[PATCH v3 26/27] mm/userfaultfd: Enable write protection for shmem & hugetlbfs

[Peter Xu]

We've had all the necessary changes ready for both shmem and hugetlbfs.  Turn
on all the shmem/hugetlbfs switches for userfaultfd-wp.

We can expand UFFD_API_RANGE_IOCTLS_BASIC with _UFFDIO_WRITEPROTECT too because
all existing types now support write protection mode.

Since vma_can_userfault() will be used elsewhere, move into userfaultfd_k.h.

Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
---
 fs/userfaultfd.c                 | 18 ------------------
 include/linux/userfaultfd_k.h    | 12 ++++++++++++
 include/uapi/linux/userfaultfd.h | 10 ++++++++--
 mm/userfaultfd.c                 |  9 +++------
 4 files changed, 23 insertions(+), 26 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 6ef7b56760bf..140bab07935e 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1275,24 +1275,6 @@ static __always_inline int validate_range(struct mm_struct *mm,
 	return 0;
 }
 
-static inline bool vma_can_userfault(struct vm_area_struct *vma,
-				     unsigned long vm_flags)
-{
-	/* FIXME: add WP support to hugetlbfs and shmem */
-	if (vm_flags & VM_UFFD_WP) {
-		if (is_vm_hugetlb_page(vma) || vma_is_shmem(vma))
-			return false;
-	}
-
-	if (vm_flags & VM_UFFD_MINOR) {
-		if (!(is_vm_hugetlb_page(vma) || vma_is_shmem(vma)))
-			return false;
-	}
-
-	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
-	       vma_is_shmem(vma);
-}
-
 static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 				unsigned long arg)
 {
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index ca3f794d07e9..489fb375e66c 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -16,6 +16,7 @@
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <asm-generic/pgtable_uffd.h>
+#include <linux/hugetlb_inline.h>
 
 /* The set of all possible UFFD-related VM flags. */
 #define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR)
@@ -138,6 +139,17 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 	return vma->vm_flags & __VM_UFFD_FLAGS;
 }
 
+static inline bool vma_can_userfault(struct vm_area_struct *vma,
+				     unsigned long vm_flags)
+{
+	if (vm_flags & VM_UFFD_MINOR)
+		return is_vm_hugetlb_page(vma) || vma_is_shmem(vma);
+
+	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
+	       vma_is_shmem(vma);
+}
+
+
 extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *);
 extern void dup_userfaultfd_complete(struct list_head *);
 
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 159a74e9564f..09b7ec69c97d 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -32,7 +32,8 @@
 			   UFFD_FEATURE_SIGBUS |		\
 			   UFFD_FEATURE_THREAD_ID |		\
 			   UFFD_FEATURE_MINOR_HUGETLBFS |	\
-			   UFFD_FEATURE_MINOR_SHMEM)
+			   UFFD_FEATURE_MINOR_SHMEM |		\
+			   UFFD_FEATURE_WP_HUGETLBFS_SHMEM)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -46,7 +47,8 @@
 #define UFFD_API_RANGE_IOCTLS_BASIC		\
 	((__u64)1 << _UFFDIO_WAKE |		\
 	 (__u64)1 << _UFFDIO_COPY |		\
-	 (__u64)1 << _UFFDIO_CONTINUE)
+	 (__u64)1 << _UFFDIO_CONTINUE |		\
+	 (__u64)1 << _UFFDIO_WRITEPROTECT)
 
 /*
  * Valid ioctl command number range with this API is from 0x00 to
@@ -189,6 +191,9 @@ struct uffdio_api {
 	 *
 	 * UFFD_FEATURE_MINOR_SHMEM indicates the same support as
 	 * UFFD_FEATURE_MINOR_HUGETLBFS, but for shmem-backed pages instead.
+	 *
+	 * UFFD_FEATURE_WP_HUGETLBFS_SHMEM indicates that userfaultfd
+	 * write-protection mode is supported on both shmem and hugetlbfs.
 	 */
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
@@ -201,6 +206,7 @@ struct uffdio_api {
 #define UFFD_FEATURE_THREAD_ID			(1<<8)
 #define UFFD_FEATURE_MINOR_HUGETLBFS		(1<<9)
 #define UFFD_FEATURE_MINOR_SHMEM		(1<<10)
+#define UFFD_FEATURE_WP_HUGETLBFS_SHMEM		(1<<11)
 	__u64 features;
 
 	__u64 ioctls;
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index af79f3d3a001..7ff9176149e0 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -772,15 +772,12 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
 
 	err = -ENOENT;
 	dst_vma = find_dst_vma(dst_mm, start, len);
-	/*
-	 * Make sure the vma is not shared, that the dst range is
-	 * both valid and fully within a single existing vma.
-	 */
-	if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
+
+	if (!dst_vma)
 		goto out_unlock;
 	if (!userfaultfd_wp(dst_vma))
 		goto out_unlock;
-	if (!vma_is_anonymous(dst_vma))
+	if (!vma_can_userfault(dst_vma, dst_vma->vm_flags))
 		goto out_unlock;
 
 	if (is_vm_hugetlb_page(dst_vma)) {
-- 
2.31.1