1 files changed, 121 insertions, 154 deletions

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index cbe0cdade38a..4bceb5ca3a89 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -36,6 +36,7 @@
 #include <asm/debugreg.h>
 #include <asm/desc.h>
 #include <asm/fpu/internal.h>
+#include <asm/idtentry.h>
 #include <asm/io.h>
 #include <asm/irq_remapping.h>
 #include <asm/kexec.h>
@@ -454,21 +455,6 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx)
 
 static unsigned long host_idt_base;
 
-/*
- * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm
- * will emulate SYSCALL in legacy mode if the vendor string in guest
- * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To
- * support this emulation, IA32_STAR must always be included in
- * vmx_uret_msrs_list[], even in i386 builds.
- */
-static const u32 vmx_uret_msrs_list[] = {
-#ifdef CONFIG_X86_64
-	MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
-#endif
-	MSR_EFER, MSR_TSC_AUX, MSR_STAR,
-	MSR_IA32_TSX_CTRL,
-};
-
 #if IS_ENABLED(CONFIG_HYPERV)
 static bool __read_mostly enlightened_vmcs = true;
 module_param(enlightened_vmcs, bool, 0444);
@@ -696,21 +682,11 @@ static bool is_valid_passthrough_msr(u32 msr)
 	return r;
 }
 
-static inline int __vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr)
-{
-	int i;
-
-	for (i = 0; i < vmx->nr_uret_msrs; ++i)
-		if (vmx_uret_msrs_list[vmx->guest_uret_msrs[i].slot] == msr)
-			return i;
-	return -1;
-}
-
 struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr)
 {
 	int i;
 
-	i = __vmx_find_uret_msr(vmx, msr);
+	i = kvm_find_user_return_msr(msr);
 	if (i >= 0)
 		return &vmx->guest_uret_msrs[i];
 	return NULL;
@@ -719,13 +695,14 @@ struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr)
 static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx,
 				  struct vmx_uret_msr *msr, u64 data)
 {
+	unsigned int slot = msr - vmx->guest_uret_msrs;
 	int ret = 0;
 
 	u64 old_msr_data = msr->data;
 	msr->data = data;
-	if (msr - vmx->guest_uret_msrs < vmx->nr_active_uret_msrs) {
+	if (msr->load_into_hardware) {
 		preempt_disable();
-		ret = kvm_set_user_return_msr(msr->slot, msr->data, msr->mask);
+		ret = kvm_set_user_return_msr(slot, msr->data, msr->mask);
 		preempt_enable();
 		if (ret)
 			msr->data = old_msr_data;
@@ -1077,7 +1054,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx)
 		return false;
 	}
 
-	i = __vmx_find_uret_msr(vmx, MSR_EFER);
+	i = kvm_find_user_return_msr(MSR_EFER);
 	if (i < 0)
 		return false;
 
@@ -1239,11 +1216,14 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	 */
 	if (!vmx->guest_uret_msrs_loaded) {
 		vmx->guest_uret_msrs_loaded = true;
-		for (i = 0; i < vmx->nr_active_uret_msrs; ++i)
-			kvm_set_user_return_msr(vmx->guest_uret_msrs[i].slot,
+		for (i = 0; i < kvm_nr_uret_msrs; ++i) {
+			if (!vmx->guest_uret_msrs[i].load_into_hardware)
+				continue;
+
+			kvm_set_user_return_msr(i,
 						vmx->guest_uret_msrs[i].data,
 						vmx->guest_uret_msrs[i].mask);
-
+		}
 	}
 
     	if (vmx->nested.need_vmcs12_to_shadow_sync)
@@ -1750,19 +1730,16 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
 	vmx_clear_hlt(vcpu);
 }
 
-static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr)
+static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr,
+			       bool load_into_hardware)
 {
-	struct vmx_uret_msr tmp;
-	int from, to;
+	struct vmx_uret_msr *uret_msr;
 
-	from = __vmx_find_uret_msr(vmx, msr);
-	if (from < 0)
+	uret_msr = vmx_find_uret_msr(vmx, msr);
+	if (!uret_msr)
 		return;
-	to = vmx->nr_active_uret_msrs++;
 
-	tmp = vmx->guest_uret_msrs[to];
-	vmx->guest_uret_msrs[to] = vmx->guest_uret_msrs[from];
-	vmx->guest_uret_msrs[from] = tmp;
+	uret_msr->load_into_hardware = load_into_hardware;
 }
 
 /*
@@ -1772,29 +1749,42 @@ static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr)
  */
 static void setup_msrs(struct vcpu_vmx *vmx)
 {
-	vmx->guest_uret_msrs_loaded = false;
-	vmx->nr_active_uret_msrs = 0;
 #ifdef CONFIG_X86_64
+	bool load_syscall_msrs;
+
 	/*
 	 * The SYSCALL MSRs are only needed on long mode guests, and only
 	 * when EFER.SCE is set.
 	 */
-	if (is_long_mode(&vmx->vcpu) && (vmx->vcpu.arch.efer & EFER_SCE)) {
-		vmx_setup_uret_msr(vmx, MSR_STAR);
-		vmx_setup_uret_msr(vmx, MSR_LSTAR);
-		vmx_setup_uret_msr(vmx, MSR_SYSCALL_MASK);
-	}
+	load_syscall_msrs = is_long_mode(&vmx->vcpu) &&
+			    (vmx->vcpu.arch.efer & EFER_SCE);
+
+	vmx_setup_uret_msr(vmx, MSR_STAR, load_syscall_msrs);
+	vmx_setup_uret_msr(vmx, MSR_LSTAR, load_syscall_msrs);
+	vmx_setup_uret_msr(vmx, MSR_SYSCALL_MASK, load_syscall_msrs);
 #endif
-	if (update_transition_efer(vmx))
-		vmx_setup_uret_msr(vmx, MSR_EFER);
+	vmx_setup_uret_msr(vmx, MSR_EFER, update_transition_efer(vmx));
 
-	if (guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP))
-		vmx_setup_uret_msr(vmx, MSR_TSC_AUX);
+	vmx_setup_uret_msr(vmx, MSR_TSC_AUX,
+			   guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP) ||
+			   guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDPID));
 
-	vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL);
+	/*
+	 * hle=0, rtm=0, tsx_ctrl=1 can be found with some combinations of new
+	 * kernel and old userspace.  If those guests run on a tsx=off host, do
+	 * allow guests to use TSX_CTRL, but don't change the value in hardware
+	 * so that TSX remains always disabled.
+	 */
+	vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL, boot_cpu_has(X86_FEATURE_RTM));
 
 	if (cpu_has_vmx_msr_bitmap())
 		vmx_update_msr_bitmap(&vmx->vcpu);
+
+	/*
+	 * The set of MSRs to load may have changed, reload MSRs before the
+	 * next VM-Enter.
+	 */
+	vmx->guest_uret_msrs_loaded = false;
 }
 
 static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
@@ -1992,11 +1982,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		else
 			msr_info->data = vmx->pt_desc.guest.addr_a[index / 2];
 		break;
-	case MSR_TSC_AUX:
-		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
-			return 1;
-		goto find_uret_msr;
 	case MSR_IA32_DEBUGCTLMSR:
 		msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL);
 		break;
@@ -2030,6 +2015,9 @@ static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu)
 	if (!intel_pmu_lbr_is_enabled(vcpu))
 		debugctl &= ~DEBUGCTLMSR_LBR_MASK;
 
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))
+		debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT;
+
 	return debugctl;
 }
 
@@ -2312,14 +2300,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		else
 			vmx->pt_desc.guest.addr_a[index / 2] = data;
 		break;
-	case MSR_TSC_AUX:
-		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
-			return 1;
-		/* Check reserved bit, higher 32 bits should be zero */
-		if ((data >> 32) != 0)
-			return 1;
-		goto find_uret_msr;
 	case MSR_IA32_PERF_CAPABILITIES:
 		if (data && !vcpu_to_pmu(vcpu)->version)
 			return 1;
@@ -4368,7 +4348,23 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 						  xsaves_enabled, false);
 	}
 
-	vmx_adjust_sec_exec_feature(vmx, &exec_control, rdtscp, RDTSCP);
+	/*
+	 * RDPID is also gated by ENABLE_RDTSCP, turn on the control if either
+	 * feature is exposed to the guest.  This creates a virtualization hole
+	 * if both are supported in hardware but only one is exposed to the
+	 * guest, but letting the guest execute RDTSCP or RDPID when either one
+	 * is advertised is preferable to emulating the advertised instruction
+	 * in KVM on #UD, and obviously better than incorrectly injecting #UD.
+	 */
+	if (cpu_has_vmx_rdtscp()) {
+		bool rdpid_or_rdtscp_enabled =
+			guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) ||
+			guest_cpuid_has(vcpu, X86_FEATURE_RDPID);
+
+		vmx_adjust_secondary_exec_control(vmx, &exec_control,
+						  SECONDARY_EXEC_ENABLE_RDTSCP,
+						  rdpid_or_rdtscp_enabled, false);
+	}
 	vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID);
 
 	vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND);
@@ -6415,18 +6411,17 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 
 void vmx_do_interrupt_nmi_irqoff(unsigned long entry);
 
-static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu, u32 intr_info)
+static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu,
+					unsigned long entry)
 {
-	unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK;
-	gate_desc *desc = (gate_desc *)host_idt_base + vector;
-
 	kvm_before_interrupt(vcpu);
-	vmx_do_interrupt_nmi_irqoff(gate_offset(desc));
+	vmx_do_interrupt_nmi_irqoff(entry);
 	kvm_after_interrupt(vcpu);
 }
 
 static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
 {
+	const unsigned long nmi_entry = (unsigned long)asm_exc_nmi_noist;
 	u32 intr_info = vmx_get_intr_info(&vmx->vcpu);
 
 	/* if exit due to PF check for async PF */
@@ -6437,18 +6432,20 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
 		kvm_machine_check();
 	/* We need to handle NMIs before interrupts are enabled */
 	else if (is_nmi(intr_info))
-		handle_interrupt_nmi_irqoff(&vmx->vcpu, intr_info);
+		handle_interrupt_nmi_irqoff(&vmx->vcpu, nmi_entry);
 }
 
 static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 {
 	u32 intr_info = vmx_get_intr_info(vcpu);
+	unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK;
+	gate_desc *desc = (gate_desc *)host_idt_base + vector;
 
 	if (WARN_ONCE(!is_external_intr(intr_info),
 	    "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info))
 		return;
 
-	handle_interrupt_nmi_irqoff(vcpu, intr_info);
+	handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc));
 }
 
 static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
@@ -6662,25 +6659,7 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 					struct vcpu_vmx *vmx)
 {
-	/*
-	 * VMENTER enables interrupts (host state), but the kernel state is
-	 * interrupts disabled when this is invoked. Also tell RCU about
-	 * it. This is the same logic as for exit_to_user_mode().
-	 *
-	 * This ensures that e.g. latency analysis on the host observes
-	 * guest mode as interrupt enabled.
-	 *
-	 * guest_enter_irqoff() informs context tracking about the
-	 * transition to guest mode and if enabled adjusts RCU state
-	 * accordingly.
-	 */
-	instrumentation_begin();
-	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
-	instrumentation_end();
-
-	guest_enter_irqoff();
-	lockdep_hardirqs_on(CALLER_ADDR0);
+	kvm_guest_enter_irqoff();
 
 	/* L1D Flush includes CPU buffer clear to mitigate MDS */
 	if (static_branch_unlikely(&vmx_l1d_should_flush))
@@ -6696,24 +6675,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 
 	vcpu->arch.cr2 = native_read_cr2();
 
-	/*
-	 * VMEXIT disables interrupts (host state), but tracing and lockdep
-	 * have them in state 'on' as recorded before entering guest mode.
-	 * Same as enter_from_user_mode().
-	 *
-	 * guest_exit_irqoff() restores host context and reinstates RCU if
-	 * enabled and required.
-	 *
-	 * This needs to be done before the below as native_read_msr()
-	 * contains a tracepoint and x86_spec_ctrl_restore_host() calls
-	 * into world and some more.
-	 */
-	lockdep_hardirqs_off(CALLER_ADDR0);
-	guest_exit_irqoff();
-
-	instrumentation_begin();
-	trace_hardirqs_off_finish();
-	instrumentation_end();
+	kvm_guest_exit_irqoff();
 }
 
 static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
@@ -6888,6 +6850,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 
 static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 {
+	struct vmx_uret_msr *tsx_ctrl;
 	struct vcpu_vmx *vmx;
 	int i, cpu, err;
 
@@ -6910,43 +6873,19 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 			goto free_vpid;
 	}
 
-	BUILD_BUG_ON(ARRAY_SIZE(vmx_uret_msrs_list) != MAX_NR_USER_RETURN_MSRS);
-
-	for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) {
-		u32 index = vmx_uret_msrs_list[i];
-		u32 data_low, data_high;
-		int j = vmx->nr_uret_msrs;
-
-		if (rdmsr_safe(index, &data_low, &data_high) < 0)
-			continue;
-		if (wrmsr_safe(index, data_low, data_high) < 0)
-			continue;
-
-		vmx->guest_uret_msrs[j].slot = i;
-		vmx->guest_uret_msrs[j].data = 0;
-		switch (index) {
-		case MSR_IA32_TSX_CTRL:
-			/*
-			 * TSX_CTRL_CPUID_CLEAR is handled in the CPUID
-			 * interception.  Keep the host value unchanged to avoid
-			 * changing CPUID bits under the host kernel's feet.
-			 *
-			 * hle=0, rtm=0, tsx_ctrl=1 can be found with some
-			 * combinations of new kernel and old userspace.  If
-			 * those guests run on a tsx=off host, do allow guests
-			 * to use TSX_CTRL, but do not change the value on the
-			 * host so that TSX remains always disabled.
-			 */
-			if (boot_cpu_has(X86_FEATURE_RTM))
-				vmx->guest_uret_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
-			else
-				vmx->guest_uret_msrs[j].mask = 0;
-			break;
-		default:
-			vmx->guest_uret_msrs[j].mask = -1ull;
-			break;
-		}
-		++vmx->nr_uret_msrs;
+	for (i = 0; i < kvm_nr_uret_msrs; ++i) {
+		vmx->guest_uret_msrs[i].data = 0;
+		vmx->guest_uret_msrs[i].mask = -1ull;
+	}
+	if (boot_cpu_has(X86_FEATURE_RTM)) {
+		/*
+		 * TSX_CTRL_CPUID_CLEAR is handled in the CPUID interception.
+		 * Keep the host value unchanged to avoid changing CPUID bits
+		 * under the host kernel's feet.
+		 */
+		tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL);
+		if (tsx_ctrl)
+			vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
 	}
 
 	err = alloc_loaded_vmcs(&vmx->vmcs01);
@@ -7377,9 +7316,11 @@ static __init void vmx_set_cpu_caps(void)
 	if (!cpu_has_vmx_xsaves())
 		kvm_cpu_cap_clear(X86_FEATURE_XSAVES);
 
-	/* CPUID 0x80000001 */
-	if (!cpu_has_vmx_rdtscp())
+	/* CPUID 0x80000001 and 0x7 (RDPID) */
+	if (!cpu_has_vmx_rdtscp()) {
 		kvm_cpu_cap_clear(X86_FEATURE_RDTSCP);
+		kvm_cpu_cap_clear(X86_FEATURE_RDPID);
+	}
 
 	if (cpu_has_vmx_waitpkg())
 		kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG);
@@ -7435,8 +7376,9 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 	/*
 	 * RDPID causes #UD if disabled through secondary execution controls.
 	 * Because it is marked as EmulateOnUD, we need to intercept it here.
+	 * Note, RDPID is hidden behind ENABLE_RDTSCP.
 	 */
-	case x86_intercept_rdtscp:
+	case x86_intercept_rdpid:
 		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_RDTSCP)) {
 			exception->vector = UD_VECTOR;
 			exception->error_code_valid = false;
@@ -7802,17 +7744,42 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
 };
 
+static __init void vmx_setup_user_return_msrs(void)
+{
+
+	/*
+	 * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm
+	 * will emulate SYSCALL in legacy mode if the vendor string in guest
+	 * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To
+	 * support this emulation, MSR_STAR is included in the list for i386,
+	 * but is never loaded into hardware.  MSR_CSTAR is also never loaded
+	 * into hardware and is here purely for emulation purposes.
+	 */
+	const u32 vmx_uret_msrs_list[] = {
+	#ifdef CONFIG_X86_64
+		MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
+	#endif
+		MSR_EFER, MSR_TSC_AUX, MSR_STAR,
+		MSR_IA32_TSX_CTRL,
+	};
+	int i;
+
+	BUILD_BUG_ON(ARRAY_SIZE(vmx_uret_msrs_list) != MAX_NR_USER_RETURN_MSRS);
+
+	for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i)
+		kvm_add_user_return_msr(vmx_uret_msrs_list[i]);
+}
+
 static __init int hardware_setup(void)
 {
 	unsigned long host_bndcfgs;
 	struct desc_ptr dt;
-	int r, i, ept_lpage_level;
+	int r, ept_lpage_level;
 
 	store_idt(&dt);
 	host_idt_base = dt.address;
 
-	for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i)
-		kvm_define_user_return_msr(i, vmx_uret_msrs_list[i]);
+	vmx_setup_user_return_msrs();
 
 	if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0)
 		return -EIO;