KVM: arm64: Block cacheable PFNMAP mapping

Fixes a security bug due to mismatched attributes between S1 and
S2 mapping.

Currently, it is possible for a region to be cacheable in the userspace
VMA, but mapped non cached in S2. This creates a potential issue where
the VMM may sanitize cacheable memory across VMs using cacheable stores,
ensuring it is zeroed. However, if KVM subsequently assigns this memory
to a VM as uncached, the VM could end up accessing stale, non-zeroed data
from a previous VM, leading to unintended data exposure. This is a security
risk.

Block such mismatch attributes case by returning EINVAL when userspace
try to map PFNMAP cacheable. Only allow NORMAL_NC and DEVICE_*.

CC: Oliver Upton <oliver.upton@linux.dev>
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Sean Christopherson <seanjc@google.com>
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Tested-by: Donald Dutile <ddutile@redhat.com>
Signed-off-by: Ankit Agrawal <ankita@nvidia.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20250705071717.5062-4-ankita@nvidia.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

Author: ankita-nv

arch/arm64/kvm/mmu.c

@@ -1465,14 +1465,26 @@ static bool kvm_vma_mte_allowed(struct vm_area_struct *vma)
 	return vma->vm_flags & VM_MTE_ALLOWED;
 }
 
+static bool kvm_vma_is_cacheable(struct vm_area_struct *vma)
+{
+	switch (FIELD_GET(PTE_ATTRINDX_MASK, pgprot_val(vma->vm_page_prot))) {
+	case MT_NORMAL_NC:
+	case MT_DEVICE_nGnRnE:
+	case MT_DEVICE_nGnRE:
+		return false;
+	default:
+		return true;
+	}
+}
+
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  struct kvm_s2_trans *nested,
 			  struct kvm_memory_slot *memslot, unsigned long hva,
 			  bool fault_is_perm)
 {
 	int ret = 0;
 	bool write_fault, writable, force_pte = false;
-	bool exec_fault, mte_allowed;
+	bool exec_fault, mte_allowed, is_vma_cacheable;
 	bool s2_force_noncacheable = false, vfio_allow_any_uc = false;
 	unsigned long mmu_seq;
 	phys_addr_t ipa = fault_ipa;
@@ -1617,6 +1629,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 	vm_flags = vma->vm_flags;
 
+	is_vma_cacheable = kvm_vma_is_cacheable(vma);
+
 	/* Don't use the VMA after the unlock -- it may have vanished */
 	vma = NULL;
 
@@ -1660,6 +1674,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		writable = false;
 	}
 
+	/*
+	 * Prevent non-cacheable mappings in the stage-2 if a region of memory
+	 * is cacheable in the primary MMU and the kernel lacks a cacheable
+	 * alias. KVM cannot guarantee coherency between the guest/host aliases
+	 * without the ability to perform CMOs.
+	 */
+	if (is_vma_cacheable && s2_force_noncacheable)
+		return -EINVAL;
+
 	if (exec_fault && s2_force_noncacheable)
 		return -ENOEXEC;
 
@@ -2219,6 +2242,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				ret = -EINVAL;
 				break;
 			}
+
+			/* Cacheable PFNMAP is not allowed */
+			if (kvm_vma_is_cacheable(vma)) {
+				ret = -EINVAL;
+				break;
+			}
 		}
 		hva = min(reg_end, vma->vm_end);
 	} while (hva < reg_end);