From: Fred Griffoul <fgriffo@amazon.co.uk>

Implement state validation for nested virtualization to enable pfncache
support for L1 guest pages.

This adds a new nested_ops callback 'is_nested_state_invalid()' that
detects when KVM needs to reload nested virtualization state. A
KVM_REQ_GET_NESTED_STATE_PAGES request is triggered to reload affected
pages before L2 execution when it detects invalid state. The callback
monitors L1 guest pages during guest entry/exit while the vCPU runs in
IN_GUEST_MODE.

Currently, VMX implementations return false, with full support planned
for the next patch.

Signed-off-by: Fred Griffoul <fgriffo@amazon.co.uk>
---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/vmx/nested.c       |  6 ++++++
 arch/x86/kvm/x86.c              | 14 +++++++++++++-
 3 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c56cc54d682a..97df7cac14e6 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1939,6 +1939,7 @@ struct kvm_x86_nested_ops {
 			 struct kvm_nested_state __user *user_kvm_nested_state,
 			 struct kvm_nested_state *kvm_state);
 	bool (*get_nested_state_pages)(struct kvm_vcpu *vcpu);
+	bool (*is_nested_state_invalid)(struct kvm_vcpu *vcpu);
 	int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 	int (*enable_evmcs)(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index aa4fe1fe571d..06187b8baa19 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -3472,6 +3472,11 @@ static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu)
 	return true;
 }
 
+static bool vmx_is_nested_state_invalid(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
 static int nested_vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
 	struct vmcs12 *vmcs12;
@@ -7366,6 +7371,7 @@ struct kvm_x86_nested_ops vmx_nested_ops = {
 	.get_state = vmx_get_nested_state,
 	.set_state = vmx_set_nested_state,
 	.get_nested_state_pages = vmx_get_nested_state_pages,
+	.is_nested_state_invalid = vmx_is_nested_state_invalid,
 	.write_log_dirty = nested_vmx_write_pml_buffer,
 #ifdef CONFIG_KVM_HYPERV
 	.enable_evmcs = nested_enable_evmcs,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 33fba801b205..db4a6b62f81f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2125,12 +2125,24 @@ int kvm_emulate_monitor(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_monitor);
 
+static inline bool kvm_invalid_nested_state(struct kvm_vcpu *vcpu)
+{
+	if (is_guest_mode(vcpu) &&
+	    kvm_x86_ops.nested_ops->is_nested_state_invalid &&
+	    kvm_x86_ops.nested_ops->is_nested_state_invalid(vcpu)) {
+		kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
+		return true;
+	}
+	return false;
+}
+
 static inline bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu)
 {
 	xfer_to_guest_mode_prepare();
 
 	return READ_ONCE(vcpu->mode) == EXITING_GUEST_MODE ||
-	       kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending();
+	       kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending() ||
+	       kvm_invalid_nested_state(vcpu);
 }
 
 /*
-- 
2.51.0