Merge tag 'ovl-update-4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs

Pull overlayfs updates from Miklos Szeredi:
 "This contains two new features:

   - Stack file operations: this allows removal of several hacks from
     the VFS, proper interaction of read-only open files with copy-up,
     possibility to implement fs modifying ioctls properly, and others.

   - Metadata only copy-up: when file is on lower layer and only
     metadata is modified (except size) then only copy up the metadata
     and continue to use the data from the lower file"

* tag 'ovl-update-4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs: (66 commits)
  ovl: Enable metadata only feature
  ovl: Do not do metacopy only for ioctl modifying file attr
  ovl: Do not do metadata only copy-up for truncate operation
  ovl: add helper to force data copy-up
  ovl: Check redirect on index as well
  ovl: Set redirect on upper inode when it is linked
  ovl: Set redirect on metacopy files upon rename
  ovl: Do not set dentry type ORIGIN for broken hardlinks
  ovl: Add an inode flag OVL_CONST_INO
  ovl: Treat metacopy dentries as type OVL_PATH_MERGE
  ovl: Check redirects for metacopy files
  ovl: Move some dir related ovl_lookup_single() code in else block
  ovl: Do not expose metacopy only dentry from d_real()
  ovl: Open file with data except for the case of fsync
  ovl: Add helper ovl_inode_realdata()
  ovl: Store lower data inode in ovl_inode
  ovl: Fix ovl_getattr() to get number of blocks from lower
  ovl: Add helper ovl_dentry_lowerdata() to get lower data dentry
  ovl: Copy up meta inode data from lowest data inode
  ovl: Modify ovl_lookup() and friends to lookup metacopy dentry
  ...

include/linux/dcache.h

@@ -145,8 +145,7 @@ struct dentry_operations {
 	char *(*d_dname)(struct dentry *, char *, int);
 	struct vfsmount *(*d_automount)(struct path *);
 	int (*d_manage)(const struct path *, bool);
-	struct dentry *(*d_real)(struct dentry *, const struct inode *,
-				 unsigned int, unsigned int);
+	struct dentry *(*d_real)(struct dentry *, const struct inode *);
 } ____cacheline_aligned;
 
 /*
@@ -561,15 +560,10 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper)
 	return upper;
 }
 
-/* d_real() flags */
-#define D_REAL_UPPER	0x2	/* return upper dentry or NULL if non-upper */
-
 /**
  * d_real - Return the real dentry
  * @dentry: the dentry to query
  * @inode: inode to select the dentry from multiple layers (can be NULL)
- * @open_flags: open flags to control copy-up behavior
- * @flags: flags to control what is returned by this function
  *
  * If dentry is on a union/overlay, then return the underlying, real dentry.
  * Otherwise return the dentry itself.
@@ -577,11 +571,10 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper)
  * See also: Documentation/filesystems/vfs.txt
  */
 static inline struct dentry *d_real(struct dentry *dentry,
-				    const struct inode *inode,
-				    unsigned int open_flags, unsigned int flags)
+				    const struct inode *inode)
 {
 	if (unlikely(dentry->d_flags & DCACHE_OP_REAL))
-		return dentry->d_op->d_real(dentry, inode, open_flags, flags);
+		return dentry->d_op->d_real(dentry, inode);
 	else
 		return dentry;
 }
@@ -596,7 +589,7 @@ static inline struct dentry *d_real(struct dentry *dentry,
 static inline struct inode *d_real_inode(const struct dentry *dentry)
 {
 	/* This usage of d_real() results in const dentry */
-	return d_backing_inode(d_real((struct dentry *) dentry, NULL, 0, 0));
+	return d_backing_inode(d_real((struct dentry *) dentry, NULL));
 }
 
 struct name_snapshot {

include/linux/fs.h

@@ -157,6 +157,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File is capable of returning -EAGAIN if I/O will block */
 #define FMODE_NOWAIT	((__force fmode_t)0x8000000)
 
+/* File does not contribute to nr_files count */
+#define FMODE_NOACCOUNT	((__force fmode_t)0x20000000)
+
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
  * that indicates that they should check the contents of the iovec are
@@ -1067,17 +1070,7 @@ struct file_lock_context {
 
 extern void send_sigio(struct fown_struct *fown, int fd, int band);
 
-/*
- * Return the inode to use for locking
- *
- * For overlayfs this should be the overlay inode, not the real inode returned
- * by file_inode().  For any other fs file_inode(filp) and locks_inode(filp) are
- * equal.
- */
-static inline struct inode *locks_inode(const struct file *f)
-{
-	return f->f_path.dentry->d_inode;
-}
+#define locks_inode(f) file_inode(f)
 
 #ifdef CONFIG_FILE_LOCKING
 extern int fcntl_getlk(struct file *, unsigned int, struct flock *);
@@ -1262,7 +1255,7 @@ static inline struct inode *file_inode(const struct file *f)
 
 static inline struct dentry *file_dentry(const struct file *file)
 {
-	return d_real(file->f_path.dentry, file_inode(file), 0, 0);
+	return d_real(file->f_path.dentry, file_inode(file));
 }
 
 static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
@@ -1318,7 +1311,6 @@ extern int send_sigurg(struct fown_struct *fown);
 
 /* These sb flags are internal to the kernel */
 #define SB_SUBMOUNT     (1<<26)
-#define SB_NOREMOTELOCK	(1<<27)
 #define SB_NOSEC	(1<<28)
 #define SB_BORN		(1<<29)
 #define SB_ACTIVE	(1<<30)
@@ -1647,6 +1639,8 @@ int vfs_mkobj(struct dentry *, umode_t,
 		int (*f)(struct dentry *, umode_t, void *),
 		void *);
 
+extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+
 /*
  * VFS file helper functions.
  */
@@ -1765,7 +1759,7 @@ struct file_operations {
 			loff_t, size_t, unsigned int);
 	int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t,
 			u64);
-	ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *,
+	int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t,
 			u64);
 } __randomize_layout;
 
@@ -1838,6 +1832,10 @@ extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 					 loff_t len, bool *is_same);
 extern int vfs_dedupe_file_range(struct file *file,
 				 struct file_dedupe_range *same);
+extern int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
+				     struct file *dst_file, loff_t dst_pos,
+				     u64 len);
+
 
 struct super_operations {
    	struct inode *(*alloc_inode)(struct super_block *sb);
@@ -2096,6 +2094,7 @@ enum file_time_flags {
 	S_VERSION = 8,
 };
 
+extern bool atime_needs_update(const struct path *, struct inode *);
 extern void touch_atime(const struct path *);
 static inline void file_accessed(struct file *file)
 {
@@ -2441,6 +2440,8 @@ extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
 				   const char *, int, umode_t);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
+extern struct file * open_with_fake_path(const struct path *, int,
+					 struct inode*, const struct cred *);
 static inline struct file *file_clone_open(struct file *file)
 {
 	return dentry_open(&file->f_path, file->f_flags, file->f_cred);

include/linux/fsnotify.h

@@ -30,11 +30,7 @@ static inline int fsnotify_parent(const struct path *path, struct dentry *dentry
 static inline int fsnotify_perm(struct file *file, int mask)
 {
 	const struct path *path = &file->f_path;
-	/*
-	 * Do not use file_inode() here or anywhere in this file to get the
-	 * inode.  That would break *notity on overlayfs.
-	 */
-	struct inode *inode = path->dentry->d_inode;
+	struct inode *inode = file_inode(file);
 	__u32 fsnotify_mask = 0;
 	int ret;
 
@@ -178,7 +174,7 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
 static inline void fsnotify_access(struct file *file)
 {
 	const struct path *path = &file->f_path;
-	struct inode *inode = path->dentry->d_inode;
+	struct inode *inode = file_inode(file);
 	__u32 mask = FS_ACCESS;
 
 	if (S_ISDIR(inode->i_mode))
@@ -196,7 +192,7 @@ static inline void fsnotify_access(struct file *file)
 static inline void fsnotify_modify(struct file *file)
 {
 	const struct path *path = &file->f_path;
-	struct inode *inode = path->dentry->d_inode;
+	struct inode *inode = file_inode(file);
 	__u32 mask = FS_MODIFY;
 
 	if (S_ISDIR(inode->i_mode))
@@ -214,7 +210,7 @@ static inline void fsnotify_modify(struct file *file)
 static inline void fsnotify_open(struct file *file)
 {
 	const struct path *path = &file->f_path;
-	struct inode *inode = path->dentry->d_inode;
+	struct inode *inode = file_inode(file);
 	__u32 mask = FS_OPEN;
 
 	if (S_ISDIR(inode->i_mode))
@@ -230,7 +226,7 @@ static inline void fsnotify_open(struct file *file)
 static inline void fsnotify_close(struct file *file)
 {
 	const struct path *path = &file->f_path;
-	struct inode *inode = path->dentry->d_inode;
+	struct inode *inode = file_inode(file);
 	fmode_t mode = file->f_mode;
 	__u32 mask = (mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE;