Merge tag 'kvm-x86-vmx-6.12' of https://github.com/kvm-x86/linux into HEAD

KVM VMX changes for 6.12:

 - Set FINAL/PAGE in the page fault error code for EPT Violations if and only
   if the GVA is valid.  If the GVA is NOT valid, there is no guest-side page
   table walk and so stuffing paging related metadata is nonsensical.

 - Fix a bug where KVM would incorrectly synthesize a nested VM-Exit instead of
   emulating posted interrupt delivery to L2.

 - Add a lockdep assertion to detect unsafe accesses of vmcs12 structures.

 - Harden eVMCS loading against an impossible NULL pointer deref (really truly
   should be impossible).

 - Minor SGX fix and a cleanup.

Author: bonzini

Documentation/virt/kvm/api.rst

@@ -4214,7 +4214,9 @@ whether or not KVM_CAP_X86_USER_SPACE_MSR's KVM_MSR_EXIT_REASON_FILTER is
 enabled.  If KVM_MSR_EXIT_REASON_FILTER is enabled, KVM will exit to userspace
 on denied accesses, i.e. userspace effectively intercepts the MSR access.  If
 KVM_MSR_EXIT_REASON_FILTER is not enabled, KVM will inject a #GP into the guest
-on denied accesses.
+on denied accesses.  Note, if an MSR access is denied during emulation of MSR
+load/stores during VMX transitions, KVM ignores KVM_MSR_EXIT_REASON_FILTER.
+See the below warning for full details.
 
 If an MSR access is allowed by userspace, KVM will emulate and/or virtualize
 the access in accordance with the vCPU model.  Note, KVM may still ultimately
@@ -4229,9 +4231,22 @@ filtering. In that mode, ``KVM_MSR_FILTER_DEFAULT_DENY`` is invalid and causes
 an error.
 
 .. warning::
-   MSR accesses as part of nested VM-Enter/VM-Exit are not filtered.
-   This includes both writes to individual VMCS fields and reads/writes
-   through the MSR lists pointed to by the VMCS.
+   MSR accesses that are side effects of instruction execution (emulated or
+   native) are not filtered as hardware does not honor MSR bitmaps outside of
+   RDMSR and WRMSR, and KVM mimics that behavior when emulating instructions
+   to avoid pointless divergence from hardware.  E.g. RDPID reads MSR_TSC_AUX,
+   SYSENTER reads the SYSENTER MSRs, etc.
+
+   MSRs that are loaded/stored via dedicated VMCS fields are not filtered as
+   part of VM-Enter/VM-Exit emulation.
+
+   MSRs that are loaded/store via VMX's load/store lists _are_ filtered as part
+   of VM-Enter/VM-Exit emulation.  If an MSR access is denied on VM-Enter, KVM
+   synthesizes a consistency check VM-Exit(EXIT_REASON_MSR_LOAD_FAIL).  If an
+   MSR access is denied on VM-Exit, KVM synthesizes a VM-Abort.  In short, KVM
+   extends Intel's architectural list of MSRs that cannot be loaded/saved via
+   the VM-Enter/VM-Exit MSR list.  It is platform owner's responsibility to
+   to communicate any such restrictions to their end users.
 
    x2APIC MSR accesses cannot be filtered (KVM silently ignores filters that
    cover any x2APIC MSRs).

arch/x86/include/asm/kvm_host.h

@@ -2062,6 +2062,8 @@ void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu);
 
 void kvm_enable_efer_bits(u64);
 bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer);
+int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data);
+int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data);
 int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated);
 int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data);
 int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data);
@@ -2264,6 +2266,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_cpu_has_extint(struct kvm_vcpu *v);
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
+int kvm_cpu_get_extint(struct kvm_vcpu *v);
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
 

arch/x86/kvm/irq.c

@@ -108,7 +108,7 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt);
  * Read pending interrupt(from non-APIC source)
  * vector and intack.
  */
-static int kvm_cpu_get_extint(struct kvm_vcpu *v)
+int kvm_cpu_get_extint(struct kvm_vcpu *v)
 {
 	if (!kvm_cpu_has_extint(v)) {
 		WARN_ON(!lapic_in_kernel(v));
@@ -131,6 +131,7 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v)
 	} else
 		return kvm_pic_read_irq(v->kvm); /* PIC */
 }
+EXPORT_SYMBOL_GPL(kvm_cpu_get_extint);
 
 /*
  * Read pending interrupt vector and intack.
@@ -141,9 +142,12 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 	if (vector != -1)
 		return vector;			/* PIC */
 
-	return kvm_get_apic_interrupt(v);	/* APIC */
+	vector = kvm_apic_has_interrupt(v);	/* APIC */
+	if (vector != -1)
+		kvm_apic_ack_interrupt(v, vector);
+
+	return vector;
 }
-EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt);
 
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
 {

arch/x86/kvm/lapic.c

@@ -2959,14 +2959,13 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
 	}
 }
 
-int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
+void kvm_apic_ack_interrupt(struct kvm_vcpu *vcpu, int vector)
 {
-	int vector = kvm_apic_has_interrupt(vcpu);
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u32 ppr;
 
-	if (vector == -1)
-		return -1;
+	if (WARN_ON_ONCE(vector < 0 || !apic))
+		return;
 
 	/*
 	 * We get here even with APIC virtualization enabled, if doing
@@ -2994,8 +2993,8 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
 		__apic_update_ppr(apic, &ppr);
 	}
 
-	return vector;
 }
+EXPORT_SYMBOL_GPL(kvm_apic_ack_interrupt);
 
 static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
 		struct kvm_lapic_state *s, bool set)

arch/x86/kvm/lapic.h

@@ -88,8 +88,8 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu);
 void kvm_free_lapic(struct kvm_vcpu *vcpu);
 
 int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
+void kvm_apic_ack_interrupt(struct kvm_vcpu *vcpu, int vector);
 int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu);
-int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu);
 int kvm_apic_accept_events(struct kvm_vcpu *vcpu);
 void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event);
 u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu);

arch/x86/kvm/vmx/nested.c

@@ -981,7 +981,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 				__func__, i, e.index, e.reserved);
 			goto fail;
 		}
-		if (kvm_set_msr(vcpu, e.index, e.value)) {
+		if (kvm_set_msr_with_filter(vcpu, e.index, e.value)) {
 			pr_debug_ratelimited(
 				"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
 				__func__, i, e.index, e.value);
@@ -1017,7 +1017,7 @@ static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu,
 		}
 	}
 
-	if (kvm_get_msr(vcpu, msr_index, data)) {
+	if (kvm_get_msr_with_filter(vcpu, msr_index, data)) {
 		pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__,
 			msr_index);
 		return false;
@@ -1112,9 +1112,9 @@ static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu,
 			/*
 			 * Emulated VMEntry does not fail here.  Instead a less
 			 * accurate value will be returned by
-			 * nested_vmx_get_vmexit_msr_value() using kvm_get_msr()
-			 * instead of reading the value from the vmcs02 VMExit
-			 * MSR-store area.
+			 * nested_vmx_get_vmexit_msr_value() by reading KVM's
+			 * internal MSR state instead of reading the value from
+			 * the vmcs02 VMExit MSR-store area.
 			 */
 			pr_warn_ratelimited(
 				"Not enough msr entries in msr_autostore.  Can't add msr %x\n",
@@ -2341,10 +2341,12 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
 
 	/* Posted interrupts setting is only taken from vmcs12.  */
 	vmx->nested.pi_pending = false;
-	if (nested_cpu_has_posted_intr(vmcs12))
+	if (nested_cpu_has_posted_intr(vmcs12)) {
 		vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
-	else
+	} else {
+		vmx->nested.posted_intr_nv = -1;
 		exec_control &= ~PIN_BASED_POSTED_INTR;
+	}
 	pin_controls_set(vmx, exec_control);
 
 	/*
@@ -2494,6 +2496,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 
 	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
 			   HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
+
 		vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
 		vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
 		vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
@@ -2531,7 +2534,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 		vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
 		vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
 
-		vmx->segment_cache.bitmask = 0;
+		vmx_segment_cache_clear(vmx);
 	}
 
 	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
@@ -4308,11 +4311,52 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
 	}
 
 	if (kvm_cpu_has_interrupt(vcpu) && !vmx_interrupt_blocked(vcpu)) {
+		int irq;
+
 		if (block_nested_events)
 			return -EBUSY;
 		if (!nested_exit_on_intr(vcpu))
 			goto no_vmexit;
-		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
+
+		if (!nested_exit_intr_ack_set(vcpu)) {
+			nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
+			return 0;
+		}
+
+		irq = kvm_cpu_get_extint(vcpu);
+		if (irq != -1) {
+			nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT,
+					  INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0);
+			return 0;
+		}
+
+		irq = kvm_apic_has_interrupt(vcpu);
+		if (WARN_ON_ONCE(irq < 0))
+			goto no_vmexit;
+
+		/*
+		 * If the IRQ is L2's PI notification vector, process posted
+		 * interrupts for L2 instead of injecting VM-Exit, as the
+		 * detection/morphing architecturally occurs when the IRQ is
+		 * delivered to the CPU.  Note, only interrupts that are routed
+		 * through the local APIC trigger posted interrupt processing,
+		 * and enabling posted interrupts requires ACK-on-exit.
+		 */
+		if (irq == vmx->nested.posted_intr_nv) {
+			vmx->nested.pi_pending = true;
+			kvm_apic_clear_irr(vcpu, irq);
+			goto no_vmexit;
+		}
+
+		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT,
+				  INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0);
+
+		/*
+		 * ACK the interrupt _after_ emulating VM-Exit, as the IRQ must
+		 * be marked as in-service in vmcs01.GUEST_INTERRUPT_STATUS.SVI
+		 * if APICv is active.
+		 */
+		kvm_apic_ack_interrupt(vcpu, irq);
 		return 0;
 	}
 
@@ -4830,7 +4874,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
 				goto vmabort;
 			}
 
-			if (kvm_set_msr(vcpu, h.index, h.value)) {
+			if (kvm_set_msr_with_filter(vcpu, h.index, h.value)) {
 				pr_debug_ratelimited(
 					"%s WRMSR failed (%u, 0x%x, 0x%llx)\n",
 					__func__, j, h.index, h.value);
@@ -4993,14 +5037,6 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 	if (likely(!vmx->fail)) {
-		if ((u16)vm_exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
-		    nested_exit_intr_ack_set(vcpu)) {
-			int irq = kvm_cpu_get_interrupt(vcpu);
-			WARN_ON(irq < 0);
-			vmcs12->vm_exit_intr_info = irq |
-				INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR;
-		}
-
 		if (vm_exit_reason != -1)
 			trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason,
 						       vmcs12->exit_qualification,

arch/x86/kvm/vmx/nested.h

@@ -39,11 +39,17 @@ bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
 
 static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
 {
+	lockdep_assert_once(lockdep_is_held(&vcpu->mutex) ||
+			    !refcount_read(&vcpu->kvm->users_count));
+
 	return to_vmx(vcpu)->nested.cached_vmcs12;
 }
 
 static inline struct vmcs12 *get_shadow_vmcs12(struct kvm_vcpu *vcpu)
 {
+	lockdep_assert_once(lockdep_is_held(&vcpu->mutex) ||
+			    !refcount_read(&vcpu->kvm->users_count));
+
 	return to_vmx(vcpu)->nested.cached_shadow_vmcs12;
 }
 

arch/x86/kvm/vmx/sgx.c

@@ -274,7 +274,7 @@ static int handle_encls_ecreate(struct kvm_vcpu *vcpu)
 	 * simultaneously set SGX_ATTR_PROVISIONKEY to bypass the check to
 	 * enforce restriction of access to the PROVISIONKEY.
 	 */
-	contents = (struct sgx_secs *)__get_free_page(GFP_KERNEL_ACCOUNT);
+	contents = (struct sgx_secs *)__get_free_page(GFP_KERNEL);
 	if (!contents)
 		return -ENOMEM;
 

arch/x86/kvm/vmx/vmx.c

@@ -525,10 +525,6 @@ static const struct kvm_vmx_segment_field {
 	VMX_SEGMENT_FIELD(LDTR),
 };
 
-static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx)
-{
-	vmx->segment_cache.bitmask = 0;
-}
 
 static unsigned long host_idt_base;
 
@@ -4219,6 +4215,13 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	/*
+	 * DO NOT query the vCPU's vmcs12, as vmcs12 is dynamically allocated
+	 * and freed, and must not be accessed outside of vcpu->mutex.  The
+	 * vCPU's cached PI NV is valid if and only if posted interrupts
+	 * enabled in its vmcs12, i.e. checking the vector also checks that
+	 * L1 has enabled posted interrupts for L2.
+	 */
 	if (is_guest_mode(vcpu) &&
 	    vector == vmx->nested.posted_intr_nv) {
 		/*
@@ -5804,8 +5807,9 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	error_code |= (exit_qualification & EPT_VIOLATION_RWX_MASK)
 		      ? PFERR_PRESENT_MASK : 0;
 
-	error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ?
-	       PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
+	if (error_code & EPT_VIOLATION_GVA_IS_VALID)
+		error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ?
+			      PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
 
 	/*
 	 * Check that the GPA doesn't exceed physical memory limits, as that is
@@ -7969,6 +7973,7 @@ static __init void vmx_set_cpu_caps(void)
 		kvm_cpu_cap_clear(X86_FEATURE_SGX_LC);
 		kvm_cpu_cap_clear(X86_FEATURE_SGX1);
 		kvm_cpu_cap_clear(X86_FEATURE_SGX2);
+		kvm_cpu_cap_clear(X86_FEATURE_SGX_EDECCSSA);
 	}
 
 	if (vmx_umip_emulated())

arch/x86/kvm/vmx/vmx.h

@@ -752,4 +752,9 @@ static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu)
 	return  lapic_in_kernel(vcpu) && enable_ipiv;
 }
 
+static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx)
+{
+	vmx->segment_cache.bitmask = 0;
+}
+
 #endif /* __KVM_X86_VMX_H */

arch/x86/kvm/vmx/vmx_onhyperv.h

@@ -104,6 +104,14 @@ static inline void evmcs_load(u64 phys_addr)
 	struct hv_vp_assist_page *vp_ap =
 		hv_get_vp_assist_page(smp_processor_id());
 
+	/*
+	 * When enabling eVMCS, KVM verifies that every CPU has a valid hv_vp_assist_page()
+	 * and aborts enabling the feature otherwise. CPU onlining path is also checked in
+	 * vmx_hardware_enable().
+	 */
+	if (KVM_BUG_ON(!vp_ap, kvm_get_running_vcpu()->kvm))
+		return;
+
 	if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall)
 		vp_ap->nested_control.features.directhypercall = 1;
 	vp_ap->current_nested_vmcs = phys_addr;

arch/x86/kvm/vmx/vmx_ops.h

@@ -47,7 +47,7 @@ static __always_inline void vmcs_check16(unsigned long field)
 	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001,
 			 "16-bit accessor invalid for 64-bit high field");
 	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000,
-			 "16-bit accessor invalid for 32-bit high field");
+			 "16-bit accessor invalid for 32-bit field");
 	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000,
 			 "16-bit accessor invalid for natural width field");
 }

arch/x86/kvm/x86.c

@@ -1958,19 +1958,21 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu,
 				 __kvm_get_msr);
 }
 
-static int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data)
+int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data)
 {
 	if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ))
 		return KVM_MSR_RET_FILTERED;
 	return kvm_get_msr_ignored_check(vcpu, index, data, false);
 }
+EXPORT_SYMBOL_GPL(kvm_get_msr_with_filter);
 
-static int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data)
+int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data)
 {
 	if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE))
 		return KVM_MSR_RET_FILTERED;
 	return kvm_set_msr_ignored_check(vcpu, index, data, false);
 }
+EXPORT_SYMBOL_GPL(kvm_set_msr_with_filter);
 
 int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data)
 {