[PATCH v2 23/24] 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.

Now we can remove the flags parameter for vma_can_userfault() since not used
any more.  Meanwhile, 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                 | 19 -------------------
 include/linux/userfaultfd_k.h    | 15 +++++++++++++++
 include/uapi/linux/userfaultfd.h |  7 +++++--
 mm/userfaultfd.c                 | 10 +++-------
 4 files changed, 23 insertions(+), 28 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index a41e0631af512..a436a1feb10db 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1275,25 +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) {
-		/* FIXME: Add minor fault interception for shmem. */
-		if (!is_vm_hugetlb_page(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 fefebe6e96560..95afd4814ab29 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)
@@ -132,6 +133,20 @@ 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) {
+		/* FIXME: Add minor fault interception for shmem. */
+		if (!is_vm_hugetlb_page(vma))
+			return false;
+	}
+
+	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 bafbeb1a26245..298fbd4e2d1d3 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_WP_HUGETLBFS_SHMEM)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -45,7 +46,8 @@
 #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
@@ -196,6 +198,7 @@ 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_WP_HUGETLBFS_SHMEM		(1<<10)
 	__u64 features;
 
 	__u64 ioctls;
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 2cd6ad5c3d8f8..3930e56aaefd8 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -445,7 +445,6 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
 			err = mfill_zeropage_pte(dst_mm, dst_pmd,
 						 dst_vma, dst_addr);
 	} else {
-		VM_WARN_ON_ONCE(wp_copy);
 		if (!zeropage)
 			err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd,
 						     dst_vma, dst_addr,
@@ -682,15 +681,12 @@ 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)) {
-- 
2.26.2