[RFC PATCH v6 2/2] userfaulfd: add minor mode for guestmem

["Kalyazin, Nikita" <kalyazin@amazon.co.uk>]

From: Nikita Kalyazin <kalyazin@amazon.com>

UserfaultFD support in guestmem enables use cases like restoring a
guest_memfd-backed VM from a memory snapshot in Firecracker [1] where an
external process is responsible for supplying the content of the guest
memory or live migration of guest_memfd-backed VMs.

[1] https://github.com/firecracker-microvm/firecracker/blob/main/docs/snapshotting/handling-page-faults-on-snapshot-resume.md

Signed-off-by: Nikita Kalyazin <kalyazin@amazon.com>
---
 Documentation/admin-guide/mm/userfaultfd.rst |  4 +++-
 fs/userfaultfd.c                             |  3 ++-
 include/linux/userfaultfd_k.h                |  8 +++++---
 include/uapi/linux/userfaultfd.h             |  8 +++++++-
 mm/userfaultfd.c                             | 14 +++++++++++---
 5 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/Documentation/admin-guide/mm/userfaultfd.rst b/Documentation/admin-guide/mm/userfaultfd.rst
index e5cc8848dcb3..ca8c5954ffdb 100644
--- a/Documentation/admin-guide/mm/userfaultfd.rst
+++ b/Documentation/admin-guide/mm/userfaultfd.rst
@@ -111,7 +111,9 @@ events, except page fault notifications, may be generated:
 - ``UFFD_FEATURE_MINOR_HUGETLBFS`` indicates that the kernel supports
   ``UFFDIO_REGISTER_MODE_MINOR`` registration for hugetlbfs virtual memory
   areas. ``UFFD_FEATURE_MINOR_SHMEM`` is the analogous feature indicating
-  support for shmem virtual memory areas.
+  support for shmem virtual memory areas. ``UFFD_FEATURE_MINOR_GUESTMEM``
+  is the analogous feature indicating support for guestmem-backed memory
+  areas.
 
 - ``UFFD_FEATURE_MOVE`` indicates that the kernel supports moving an
   existing page contents from userspace.
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 54c6cc7fe9c6..e4e80f1072a6 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1978,7 +1978,8 @@ 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_GUESTMEM);
 #endif
 #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
 	uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP;
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index c0e716aec26a..37bd4e71b611 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -14,6 +14,7 @@
 #include <linux/userfaultfd.h> /* linux/include/uapi/linux/userfaultfd.h */
 
 #include <linux/fcntl.h>
+#include <linux/guestmem.h>
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
@@ -218,7 +219,8 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
 		return false;
 
 	if ((vm_flags & VM_UFFD_MINOR) &&
-	    (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma)))
+	    (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma) &&
+		!guestmem_vma_is_guestmem(vma)))
 		return false;
 
 	/*
@@ -238,9 +240,9 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
 		return false;
 #endif
 
-	/* By default, allow any of anon|shmem|hugetlb */
+	/* By default, allow any of anon|shmem|hugetlb|guestmem */
 	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
-	    vma_is_shmem(vma);
+	    vma_is_shmem(vma) || guestmem_vma_is_guestmem(vma);
 }
 
 static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma)
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 2841e4ea8f2c..0fe9fbd29772 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_GUESTMEM)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -230,6 +231,10 @@ struct uffdio_api {
 	 *
 	 * UFFD_FEATURE_MOVE indicates that the kernel supports moving an
 	 * existing page contents from userspace.
+	 *
+	 * UFFD_FEATURE_MINOR_GUESTMEM indicates the same support as
+	 * UFFD_FEATURE_MINOR_HUGETLBFS, but for guestmem-backed pages
+	 * instead.
 	 */
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
@@ -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_GUESTMEM		(1<<17)
 	__u64 features;
 
 	__u64 ioctls;
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 45e6290e2e8b..304e5d7dbb70 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -388,7 +388,14 @@ static int mfill_atomic_pte_continue(pmd_t *dst_pmd,
 	struct page *page;
 	int ret;
 
-	ret = shmem_get_folio(inode, pgoff, 0, &folio, SGP_NOALLOC);
+	if (guestmem_vma_is_guestmem(dst_vma)) {
+		ret = 0;
+		folio = guestmem_grab_folio(inode->i_mapping, pgoff);
+		if (IS_ERR(folio))
+			ret = PTR_ERR(folio);
+	} else {
+		ret = shmem_get_folio(inode, pgoff, 0, &folio, SGP_NOALLOC);
+	}
 	/* Our caller expects us to return -EFAULT if we failed to find folio */
 	if (ret == -ENOENT)
 		ret = -EFAULT;
@@ -766,9 +773,10 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
 		return  mfill_atomic_hugetlb(ctx, dst_vma, dst_start,
 					     src_start, len, flags);
 
-	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
+	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)
+	    && !guestmem_vma_is_guestmem(dst_vma))
 		goto out_unlock;
-	if (!vma_is_shmem(dst_vma) &&
+	if (!vma_is_shmem(dst_vma) && !guestmem_vma_is_guestmem(dst_vma) &&
 	    uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE))
 		goto out_unlock;
 
-- 
2.50.1