KVM: nVMX: Switch to vmcs01 to update PML controls on-demand if L2 is active

If KVM toggles "CPU dirty logging", a.k.a. Page-Modification Logging (PML),
while L2 is active, temporarily load vmcs01 and immediately update the
relevant controls instead of deferring the update until the next nested
VM-Exit.  For PML, deferring the update is relatively straightforward, but
for several APICv related updates, deferring updates creates ordering and
state consistency problems, e.g. KVM at-large thinks APICv is enabled, but
vmcs01 is still running with stale (and effectively unknown) state.

Convert PML first precisely because it's the simplest case to handle: if
something is broken with the vmcs01 <=> vmcs02 dance, then hopefully bugs
will bisect here.

Reviewed-by: Chao Gao <chao.gao@intel.com>
Link: https://patch.msgid.link/20260109034532.1012993-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

3 files changed, 36 insertions, 10 deletions

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 6dd1da94f00c..e8adff614bd5 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5131,11 +5131,6 @@ void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		vmx_set_virtual_apic_mode(vcpu);
 	}
 
-	if (vmx->nested.update_vmcs01_cpu_dirty_logging) {
-		vmx->nested.update_vmcs01_cpu_dirty_logging = false;
-		vmx_update_cpu_dirty_logging(vcpu);
-	}
-
 	nested_put_vmcs12_pages(vcpu);
 
 	if (vmx->nested.reload_vmcs01_apic_access_page) {
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 1f4d15cc898e..3aa0e055e2b0 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1594,6 +1594,41 @@ void vmx_vcpu_put(struct kvm_vcpu *vcpu)
 	vmx_prepare_switch_to_host(to_vmx(vcpu));
 }
 
+static void vmx_switch_loaded_vmcs(struct kvm_vcpu *vcpu,
+				   struct loaded_vmcs *vmcs)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int cpu;
+
+	cpu = get_cpu();
+	vmx->loaded_vmcs = vmcs;
+	vmx_vcpu_load_vmcs(vcpu, cpu);
+	put_cpu();
+}
+
+static void vmx_load_vmcs01(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!is_guest_mode(vcpu)) {
+		WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->vmcs01);
+		return;
+	}
+
+	WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->nested.vmcs02);
+	vmx_switch_loaded_vmcs(vcpu, &vmx->vmcs01);
+}
+
+static void vmx_put_vmcs01(struct kvm_vcpu *vcpu)
+{
+	if (!is_guest_mode(vcpu))
+		return;
+
+	vmx_switch_loaded_vmcs(vcpu, &to_vmx(vcpu)->nested.vmcs02);
+}
+DEFINE_GUARD(vmx_vmcs01, struct kvm_vcpu *,
+	     vmx_load_vmcs01(_T), vmx_put_vmcs01(_T))
+
 bool vmx_emulation_required(struct kvm_vcpu *vcpu)
 {
 	return emulate_invalid_guest_state && !vmx_guest_state_valid(vcpu);
@@ -8276,10 +8311,7 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
 	if (WARN_ON_ONCE(!enable_pml))
 		return;
 
-	if (is_guest_mode(vcpu)) {
-		vmx->nested.update_vmcs01_cpu_dirty_logging = true;
-		return;
-	}
+	guard(vmx_vmcs01)(vcpu);
 
 	/*
 	 * Note, nr_memslots_dirty_logging can be changed concurrent with this
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index bc3ed3145d7e..b44eda6225f4 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -133,7 +133,6 @@ struct nested_vmx {
 
 	bool change_vmcs01_virtual_apic_mode;
 	bool reload_vmcs01_apic_access_page;
-	bool update_vmcs01_cpu_dirty_logging;
 	bool update_vmcs01_apicv_status;
 	bool update_vmcs01_hwapic_isr;