[PATCH v12 23/29] KVM: x86: Implement gmem hook for determining max NPT mapping level

[Michael Roth]

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. The existing mixed-attribute tracking in KVM is
insufficient here, for instance:

  - gmem allocates 2MB page
  - guest issues PVALIDATE on 2MB page
  - guest later converts a subpage to shared
  - SNP host code issues PSMASH to split 2MB RMP mapping to 4K
  - KVM MMU splits NPT mapping to 4K
  - guest later converts that shared page back to private

At this point there are no mixed attributes, and KVM would normally
allow for 2MB NPT mappings again, but this is actually not allowed
because the RMP table mappings are 4K and cannot be promoted on the
hypervisor side, so the NPT mappings must still be limited to 4K to
match this.

Implement a kvm_x86_ops.gmem_validate_fault() hook for SEV that checks
for this condition and adjusts the mapping level accordingly.

Signed-off-by: Michael Roth <michael.roth@xxxxxxx>
---
 arch/x86/kvm/svm/sev.c | 32 ++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c |  1 +
 arch/x86/kvm/svm/svm.h |  7 +++++++
 3 files changed, 40 insertions(+)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 87d621d013a4..31f6f4786503 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -4443,3 +4443,35 @@ void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
 		pfn += use_2m_update ? PTRS_PER_PMD : 1;
 	}
 }
+
+/*
+ * Re-check whether an #NPF for a private/gmem page can still be serviced, and
+ * adjust maximum mapping level if needed.
+ */
+int sev_gmem_validate_fault(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, bool is_private,
+			    u8 *max_level)
+{
+	int level, rc;
+	bool assigned;
+
+	if (!sev_snp_guest(kvm))
+		return 0;
+
+	rc = snp_lookup_rmpentry(pfn, &assigned, &level);
+	if (rc) {
+		pr_err_ratelimited("SEV: RMP entry not found: GFN %llx PFN %llx level %d error %d\n",
+				   gfn, pfn, level, rc);
+		return -ENOENT;
+	}
+
+	if (!assigned) {
+		pr_err_ratelimited("SEV: RMP entry is not assigned: GFN %llx PFN %llx level %d\n",
+				   gfn, pfn, level);
+		return -EINVAL;
+	}
+
+	if (level < *max_level)
+		*max_level = level;
+
+	return 0;
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index b456906f2670..298b4ce77a5f 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -5081,6 +5081,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 
 	.gmem_prepare = sev_gmem_prepare,
 	.gmem_invalidate = sev_gmem_invalidate,
+	.gmem_validate_fault = sev_gmem_validate_fault,
 };
 
 /*
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 3f1f6d3d3ade..746f819a6de4 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -732,6 +732,8 @@ void sev_vcpu_unblocking(struct kvm_vcpu *vcpu);
 void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu);
 int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
 void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
+int sev_gmem_validate_fault(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, bool is_private,
+			    u8 *max_level);
 #else
 static inline struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) {
 	return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
@@ -753,6 +755,11 @@ static inline int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, in
 	return 0;
 }
 static inline void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) {}
+static inline int sev_gmem_validate_fault(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn,
+					  bool is_private, u8 *max_level)
+{
+	return 0;
+}
 
 #endif
 
-- 
2.25.1