Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "Bugfixes for x86 and s390"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: nVMX: avoid NULL pointer dereference with incorrect EVMCS GPAs
  KVM: x86: Initializing all kvm_lapic_irq fields in ioapic_write_indirect
  KVM: VMX: Condition ENCLS-exiting enabling on CPU support for SGX1
  KVM: s390: Also reset registers in sync regs for initial cpu reset
  KVM: fix Kconfig menu text for -Werror
  KVM: x86: remove stale comment from struct x86_emulate_ctxt
  KVM: x86: clear stale x86_emulate_ctxt->intercept value
  KVM: SVM: Fix the svm vmexit code for WRMSR
  KVM: X86: Fix dereference null cpufreq policy

Author: torvalds

arch/s390/kvm/kvm-s390.c

@@ -3268,7 +3268,10 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
 	/* Initial reset is a superset of the normal reset */
 	kvm_arch_vcpu_ioctl_normal_reset(vcpu);
 
-	/* this equals initial cpu reset in pop, but we don't switch to ESA */
+	/*
+	 * This equals initial cpu reset in pop, but we don't switch to ESA.
+	 * We do not only reset the internal data, but also ...
+	 */
 	vcpu->arch.sie_block->gpsw.mask = 0;
 	vcpu->arch.sie_block->gpsw.addr = 0;
 	kvm_s390_set_prefix(vcpu, 0);
@@ -3278,6 +3281,19 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
 	memset(vcpu->arch.sie_block->gcr, 0, sizeof(vcpu->arch.sie_block->gcr));
 	vcpu->arch.sie_block->gcr[0] = CR0_INITIAL_MASK;
 	vcpu->arch.sie_block->gcr[14] = CR14_INITIAL_MASK;
+
+	/* ... the data in sync regs */
+	memset(vcpu->run->s.regs.crs, 0, sizeof(vcpu->run->s.regs.crs));
+	vcpu->run->s.regs.ckc = 0;
+	vcpu->run->s.regs.crs[0] = CR0_INITIAL_MASK;
+	vcpu->run->s.regs.crs[14] = CR14_INITIAL_MASK;
+	vcpu->run->psw_addr = 0;
+	vcpu->run->psw_mask = 0;
+	vcpu->run->s.regs.todpr = 0;
+	vcpu->run->s.regs.cputm = 0;
+	vcpu->run->s.regs.ckc = 0;
+	vcpu->run->s.regs.pp = 0;
+	vcpu->run->s.regs.gbea = 1;
 	vcpu->run->s.regs.fpc = 0;
 	vcpu->arch.sie_block->gbea = 1;
 	vcpu->arch.sie_block->pp = 0;

arch/x86/include/asm/kvm_emulate.h

@@ -360,7 +360,6 @@ struct x86_emulate_ctxt {
 	u64 d;
 	unsigned long _eip;
 	struct operand memop;
-	/* Fields above regs are cleared together. */
 	unsigned long _regs[NR_VCPU_REGS];
 	struct operand *memopp;
 	struct fetch_cache fetch;

arch/x86/kvm/Kconfig

@@ -68,7 +68,7 @@ config KVM_WERROR
 	depends on (X86_64 && !KASAN) || !COMPILE_TEST
 	depends on EXPERT
 	help
-	  Add -Werror to the build flags for (and only for) i915.ko.
+	  Add -Werror to the build flags for KVM.
 
 	  If in doubt, say "N".
 

arch/x86/kvm/emulate.c

@@ -5173,6 +5173,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	ctxt->fetch.ptr = ctxt->fetch.data;
 	ctxt->fetch.end = ctxt->fetch.data + insn_len;
 	ctxt->opcode_len = 1;
+	ctxt->intercept = x86_intercept_none;
 	if (insn_len > 0)
 		memcpy(ctxt->fetch.data, insn, insn_len);
 	else {

arch/x86/kvm/ioapic.c

@@ -378,12 +378,15 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		if (e->fields.delivery_mode == APIC_DM_FIXED) {
 			struct kvm_lapic_irq irq;
 
-			irq.shorthand = APIC_DEST_NOSHORT;
 			irq.vector = e->fields.vector;
 			irq.delivery_mode = e->fields.delivery_mode << 8;
-			irq.dest_id = e->fields.dest_id;
 			irq.dest_mode =
 			    kvm_lapic_irq_dest_mode(!!e->fields.dest_mode);
+			irq.level = false;
+			irq.trig_mode = e->fields.trig_mode;
+			irq.shorthand = APIC_DEST_NOSHORT;
+			irq.dest_id = e->fields.dest_id;
+			irq.msi_redir_hint = false;
 			bitmap_zero(&vcpu_bitmap, 16);
 			kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
 						 &vcpu_bitmap);

arch/x86/kvm/svm.c

@@ -6312,7 +6312,8 @@ static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu,
 	enum exit_fastpath_completion *exit_fastpath)
 {
 	if (!is_guest_mode(vcpu) &&
-		to_svm(vcpu)->vmcb->control.exit_code == EXIT_REASON_MSR_WRITE)
+	    to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR &&
+	    to_svm(vcpu)->vmcb->control.exit_info_1)
 		*exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu);
 }
 

arch/x86/kvm/vmx/nested.c

@@ -224,7 +224,7 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
 		return;
 
 	kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true);
-	vmx->nested.hv_evmcs_vmptr = -1ull;
+	vmx->nested.hv_evmcs_vmptr = 0;
 	vmx->nested.hv_evmcs = NULL;
 }
 
@@ -1923,7 +1923,8 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu,
 	if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa))
 		return 1;
 
-	if (unlikely(evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) {
+	if (unlikely(!vmx->nested.hv_evmcs ||
+		     evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) {
 		if (!vmx->nested.hv_evmcs)
 			vmx->nested.current_vmptr = -1ull;
 

arch/x86/kvm/vmx/vmx.c

@@ -2338,6 +2338,17 @@ static void hardware_disable(void)
 	kvm_cpu_vmxoff();
 }
 
+/*
+ * There is no X86_FEATURE for SGX yet, but anyway we need to query CPUID
+ * directly instead of going through cpu_has(), to ensure KVM is trapping
+ * ENCLS whenever it's supported in hardware.  It does not matter whether
+ * the host OS supports or has enabled SGX.
+ */
+static bool cpu_has_sgx(void)
+{
+	return cpuid_eax(0) >= 0x12 && (cpuid_eax(0x12) & BIT(0));
+}
+
 static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
 				      u32 msr, u32 *result)
 {
@@ -2418,8 +2429,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 			SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |
 			SECONDARY_EXEC_PT_USE_GPA |
 			SECONDARY_EXEC_PT_CONCEAL_VMX |
-			SECONDARY_EXEC_ENABLE_VMFUNC |
-			SECONDARY_EXEC_ENCLS_EXITING;
+			SECONDARY_EXEC_ENABLE_VMFUNC;
+		if (cpu_has_sgx())
+			opt2 |= SECONDARY_EXEC_ENCLS_EXITING;
 		if (adjust_vmx_controls(min2, opt2,
 					MSR_IA32_VMX_PROCBASED_CTLS2,
 					&_cpu_based_2nd_exec_control) < 0)

arch/x86/kvm/x86.c

@@ -7195,10 +7195,12 @@ static void kvm_timer_init(void)
 
 		cpu = get_cpu();
 		policy = cpufreq_cpu_get(cpu);
-		if (policy && policy->cpuinfo.max_freq)
-			max_tsc_khz = policy->cpuinfo.max_freq;
+		if (policy) {
+			if (policy->cpuinfo.max_freq)
+				max_tsc_khz = policy->cpuinfo.max_freq;
+			cpufreq_cpu_put(policy);
+		}
 		put_cpu();
-		cpufreq_cpu_put(policy);
 #endif
 		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
 					  CPUFREQ_TRANSITION_NOTIFIER);