---

yaml
---
r: 215815
b: refs/heads/master
c: 8b1fe17
h: refs/heads/master
i:
  215813: 48d3182
  215811: b6567d7
  215807: 499f630
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 84e0cefa8ddd5d5018d3b582e1e90585ed551757
+refs/heads/master: 8b1fe17cc7a8b2c62b400dcbfaebd96da6b4f58e

trunk/arch/x86/kvm/Kconfig

@@ -64,6 +64,13 @@ config KVM_AMD
 	  To compile this as a module, choose M here: the module
 	  will be called kvm-amd.
 
+config KVM_MMU_AUDIT
+	bool "Audit KVM MMU"
+	depends on KVM && TRACEPOINTS
+	---help---
+	 This option adds a R/W kVM module parameter 'mmu_audit', which allows
+	 audit  KVM MMU at runtime.
+
 # OK, it's a little counter-intuitive to do this, but it puts it neatly under
 # the virtualization menu.
 source drivers/vhost/Kconfig

trunk/arch/x86/kvm/mmu.c

@@ -49,15 +49,21 @@
  */
 bool tdp_enabled = false;
 
-#undef MMU_DEBUG
+enum {
+	AUDIT_PRE_PAGE_FAULT,
+	AUDIT_POST_PAGE_FAULT,
+	AUDIT_PRE_PTE_WRITE,
+	AUDIT_POST_PTE_WRITE
+};
 
-#undef AUDIT
+char *audit_point_name[] = {
+	"pre page fault",
+	"post page fault",
+	"pre pte write",
+	"post pte write"
+};
 
-#ifdef AUDIT
-static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg);
-#else
-static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) {}
-#endif
+#undef MMU_DEBUG
 
 #ifdef MMU_DEBUG
 
@@ -71,7 +77,7 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) {}
 
 #endif
 
-#if defined(MMU_DEBUG) || defined(AUDIT)
+#ifdef MMU_DEBUG
 static int dbg = 0;
 module_param(dbg, bool, 0644);
 #endif
@@ -2964,7 +2970,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	kvm_mmu_access_page(vcpu, gfn);
 	kvm_mmu_free_some_pages(vcpu);
 	++vcpu->kvm->stat.mmu_pte_write;
-	kvm_mmu_audit(vcpu, "pre pte write");
+	trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
 	if (guest_initiated) {
 		if (gfn == vcpu->arch.last_pt_write_gfn
 		    && !last_updated_pte_accessed(vcpu)) {
@@ -3037,7 +3043,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	}
 	mmu_pte_write_flush_tlb(vcpu, zap_page, remote_flush, local_flush);
 	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
-	kvm_mmu_audit(vcpu, "post pte write");
+	trace_kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE);
 	spin_unlock(&vcpu->kvm->mmu_lock);
 	if (!is_error_pfn(vcpu->arch.update_pte.pfn)) {
 		kvm_release_pfn_clean(vcpu->arch.update_pte.pfn);
@@ -3483,8 +3489,7 @@ int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4])
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy);
 
-#ifdef AUDIT
-
+#ifdef CONFIG_KVM_MMU_AUDIT
 static const char *audit_msg;
 
 typedef void (*inspect_spte_fn) (struct kvm *kvm, u64 *sptep);
@@ -3699,18 +3704,68 @@ static void audit_write_protection(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg)
+static void kvm_mmu_audit(void *ignore, struct kvm_vcpu *vcpu, int audit_point)
 {
-	int olddbg = dbg;
-
-	dbg = 0;
-	audit_msg = msg;
+	audit_msg = audit_point_name[audit_point];
 	audit_rmap(vcpu);
 	audit_write_protection(vcpu);
 	if (strcmp("pre pte write", audit_msg) != 0)
 		audit_mappings(vcpu);
 	audit_sptes_have_rmaps(vcpu);
-	dbg = olddbg;
 }
 
+static bool mmu_audit;
+
+static void mmu_audit_enable(void)
+{
+	int ret;
+
+	if (mmu_audit)
+		return;
+
+	ret = register_trace_kvm_mmu_audit(kvm_mmu_audit, NULL);
+	WARN_ON(ret);
+
+	mmu_audit = true;
+}
+
+static void mmu_audit_disable(void)
+{
+	if (!mmu_audit)
+		return;
+
+	unregister_trace_kvm_mmu_audit(kvm_mmu_audit, NULL);
+	tracepoint_synchronize_unregister();
+	mmu_audit = false;
+}
+
+static int mmu_audit_set(const char *val, const struct kernel_param *kp)
+{
+	int ret;
+	unsigned long enable;
+
+	ret = strict_strtoul(val, 10, &enable);
+	if (ret < 0)
+		return -EINVAL;
+
+	switch (enable) {
+	case 0:
+		mmu_audit_disable();
+		break;
+	case 1:
+		mmu_audit_enable();
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct kernel_param_ops audit_param_ops = {
+	.set = mmu_audit_set,
+	.get = param_get_bool,
+};
+
+module_param_cb(mmu_audit, &audit_param_ops, &mmu_audit, 0644);
 #endif

trunk/arch/x86/kvm/mmutrace.h

@@ -195,6 +195,25 @@ DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_prepare_zap_page,
 
 	TP_ARGS(sp)
 );
+
+TRACE_EVENT(
+	kvm_mmu_audit,
+	TP_PROTO(struct kvm_vcpu *vcpu, int audit_point),
+	TP_ARGS(vcpu, audit_point),
+
+	TP_STRUCT__entry(
+		__field(struct kvm_vcpu *, vcpu)
+		__field(int, audit_point)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu = vcpu;
+		__entry->audit_point = audit_point;
+	),
+
+	TP_printk("vcpu:%d %s", __entry->vcpu->cpu,
+		  audit_point_name[__entry->audit_point])
+);
 #endif /* _TRACE_KVMMMU_H */
 
 #undef TRACE_INCLUDE_PATH

trunk/arch/x86/kvm/paging_tmpl.h

@@ -542,7 +542,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 	if (mmu_notifier_retry(vcpu, mmu_seq))
 		goto out_unlock;
 
-	kvm_mmu_audit(vcpu, "pre page fault");
+	trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
 	kvm_mmu_free_some_pages(vcpu);
 	sptep = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
 			     level, &write_pt, pfn);
@@ -554,7 +554,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 		vcpu->arch.last_pt_write_count = 0; /* reset fork detector */
 
 	++vcpu->stat.pf_fixed;
-	kvm_mmu_audit(vcpu, "post page fault (fixed)");
+	trace_kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
 	spin_unlock(&vcpu->kvm->mmu_lock);
 
 	return write_pt;