Now that the svm_copy_vmrun_state() copies the g_pat field, L1's g_pat
will be stored in the serialized nested state. Add a 'flags' field to
the SVM nested state header, define a VALID_GPAT flag, and start
reporting this flag in the serialized nested state populated by
KVM_GET_NESTED_STATE.

Note that struct kvm_svm_nested_state_hdr is included in a union
padded to 120 bytes, so there is room to add the flags field without
changing any offsets.

Signed-off-by: Jim Mattson <jmattson@google.com>
---
 arch/x86/include/uapi/asm/kvm.h | 3 +++
 arch/x86/kvm/svm/nested.c       | 1 +
 2 files changed, 4 insertions(+)

diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 7ceff6583652..18581c4b2511 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -495,6 +495,8 @@ struct kvm_sync_regs {
 
 #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE	0x00000001
 
+#define KVM_STATE_SVM_VALID_GPAT	0x00000001
+
 /* vendor-independent attributes for system fd (group 0) */
 #define KVM_X86_GRP_SYSTEM		0
 #  define KVM_X86_XCOMP_GUEST_SUPP	0
@@ -530,6 +532,7 @@ struct kvm_svm_nested_state_data {
 
 struct kvm_svm_nested_state_hdr {
 	__u64 vmcb_pa;
+	__u32 flags;
 };
 
 /* for KVM_CAP_NESTED_STATE */
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index a0e5bf1aba52..ed24e08d2d21 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1769,6 +1769,7 @@ static int svm_get_nested_state(struct kvm_vcpu *vcpu,
 	/* First fill in the header and copy it out.  */
 	if (is_guest_mode(vcpu)) {
 		kvm_state.hdr.svm.vmcb_pa = svm->nested.vmcb12_gpa;
+		kvm_state.hdr.svm.flags = KVM_STATE_SVM_VALID_GPAT;
 		kvm_state.size += KVM_STATE_NESTED_SVM_VMCB_SIZE;
 		kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE;
 
-- 
2.52.0.457.g6b5491de43-goog

On Mon, Jan 12, 2026, Jim Mattson wrote:
>  /* for KVM_CAP_NESTED_STATE */
> diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
> index a0e5bf1aba52..ed24e08d2d21 100644
> --- a/arch/x86/kvm/svm/nested.c
> +++ b/arch/x86/kvm/svm/nested.c
> @@ -1769,6 +1769,7 @@ static int svm_get_nested_state(struct kvm_vcpu *vcpu,
>  	/* First fill in the header and copy it out.  */
>  	if (is_guest_mode(vcpu)) {
>  		kvm_state.hdr.svm.vmcb_pa = svm->nested.vmcb12_gpa;
> +		kvm_state.hdr.svm.flags = KVM_STATE_SVM_VALID_GPAT;

Assuming this survives to v2, make this:

		kvm_state.hdr.svm.flags |= KVM_STATE_SVM_VALID_GPAT;

both to communicate that there's no pre-existing bug where KVM doesn't initialize
flags, and so that there's less risk of clobbering others flags, e.g. if a new
flag is added in the future and is set before this point.

>  		kvm_state.size += KVM_STATE_NESTED_SVM_VMCB_SIZE;
>  		kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE;
>  
> -- 
> 2.52.0.457.g6b5491de43-goog
>