1 files changed, 115 insertions, 58 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f973cfa8ff4f..516d8b1562c8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -961,6 +961,7 @@ static u32 msrs_to_save[] = {
 #endif
 	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
 	MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
+	MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES
 };
 
 static unsigned num_msrs_to_save;
@@ -984,15 +985,13 @@ static u32 emulated_msrs[] = {
 	MSR_IA32_MCG_STATUS,
 	MSR_IA32_MCG_CTL,
 	MSR_IA32_SMBASE,
+	MSR_AMD64_VIRT_SPEC_CTRL,
 };
 
 static unsigned num_emulated_msrs;
 
-bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
+static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
-	if (efer & efer_reserved_bits)
-		return false;
-
 	if (efer & EFER_FFXSR) {
 		struct kvm_cpuid_entry2 *feat;
 
@@ -1010,19 +1009,33 @@ bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
 	}
 
 	return true;
+
+}
+bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
+{
+	if (efer & efer_reserved_bits)
+		return false;
+
+	return __kvm_valid_efer(vcpu, efer);
 }
 EXPORT_SYMBOL_GPL(kvm_valid_efer);
 
-static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
+static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	u64 old_efer = vcpu->arch.efer;
+	u64 efer = msr_info->data;
 
-	if (!kvm_valid_efer(vcpu, efer))
+	if (efer & efer_reserved_bits)
 		return 1;
 
-	if (is_paging(vcpu)
-	    && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
-		return 1;
+	if (!msr_info->host_initiated) {
+		if (!__kvm_valid_efer(vcpu, efer))
+			return 1;
+
+		if (is_paging(vcpu) &&
+		    (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
+			return 1;
+	}
 
 	efer &= ~EFER_LMA;
 	efer |= vcpu->arch.efer & EFER_LMA;
@@ -2053,7 +2066,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 
 	case MSR_EFER:
-		return set_efer(vcpu, data);
+		return set_efer(vcpu, msr_info);
 	case MSR_K7_HWCR:
 		data &= ~(u64)0x40;	/* ignore flush filter disable */
 		data &= ~(u64)0x100;	/* ignore ignne emulation enable */
@@ -2583,7 +2596,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 * fringe case that is not enabled except via specific settings
 		 * of the module parameters.
 		 */
-		r = kvm_x86_ops->cpu_has_high_real_mode_segbase();
+		r = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE);
 		break;
 	case KVM_CAP_COALESCED_MMIO:
 		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
@@ -2755,6 +2768,12 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->vcpu_put(vcpu);
 	kvm_put_guest_fpu(vcpu);
 	vcpu->arch.last_host_tsc = rdtsc();
+	/*
+	 * If userspace has set any breakpoints or watchpoints, dr6 is restored
+	 * on every vmexit, but if not, we might have a stale dr6 from the
+	 * guest. do_debug expects dr6 to be cleared after it runs, do the same.
+	 */
+	set_debugreg(0, 6);
 }
 
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
@@ -2964,6 +2983,10 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 			      | KVM_VCPUEVENT_VALID_SMM))
 		return -EINVAL;
 
+	if (events->exception.injected &&
+	    (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
+		return -EINVAL;
+
 	/* INITs are latched while in SMM */
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM &&
 	    (events->smi.smm || events->smi.pending) &&
@@ -3967,13 +3990,14 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		mutex_unlock(&kvm->lock);
 		break;
 	case KVM_XEN_HVM_CONFIG: {
+		struct kvm_xen_hvm_config xhc;
 		r = -EFAULT;
-		if (copy_from_user(&kvm->arch.xen_hvm_config, argp,
-				   sizeof(struct kvm_xen_hvm_config)))
+		if (copy_from_user(&xhc, argp, sizeof(xhc)))
 			goto out;
 		r = -EINVAL;
-		if (kvm->arch.xen_hvm_config.flags)
+		if (xhc.flags)
 			goto out;
+		memcpy(&kvm->arch.xen_hvm_config, &xhc, sizeof(xhc));
 		r = 0;
 		break;
 	}
@@ -4065,14 +4089,8 @@ static void kvm_init_msr_list(void)
 	num_msrs_to_save = j;
 
 	for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
-		switch (emulated_msrs[i]) {
-		case MSR_IA32_SMBASE:
-			if (!kvm_x86_ops->cpu_has_high_real_mode_segbase())
-				continue;
-			break;
-		default:
-			break;
-		}
+		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+			continue;
 
 		if (j < i)
 			emulated_msrs[j] = emulated_msrs[i];
@@ -4238,24 +4256,35 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt,
 	return X86EMUL_CONTINUE;
 }
 
-int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt,
+int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
 			       gva_t addr, void *val, unsigned int bytes,
 			       struct x86_exception *exception)
 {
-	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
 
+	/*
+	 * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
+	 * is returned, but our callers are not ready for that and they blindly
+	 * call kvm_inject_page_fault.  Ensure that they at least do not leak
+	 * uninitialized kernel stack memory into cr2 and error code.
+	 */
+	memset(exception, 0, sizeof(*exception));
 	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access,
 					  exception);
 }
 EXPORT_SYMBOL_GPL(kvm_read_guest_virt);
 
-static int kvm_read_guest_virt_system(struct x86_emulate_ctxt *ctxt,
-				      gva_t addr, void *val, unsigned int bytes,
-				      struct x86_exception *exception)
+static int emulator_read_std(struct x86_emulate_ctxt *ctxt,
+			     gva_t addr, void *val, unsigned int bytes,
+			     struct x86_exception *exception, bool system)
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, exception);
+	u32 access = 0;
+
+	if (!system && kvm_x86_ops->get_cpl(vcpu) == 3)
+		access |= PFERR_USER_MASK;
+
+	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception);
 }
 
 static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt,
@@ -4267,18 +4296,16 @@ static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt,
 	return r < 0 ? X86EMUL_IO_NEEDED : X86EMUL_CONTINUE;
 }
 
-int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
-				       gva_t addr, void *val,
-				       unsigned int bytes,
-				       struct x86_exception *exception)
+static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
+				      struct kvm_vcpu *vcpu, u32 access,
+				      struct x86_exception *exception)
 {
-	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 	void *data = val;
 	int r = X86EMUL_CONTINUE;
 
 	while (bytes) {
 		gpa_t gpa =  vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr,
-							     PFERR_WRITE_MASK,
+							     access,
 							     exception);
 		unsigned offset = addr & (PAGE_SIZE-1);
 		unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset);
@@ -4299,6 +4326,27 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
 out:
 	return r;
 }
+
+static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val,
+			      unsigned int bytes, struct x86_exception *exception,
+			      bool system)
+{
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	u32 access = PFERR_WRITE_MASK;
+
+	if (!system && kvm_x86_ops->get_cpl(vcpu) == 3)
+		access |= PFERR_USER_MASK;
+
+	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
+					   access, exception);
+}
+
+int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val,
+				unsigned int bytes, struct x86_exception *exception)
+{
+	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
+					   PFERR_WRITE_MASK, exception);
+}
 EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system);
 
 static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
@@ -5018,8 +5066,8 @@ static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_fla
 static const struct x86_emulate_ops emulate_ops = {
 	.read_gpr            = emulator_read_gpr,
 	.write_gpr           = emulator_write_gpr,
-	.read_std            = kvm_read_guest_virt_system,
-	.write_std           = kvm_write_guest_virt_system,
+	.read_std            = emulator_read_std,
+	.write_std           = emulator_write_std,
 	.read_phys           = kvm_read_guest_phys_system,
 	.fetch               = kvm_fetch_guest_virt,
 	.read_emulated       = emulator_read_emulated,
@@ -5153,7 +5201,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
 		vcpu->run->internal.ndata = 0;
-		r = EMULATE_FAIL;
+		r = EMULATE_USER_EXIT;
 	}
 	kvm_queue_exception(vcpu, UD_VECTOR);
 
@@ -5410,7 +5458,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		 * handle watchpoints yet, those would be handled in
 		 * the emulate_ops.
 		 */
-		if (kvm_vcpu_check_breakpoint(vcpu, &r))
+		if (!(emulation_type & EMULTYPE_SKIP) &&
+		    kvm_vcpu_check_breakpoint(vcpu, &r))
 			return r;
 
 		ctxt->interruptibility = 0;
@@ -5497,8 +5546,7 @@ restart:
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 		kvm_rip_write(vcpu, ctxt->eip);
-		if (r == EMULATE_DONE &&
-		    (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
+		if (r == EMULATE_DONE && ctxt->tf)
 			kvm_vcpu_do_singlestep(vcpu, &r);
 		if (!ctxt->have_exception ||
 		    exception_type(ctxt->exception.vector) == EXCPT_TRAP)
@@ -6445,6 +6493,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		}
 		if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+			vcpu->mmio_needed = 0;
 			r = 0;
 			goto out;
 		}
@@ -7289,16 +7338,6 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 	copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
 	__kernel_fpu_end();
 	++vcpu->stat.fpu_reload;
-	/*
-	 * If using eager FPU mode, or if the guest is a frequent user
-	 * of the FPU, just leave the FPU active for next time.
-	 * Every 255 times fpu_counter rolls over to 0; a guest that uses
-	 * the FPU in bursts will revert to loading it on demand.
-	 */
-	if (!vcpu->arch.eager_fpu) {
-		if (++vcpu->fpu_counter < 5)
-			kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
-	}
 	trace_kvm_fpu(0);
 }
 
@@ -8204,6 +8243,13 @@ static int apf_put_user(struct kvm_vcpu *vcpu, u32 val)
 				      sizeof(val));
 }
 
+static int apf_get_user(struct kvm_vcpu *vcpu, u32 *val)
+{
+
+	return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, val,
+				      sizeof(u32));
+}
+
 void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 				     struct kvm_async_pf *work)
 {
@@ -8230,6 +8276,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 				 struct kvm_async_pf *work)
 {
 	struct x86_exception fault;
+	u32 val;
 
 	if (work->wakeup_all)
 		work->arch.token = ~0; /* broadcast wakeup */
@@ -8237,14 +8284,24 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
 	trace_kvm_async_pf_ready(work->arch.token, work->gva);
 
-	if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) &&
-	    !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
-		fault.vector = PF_VECTOR;
-		fault.error_code_valid = true;
-		fault.error_code = 0;
-		fault.nested_page_fault = false;
-		fault.address = work->arch.token;
-		kvm_inject_page_fault(vcpu, &fault);
+	if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED &&
+	    !apf_get_user(vcpu, &val)) {
+		if (val == KVM_PV_REASON_PAGE_NOT_PRESENT &&
+		    vcpu->arch.exception.pending &&
+		    vcpu->arch.exception.nr == PF_VECTOR &&
+		    !apf_put_user(vcpu, 0)) {
+			vcpu->arch.exception.pending = false;
+			vcpu->arch.exception.nr = 0;
+			vcpu->arch.exception.has_error_code = false;
+			vcpu->arch.exception.error_code = 0;
+		} else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
+			fault.vector = PF_VECTOR;
+			fault.error_code_valid = true;
+			fault.error_code = 0;
+			fault.nested_page_fault = false;
+			fault.address = work->arch.token;
+			kvm_inject_page_fault(vcpu, &fault);
+		}
 	}
 	vcpu->arch.apf.halted = false;
 	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;