[PATCH v6 03/10] userfaultfd/shmem: support minor fault registration for shmem

[Axel Rasmussen <axelrasmussen@google.com>]

This patch allows shmem-backed VMAs to be registered for minor faults.
Minor faults are appropriately relayed to userspace in the fault path,
for VMAs with the relevant flag.

This commit doesn't hook up the UFFDIO_CONTINUE ioctl for shmem-backed
minor faults, though, so userspace doesn't yet have a way to resolve
such faults.

Because of this, we also don't yet advertise this as a supported
feature. That will be done in a separate commit when the feature is
fully implemented.

Acked-by: Peter Xu <peterx@redhat.com>
Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
---
 fs/userfaultfd.c |  3 +--
 mm/memory.c      |  8 +++++---
 mm/shmem.c       | 12 +++++++++++-
 3 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 14f92285d04f..468556fb04a9 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1267,8 +1267,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
 	}
 
 	if (vm_flags & VM_UFFD_MINOR) {
-		/* FIXME: Add minor fault interception for shmem. */
-		if (!is_vm_hugetlb_page(vma))
+		if (!(is_vm_hugetlb_page(vma) || vma_is_shmem(vma)))
 			return false;
 	}
 
diff --git a/mm/memory.c b/mm/memory.c
index 86ba6c1f6821..9a536cfde7c8 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3972,9 +3972,11 @@ static vm_fault_t do_read_fault(struct vm_fault *vmf)
 	 * something).
 	 */
 	if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) {
-		ret = do_fault_around(vmf);
-		if (ret)
-			return ret;
+		if (likely(!userfaultfd_minor(vmf->vma))) {
+			ret = do_fault_around(vmf);
+			if (ret)
+				return ret;
+		}
 	}
 
 	ret = __do_fault(vmf);
diff --git a/mm/shmem.c b/mm/shmem.c
index 04de845b50b3..e361f1d81c8d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1785,7 +1785,7 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
  * vm. If we swap it in we mark it dirty since we also free the swap
  * entry since a page cannot live in both the swap and page cache.
  *
- * vmf and fault_type are only supplied by shmem_fault:
+ * vma, vmf, and fault_type are only supplied by shmem_fault:
  * otherwise they are NULL.
  */
 static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
@@ -1820,6 +1820,16 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 
 	page = pagecache_get_page(mapping, index,
 					FGP_ENTRY | FGP_HEAD | FGP_LOCK, 0);
+
+	if (page && vma && userfaultfd_minor(vma)) {
+		if (!xa_is_value(page)) {
+			unlock_page(page);
+			put_page(page);
+		}
+		*fault_type = handle_userfault(vmf, VM_UFFD_MINOR);
+		return 0;
+	}
+
 	if (xa_is_value(page)) {
 		error = shmem_swapin_page(inode, index, &page,
 					  sgp, gfp, vma, fault_type);
-- 
2.31.1.527.g47e6f16901-goog