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

Pull second set of KVM updates from Paolo Bonzini:
 "ARM:
   - Support for Group0 interrupts in guests
   - Cache management optimizations for ARMv8.4 systems
   - Userspace interface for RAS
   - Fault path optimization
   - Emulated physical timer fixes
   - Random cleanups

  x86:
   - fixes for L1TF
   - a new test case
   - non-support for SGX (inject the right exception in the guest)
   - fix lockdep false positive"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (49 commits)
  KVM: VMX: fixes for vmentry_l1d_flush module parameter
  kvm: selftest: add dirty logging test
  kvm: selftest: pass in extra memory when create vm
  kvm: selftest: include the tools headers
  kvm: selftest: unify the guest port macros
  tools: introduce test_and_clear_bit
  KVM: x86: SVM: Call x86_spec_ctrl_set_guest/host() with interrupts disabled
  KVM: vmx: Inject #UD for SGX ENCLS instruction in guest
  KVM: vmx: Add defines for SGX ENCLS exiting
  x86/kvm/vmx: Fix coding style in vmx_setup_l1d_flush()
  x86: kvm: avoid unused variable warning
  KVM: Documentation: rename the capability of KVM_CAP_ARM_SET_SERROR_ESR
  KVM: arm/arm64: Skip updating PTE entry if no change
  KVM: arm/arm64: Skip updating PMD entry if no change
  KVM: arm: Use true and false for boolean values
  KVM: arm/arm64: vgic: Do not use spin_lock_irqsave/restore with irq disabled
  KVM: arm/arm64: vgic: Move DEBUG_SPINLOCK_BUG_ON to vgic.h
  KVM: arm: vgic-v3: Add support for ICC_SGI0R and ICC_ASGI1R accesses
  KVM: arm64: vgic-v3: Add support for ICC_SGI0R_EL1 and ICC_ASGI1R_EL1 accesses
  KVM: arm/arm64: vgic-v3: Add core support for Group0 SGIs
  ...

3 files changed, 58 insertions, 26 deletions

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 73e27a98456f..6276140044d0 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -5586,8 +5586,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 
 	clgi();
 
-	local_irq_enable();
-
 	/*
 	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
 	 * it's non-zero. Since vmentry is serialising on affected CPUs, there
@@ -5596,6 +5594,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	 */
 	x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
 
+	local_irq_enable();
+
 	asm volatile (
 		"push %%" _ASM_BP "; \n\t"
 		"mov %c[rbx](%[svm]), %%" _ASM_BX " \n\t"
@@ -5718,12 +5718,12 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
 		svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
 
-	x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
-
 	reload_tss(vcpu);
 
 	local_irq_disable();
 
+	x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
+
 	vcpu->arch.cr2 = svm->vmcb->save.cr2;
 	vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax;
 	vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1519f030fd73..8dae47e7267a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -198,12 +198,14 @@ static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_
 
 static const struct {
 	const char *option;
-	enum vmx_l1d_flush_state cmd;
+	bool for_parse;
 } vmentry_l1d_param[] = {
-	{"auto",	VMENTER_L1D_FLUSH_AUTO},
-	{"never",	VMENTER_L1D_FLUSH_NEVER},
-	{"cond",	VMENTER_L1D_FLUSH_COND},
-	{"always",	VMENTER_L1D_FLUSH_ALWAYS},
+	[VMENTER_L1D_FLUSH_AUTO]	 = {"auto", true},
+	[VMENTER_L1D_FLUSH_NEVER]	 = {"never", true},
+	[VMENTER_L1D_FLUSH_COND]	 = {"cond", true},
+	[VMENTER_L1D_FLUSH_ALWAYS]	 = {"always", true},
+	[VMENTER_L1D_FLUSH_EPT_DISABLED] = {"EPT disabled", false},
+	[VMENTER_L1D_FLUSH_NOT_REQUIRED] = {"not required", false},
 };
 
 #define L1D_CACHE_ORDER 4
@@ -219,15 +221,15 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 		return 0;
 	}
 
-       if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
-	       u64 msr;
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
+		u64 msr;
 
-	       rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
-	       if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
-		       l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
-		       return 0;
-	       }
-       }
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
+		if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
+			l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
+			return 0;
+		}
+	}
 
 	/* If set to auto use the default l1tf mitigation method */
 	if (l1tf == VMENTER_L1D_FLUSH_AUTO) {
@@ -287,8 +289,9 @@ static int vmentry_l1d_flush_parse(const char *s)
 
 	if (s) {
 		for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) {
-			if (sysfs_streq(s, vmentry_l1d_param[i].option))
-				return vmentry_l1d_param[i].cmd;
+			if (vmentry_l1d_param[i].for_parse &&
+			    sysfs_streq(s, vmentry_l1d_param[i].option))
+				return i;
 		}
 	}
 	return -EINVAL;
@@ -298,13 +301,13 @@ static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
 {
 	int l1tf, ret;
 
-	if (!boot_cpu_has(X86_BUG_L1TF))
-		return 0;
-
 	l1tf = vmentry_l1d_flush_parse(s);
 	if (l1tf < 0)
 		return l1tf;
 
+	if (!boot_cpu_has(X86_BUG_L1TF))
+		return 0;
+
 	/*
 	 * Has vmx_init() run already? If not then this is the pre init
 	 * parameter parsing. In that case just store the value and let
@@ -324,6 +327,9 @@ static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
 
 static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
 {
+	if (WARN_ON_ONCE(l1tf_vmx_mitigation >= ARRAY_SIZE(vmentry_l1d_param)))
+		return sprintf(s, "???\n");
+
 	return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option);
 }
 
@@ -1684,6 +1690,12 @@ static inline bool cpu_has_vmx_virtual_intr_delivery(void)
 		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
 }
 
+static inline bool cpu_has_vmx_encls_vmexit(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_ENCLS_EXITING;
+}
+
 /*
  * Comment's format: document - errata name - stepping - processor name.
  * Refer from
@@ -4551,7 +4563,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 			SECONDARY_EXEC_RDRAND_EXITING |
 			SECONDARY_EXEC_ENABLE_PML |
 			SECONDARY_EXEC_TSC_SCALING |
-			SECONDARY_EXEC_ENABLE_VMFUNC;
+			SECONDARY_EXEC_ENABLE_VMFUNC |
+			SECONDARY_EXEC_ENCLS_EXITING;
 		if (adjust_vmx_controls(min2, opt2,
 					MSR_IA32_VMX_PROCBASED_CTLS2,
 					&_cpu_based_2nd_exec_control) < 0)
@@ -6648,6 +6661,9 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
 		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
 	}
+
+	if (cpu_has_vmx_encls_vmexit())
+		vmcs_write64(ENCLS_EXITING_BITMAP, -1ull);
 }
 
 static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -9314,6 +9330,17 @@ fail:
 	return 1;
 }
 
+static int handle_encls(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * SGX virtualization is not yet supported.  There is no software
+	 * enable bit for SGX, so we have to trap ENCLS and inject a #UD
+	 * to prevent the guest from executing ENCLS.
+	 */
+	kvm_queue_exception(vcpu, UD_VECTOR);
+	return 1;
+}
+
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -9371,6 +9398,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_INVPCID]                 = handle_invpcid,
 	[EXIT_REASON_VMFUNC]                  = handle_vmfunc,
 	[EXIT_REASON_PREEMPTION_TIMER]	      = handle_preemption_timer,
+	[EXIT_REASON_ENCLS]		      = handle_encls,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -9741,6 +9769,9 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
 	case EXIT_REASON_VMFUNC:
 		/* VM functions are emulated through L2->L0 vmexits. */
 		return false;
+	case EXIT_REASON_ENCLS:
+		/* SGX is never exposed to L1 */
+		return false;
 	default:
 		return true;
 	}
@@ -12101,6 +12132,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)
 			vmcs_write64(APIC_ACCESS_ADDR, -1ull);
 
+		if (exec_control & SECONDARY_EXEC_ENCLS_EXITING)
+			vmcs_write64(ENCLS_EXITING_BITMAP, -1ull);
+
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
 	}
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4a74a7cf0a8b..506bd2b4b8bb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6576,14 +6576,12 @@ static void kvm_set_mmio_spte_mask(void)
 	/* Set the present bit. */
 	mask |= 1ull;
 
-#ifdef CONFIG_X86_64
 	/*
 	 * If reserved bit is not supported, clear the present bit to disable
 	 * mmio page fault.
 	 */
-	if (maxphyaddr == 52)
+	if (IS_ENABLED(CONFIG_X86_64) && maxphyaddr == 52)
 		mask &= ~1ull;
-#endif
 
 	kvm_mmu_set_mmio_spte_mask(mask, mask);
 }