1 files changed, 133 insertions, 113 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a34fb7284024..2ad59d8553a5 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -714,7 +714,6 @@ struct vcpu_vmx {
 	u64 		      msr_guest_kernel_gs_base;
 #endif
 
-	u64 		      arch_capabilities;
 	u64 		      spec_ctrl;
 
 	u32 vm_entry_controls_shadow;
@@ -1548,7 +1547,7 @@ static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
 	return -1;
 }
 
-static inline void __invvpid(int ext, u16 vpid, gva_t gva)
+static inline void __invvpid(unsigned long ext, u16 vpid, gva_t gva)
 {
     struct {
 	u64 vpid : 16;
@@ -1562,7 +1561,7 @@ static inline void __invvpid(int ext, u16 vpid, gva_t gva)
 		  : : "a"(&operand), "c"(ext) : "cc", "memory");
 }
 
-static inline void __invept(int ext, u64 eptp, gpa_t gpa)
+static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa)
 {
 	struct {
 		u64 eptp, gpa;
@@ -1620,43 +1619,15 @@ static void vmcs_load(struct vmcs *vmcs)
 }
 
 #ifdef CONFIG_KEXEC_CORE
-/*
- * This bitmap is used to indicate whether the vmclear
- * operation is enabled on all cpus. All disabled by
- * default.
- */
-static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE;
-
-static inline void crash_enable_local_vmclear(int cpu)
-{
-	cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
-static inline void crash_disable_local_vmclear(int cpu)
-{
-	cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
-static inline int crash_local_vmclear_enabled(int cpu)
-{
-	return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
 static void crash_vmclear_local_loaded_vmcss(void)
 {
 	int cpu = raw_smp_processor_id();
 	struct loaded_vmcs *v;
 
-	if (!crash_local_vmclear_enabled(cpu))
-		return;
-
 	list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
 			    loaded_vmcss_on_cpu_link)
 		vmcs_clear(v->vmcs);
 }
-#else
-static inline void crash_enable_local_vmclear(int cpu) { }
-static inline void crash_disable_local_vmclear(int cpu) { }
 #endif /* CONFIG_KEXEC_CORE */
 
 static void __loaded_vmcs_clear(void *arg)
@@ -1668,19 +1639,24 @@ static void __loaded_vmcs_clear(void *arg)
 		return; /* vcpu migration can race with cpu offline */
 	if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs)
 		per_cpu(current_vmcs, cpu) = NULL;
-	crash_disable_local_vmclear(cpu);
+
+	vmcs_clear(loaded_vmcs->vmcs);
+	if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched)
+		vmcs_clear(loaded_vmcs->shadow_vmcs);
+
 	list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link);
 
 	/*
-	 * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link
-	 * is before setting loaded_vmcs->vcpu to -1 which is done in
-	 * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist
-	 * then adds the vmcs into percpu list before it is deleted.
+	 * Ensure all writes to loaded_vmcs, including deleting it from its
+	 * current percpu list, complete before setting loaded_vmcs->vcpu to
+	 * -1, otherwise a different cpu can see vcpu == -1 first and add
+	 * loaded_vmcs to its percpu list before it's deleted from this cpu's
+	 * list. Pairs with the smp_rmb() in vmx_vcpu_load_vmcs().
 	 */
 	smp_wmb();
 
-	loaded_vmcs_init(loaded_vmcs);
-	crash_enable_local_vmclear(cpu);
+	loaded_vmcs->cpu = -1;
+	loaded_vmcs->launched = 0;
 }
 
 static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
@@ -2220,17 +2196,9 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 	u64 guest_efer = vmx->vcpu.arch.efer;
 	u64 ignore_bits = 0;
 
-	if (!enable_ept) {
-		/*
-		 * NX is needed to handle CR0.WP=1, CR4.SMEP=1.  Testing
-		 * host CPUID is more efficient than testing guest CPUID
-		 * or CR4.  Host SMEP is anyway a requirement for guest SMEP.
-		 */
-		if (boot_cpu_has(X86_FEATURE_SMEP))
-			guest_efer |= EFER_NX;
-		else if (!(guest_efer & EFER_NX))
-			ignore_bits |= EFER_NX;
-	}
+	/* Shadow paging assumes NX to be available.  */
+	if (!enable_ept)
+		guest_efer |= EFER_NX;
 
 	/*
 	 * LMA and LME handled by hardware; SCE meaningless outside long mode.
@@ -2480,18 +2448,17 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	if (!already_loaded) {
 		local_irq_disable();
-		crash_disable_local_vmclear(cpu);
 
 		/*
-		 * Read loaded_vmcs->cpu should be before fetching
-		 * loaded_vmcs->loaded_vmcss_on_cpu_link.
-		 * See the comments in __loaded_vmcs_clear().
+		 * Ensure loaded_vmcs->cpu is read before adding loaded_vmcs to
+		 * this cpu's percpu list, otherwise it may not yet be deleted
+		 * from its previous cpu's percpu list.  Pairs with the
+		 * smb_wmb() in __loaded_vmcs_clear().
 		 */
 		smp_rmb();
 
 		list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link,
 			 &per_cpu(loaded_vmcss_on_cpu, cpu));
-		crash_enable_local_vmclear(cpu);
 		local_irq_enable();
 	}
 
@@ -3209,12 +3176,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 		msr_info->data = to_vmx(vcpu)->spec_ctrl;
 		break;
-	case MSR_IA32_ARCH_CAPABILITIES:
-		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has_arch_capabilities(vcpu))
-			return 1;
-		msr_info->data = to_vmx(vcpu)->arch_capabilities;
-		break;
 	case MSR_IA32_SYSENTER_CS:
 		msr_info->data = vmcs_read32(GUEST_SYSENTER_CS);
 		break;
@@ -3376,11 +3337,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
 					      MSR_TYPE_W);
 		break;
-	case MSR_IA32_ARCH_CAPABILITIES:
-		if (!msr_info->host_initiated)
-			return 1;
-		vmx->arch_capabilities = data;
-		break;
 	case MSR_IA32_CR_PAT:
 		if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
 			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
@@ -3526,21 +3482,6 @@ static int hardware_enable(void)
 	if (cr4_read_shadow() & X86_CR4_VMXE)
 		return -EBUSY;
 
-	INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
-	INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
-	spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
-
-	/*
-	 * Now we can enable the vmclear operation in kdump
-	 * since the loaded_vmcss_on_cpu list on this cpu
-	 * has been initialized.
-	 *
-	 * Though the cpu is not in VMX operation now, there
-	 * is no problem to enable the vmclear operation
-	 * for the loaded_vmcss_on_cpu list is empty!
-	 */
-	crash_enable_local_vmclear(cpu);
-
 	rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
 
 	test_bits = FEATURE_CONTROL_LOCKED;
@@ -4661,6 +4602,26 @@ static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu)
 		 (ss.selector & SEGMENT_RPL_MASK));
 }
 
+static bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu,
+					unsigned int port, int size);
+static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
+				       struct vmcs12 *vmcs12)
+{
+	unsigned long exit_qualification;
+	unsigned short port;
+	int size;
+
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
+
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+	port = exit_qualification >> 16;
+	size = (exit_qualification & 7) + 1;
+
+	return nested_vmx_check_io_bitmaps(vcpu, port, size);
+}
+
 /*
  * Check if guest state is valid. Returns true if valid, false if
  * not.
@@ -5468,8 +5429,6 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		++vmx->nmsrs;
 	}
 
-	vmx->arch_capabilities = kvm_get_arch_capabilities();
-
 	vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);
 
 	/* 22.2.1, 20.8.1 */
@@ -6566,20 +6525,13 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 			return 1;
 		}
 		else
-			return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP,
-						       NULL, 0) == EMULATE_DONE;
+			return emulate_instruction(vcpu, EMULTYPE_SKIP) ==
+								EMULATE_DONE;
 	}
 
-	ret = handle_mmio_page_fault(vcpu, gpa, true);
-	if (likely(ret == RET_MMIO_PF_EMULATE))
-		return x86_emulate_instruction(vcpu, gpa, 0, NULL, 0) ==
-					      EMULATE_DONE;
-
-	if (unlikely(ret == RET_MMIO_PF_INVALID))
-		return kvm_mmu_page_fault(vcpu, gpa, 0, NULL, 0);
-
-	if (unlikely(ret == RET_MMIO_PF_RETRY))
-		return 1;
+	ret = kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0);
+	if (ret >= 0)
+		return ret;
 
 	/* It is the real ept misconfig */
 	WARN_ON(1);
@@ -7653,6 +7605,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
 	gva_t gva = 0;
+	struct x86_exception e;
 
 	if (!nested_vmx_check_permission(vcpu) ||
 	    !nested_vmx_check_vmcs12(vcpu))
@@ -7679,8 +7632,12 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 				vmx_instruction_info, true, &gva))
 			return 1;
 		/* _system ok, as nested_vmx_check_permission verified cpl=0 */
-		kvm_write_guest_virt_system(vcpu, gva, &field_value,
-					    (is_long_mode(vcpu) ? 8 : 4), NULL);
+		if (kvm_write_guest_virt_system(vcpu, gva, &field_value,
+						(is_long_mode(vcpu) ? 8 : 4),
+						&e)) {
+			kvm_inject_page_fault(vcpu, &e);
+			return 1;
+		}
 	}
 
 	nested_vmx_succeed(vcpu);
@@ -8050,23 +8007,17 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 static const int kvm_vmx_max_exit_handlers =
 	ARRAY_SIZE(kvm_vmx_exit_handlers);
 
-static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
-				       struct vmcs12 *vmcs12)
+/*
+ * Return true if an IO instruction with the specified port and size should cause
+ * a VM-exit into L1.
+ */
+bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
+				 int size)
 {
-	unsigned long exit_qualification;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	gpa_t bitmap, last_bitmap;
-	unsigned int port;
-	int size;
 	u8 b;
 
-	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
-		return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
-
-	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-
-	port = exit_qualification >> 16;
-	size = (exit_qualification & 7) + 1;
-
 	last_bitmap = (gpa_t)-1;
 	b = -1;
 
@@ -9220,8 +9171,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	vmx->__launched = vmx->loaded_vmcs->launched;
 
+	/* L1D Flush includes CPU buffer clear to mitigate MDS */
 	if (static_branch_unlikely(&vmx_l1d_should_flush))
 		vmx_l1d_flush(vcpu);
+	else if (static_branch_unlikely(&mds_user_clear))
+		mds_clear_cpu_buffers();
 
 	asm(
 		/* Store host registers */
@@ -9580,8 +9534,8 @@ free_vcpu:
 	return ERR_PTR(err);
 }
 
-#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
-#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
+#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n"
+#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n"
 
 static int vmx_vm_init(struct kvm *kvm)
 {
@@ -11356,11 +11310,71 @@ static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu,
 		to_vmx(vcpu)->nested.sync_shadow_vmcs = true;
 }
 
+static int vmx_check_intercept_io(struct kvm_vcpu *vcpu,
+				  struct x86_instruction_info *info)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	unsigned short port;
+	bool intercept;
+	int size;
+
+	if (info->intercept == x86_intercept_in ||
+	    info->intercept == x86_intercept_ins) {
+		port = info->src_val;
+		size = info->dst_bytes;
+	} else {
+		port = info->dst_val;
+		size = info->src_bytes;
+	}
+
+	/*
+	 * If the 'use IO bitmaps' VM-execution control is 0, IO instruction
+	 * VM-exits depend on the 'unconditional IO exiting' VM-execution
+	 * control.
+	 *
+	 * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps.
+	 */
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		intercept = nested_cpu_has(vmcs12,
+					   CPU_BASED_UNCOND_IO_EXITING);
+	else
+		intercept = nested_vmx_check_io_bitmaps(vcpu, port, size);
+
+	return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE;
+}
+
 static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 			       struct x86_instruction_info *info,
 			       enum x86_intercept_stage stage)
 {
-	return X86EMUL_CONTINUE;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
+
+	switch (info->intercept) {
+	/*
+	 * RDPID causes #UD if disabled through secondary execution controls.
+	 * Because it is marked as EmulateOnUD, we need to intercept it here.
+	 */
+	case x86_intercept_rdtscp:
+		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
+			ctxt->exception.vector = UD_VECTOR;
+			ctxt->exception.error_code_valid = false;
+			return X86EMUL_PROPAGATE_FAULT;
+		}
+		break;
+
+	case x86_intercept_in:
+	case x86_intercept_ins:
+	case x86_intercept_out:
+	case x86_intercept_outs:
+		return vmx_check_intercept_io(vcpu, info);
+
+	/* TODO: check more intercepts... */
+	default:
+		break;
+	}
+
+	return X86EMUL_UNHANDLEABLE;
 }
 
 #ifdef CONFIG_X86_64
@@ -11842,7 +11856,7 @@ module_exit(vmx_exit)
 
 static int __init vmx_init(void)
 {
-	int r;
+	int r, cpu;
 
 	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
 		     __alignof__(struct vcpu_vmx), THIS_MODULE);
@@ -11864,6 +11878,12 @@ static int __init vmx_init(void)
 		}
 	}
 
+	for_each_possible_cpu(cpu) {
+		INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
+		INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
+		spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+	}
+
 #ifdef CONFIG_KEXEC_CORE
 	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
 			   crash_vmclear_local_loaded_vmcss);