[RFC PATCH v4 10/25] KVM: guest_memfd: Add shared device mmap through PFN providers

["Aneesh Kumar K.V (Arm)" <aneesh.kumar@kernel.org>]

Map shared device memory through the existing get_pfn callback. Set
device VMA flags and protections in the core, and retain inode exclusion
through PFN lookup and PTE insertion. Validate BAR access at fault time;
memslot creation validates the complete interval separately.

Private pages remain inaccessible to userspace. Conversion revokes host
mappings before changing attributes. VFIO fd mmap remains excluded.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: kvm@vger.kernel.org
Cc: patches@lists.linux.dev
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
 include/linux/guest_memfd.h |  6 +++++-
 virt/kvm/guest_memfd.c      | 18 +++++++++++++++---
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/include/linux/guest_memfd.h b/include/linux/guest_memfd.h
index 9869e2ffb4a2..88c9102b21fa 100644
--- a/include/linux/guest_memfd.h
+++ b/include/linux/guest_memfd.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_GUEST_MEMFD_H
 #define _LINUX_GUEST_MEMFD_H
 
+#include <linux/mm_types.h>
 #include <linux/types.h>
 
 struct file;
@@ -45,7 +46,10 @@ struct guest_memfd_device {
  *          in the device argument, which is NULL for other providers.
  * @release: Release provider context and unpin any resources. Must not access
  *           the VM here; its file reference may be gone.
- * @device_memory: Backing is device MMIO rather than RAM.
+ * @device_memory: Backing is device MMIO rather than RAM. The core maps its
+ *                 userspace VMAs noncached and decrypted, with device flags.
+ *                 Shared userspace faults are resolved through @get_pfn, with
+ *                 the same error handling as RAM providers.
  * @prepare_memory_region: Optional check of a memory range and preparation of
  *                         access to its backing memory. Called after common
  *                         file checks and before publishing the memslot.
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 4c9ac047d06f..dd567979d938 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -949,12 +949,16 @@ static const struct vm_operations_struct kvm_gmem_vm_ops = {
 #endif
 };
 
+static const struct vm_operations_struct kvm_gmem_device_vm_ops = {
+	.fault = kvm_gmem_fault_user_mapping,
+};
+
 static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma)
 {
-	struct gmem_inode *gi = GMEM_I(file_inode(file));
+	struct inode *inode = file_inode(file);
+	struct gmem_inode *gi = GMEM_I(inode);
 
-	if (gmem_provider_is_device(gi) ||
-	    !kvm_gmem_supports_mmap(file_inode(file)))
+	if (!kvm_gmem_supports_mmap(inode))
 		return -ENODEV;
 
 	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) !=
@@ -965,6 +969,14 @@ static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma)
 	if (kvm_gmem_is_pfn_mode(gi))
 		vm_flags_set(vma, VM_PFNMAP);
 
+	if (gmem_provider_is_device(gi)) {
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+		vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
+		vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
+		vma->vm_ops = &kvm_gmem_device_vm_ops;
+		return 0;
+	}
+
 	vma->vm_ops = &kvm_gmem_vm_ops;
 
 	return 0;
-- 
2.43.0