1 files changed, 117 insertions, 76 deletions

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4bd1bf6214ee..c93070829790 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -31,6 +31,7 @@
 #include <asm/apic.h>
 #include <asm/asm.h>
 #include <asm/cpu.h>
+#include <asm/cpu_device_id.h>
 #include <asm/debugreg.h>
 #include <asm/desc.h>
 #include <asm/fpu/internal.h>
@@ -358,9 +359,9 @@ static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx)
 	if (!vmx->disable_fb_clear)
 		return;
 
-	rdmsrl(MSR_IA32_MCU_OPT_CTRL, msr);
+	msr = __rdmsr(MSR_IA32_MCU_OPT_CTRL);
 	msr |= FB_CLEAR_DIS;
-	wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr);
+	native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr);
 	/* Cache the MSR value to avoid reading it later */
 	vmx->msr_ia32_mcu_opt_ctrl = msr;
 }
@@ -371,7 +372,7 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)
 		return;
 
 	vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS;
-	wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl);
+	native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl);
 }
 
 static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
@@ -862,6 +863,24 @@ static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr)
 	return true;
 }
 
+unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx)
+{
+	unsigned int flags = 0;
+
+	if (vmx->loaded_vmcs->launched)
+		flags |= VMX_RUN_VMRESUME;
+
+	/*
+	 * If writes to the SPEC_CTRL MSR aren't intercepted, the guest is free
+	 * to change it directly without causing a vmexit.  In that case read
+	 * it after vmexit and store it in vmx->spec_ctrl.
+	 */
+	if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL)))
+		flags |= VMX_RUN_SAVE_SPEC_CTRL;
+
+	return flags;
+}
+
 static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 		unsigned long entry, unsigned long exit)
 {
@@ -1378,8 +1397,10 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
 
 		/*
 		 * No indirect branch prediction barrier needed when switching
-		 * the active VMCS within a guest, e.g. on nested VM-Enter.
-		 * The L1 VMM can protect itself with retpolines, IBPB or IBRS.
+		 * the active VMCS within a vCPU, unless IBRS is advertised to
+		 * the vCPU.  To minimize the number of IBPBs executed, KVM
+		 * performs IBPB on nested VM-Exit (a single nested transition
+		 * may switch the active VMCS multiple times).
 		 */
 		if (!buddy || WARN_ON_ONCE(buddy->vmcs != prev))
 			indirect_branch_prediction_barrier();
@@ -1657,7 +1678,17 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
 	kvm_deliver_exception_payload(vcpu);
 
 	if (has_error_code) {
-		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
+		/*
+		 * Despite the error code being architecturally defined as 32
+		 * bits, and the VMCS field being 32 bits, Intel CPUs and thus
+		 * VMX don't actually supporting setting bits 31:16.  Hardware
+		 * will (should) never provide a bogus error code, but AMD CPUs
+		 * do generate error codes with bits 31:16 set, and so KVM's
+		 * ABI lets userspace shove in arbitrary 32-bit values.  Drop
+		 * the upper bits to avoid VM-Fail, losing information that
+		 * does't really exist is preferable to killing the VM.
+		 */
+		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, (u16)error_code);
 		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
 	}
 
@@ -1751,7 +1782,7 @@ static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
 	if (is_guest_mode(vcpu) &&
-	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
+	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING))
 		return vcpu->arch.tsc_offset - vmcs12->tsc_offset;
 
 	return vcpu->arch.tsc_offset;
@@ -1769,7 +1800,7 @@ static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	 * to the newly set TSC to get L2's TSC.
 	 */
 	if (is_guest_mode(vcpu) &&
-	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
+	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING))
 		g_tsc_offset = vmcs12->tsc_offset;
 
 	trace_kvm_write_tsc_offset(vcpu->vcpu_id,
@@ -2396,7 +2427,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 	      CPU_BASED_CR3_STORE_EXITING |
 	      CPU_BASED_UNCOND_IO_EXITING |
 	      CPU_BASED_MOV_DR_EXITING |
-	      CPU_BASED_USE_TSC_OFFSETING |
+	      CPU_BASED_USE_TSC_OFFSETTING |
 	      CPU_BASED_MWAIT_EXITING |
 	      CPU_BASED_MONITOR_EXITING |
 	      CPU_BASED_INVLPG_EXITING |
@@ -3212,18 +3243,15 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var)
 {
 	u32 ar;
 
-	if (var->unusable || !var->present)
-		ar = 1 << 16;
-	else {
-		ar = var->type & 15;
-		ar |= (var->s & 1) << 4;
-		ar |= (var->dpl & 3) << 5;
-		ar |= (var->present & 1) << 7;
-		ar |= (var->avl & 1) << 12;
-		ar |= (var->l & 1) << 13;
-		ar |= (var->db & 1) << 14;
-		ar |= (var->g & 1) << 15;
-	}
+	ar = var->type & 15;
+	ar |= (var->s & 1) << 4;
+	ar |= (var->dpl & 3) << 5;
+	ar |= (var->present & 1) << 7;
+	ar |= (var->avl & 1) << 12;
+	ar |= (var->l & 1) << 13;
+	ar |= (var->db & 1) << 14;
+	ar |= (var->g & 1) << 15;
+	ar |= (var->unusable || !var->present) << 16;
 
 	return ar;
 }
@@ -4429,7 +4457,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 static void enable_irq_window(struct kvm_vcpu *vcpu)
 {
-	exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING);
+	exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING);
 }
 
 static void enable_nmi_window(struct kvm_vcpu *vcpu)
@@ -4440,7 +4468,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu)
 		return;
 	}
 
-	exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING);
+	exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING);
 }
 
 static void vmx_inject_irq(struct kvm_vcpu *vcpu)
@@ -4773,7 +4801,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static int handle_external_interrupt(struct kvm_vcpu *vcpu)
+static __always_inline int handle_external_interrupt(struct kvm_vcpu *vcpu)
 {
 	++vcpu->stat.irq_exits;
 	return 1;
@@ -5045,21 +5073,6 @@ static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
 	vmcs_writel(GUEST_DR7, val);
 }
 
-static int handle_cpuid(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_cpuid(vcpu);
-}
-
-static int handle_rdmsr(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_rdmsr(vcpu);
-}
-
-static int handle_wrmsr(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_wrmsr(vcpu);
-}
-
 static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu)
 {
 	kvm_apic_update_ppr(vcpu);
@@ -5068,7 +5081,7 @@ static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu)
 
 static int handle_interrupt_window(struct kvm_vcpu *vcpu)
 {
-	exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING);
+	exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING);
 
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
@@ -5076,11 +5089,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static int handle_halt(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_halt(vcpu);
-}
-
 static int handle_vmcall(struct kvm_vcpu *vcpu)
 {
 	return kvm_emulate_hypercall(vcpu);
@@ -5286,7 +5294,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 static int handle_nmi_window(struct kvm_vcpu *vcpu)
 {
 	WARN_ON_ONCE(!enable_vnmi);
-	exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING);
+	exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING);
 	++vcpu->stat.nmi_window_exits;
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
@@ -5307,7 +5315,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 	WARN_ON_ONCE(vmx->emulation_required && vmx->nested.nested_run_pending);
 
 	intr_window_requested = exec_controls_get(vmx) &
-				CPU_BASED_VIRTUAL_INTR_PENDING;
+				CPU_BASED_INTR_WINDOW_EXITING;
 
 	while (vmx->emulation_required && count-- != 0) {
 		if (intr_window_requested && vmx_interrupt_allowed(vcpu))
@@ -5628,11 +5636,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_IO_INSTRUCTION]          = handle_io,
 	[EXIT_REASON_CR_ACCESS]               = handle_cr,
 	[EXIT_REASON_DR_ACCESS]               = handle_dr,
-	[EXIT_REASON_CPUID]                   = handle_cpuid,
-	[EXIT_REASON_MSR_READ]                = handle_rdmsr,
-	[EXIT_REASON_MSR_WRITE]               = handle_wrmsr,
-	[EXIT_REASON_PENDING_INTERRUPT]       = handle_interrupt_window,
-	[EXIT_REASON_HLT]                     = handle_halt,
+	[EXIT_REASON_CPUID]                   = kvm_emulate_cpuid,
+	[EXIT_REASON_MSR_READ]                = kvm_emulate_rdmsr,
+	[EXIT_REASON_MSR_WRITE]               = kvm_emulate_wrmsr,
+	[EXIT_REASON_INTERRUPT_WINDOW]        = handle_interrupt_window,
+	[EXIT_REASON_HLT]                     = kvm_emulate_halt,
 	[EXIT_REASON_INVD]		      = handle_invd,
 	[EXIT_REASON_INVLPG]		      = handle_invlpg,
 	[EXIT_REASON_RDPMC]                   = handle_rdpmc,
@@ -6006,9 +6014,23 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	}
 
 	if (exit_reason < kvm_vmx_max_exit_handlers
-	    && kvm_vmx_exit_handlers[exit_reason])
+	    && kvm_vmx_exit_handlers[exit_reason]) {
+#ifdef CONFIG_RETPOLINE
+		if (exit_reason == EXIT_REASON_MSR_WRITE)
+			return kvm_emulate_wrmsr(vcpu);
+		else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER)
+			return handle_preemption_timer(vcpu);
+		else if (exit_reason == EXIT_REASON_INTERRUPT_WINDOW)
+			return handle_interrupt_window(vcpu);
+		else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
+			return handle_external_interrupt(vcpu);
+		else if (exit_reason == EXIT_REASON_HLT)
+			return kvm_emulate_halt(vcpu);
+		else if (exit_reason == EXIT_REASON_EPT_MISCONFIG)
+			return handle_ept_misconfig(vcpu);
+#endif
 		return kvm_vmx_exit_handlers[exit_reason](vcpu);
-	else {
+	} else {
 		vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
 				exit_reason);
 		dump_vmcs();
@@ -6336,6 +6358,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 	);
 
 	kvm_after_interrupt(vcpu);
+	vcpu->arch.at_instruction_boundary = true;
 }
 STACK_FRAME_NON_STANDARD(handle_external_interrupt_irqoff);
 
@@ -6539,7 +6562,30 @@ void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp)
 	}
 }
 
-bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched);
+void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx,
+					unsigned int flags)
+{
+	u64 hostval = this_cpu_read(x86_spec_ctrl_current);
+
+	if (!cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL))
+		return;
+
+	if (flags & VMX_RUN_SAVE_SPEC_CTRL)
+		vmx->spec_ctrl = __rdmsr(MSR_IA32_SPEC_CTRL);
+
+	/*
+	 * If the guest/host SPEC_CTRL values differ, restore the host value.
+	 *
+	 * For legacy IBRS, the IBRS bit always needs to be written after
+	 * transitioning from a less privileged predictor mode, regardless of
+	 * whether the guest/host values differ.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) ||
+	    vmx->spec_ctrl != hostval)
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval);
+
+	barrier_nospec();
+}
 
 static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 {
@@ -6628,32 +6674,12 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		write_cr2(vcpu->arch.cr2);
 
 	vmx->fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs,
-				   vmx->loaded_vmcs->launched);
+				   __vmx_vcpu_run_flags(vmx));
 
 	vcpu->arch.cr2 = read_cr2();
 
 	vmx_enable_fb_clear(vmx);
 
-	/*
-	 * We do not use IBRS in the kernel. If this vCPU has used the
-	 * SPEC_CTRL MSR it may have left it on; save the value and
-	 * turn it off. This is much more efficient than blindly adding
-	 * it to the atomic save/restore list. Especially as the former
-	 * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
-	 *
-	 * For non-nested case:
-	 * If the L01 MSR bitmap does not intercept the MSR, then we need to
-	 * save it.
-	 *
-	 * For nested case:
-	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
-	 * save it.
-	 */
-	if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL)))
-		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
-
-	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
-
 	/* All fields are clean at this point */
 	if (static_branch_unlikely(&enable_evmcs))
 		current_evmcs->hv_clean_fields |=
@@ -7241,6 +7267,21 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 		/* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED.  */
 		break;
 
+	case x86_intercept_pause:
+		/*
+		 * PAUSE is a single-byte NOP with a REPE prefix, i.e. collides
+		 * with vanilla NOPs in the emulator.  Apply the interception
+		 * check only to actual PAUSE instructions.  Don't check
+		 * PAUSE-loop-exiting, software can't expect a given PAUSE to
+		 * exit, i.e. KVM is within its rights to allow L2 to execute
+		 * the PAUSE.
+		 */
+		if ((info->rep_prefix != REPE_PREFIX) ||
+		    !nested_cpu_has2(vmcs12, CPU_BASED_PAUSE_EXITING))
+			return X86EMUL_CONTINUE;
+
+		break;
+
 	/* TODO: check more intercepts... */
 	default:
 		break;