Add a 'gpat' field to kvm_svm_nested_state_hdr to carry L2's guest PAT
value across save and restore.

When KVM_X86_QUIRK_NESTED_SVM_SHARED_PAT is disabled and the vCPU is in
guest mode with nested NPT enabled, save vmcb02's g_pat into the header on
KVM_GET_NESTED_STATE, and restore it on KVM_SET_NESTED_STATE.

Host-initiated accesses to IA32_PAT (via KVM_GET/SET_MSRS) always target
L1's hPAT, so they cannot be used to save or restore gPAT. The separate
header field ensures that KVM_GET/SET_MSRS and KVM_GET/SET_NESTED_STATE are
independent and can be ordered arbitrarily during save and restore.

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

Fixes: cc440cdad5b7 ("KVM: nSVM: implement KVM_GET_NESTED_STATE and KVM_SET_NESTED_STATE")
Signed-off-by: Jim Mattson <jmattson@google.com>
---
 Documentation/virt/kvm/api.rst  |  1 +
 arch/x86/include/uapi/asm/kvm.h |  1 +
 arch/x86/kvm/svm/nested.c       | 20 ++++++++++++++++++++
 3 files changed, 22 insertions(+)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 0a2d873ca5a3..d6bbb7bad173 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -4965,6 +4965,7 @@ Errors:
 
   struct kvm_svm_nested_state_hdr {
 	__u64 vmcb_pa;
+	__u64 gpat;
   };
 
   struct kvm_vmx_nested_state_data {
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 3ada2fa9ca86..1585ec804066 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -533,6 +533,7 @@ struct kvm_svm_nested_state_data {
 
 struct kvm_svm_nested_state_hdr {
 	__u64 vmcb_pa;
+	__u64 gpat;
 };
 
 /* for KVM_CAP_NESTED_STATE */
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index add57f2a2d9f..54399e642745 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1865,6 +1865,9 @@ 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.gpat = 0;
+		if (l2_has_separate_pat(svm))
+			kvm_state.hdr.svm.gpat = svm->vmcb->save.g_pat;
 		kvm_state.size += KVM_STATE_NESTED_SVM_VMCB_SIZE;
 		kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE;
 
@@ -1918,6 +1921,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	struct vmcb_save_area_cached save_cached;
 	struct vmcb_ctrl_area_cached ctl_cached;
 	unsigned long cr0;
+	bool use_separate_l2_pat;
 	int ret;
 
 	BUILD_BUG_ON(sizeof(struct vmcb_control_area) + sizeof(struct vmcb_save_area) >
@@ -1993,6 +1997,18 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	    !nested_vmcb_check_save(vcpu, &save_cached, false))
 		goto out_free;
 
+	/*
+	 * Validate gPAT when the shared PAT quirk is disabled (i.e. L2
+	 * has its own gPAT). This is done separately from the
+	 * vmcb_save_area_cached validation above, because gPAT is L2
+	 * state, but the vmcb_save_area_cached is populated with L1 state.
+	 */
+	use_separate_l2_pat =
+		(ctl_cached.misc_ctl & SVM_MISC_ENABLE_NP) &&
+		!kvm_check_has_quirk(vcpu->kvm,
+				     KVM_X86_QUIRK_NESTED_SVM_SHARED_PAT);
+	if (use_separate_l2_pat && !kvm_pat_valid(kvm_state->hdr.svm.gpat))
+		goto out_free;
 
 	/*
 	 * All checks done, we can enter guest mode. Userspace provides
@@ -2017,6 +2033,10 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	nested_copy_vmcb_control_to_cache(svm, ctl);
 
 	svm_switch_vmcb(svm, &svm->nested.vmcb02);
+
+	if (use_separate_l2_pat)
+		vmcb_set_gpat(svm->vmcb, kvm_state->hdr.svm.gpat);
+
 	nested_vmcb02_prepare_control(svm);
 
 	/*
-- 
2.53.0.1018.g2bb0e51243-goog