[RFC PATCH v3 10/11] KVM: x86: Add gmem hook for initializing private memory

[isaku . yamahata]

From: Michael Roth <michael.roth@xxxxxxx>

All gmem pages are expected to be 'private' as defined by a particular
arch/platform. Platforms like SEV-SNP require additional operations to
move these pages into a private state, so implement a hook that can be
used to prepare this memory prior to mapping it into a guest.

In the case of SEV-SNP, whether or not a 2MB page can be mapped via a
2MB mapping in the guest's nested page table depends on whether or not
any subpages within the range have already been initialized as private
in the RMP table, so this hook will also be used by the KVM MMU to clamp
the maximum mapping size accordingly.

Signed-off-by: Michael Roth <michael.roth@xxxxxxx>
Link: https://lore.kernel.org/r/20230612042559.375660-2-michael.roth@xxxxxxx

---
Changes v2 -> v3:
- Newly added
---
 arch/x86/include/asm/kvm-x86-ops.h |  1 +
 arch/x86/include/asm/kvm_host.h    |  3 +++
 arch/x86/kvm/mmu/mmu.c             | 11 ++++++++++-
 3 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index fc65374a8bad..cce8621e3216 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -135,6 +135,7 @@ KVM_X86_OP(msr_filter_changed)
 KVM_X86_OP(complete_emulated_msr)
 KVM_X86_OP(vcpu_deliver_sipi_vector)
 KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
+KVM_X86_OP_OPTIONAL_RET0(gmem_prepare)
 
 #undef KVM_X86_OP
 #undef KVM_X86_OP_OPTIONAL
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a4af4175034b..653f208979cf 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1738,6 +1738,9 @@ struct kvm_x86_ops {
 	 * Returns vCPU specific APICv inhibit reasons
 	 */
 	unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
+
+	int (*gmem_prepare)(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    kvm_pfn_t pfn, gfn_t gfn, u8 *max_level);
 };
 
 struct kvm_x86_nested_ops {
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 3795f447603c..fdd89cd8f68e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4341,6 +4341,7 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
 				   struct kvm_page_fault *fault)
 {
 	int order, r;
+	u8 max_level;
 
 	if (!kvm_slot_can_be_private(fault->slot))
 		return kvm_do_memory_fault_exit(vcpu, fault);
@@ -4349,7 +4350,15 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
 	if (r)
 		return r;
 
-	fault->max_level = min(kvm_max_level_for_order(order), fault->max_level);
+	max_level = kvm_max_level_for_order(order);
+	r = static_call(kvm_x86_gmem_prepare)(vcpu->kvm, fault->slot, fault->pfn,
+					      fault->gfn, &max_level);
+	if (r) {
+		kvm_release_pfn_clean(fault->pfn);
+		return r;
+	}
+
+	fault->max_level = min(max_level, fault->max_level);
 	fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY);
 	return RET_PF_CONTINUE;
 }
-- 
2.25.1