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

Pull kvm fixes from Paolo Bonzini:
 "x86:

   - fix lock initialization race in gfn-to-pfn cache (+selftests)

   - fix two refcounting errors

   - emulator fixes

   - mask off reserved bits in CPUID

   - fix bug with disabling SGX

  RISC-V:

   - update MAINTAINERS"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86/xen: Fix eventfd error handling in kvm_xen_eventfd_assign()
  KVM: x86: smm: number of GPRs in the SMRAM image depends on the image format
  KVM: x86: emulator: update the emulation mode after CR0 write
  KVM: x86: emulator: update the emulation mode after rsm
  KVM: x86: emulator: introduce emulator_recalc_and_set_mode
  KVM: x86: emulator: em_sysexit should update ctxt->mode
  KVM: selftests: Mark "guest_saw_irq" as volatile in xen_shinfo_test
  KVM: selftests: Add tests in xen_shinfo_test to detect lock races
  KVM: Reject attempts to consume or refresh inactive gfn_to_pfn_cache
  KVM: Initialize gfn_to_pfn_cache locks in dedicated helper
  KVM: VMX: fully disable SGX if SECONDARY_EXEC_ENCLS_EXITING unavailable
  KVM: x86: Exempt pending triple fault from event injection sanity check
  MAINTAINERS: git://github -> https://github.com for kvm-riscv
  KVM: debugfs: Return retval of simple_attr_open() if it fails
  KVM: x86: Reduce refcount if single_open() fails in kvm_mmu_rmaps_stat_open()
  KVM: x86: Mask off reserved bits in CPUID.8000001FH
  KVM: x86: Mask off reserved bits in CPUID.8000001AH
  KVM: x86: Mask off reserved bits in CPUID.80000008H
  KVM: x86: Mask off reserved bits in CPUID.80000006H
  KVM: x86: Mask off reserved bits in CPUID.80000001H

Author: torvalds

MAINTAINERS

@@ -11248,7 +11248,7 @@ L:	kvm@vger.kernel.org
 L:	kvm-riscv@lists.infradead.org
 L:	linux-riscv@lists.infradead.org
 S:	Maintained
-T:	git git://github.com/kvm-riscv/linux.git
+T:	git https://github.com/kvm-riscv/linux.git
 F:	arch/riscv/include/asm/kvm*
 F:	arch/riscv/include/uapi/asm/kvm*
 F:	arch/riscv/kvm/

arch/x86/kvm/cpuid.c

@@ -1133,11 +1133,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 			entry->eax = max(entry->eax, 0x80000021);
 		break;
 	case 0x80000001:
+		entry->ebx &= ~GENMASK(27, 16);
 		cpuid_entry_override(entry, CPUID_8000_0001_EDX);
 		cpuid_entry_override(entry, CPUID_8000_0001_ECX);
 		break;
 	case 0x80000006:
-		/* L2 cache and TLB: pass through host info. */
+		/* Drop reserved bits, pass host L2 cache and TLB info. */
+		entry->edx &= ~GENMASK(17, 16);
 		break;
 	case 0x80000007: /* Advanced power management */
 		/* invariant TSC is CPUID.80000007H:EDX[8] */
@@ -1167,6 +1169,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 			g_phys_as = phys_as;
 
 		entry->eax = g_phys_as | (virt_as << 8);
+		entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8));
 		entry->edx = 0;
 		cpuid_entry_override(entry, CPUID_8000_0008_EBX);
 		break;
@@ -1186,14 +1189,18 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		entry->ecx = entry->edx = 0;
 		break;
 	case 0x8000001a:
+		entry->eax &= GENMASK(2, 0);
+		entry->ebx = entry->ecx = entry->edx = 0;
+		break;
 	case 0x8000001e:
 		break;
 	case 0x8000001F:
 		if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) {
 			entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
 		} else {
 			cpuid_entry_override(entry, CPUID_8000_001F_EAX);
-
+			/* Clear NumVMPL since KVM does not support VMPL.  */
+			entry->ebx &= ~GENMASK(31, 12);
 			/*
 			 * Enumerate '0' for "PA bits reduction", the adjusted
 			 * MAXPHYADDR is enumerated directly (see 0x80000008).

arch/x86/kvm/debugfs.c

@@ -158,11 +158,16 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v)
 static int kvm_mmu_rmaps_stat_open(struct inode *inode, struct file *file)
 {
 	struct kvm *kvm = inode->i_private;
+	int r;
 
 	if (!kvm_get_kvm_safe(kvm))
 		return -ENOENT;
 
-	return single_open(file, kvm_mmu_rmaps_stat_show, kvm);
+	r = single_open(file, kvm_mmu_rmaps_stat_show, kvm);
+	if (r < 0)
+		kvm_put_kvm(kvm);
+
+	return r;
 }
 
 static int kvm_mmu_rmaps_stat_release(struct inode *inode, struct file *file)

arch/x86/kvm/emulate.c

@@ -791,8 +791,7 @@ static int linearize(struct x86_emulate_ctxt *ctxt,
 			   ctxt->mode, linear);
 }
 
-static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst,
-			     enum x86emul_mode mode)
+static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst)
 {
 	ulong linear;
 	int rc;
@@ -802,41 +801,71 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst,
 
 	if (ctxt->op_bytes != sizeof(unsigned long))
 		addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1);
-	rc = __linearize(ctxt, addr, &max_size, 1, false, true, mode, &linear);
+	rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear);
 	if (rc == X86EMUL_CONTINUE)
 		ctxt->_eip = addr.ea;
 	return rc;
 }
 
+static inline int emulator_recalc_and_set_mode(struct x86_emulate_ctxt *ctxt)
+{
+	u64 efer;
+	struct desc_struct cs;
+	u16 selector;
+	u32 base3;
+
+	ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
+
+	if (!(ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PE)) {
+		/* Real mode. cpu must not have long mode active */
+		if (efer & EFER_LMA)
+			return X86EMUL_UNHANDLEABLE;
+		ctxt->mode = X86EMUL_MODE_REAL;
+		return X86EMUL_CONTINUE;
+	}
+
+	if (ctxt->eflags & X86_EFLAGS_VM) {
+		/* Protected/VM86 mode. cpu must not have long mode active */
+		if (efer & EFER_LMA)
+			return X86EMUL_UNHANDLEABLE;
+		ctxt->mode = X86EMUL_MODE_VM86;
+		return X86EMUL_CONTINUE;
+	}
+
+	if (!ctxt->ops->get_segment(ctxt, &selector, &cs, &base3, VCPU_SREG_CS))
+		return X86EMUL_UNHANDLEABLE;
+
+	if (efer & EFER_LMA) {
+		if (cs.l) {
+			/* Proper long mode */
+			ctxt->mode = X86EMUL_MODE_PROT64;
+		} else if (cs.d) {
+			/* 32 bit compatibility mode*/
+			ctxt->mode = X86EMUL_MODE_PROT32;
+		} else {
+			ctxt->mode = X86EMUL_MODE_PROT16;
+		}
+	} else {
+		/* Legacy 32 bit / 16 bit mode */
+		ctxt->mode = cs.d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
+	}
+
+	return X86EMUL_CONTINUE;
+}
+
 static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst)
 {
-	return assign_eip(ctxt, dst, ctxt->mode);
+	return assign_eip(ctxt, dst);
 }
 
-static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst,
-			  const struct desc_struct *cs_desc)
+static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst)
 {
-	enum x86emul_mode mode = ctxt->mode;
-	int rc;
+	int rc = emulator_recalc_and_set_mode(ctxt);
 
-#ifdef CONFIG_X86_64
-	if (ctxt->mode >= X86EMUL_MODE_PROT16) {
-		if (cs_desc->l) {
-			u64 efer = 0;
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
 
-			ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
-			if (efer & EFER_LMA)
-				mode = X86EMUL_MODE_PROT64;
-		} else
-			mode = X86EMUL_MODE_PROT32; /* temporary value */
-	}
-#endif
-	if (mode == X86EMUL_MODE_PROT16 || mode == X86EMUL_MODE_PROT32)
-		mode = cs_desc->d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
-	rc = assign_eip(ctxt, dst, mode);
-	if (rc == X86EMUL_CONTINUE)
-		ctxt->mode = mode;
-	return rc;
+	return assign_eip(ctxt, dst);
 }
 
 static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
@@ -2172,7 +2201,7 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
+	rc = assign_eip_far(ctxt, ctxt->src.val);
 	/* Error handling is not implemented. */
 	if (rc != X86EMUL_CONTINUE)
 		return X86EMUL_UNHANDLEABLE;
@@ -2250,7 +2279,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 				       &new_desc);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
-	rc = assign_eip_far(ctxt, eip, &new_desc);
+	rc = assign_eip_far(ctxt, eip);
 	/* Error handling is not implemented. */
 	if (rc != X86EMUL_CONTINUE)
 		return X86EMUL_UNHANDLEABLE;
@@ -2432,7 +2461,7 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
 	ctxt->eflags =             GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
 	ctxt->_eip =               GET_SMSTATE(u32, smstate, 0x7ff0);
 
-	for (i = 0; i < NR_EMULATOR_GPRS; i++)
+	for (i = 0; i < 8; i++)
 		*reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
 
 	val = GET_SMSTATE(u32, smstate, 0x7fcc);
@@ -2489,7 +2518,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
 	u16 selector;
 	int i, r;
 
-	for (i = 0; i < NR_EMULATOR_GPRS; i++)
+	for (i = 0; i < 16; i++)
 		*reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
 
 	ctxt->_eip   = GET_SMSTATE(u64, smstate, 0x7f78);
@@ -2633,7 +2662,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
 	 * those side effects need to be explicitly handled for both success
 	 * and shutdown.
 	 */
-	return X86EMUL_CONTINUE;
+	return emulator_recalc_and_set_mode(ctxt);
 
 emulate_shutdown:
 	ctxt->ops->triple_fault(ctxt);
@@ -2876,6 +2905,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
 	ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
 
 	ctxt->_eip = rdx;
+	ctxt->mode = usermode;
 	*reg_write(ctxt, VCPU_REGS_RSP) = rcx;
 
 	return X86EMUL_CONTINUE;
@@ -3469,7 +3499,7 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
+	rc = assign_eip_far(ctxt, ctxt->src.val);
 	if (rc != X86EMUL_CONTINUE)
 		goto fail;
 
@@ -3611,11 +3641,25 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt)
 
 static int em_cr_write(struct x86_emulate_ctxt *ctxt)
 {
-	if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val))
+	int cr_num = ctxt->modrm_reg;
+	int r;
+
+	if (ctxt->ops->set_cr(ctxt, cr_num, ctxt->src.val))
 		return emulate_gp(ctxt, 0);
 
 	/* Disable writeback. */
 	ctxt->dst.type = OP_NONE;
+
+	if (cr_num == 0) {
+		/*
+		 * CR0 write might have updated CR0.PE and/or CR0.PG
+		 * which can affect the cpu's execution mode.
+		 */
+		r = emulator_recalc_and_set_mode(ctxt);
+		if (r != X86EMUL_CONTINUE)
+			return r;
+	}
+
 	return X86EMUL_CONTINUE;
 }
 

arch/x86/kvm/vmx/vmx.c

@@ -8263,6 +8263,11 @@ static __init int hardware_setup(void)
 	if (!cpu_has_virtual_nmis())
 		enable_vnmi = 0;
 
+#ifdef CONFIG_X86_SGX_KVM
+	if (!cpu_has_vmx_encls_vmexit())
+		enable_sgx = false;
+#endif
+
 	/*
 	 * set_apic_access_page_addr() is used to reload apic access
 	 * page upon invalidation.  No need to do anything if not

arch/x86/kvm/x86.c

@@ -2315,11 +2315,11 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time,
 
 	/* we verify if the enable bit is set... */
 	if (system_time & 1) {
-		kvm_gfn_to_pfn_cache_init(vcpu->kvm, &vcpu->arch.pv_time, vcpu,
-					  KVM_HOST_USES_PFN, system_time & ~1ULL,
-					  sizeof(struct pvclock_vcpu_time_info));
+		kvm_gpc_activate(vcpu->kvm, &vcpu->arch.pv_time, vcpu,
+				 KVM_HOST_USES_PFN, system_time & ~1ULL,
+				 sizeof(struct pvclock_vcpu_time_info));
 	} else {
-		kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time);
+		kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time);
 	}
 
 	return;
@@ -3388,7 +3388,7 @@ static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data)
 
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
-	kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time);
+	kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time);
 	vcpu->arch.time = 0;
 }
 
@@ -10044,7 +10044,20 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
 	    kvm_x86_ops.nested_ops->has_events(vcpu))
 		*req_immediate_exit = true;
 
-	WARN_ON(kvm_is_exception_pending(vcpu));
+	/*
+	 * KVM must never queue a new exception while injecting an event; KVM
+	 * is done emulating and should only propagate the to-be-injected event
+	 * to the VMCS/VMCB.  Queueing a new exception can put the vCPU into an
+	 * infinite loop as KVM will bail from VM-Enter to inject the pending
+	 * exception and start the cycle all over.
+	 *
+	 * Exempt triple faults as they have special handling and won't put the
+	 * vCPU into an infinite loop.  Triple fault can be queued when running
+	 * VMX without unrestricted guest, as that requires KVM to emulate Real
+	 * Mode events (see kvm_inject_realmode_interrupt()).
+	 */
+	WARN_ON_ONCE(vcpu->arch.exception.pending ||
+		     vcpu->arch.exception_vmexit.pending);
 	return 0;
 
 out:
@@ -11816,6 +11829,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.regs_avail = ~0;
 	vcpu->arch.regs_dirty = ~0;
 
+	kvm_gpc_init(&vcpu->arch.pv_time);
+
 	if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 	else