[RFC PATCH 3/4] userfaultfd, guest_memfd: support userfault minor mode in guest_memfd

[Mike Rapoport <rppt@kernel.org>]

From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>

* Export handle_userfault() for KVM module so that fault() handler in
  guest_memfd would be able to notify userspace about page faults in its
  address space.
* Implement get_pagecache_folio() for guest_memfd.
* And finally, introduce UFFD_FEATURE_MINOR_GENERIC that will allow
  using userfaultfd minor mode with memory types other than shmem and
  hugetlb provided they are allowed to call handle_userfault() and
  implement get_pagecache_folio().

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
 fs/userfaultfd.c                 |  4 +++-
 include/uapi/linux/userfaultfd.h |  8 +++++++-
 virt/kvm/guest_memfd.c           | 30 ++++++++++++++++++++++++++++++
 3 files changed, 40 insertions(+), 2 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 54c6cc7fe9c6..964fa2662d5c 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -537,6 +537,7 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
 out:
 	return ret;
 }
+EXPORT_SYMBOL_FOR_MODULES(handle_userfault, "kvm");
 
 static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 					      struct userfaultfd_wait_queue *ewq)
@@ -1978,7 +1979,8 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 	uffdio_api.features = UFFD_API_FEATURES;
 #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
 	uffdio_api.features &=
-		~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM);
+		~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM |
+		  UFFD_FEATURE_MINOR_GENERIC);
 #endif
 #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
 	uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP;
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 2841e4ea8f2c..c5cbd4a5a26e 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -42,7 +42,8 @@
 			   UFFD_FEATURE_WP_UNPOPULATED |	\
 			   UFFD_FEATURE_POISON |		\
 			   UFFD_FEATURE_WP_ASYNC |		\
-			   UFFD_FEATURE_MOVE)
+			   UFFD_FEATURE_MOVE |			\
+			   UFFD_FEATURE_MINOR_GENERIC)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -210,6 +211,10 @@ struct uffdio_api {
 	 * UFFD_FEATURE_MINOR_SHMEM indicates the same support as
 	 * UFFD_FEATURE_MINOR_HUGETLBFS, but for shmem-backed pages instead.
 	 *
+	 * UFFD_FEATURE_MINOR_GENERIC indicates that minor faults can be
+	 * intercepted for file-backed memory in case subsystem backing this
+	 * memory supports it.
+	 *
 	 * UFFD_FEATURE_EXACT_ADDRESS indicates that the exact address of page
 	 * faults would be provided and the offset within the page would not be
 	 * masked.
@@ -248,6 +253,7 @@ struct uffdio_api {
 #define UFFD_FEATURE_POISON			(1<<14)
 #define UFFD_FEATURE_WP_ASYNC			(1<<15)
 #define UFFD_FEATURE_MOVE			(1<<16)
+#define UFFD_FEATURE_MINOR_GENERIC		(1<<17)
 	__u64 features;
 
 	__u64 ioctls;
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index fbca8c0972da..5e3c63307fdf 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -4,6 +4,7 @@
 #include <linux/kvm_host.h>
 #include <linux/pagemap.h>
 #include <linux/anon_inodes.h>
+#include <linux/userfaultfd_k.h>
 
 #include "kvm_mm.h"
 
@@ -369,6 +370,12 @@ static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf)
 		return vmf_error(err);
 	}
 
+	if (userfaultfd_minor(vmf->vma)) {
+		folio_unlock(folio);
+		folio_put(folio);
+		return handle_userfault(vmf, VM_UFFD_MINOR);
+	}
+
 	if (WARN_ON_ONCE(folio_test_large(folio))) {
 		ret = VM_FAULT_SIGBUS;
 		goto out_folio;
@@ -390,8 +397,31 @@ static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf)
 	return ret;
 }
 
+#ifdef CONFIG_USERFAULTFD
+static struct folio *kvm_gmem_get_pagecache_folio(struct vm_area_struct *vma,
+						  pgoff_t pgoff)
+{
+	struct inode *inode = file_inode(vma->vm_file);
+	struct folio *folio;
+
+	folio = kvm_gmem_get_folio(inode, pgoff);
+	if (IS_ERR_OR_NULL(folio))
+		return folio;
+
+	if (!folio_test_uptodate(folio)) {
+		clear_highpage(folio_page(folio, 0));
+		kvm_gmem_mark_prepared(folio);
+	}
+
+	return folio;
+}
+#endif
+
 static const struct vm_operations_struct kvm_gmem_vm_ops = {
 	.fault = kvm_gmem_fault_user_mapping,
+#ifdef CONFIG_USERFAULTFD
+	.get_pagecache_folio	= kvm_gmem_get_pagecache_folio,
+#endif
 };
 
 static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma)
-- 
2.50.1