[PATCH v16 10/22] KVM: guest_memfd: Add plumbing to host to map guest_memfd pages

[Fuad Tabba <tabba@google.com>]

Introduce the core infrastructure to enable host userspace to mmap()
guest_memfd-backed memory. This is needed for several evolving KVM use
cases:

* Non-CoCo VM backing: Allows VMMs like Firecracker to run guests
  entirely backed by guest_memfd, even for non-CoCo VMs [1]. This
  provides a unified memory management model and simplifies guest memory
  handling.

* Direct map removal for enhanced security: This is an important step
  for direct map removal of guest memory [2]. By allowing host userspace
  to fault in guest_memfd pages directly, we can avoid maintaining host
  kernel direct maps of guest memory. This provides additional hardening
  against Spectre-like transient execution attacks by removing a
  potential attack surface within the kernel.

* Future guest_memfd features: This also lays the groundwork for future
  enhancements to guest_memfd, such as supporting huge pages and
  enabling in-place sharing of guest memory with the host for CoCo
  platforms that permit it [3].

Enable the basic mmap and fault handling logic within guest_memfd, but
hold off on allow userspace to actually do mmap() until the architecture
support is also in place.

[1] https://github.com/firecracker-microvm/firecracker/tree/feature/secret-hiding
[2] https://lore.kernel.org/linux-mm/cc1bb8e9bc3e1ab637700a4d3defeec95b55060a.camel@amazon.com
[3] https://lore.kernel.org/all/c1c9591d-218a-495c-957b-ba356c8f8e09@redhat.com/T/#u

Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Shivank Garg <shivankg@amd.com>
Acked-by: David Hildenbrand <david@redhat.com>
Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/x86/kvm/x86.c       | 11 +++++++
 include/linux/kvm_host.h |  4 +++
 virt/kvm/guest_memfd.c   | 70 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 85 insertions(+)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a1c49bc681c4..e5cd54ba1eaa 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13518,6 +13518,16 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
 
+#ifdef CONFIG_KVM_GUEST_MEMFD
+/*
+ * KVM doesn't yet support mmap() on guest_memfd for VMs with private memory
+ * (the private vs. shared tracking needs to be moved into guest_memfd).
+ */
+bool kvm_arch_supports_gmem_mmap(struct kvm *kvm)
+{
+	return !kvm_arch_has_private_mem(kvm);
+}
+
 #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
 int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order)
 {
@@ -13531,6 +13541,7 @@ void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
 	kvm_x86_call(gmem_invalidate)(start, end);
 }
 #endif
+#endif
 
 int kvm_spec_ctrl_test_value(u64 value)
 {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 4d1c44622056..26bad600f9fa 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -726,6 +726,10 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
 }
 #endif
 
+#ifdef CONFIG_KVM_GUEST_MEMFD
+bool kvm_arch_supports_gmem_mmap(struct kvm *kvm);
+#endif
+
 #ifndef kvm_arch_has_readonly_mem
 static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm)
 {
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index a99e11b8b77f..67e7cd7210ef 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -312,7 +312,72 @@ static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn)
 	return gfn - slot->base_gfn + slot->gmem.pgoff;
 }
 
+static bool kvm_gmem_supports_mmap(struct inode *inode)
+{
+	return false;
+}
+
+static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf)
+{
+	struct inode *inode = file_inode(vmf->vma->vm_file);
+	struct folio *folio;
+	vm_fault_t ret = VM_FAULT_LOCKED;
+
+	if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
+		return VM_FAULT_SIGBUS;
+
+	folio = kvm_gmem_get_folio(inode, vmf->pgoff);
+	if (IS_ERR(folio)) {
+		int err = PTR_ERR(folio);
+
+		if (err == -EAGAIN)
+			return VM_FAULT_RETRY;
+
+		return vmf_error(err);
+	}
+
+	if (WARN_ON_ONCE(folio_test_large(folio))) {
+		ret = VM_FAULT_SIGBUS;
+		goto out_folio;
+	}
+
+	if (!folio_test_uptodate(folio)) {
+		clear_highpage(folio_page(folio, 0));
+		kvm_gmem_mark_prepared(folio);
+	}
+
+	vmf->page = folio_file_page(folio, vmf->pgoff);
+
+out_folio:
+	if (ret != VM_FAULT_LOCKED) {
+		folio_unlock(folio);
+		folio_put(folio);
+	}
+
+	return ret;
+}
+
+static const struct vm_operations_struct kvm_gmem_vm_ops = {
+	.fault = kvm_gmem_fault_user_mapping,
+};
+
+static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!kvm_gmem_supports_mmap(file_inode(file)))
+		return -ENODEV;
+
+	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) !=
+	    (VM_SHARED | VM_MAYSHARE)) {
+		return -EINVAL;
+	}
+
+	vma->vm_ops = &kvm_gmem_vm_ops;
+
+	return 0;
+}
+
 static struct file_operations kvm_gmem_fops = {
+	.mmap		= kvm_gmem_mmap,
 	.open		= generic_file_open,
 	.release	= kvm_gmem_release,
 	.fallocate	= kvm_gmem_fallocate,
@@ -391,6 +456,11 @@ static const struct inode_operations kvm_gmem_iops = {
 	.setattr	= kvm_gmem_setattr,
 };
 
+bool __weak kvm_arch_supports_gmem_mmap(struct kvm *kvm)
+{
+	return true;
+}
+
 static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
 {
 	const char *anon_name = "[kvm-gmem]";
-- 
2.50.1.470.g6ba607880d-goog