Merge branch 'cross-rename' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs

Pull renameat2 system call from Miklos Szeredi:
 "This adds a new syscall, renameat2(), which is the same as renameat()
  but with a flags argument.

  The purpose of extending rename is to add cross-rename, a symmetric
  variant of rename, which exchanges the two files.  This allows
  interesting things, which were not possible before, for example
  atomically replacing a directory tree with a symlink, etc...  This
  also allows overlayfs and friends to operate on whiteouts atomically.

  Andy Lutomirski also suggested a "noreplace" flag, which disables the
  overwriting behavior of rename.

  These two flags, RENAME_EXCHANGE and RENAME_NOREPLACE are only
  implemented for ext4 as an example and for testing"

* 'cross-rename' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs:
  ext4: add cross rename support
  ext4: rename: split out helper functions
  ext4: rename: move EMLINK check up
  ext4: rename: create ext4_renament structure for local vars
  vfs: add cross-rename
  vfs: lock_two_nondirectories: allow directory args
  security: add flags to rename hooks
  vfs: add RENAME_NOREPLACE flag
  vfs: add renameat2 syscall
  vfs: rename: use common code for dir and non-dir
  vfs: rename: move d_move() up
  vfs: add d_is_dir()

Documentation/filesystems/Locking

@@ -47,6 +47,8 @@ prototypes:
 	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
+	int (*rename2) (struct inode *, struct dentry *,
+			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
 	void * (*follow_link) (struct dentry *, struct nameidata *);
 	void (*put_link) (struct dentry *, struct nameidata *, void *);
@@ -78,6 +80,7 @@ mkdir:		yes
 unlink:		yes (both)
 rmdir:		yes (both)	(see below)
 rename:		yes (all)	(see below)
+rename2:	yes (all)	(see below)
 readlink:	no
 follow_link:	no
 put_link:	no
@@ -96,7 +99,8 @@ tmpfile:	no
 
 	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
-	cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
+	cross-directory ->rename() and rename2() has (per-superblock)
+->s_vfs_rename_sem.
 
 See Documentation/filesystems/directory-locking for more detailed discussion
 of the locking scheme for directory operations.

Documentation/filesystems/vfs.txt

@@ -347,6 +347,8 @@ struct inode_operations {
 	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
+	int (*rename2) (struct inode *, struct dentry *,
+			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
         void * (*follow_link) (struct dentry *, struct nameidata *);
         void (*put_link) (struct dentry *, struct nameidata *, void *);
@@ -414,6 +416,20 @@ otherwise noted.
   rename: called by the rename(2) system call to rename the object to
 	have the parent and name given by the second inode and dentry.
 
+  rename2: this has an additional flags argument compared to rename.
+	If no flags are supported by the filesystem then this method
+	need not be implemented.  If some flags are supported then the
+	filesystem must return -EINVAL for any unsupported or unknown
+	flags.  Currently the following flags are implemented:
+	(1) RENAME_NOREPLACE: this flag indicates that if the target
+	of the rename exists the rename should fail with -EEXIST
+	instead of replacing the target.  The VFS already checks for
+	existence, so for local filesystems the RENAME_NOREPLACE
+	implementation is equivalent to plain rename.
+	(2) RENAME_EXCHANGE: exchange source and target.  Both must
+	exist; this is checked by the VFS.  Unlike plain rename,
+	source and target may be of different type.
+
   readlink: called by the readlink(2) system call. Only required if
 	you want to support reading symbolic links
 

arch/x86/syscalls/syscall_64.tbl

@@ -322,6 +322,7 @@
 313	common	finit_module		sys_finit_module
 314	common	sched_setattr		sys_sched_setattr
 315	common	sched_getattr		sys_sched_getattr
+316	common	renameat2		sys_renameat2
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

drivers/staging/lustre/lustre/include/linux/lustre_compat25.h

@@ -105,8 +105,8 @@ static inline void ll_set_fs_pwd(struct fs_struct *fs, struct vfsmount *mnt,
 #define ll_vfs_unlink(inode,entry,mnt)	  vfs_unlink(inode,entry)
 #define ll_vfs_mknod(dir,entry,mnt,mode,dev)    vfs_mknod(dir,entry,mode,dev)
 #define ll_security_inode_unlink(dir,entry,mnt) security_inode_unlink(dir,entry)
-#define ll_vfs_rename(old,old_dir,mnt,new,new_dir,mnt1,delegated_inode) \
-		vfs_rename(old,old_dir,new,new_dir,delegated_inode)
+#define ll_vfs_rename(old, old_dir, mnt, new, new_dir, mnt1) \
+		vfs_rename(old, old_dir, new, new_dir, NULL, 0)
 
 #define cfs_bio_io_error(a,b)   bio_io_error((a))
 #define cfs_bio_endio(a,b,c)    bio_endio((a),(c))

drivers/staging/lustre/lustre/lvfs/lvfs_linux.c

@@ -223,7 +223,7 @@ int lustre_rename(struct dentry *dir, struct vfsmount *mnt,
 		GOTO(put_old, err = PTR_ERR(dchild_new));
 
 	err = ll_vfs_rename(dir->d_inode, dchild_old, mnt,
-			    dir->d_inode, dchild_new, mnt, NULL);
+			    dir->d_inode, dchild_new, mnt);
 
 	dput(dchild_new);
 put_old:

fs/cachefiles/namei.c

@@ -391,12 +391,12 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache,
 	path.dentry = dir;
 	path_to_graveyard.mnt = cache->mnt;
 	path_to_graveyard.dentry = cache->graveyard;
-	ret = security_path_rename(&path, rep, &path_to_graveyard, grave);
+	ret = security_path_rename(&path, rep, &path_to_graveyard, grave, 0);
 	if (ret < 0) {
 		cachefiles_io_error(cache, "Rename security error %d", ret);
 	} else {
 		ret = vfs_rename(dir->d_inode, rep,
-				 cache->graveyard->d_inode, grave, NULL);
+				 cache->graveyard->d_inode, grave, NULL, 0);
 		if (ret != 0 && ret != -ENOMEM)
 			cachefiles_io_error(cache,
 					    "Rename failed with error %d", ret);

fs/dcache.c

@@ -2483,12 +2483,14 @@ static void switch_names(struct dentry *dentry, struct dentry *target)
 			dentry->d_name.name = dentry->d_iname;
 		} else {
 			/*
-			 * Both are internal.  Just copy target to dentry
+			 * Both are internal.
 			 */
-			memcpy(dentry->d_iname, target->d_name.name,
-					target->d_name.len + 1);
-			dentry->d_name.len = target->d_name.len;
-			return;
+			unsigned int i;
+			BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long)));
+			for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) {
+				swap(((long *) &dentry->d_iname)[i],
+				     ((long *) &target->d_iname)[i]);
+			}
 		}
 	}
 	swap(dentry->d_name.len, target->d_name.len);
@@ -2545,13 +2547,15 @@ static void dentry_unlock_parents_for_move(struct dentry *dentry,
  * __d_move - move a dentry
  * @dentry: entry to move
  * @target: new dentry
+ * @exchange: exchange the two dentries
  *
  * Update the dcache to reflect the move of a file name. Negative
  * dcache entries should not be moved in this way. Caller must hold
  * rename_lock, the i_mutex of the source and target directories,
  * and the sb->s_vfs_rename_mutex if they differ. See lock_rename().
  */
-static void __d_move(struct dentry * dentry, struct dentry * target)
+static void __d_move(struct dentry *dentry, struct dentry *target,
+		     bool exchange)
 {
 	if (!dentry->d_inode)
 		printk(KERN_WARNING "VFS: moving negative dcache entry\n");
@@ -2573,8 +2577,15 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
 	__d_drop(dentry);
 	__d_rehash(dentry, d_hash(target->d_parent, target->d_name.hash));
 
-	/* Unhash the target: dput() will then get rid of it */
+	/*
+	 * Unhash the target (d_delete() is not usable here).  If exchanging
+	 * the two dentries, then rehash onto the other's hash queue.
+	 */
 	__d_drop(target);
+	if (exchange) {
+		__d_rehash(target,
+			   d_hash(dentry->d_parent, dentry->d_name.hash));
+	}
 
 	list_del(&dentry->d_u.d_child);
 	list_del(&target->d_u.d_child);
@@ -2601,6 +2612,8 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
 	write_seqcount_end(&dentry->d_seq);
 
 	dentry_unlock_parents_for_move(dentry, target);
+	if (exchange)
+		fsnotify_d_move(target);
 	spin_unlock(&target->d_lock);
 	fsnotify_d_move(dentry);
 	spin_unlock(&dentry->d_lock);
@@ -2618,11 +2631,30 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
 void d_move(struct dentry *dentry, struct dentry *target)
 {
 	write_seqlock(&rename_lock);
-	__d_move(dentry, target);
+	__d_move(dentry, target, false);
 	write_sequnlock(&rename_lock);
 }
 EXPORT_SYMBOL(d_move);
 
+/*
+ * d_exchange - exchange two dentries
+ * @dentry1: first dentry
+ * @dentry2: second dentry
+ */
+void d_exchange(struct dentry *dentry1, struct dentry *dentry2)
+{
+	write_seqlock(&rename_lock);
+
+	WARN_ON(!dentry1->d_inode);
+	WARN_ON(!dentry2->d_inode);
+	WARN_ON(IS_ROOT(dentry1));
+	WARN_ON(IS_ROOT(dentry2));
+
+	__d_move(dentry1, dentry2, true);
+
+	write_sequnlock(&rename_lock);
+}
+
 /**
  * d_ancestor - search for an ancestor
  * @p1: ancestor dentry
@@ -2670,7 +2702,7 @@ static struct dentry *__d_unalias(struct inode *inode,
 	m2 = &alias->d_parent->d_inode->i_mutex;
 out_unalias:
 	if (likely(!d_mountpoint(alias))) {
-		__d_move(alias, dentry);
+		__d_move(alias, dentry, false);
 		ret = alias;
 	}
 out_err:

fs/ecryptfs/inode.c

@@ -641,7 +641,7 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 	rc = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry,
 			lower_new_dir_dentry->d_inode, lower_new_dentry,
-			NULL);
+			NULL, 0);
 	if (rc)
 		goto out_lock;
 	if (target_inode)

fs/inode.c

@@ -944,24 +944,22 @@ EXPORT_SYMBOL(unlock_new_inode);
 
 /**
  * lock_two_nondirectories - take two i_mutexes on non-directory objects
+ *
+ * Lock any non-NULL argument that is not a directory.
+ * Zero, one or two objects may be locked by this function.
+ *
  * @inode1: first inode to lock
  * @inode2: second inode to lock
  */
 void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
 {
-	WARN_ON_ONCE(S_ISDIR(inode1->i_mode));
-	if (inode1 == inode2 || !inode2) {
-		mutex_lock(&inode1->i_mutex);
-		return;
-	}
-	WARN_ON_ONCE(S_ISDIR(inode2->i_mode));
-	if (inode1 < inode2) {
+	if (inode1 > inode2)
+		swap(inode1, inode2);
+
+	if (inode1 && !S_ISDIR(inode1->i_mode))
 		mutex_lock(&inode1->i_mutex);
+	if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1)
 		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_NONDIR2);
-	} else {
-		mutex_lock(&inode2->i_mutex);
-		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_NONDIR2);
-	}
 }
 EXPORT_SYMBOL(lock_two_nondirectories);
 
@@ -972,8 +970,9 @@ EXPORT_SYMBOL(lock_two_nondirectories);
  */
 void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2)
 {
-	mutex_unlock(&inode1->i_mutex);
-	if (inode2 && inode2 != inode1)
+	if (inode1 && !S_ISDIR(inode1->i_mode))
+		mutex_unlock(&inode1->i_mutex);
+	if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1)
 		mutex_unlock(&inode2->i_mutex);
 }
 EXPORT_SYMBOL(unlock_two_nondirectories);

fs/nfsd/vfs.c

@@ -1694,7 +1694,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry)
 		goto out_dput_new;
 
-	host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL);
+	host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0);
 	if (!host_err) {
 		host_err = commit_metadata(tfhp);
 		if (!host_err)

include/linux/dcache.h

@@ -308,6 +308,7 @@ extern void dentry_update_name_case(struct dentry *, struct qstr *);
 
 /* used for rename() and baskets */
 extern void d_move(struct dentry *, struct dentry *);
+extern void d_exchange(struct dentry *, struct dentry *);
 extern struct dentry *d_ancestor(struct dentry *, struct dentry *);
 
 /* appendix may either be NULL or be used for transname suffixes */
@@ -429,7 +430,7 @@ static inline unsigned __d_entry_type(const struct dentry *dentry)
 	return dentry->d_flags & DCACHE_ENTRY_TYPE;
 }
 
-static inline bool d_is_directory(const struct dentry *dentry)
+static inline bool d_can_lookup(const struct dentry *dentry)
 {
 	return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE;
 }
@@ -439,6 +440,11 @@ static inline bool d_is_autodir(const struct dentry *dentry)
 	return __d_entry_type(dentry) == DCACHE_AUTODIR_TYPE;
 }
 
+static inline bool d_is_dir(const struct dentry *dentry)
+{
+	return d_can_lookup(dentry) || d_is_autodir(dentry);
+}
+
 static inline bool d_is_symlink(const struct dentry *dentry)
 {
 	return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE;

include/linux/fs.h

@@ -1461,7 +1461,7 @@ extern int vfs_symlink(struct inode *, struct dentry *, const char *);
 extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
 extern int vfs_rmdir(struct inode *, struct dentry *);
 extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
-extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **);
+extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
 
 /*
  * VFS dentry helper functions.
@@ -1572,6 +1572,8 @@ struct inode_operations {
 	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
+	int (*rename2) (struct inode *, struct dentry *,
+			struct inode *, struct dentry *, unsigned int);
 	int (*setattr) (struct dentry *, struct iattr *);
 	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
 	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);

include/linux/security.h

@@ -1793,7 +1793,8 @@ int security_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 int security_inode_rmdir(struct inode *dir, struct dentry *dentry);
 int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev);
 int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry,
-			  struct inode *new_dir, struct dentry *new_dentry);
+			  struct inode *new_dir, struct dentry *new_dentry,
+			  unsigned int flags);
 int security_inode_readlink(struct dentry *dentry);
 int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd);
 int security_inode_permission(struct inode *inode, int mask);
@@ -2161,7 +2162,8 @@ static inline int security_inode_mknod(struct inode *dir,
 static inline int security_inode_rename(struct inode *old_dir,
 					 struct dentry *old_dentry,
 					 struct inode *new_dir,
-					 struct dentry *new_dentry)
+					 struct dentry *new_dentry,
+					 unsigned int flags)
 {
 	return 0;
 }
@@ -2955,7 +2957,8 @@ int security_path_symlink(struct path *dir, struct dentry *dentry,
 int security_path_link(struct dentry *old_dentry, struct path *new_dir,
 		       struct dentry *new_dentry);
 int security_path_rename(struct path *old_dir, struct dentry *old_dentry,
-			 struct path *new_dir, struct dentry *new_dentry);
+			 struct path *new_dir, struct dentry *new_dentry,
+			 unsigned int flags);
 int security_path_chmod(struct path *path, umode_t mode);
 int security_path_chown(struct path *path, kuid_t uid, kgid_t gid);
 int security_path_chroot(struct path *path);
@@ -3003,7 +3006,8 @@ static inline int security_path_link(struct dentry *old_dentry,
 static inline int security_path_rename(struct path *old_dir,
 				       struct dentry *old_dentry,
 				       struct path *new_dir,
-				       struct dentry *new_dentry)
+				       struct dentry *new_dentry,
+				       unsigned int flags)
 {
 	return 0;
 }

include/uapi/linux/fs.h

@@ -35,6 +35,9 @@
 #define SEEK_HOLE	4	/* seek to the next hole */
 #define SEEK_MAX	SEEK_HOLE
 
+#define RENAME_NOREPLACE	(1 << 0)	/* Don't overwrite target */
+#define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
+
 struct fstrim_range {
 	__u64 start;
 	__u64 len;

security/security.c

@@ -433,11 +433,20 @@ int security_path_link(struct dentry *old_dentry, struct path *new_dir,
 }
 
 int security_path_rename(struct path *old_dir, struct dentry *old_dentry,
-			 struct path *new_dir, struct dentry *new_dentry)
+			 struct path *new_dir, struct dentry *new_dentry,
+			 unsigned int flags)
 {
 	if (unlikely(IS_PRIVATE(old_dentry->d_inode) ||
 		     (new_dentry->d_inode && IS_PRIVATE(new_dentry->d_inode))))
 		return 0;
+
+	if (flags & RENAME_EXCHANGE) {
+		int err = security_ops->path_rename(new_dir, new_dentry,
+						    old_dir, old_dentry);
+		if (err)
+			return err;
+	}
+
 	return security_ops->path_rename(old_dir, old_dentry, new_dir,
 					 new_dentry);
 }
@@ -524,11 +533,20 @@ int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
 }
 
 int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry,
-			   struct inode *new_dir, struct dentry *new_dentry)
+			   struct inode *new_dir, struct dentry *new_dentry,
+			   unsigned int flags)
 {
         if (unlikely(IS_PRIVATE(old_dentry->d_inode) ||
             (new_dentry->d_inode && IS_PRIVATE(new_dentry->d_inode))))
 		return 0;
+
+	if (flags & RENAME_EXCHANGE) {
+		int err = security_ops->inode_rename(new_dir, new_dentry,
+						     old_dir, old_dentry);
+		if (err)
+			return err;
+	}
+
 	return security_ops->inode_rename(old_dir, old_dentry,
 					   new_dir, new_dentry);
 }