	return get_vmcs12(vcpu)->vm_exit_controls &
+		VM_EXIT_ACK_INTR_ON_EXIT;
+}
+
 static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu)
 {
 	return get_vmcs12(vcpu)->pin_based_vm_exec_control &
@@ -4878,6 +4874,9 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 		      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
 			vcpu->arch.dr6 &= ~15;
 			vcpu->arch.dr6 |= dr6;
+			if (!(dr6 & ~DR6_RESERVED)) /* icebp */
+				skip_emulated_instruction(vcpu);
+
 			kvm_queue_exception(vcpu, DB_VECTOR);
 			return 1;
 		}
@@ -5166,7 +5165,7 @@ static int handle_dr(struct kvm_vcpu *vcpu)
 			return 1;
 		kvm_register_write(vcpu, reg, val);
 	} else
-		if (kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg]))
+		if (kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg)))
 			return 1;
 
 	skip_emulated_instruction(vcpu);
@@ -5439,7 +5438,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 	}
 
 	/* clear all local breakpoint enable flags */
-	vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55);
+	vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x55);
 
 	/*
 	 * TODO: What about debug traps on tss switch?
@@ -5565,6 +5564,10 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 	gpa_t gpa;
 
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
+	if (!kvm_io_bus_write(vcpu->kvm, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
+		skip_emulated_instruction(vcpu);
+		return 1;
+	}
 
 	ret = handle_mmio_page_fault_common(vcpu, gpa, true);
 	if (likely(ret == RET_MMIO_PF_EMULATE))
@@ -5669,12 +5672,24 @@ static int handle_pause(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static int handle_invalid_op(struct kvm_vcpu *vcpu)
+static int handle_nop(struct kvm_vcpu *vcpu)
 {
-	kvm_queue_exception(vcpu, UD_VECTOR);
+	skip_emulated_instruction(vcpu);
 	return 1;
 }
 
+static int handle_mwait(struct kvm_vcpu *vcpu)
+{
+	printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n");
+	return handle_nop(vcpu);
+}
+
+static int handle_monitor(struct kvm_vcpu *vcpu)
+{
+	printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
+	return handle_nop(vcpu);
+}
+
 /*
  * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12.
  * We could reuse a single VMCS for all the L2 guests, but we also want the
@@ -5812,6 +5827,154 @@ static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer)
 }
 
 /*
+ * Decode the memory-address operand of a vmx instruction, as recorded on an
+ * exit caused by such an instruction (run by a guest hypervisor).
+ * On success, returns 0. When the operand is invalid, returns 1 and throws
+ * #UD or #GP.
+ */
+static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
+				 unsigned long exit_qualification,
+				 u32 vmx_instruction_info, gva_t *ret)
+{
+	/*
+	 * According to Vol. 3B, "Information for VM Exits Due to Instruction
+	 * Execution", on an exit, vmx_instruction_info holds most of the
+	 * addressing components of the operand. Only the displacement part
+	 * is put in exit_qualification (see 3B, "Basic VM-Exit Information").
+	 * For how an actual address is calculated from all these components,
+	 * refer to Vol. 1, "Operand Addressing".
+	 */
+	int  scaling = vmx_instruction_info & 3;
+	int  addr_size = (vmx_instruction_info >> 7) & 7;
+	bool is_reg = vmx_instruction_info & (1u << 10);
+	int  seg_reg = (vmx_instruction_info >> 15) & 7;
+	int  index_reg = (vmx_instruction_info >> 18) & 0xf;
+	bool index_is_valid = !(vmx_instruction_info & (1u << 22));
+	int  base_reg       = (vmx_instruction_info >> 23) & 0xf;
+	bool base_is_valid  = !(vmx_instruction_info & (1u << 27));
+
+	if (is_reg) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	/* Addr = segment_base + offset */
+	/* offset = base + [index * scale] + displacement */
+	*ret = vmx_get_segment_base(vcpu, seg_reg);
+	if (base_is_valid)
+		*ret += kvm_register_read(vcpu, base_reg);
+	if (index_is_valid)
+		*ret += kvm_register_read(vcpu, index_reg)<<scaling;
+	*ret += exit_qualification; /* holds the displacement */
+
+	if (addr_size == 1) /* 32 bit */
+		*ret &= 0xffffffff;
+
+	/*
+	 * TODO: throw #GP (and return 1) in various cases that the VM*
+	 * instructions require it - e.g., offset beyond segment limit,
+	 * unusable or unreadable/unwritable segment, non-canonical 64-bit
+	 * address, and so on. Currently these are not checked.
+	 */
+	return 0;
+}
+
+/*
+ * This function performs the various checks including
+ * - if it's 4KB aligned
+ * - No bits beyond the physical address width are set
+ * - Returns 0 on success or else 1
+ * (Intel SDM Section 30.3)
+ */
+static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
+				  gpa_t *vmpointer)
+{
+	gva_t gva;
+	gpa_t vmptr;
+	struct x86_exception e;
+	struct page *page;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int maxphyaddr = cpuid_maxphyaddr(vcpu);
+
+	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+			vmcs_read32(VMX_INSTRUCTION_INFO), &gva))
+		return 1;
+
+	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
+				sizeof(vmptr), &e)) {
+		kvm_inject_page_fault(vcpu, &e);
+		return 1;
+	}
+
+	switch (exit_reason) {
+	case EXIT_REASON_VMON:
+		/*
+		 * SDM 3: 24.11.5
+		 * The first 4 bytes of VMXON region contain the supported
+		 * VMCS revision identifier
+		 *
+		 * Note - IA32_VMX_BASIC[48] will never be 1
+		 * for the nested case;
+		 * which replaces physical address width with 32
+		 *
+		 */
+		if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) {
+			nested_vmx_failInvalid(vcpu);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+
+		page = nested_get_page(vcpu, vmptr);
+		if (page == NULL ||
+		    *(u32 *)kmap(page) != VMCS12_REVISION) {
+			nested_vmx_failInvalid(vcpu);
+			kunmap(page);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		kunmap(page);
+		vmx->nested.vmxon_ptr = vmptr;
+		break;
+	case EXIT_REASON_VMCLEAR:
+		if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) {
+			nested_vmx_failValid(vcpu,
+					     VMXERR_VMCLEAR_INVALID_ADDRESS);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+
+		if (vmptr == vmx->nested.vmxon_ptr) {
+			nested_vmx_failValid(vcpu,
+					     VMXERR_VMCLEAR_VMXON_POINTER);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		break;
+	case EXIT_REASON_VMPTRLD:
+		if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) {
+			nested_vmx_failValid(vcpu,
+					     VMXERR_VMPTRLD_INVALID_ADDRESS);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+
+		if (vmptr == vmx->nested.vmxon_ptr) {
+			nested_vmx_failValid(vcpu,
+					     VMXERR_VMCLEAR_VMXON_POINTER);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		break;
+	default:
+		return 1; /* shouldn't happen */
+	}
+
+	if (vmpointer)
+		*vmpointer = vmptr;
+	return 0;
+}
+
+/*
  * Emulate the VMXON instruction.
  * Currently, we just remember that VMX is active, and do not save or even
  * inspect the argument to VMXON (the so-called "VMXON pointer") because we
@@ -5849,6 +6012,10 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		kvm_inject_gp(vcpu, 0);
 		return 1;
 	}
+
+	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL))
+		return 1;
+
 	if (vmx->nested.vmxon) {
 		nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
 		skip_emulated_instruction(vcpu);
@@ -5971,87 +6138,19 @@ static int handle_vmoff(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-/*
- * Decode the memory-address operand of a vmx instruction, as recorded on an
- * exit caused by such an instruction (run by a guest hypervisor).
- * On success, returns 0. When the operand is invalid, returns 1 and throws
- * #UD or #GP.
- */
-static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
-				 unsigned long exit_qualification,
-				 u32 vmx_instruction_info, gva_t *ret)
-{
-	/*
-	 * According to Vol. 3B, "Information for VM Exits Due to Instruction
-	 * Execution", on an exit, vmx_instruction_info holds most of the
-	 * addressing components of the operand. Only the displacement part
-	 * is put in exit_qualification (see 3B, "Basic VM-Exit Information").
-	 * For how an actual address is calculated from all these components,
-	 * refer to Vol. 1, "Operand Addressing".
-	 */
-	int  scaling = vmx_instruction_info & 3;
-	int  addr_size = (vmx_instruction_info >> 7) & 7;
-	bool is_reg = vmx_instruction_info & (1u << 10);
-	int  seg_reg = (vmx_instruction_info >> 15) & 7;
-	int  index_reg = (vmx_instruction_info >> 18) & 0xf;
-	bool index_is_valid = !(vmx_instruction_info & (1u << 22));
-	int  base_reg       = (vmx_instruction_info >> 23) & 0xf;
-	bool base_is_valid  = !(vmx_instruction_info & (1u << 27));
-
-	if (is_reg) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 1;
-	}
-
-	/* Addr = segment_base + offset */
-	/* offset = base + [index * scale] + displacement */
-	*ret = vmx_get_segment_base(vcpu, seg_reg);
-	if (base_is_valid)
-		*ret += kvm_register_read(vcpu, base_reg);
-	if (index_is_valid)
-		*ret += kvm_register_read(vcpu, index_reg)<<scaling;
-	*ret += exit_qualification; /* holds the displacement */
-
-	if (addr_size == 1) /* 32 bit */
-		*ret &= 0xffffffff;
-
-	/*
-	 * TODO: throw #GP (and return 1) in various cases that the VM*
-	 * instructions require it - e.g., offset beyond segment limit,
-	 * unusable or unreadable/unwritable segment, non-canonical 64-bit
-	 * address, and so on. Currently these are not checked.
-	 */
-	return 0;
-}
-
 /* Emulate the VMCLEAR instruction */
 static int handle_vmclear(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gva_t gva;
 	gpa_t vmptr;
 	struct vmcs12 *vmcs12;
 	struct page *page;
-	struct x86_exception e;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
-			vmcs_read32(VMX_INSTRUCTION_INFO), &gva))
-		return 1;
-
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
-				sizeof(vmptr), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
-		return 1;
-	}
-
-	if (!IS_ALIGNED(vmptr, PAGE_SIZE)) {
-		nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);
-		skip_emulated_instruction(vcpu);
+	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr))
 		return 1;
-	}
 
 	if (vmptr == vmx->nested.current_vmptr) {
 		nested_release_vmcs12(vmx);
@@ -6372,29 +6471,14 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 static int handle_vmptrld(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gva_t gva;
 	gpa_t vmptr;
-	struct x86_exception e;
 	u32 exec_control;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
-			vmcs_read32(VMX_INSTRUCTION_INFO), &gva))
-		return 1;
-
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
-				sizeof(vmptr), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
-		return 1;
-	}
-
-	if (!IS_ALIGNED(vmptr, PAGE_SIZE)) {
-		nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);
-		skip_emulated_instruction(vcpu);
+	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMPTRLD, &vmptr))
 		return 1;
-	}
 
 	if (vmx->nested.current_vmptr != vmptr) {
 		struct vmcs12 *new_vmcs12;
@@ -6471,7 +6555,6 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	struct {
 		u64 eptp, gpa;
 	} operand;
-	u64 eptp_mask = ((1ull << 51) - 1) & PAGE_MASK;
 
 	if (!(nested_vmx_secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) ||
 	    !(nested_vmx_ept_caps & VMX_EPT_INVEPT_BIT)) {
@@ -6511,16 +6594,13 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	}
 
 	switch (type) {
-	case VMX_EPT_EXTENT_CONTEXT:
-		if ((operand.eptp & eptp_mask) !=
-				(nested_ept_get_cr3(vcpu) & eptp_mask))
-			break;
 	case VMX_EPT_EXTENT_GLOBAL:
 		kvm_mmu_sync_roots(vcpu);
 		kvm_mmu_flush_tlb(vcpu);
 		nested_vmx_succeed(vcpu);
 		break;
 	default:
+		/* Trap single context invalidation invept calls */
 		BUG_ON(1);
 		break;
 	}
@@ -6571,8 +6651,8 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_EPT_VIOLATION]	      = handle_ept_violation,
 	[EXIT_REASON_EPT_MISCONFIG]           = handle_ept_misconfig,
 	[EXIT_REASON_PAUSE_INSTRUCTION]       = handle_pause,
-	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_invalid_op,
-	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_invalid_op,
+	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_mwait,
+	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_monitor,
 	[EXIT_REASON_INVEPT]                  = handle_invept,
 };
 
@@ -7413,7 +7493,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
 				  | (1 << VCPU_EXREG_RFLAGS)
-				  | (1 << VCPU_EXREG_CPL)
 				  | (1 << VCPU_EXREG_PDPTR)
 				  | (1 << VCPU_EXREG_SEGMENTS)
 				  | (1 << VCPU_EXREG_CR3));
@@ -8601,6 +8680,14 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info,
 		       exit_qualification);
 
+	if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
+	    && nested_exit_intr_ack_set(vcpu)) {
+		int irq = kvm_cpu_get_interrupt(vcpu);
+		WARN_ON(irq < 0);
+		vmcs12->vm_exit_intr_info = irq |
+			INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR;
+	}
+
 	trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason,
 				       vmcs12->exit_qualification,
 				       vmcs12->idt_vectoring_info_field,