[PATCH 3/9] userfaultfd/shmem: support minor fault registration for shmem

[Axel Rasmussen]

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.

Signed-off-by: Axel Rasmussen <axelrasmussen@xxxxxxxxxx>
---
 fs/userfaultfd.c                 |  6 +++---
 include/uapi/linux/userfaultfd.h |  7 ++++++-
 mm/memory.c                      |  8 +++++---
 mm/shmem.c                       | 20 ++++++++++++++++----
 4 files changed, 30 insertions(+), 11 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 14f92285d04f..9f3b8684cf3c 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;
 	}
 
@@ -1941,7 +1940,8 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 	/* report all available features and ioctls to userland */
 	uffdio_api.features = UFFD_API_FEATURES;
 #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
-	uffdio_api.features &= ~UFFD_FEATURE_MINOR_HUGETLBFS;
+	uffdio_api.features &=
+		~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM);
 #endif
 	uffdio_api.ioctls = UFFD_API_IOCTLS;
 	ret = -EFAULT;
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index bafbeb1a2624..159a74e9564f 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -31,7 +31,8 @@
 			   UFFD_FEATURE_MISSING_SHMEM |		\
 			   UFFD_FEATURE_SIGBUS |		\
 			   UFFD_FEATURE_THREAD_ID |		\
-			   UFFD_FEATURE_MINOR_HUGETLBFS)
+			   UFFD_FEATURE_MINOR_HUGETLBFS |	\
+			   UFFD_FEATURE_MINOR_SHMEM)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -185,6 +186,9 @@ struct uffdio_api {
 	 * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults
 	 * can be intercepted (via REGISTER_MODE_MINOR) for
 	 * hugetlbfs-backed pages.
+	 *
+	 * UFFD_FEATURE_MINOR_SHMEM indicates the same support as
+	 * UFFD_FEATURE_MINOR_HUGETLBFS, but for shmem-backed pages instead.
 	 */
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
@@ -196,6 +200,7 @@ struct uffdio_api {
 #define UFFD_FEATURE_SIGBUS			(1<<7)
 #define UFFD_FEATURE_THREAD_ID			(1<<8)
 #define UFFD_FEATURE_MINOR_HUGETLBFS		(1<<9)
+#define UFFD_FEATURE_MINOR_SHMEM		(1<<10)
 	__u64 features;
 
 	__u64 ioctls;
diff --git a/mm/memory.c b/mm/memory.c
index c8e357627318..a1e5ff55027e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3929,9 +3929,11 @@ 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 c21f20cc4204..99c54b165c16 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,
@@ -1802,6 +1802,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 	pgoff_t hindex = index;
 	gfp_t huge_gfp;
 	int error;
+	bool swapped;
 	int once = 0;
 	int alloced = 0;
 
@@ -1820,16 +1821,27 @@ 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 (xa_is_value(page)) {
+	swapped = xa_is_value(page);
+	if (swapped) {
 		error = shmem_swapin_page(inode, index, &page,
 					  sgp, gfp, vma, fault_type);
 		if (error == -EEXIST)
 			goto repeat;
-
 		*pagep = page;
-		return error;
+		if (error)
+			return error;
 	}
 
+	if (page && vma && userfaultfd_minor(vma)) {
+		unlock_page(page);
+		put_page(page);
+		*fault_type = handle_userfault(vmf, VM_UFFD_MINOR);
+		return 0;
+	}
+
+	if (swapped)
+		return 0;
+
 	if (page)
 		hindex = page->index;
 	if (page && sgp == SGP_WRITE)
-- 
2.31.1.295.g9ea45b61b8-goog