KVM: x86: Add hook for determining max NPT mapping level

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.

Add a hook to determine the max NPT mapping size in situations like
this.

Suggested-by: Sean Christopherson <[email protected]>
Signed-off-by: Michael Roth <[email protected]>
Reviewed-by: Isaku Yamahata <[email protected]>
Message-ID: <20240501085210.2213060[email protected]>
Signed-off-by: Paolo Bonzini <[email protected]>

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index c81990937ab4d7f93dec479df1aca3cea8f352ed..566d19b024836519c0ef54f6ecf025775c8eadcd 100644 (file)
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -140,6 +140,7 @@ KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
 KVM_X86_OP_OPTIONAL(get_untagged_addr)
 KVM_X86_OP_OPTIONAL(alloc_apic_backing_page)
 KVM_X86_OP_OPTIONAL_RET0(gmem_prepare)
+KVM_X86_OP_OPTIONAL_RET0(private_max_mapping_level)
 KVM_X86_OP_OPTIONAL(gmem_invalidate)
 
 #undef KVM_X86_OP

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 51bb4b785d6ac20c3b73580d354002149eee423b..0804b6019673e5bbd2fb20fccca85c5657bc2b44 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1814,6 +1814,7 @@ struct kvm_x86_ops {
        void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
        int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
        void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end);
+       int (*private_max_mapping_level)(struct kvm *kvm, kvm_pfn_t pfn);
 };
 
 struct kvm_x86_nested_ops {

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 5ae0f2f503b49729721e11819ccb2a8d59827bc4..bce8e18ba1dfc62f21bdc5b80fcfa3bb31a858c2 100644 (file)
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4270,6 +4270,25 @@ static inline u8 kvm_max_level_for_order(int order)
        return PG_LEVEL_4K;
 }
 
+static u8 kvm_max_private_mapping_level(struct kvm *kvm, kvm_pfn_t pfn,
+                                       u8 max_level, int gmem_order)
+{
+       u8 req_max_level;
+
+       if (max_level == PG_LEVEL_4K)
+               return PG_LEVEL_4K;
+
+       max_level = min(kvm_max_level_for_order(gmem_order), max_level);
+       if (max_level == PG_LEVEL_4K)
+               return PG_LEVEL_4K;
+
+       req_max_level = static_call(kvm_x86_private_max_mapping_level)(kvm, pfn);
+       if (req_max_level)
+               max_level = min(max_level, req_max_level);
+
+       return req_max_level;
+}
+
 static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
                                   struct kvm_page_fault *fault)
 {
@@ -4287,9 +4306,9 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
                return r;
        }
 
-       fault->max_level = min(kvm_max_level_for_order(max_order),
-                              fault->max_level);
        fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY);
+       fault->max_level = kvm_max_private_mapping_level(vcpu->kvm, fault->pfn,
+                                                        fault->max_level, max_order);
 
        return RET_PF_CONTINUE;
 }