Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs changes from Al Viro.
 "A lot of misc stuff.  The obvious groups:
   * Miklos' atomic_open series; kills the damn abuse of
     ->d_revalidate() by NFS, which was the major stumbling block for
     all work in that area.
   * ripping security_file_mmap() and dealing with deadlocks in the
     area; sanitizing the neighborhood of vm_mmap()/vm_munmap() in
     general.
   * ->encode_fh() switched to saner API; insane fake dentry in
     mm/cleancache.c gone.
   * assorted annotations in fs (endianness, __user)
   * parts of Artem's ->s_dirty work (jff2 and reiserfs parts)
   * ->update_time() work from Josef.
   * other bits and pieces all over the place.

  Normally it would've been in two or three pull requests, but
  signal.git stuff had eaten a lot of time during this cycle ;-/"

Fix up trivial conflicts in Documentation/filesystems/vfs.txt (the
'truncate_range' inode method was removed by the VM changes, the VFS
update adds an 'update_time()' method), and in fs/btrfs/ulist.[ch] (due
to sparse fix added twice, with other changes nearby).

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (95 commits)
  nfs: don't open in ->d_revalidate
  vfs: retry last component if opening stale dentry
  vfs: nameidata_to_filp(): don't throw away file on error
  vfs: nameidata_to_filp(): inline __dentry_open()
  vfs: do_dentry_open(): don't put filp
  vfs: split __dentry_open()
  vfs: do_last() common post lookup
  vfs: do_last(): add audit_inode before open
  vfs: do_last(): only return EISDIR for O_CREAT
  vfs: do_last(): check LOOKUP_DIRECTORY
  vfs: do_last(): make ENOENT exit RCU safe
  vfs: make follow_link check RCU safe
  vfs: do_last(): use inode variable
  vfs: do_last(): inline walk_component()
  vfs: do_last(): make exit RCU safe
  vfs: split do_lookup()
  Btrfs: move over to use ->update_time
  fs: introduce inode operation ->update_time
  reiserfs: get rid of resierfs_sync_super
  reiserfs: mark the superblock as dirty a bit later
  ...

1 files changed, 127 insertions, 50 deletions

diff --git a/fs/namei.c b/fs/namei.c
index c651f02c9fec..7d694194024a 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -449,7 +449,7 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
 	mntget(nd->path.mnt);
 
 	rcu_read_unlock();
-	br_read_unlock(vfsmount_lock);
+	br_read_unlock(&vfsmount_lock);
 	nd->flags &= ~LOOKUP_RCU;
 	return 0;
 
@@ -507,14 +507,14 @@ static int complete_walk(struct nameidata *nd)
 		if (unlikely(!__d_rcu_to_refcount(dentry, nd->seq))) {
 			spin_unlock(&dentry->d_lock);
 			rcu_read_unlock();
-			br_read_unlock(vfsmount_lock);
+			br_read_unlock(&vfsmount_lock);
 			return -ECHILD;
 		}
 		BUG_ON(nd->inode != dentry->d_inode);
 		spin_unlock(&dentry->d_lock);
 		mntget(nd->path.mnt);
 		rcu_read_unlock();
-		br_read_unlock(vfsmount_lock);
+		br_read_unlock(&vfsmount_lock);
 	}
 
 	if (likely(!(nd->flags & LOOKUP_JUMPED)))
@@ -681,15 +681,15 @@ int follow_up(struct path *path)
 	struct mount *parent;
 	struct dentry *mountpoint;
 
-	br_read_lock(vfsmount_lock);
+	br_read_lock(&vfsmount_lock);
 	parent = mnt->mnt_parent;
 	if (&parent->mnt == path->mnt) {
-		br_read_unlock(vfsmount_lock);
+		br_read_unlock(&vfsmount_lock);
 		return 0;
 	}
 	mntget(&parent->mnt);
 	mountpoint = dget(mnt->mnt_mountpoint);
-	br_read_unlock(vfsmount_lock);
+	br_read_unlock(&vfsmount_lock);
 	dput(path->dentry);
 	path->dentry = mountpoint;
 	mntput(path->mnt);
@@ -947,7 +947,7 @@ failed:
 	if (!(nd->flags & LOOKUP_ROOT))
 		nd->root.mnt = NULL;
 	rcu_read_unlock();
-	br_read_unlock(vfsmount_lock);
+	br_read_unlock(&vfsmount_lock);
 	return -ECHILD;
 }
 
@@ -1125,8 +1125,8 @@ static struct dentry *__lookup_hash(struct qstr *name,
  *  small and for now I'd prefer to have fast path as straight as possible.
  *  It _is_ time-critical.
  */
-static int do_lookup(struct nameidata *nd, struct qstr *name,
-			struct path *path, struct inode **inode)
+static int lookup_fast(struct nameidata *nd, struct qstr *name,
+		       struct path *path, struct inode **inode)
 {
 	struct vfsmount *mnt = nd->path.mnt;
 	struct dentry *dentry, *parent = nd->path.dentry;
@@ -1208,7 +1208,7 @@ unlazy:
 			goto need_lookup;
 		}
 	}
-done:
+
 	path->mnt = mnt;
 	path->dentry = dentry;
 	err = follow_managed(path, nd->flags);
@@ -1222,6 +1222,17 @@ done:
 	return 0;
 
 need_lookup:
+	return 1;
+}
+
+/* Fast lookup failed, do it the slow way */
+static int lookup_slow(struct nameidata *nd, struct qstr *name,
+		       struct path *path)
+{
+	struct dentry *dentry, *parent;
+	int err;
+
+	parent = nd->path.dentry;
 	BUG_ON(nd->inode != parent->d_inode);
 
 	mutex_lock(&parent->d_inode->i_mutex);
@@ -1229,7 +1240,16 @@ need_lookup:
 	mutex_unlock(&parent->d_inode->i_mutex);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
-	goto done;
+	path->mnt = nd->path.mnt;
+	path->dentry = dentry;
+	err = follow_managed(path, nd->flags);
+	if (unlikely(err < 0)) {
+		path_put_conditional(path, nd);
+		return err;
+	}
+	if (err)
+		nd->flags |= LOOKUP_JUMPED;
+	return 0;
 }
 
 static inline int may_lookup(struct nameidata *nd)
@@ -1265,7 +1285,7 @@ static void terminate_walk(struct nameidata *nd)
 		if (!(nd->flags & LOOKUP_ROOT))
 			nd->root.mnt = NULL;
 		rcu_read_unlock();
-		br_read_unlock(vfsmount_lock);
+		br_read_unlock(&vfsmount_lock);
 	}
 }
 
@@ -1301,21 +1321,26 @@ static inline int walk_component(struct nameidata *nd, struct path *path,
 	 */
 	if (unlikely(type != LAST_NORM))
 		return handle_dots(nd, type);
-	err = do_lookup(nd, name, path, &inode);
+	err = lookup_fast(nd, name, path, &inode);
 	if (unlikely(err)) {
-		terminate_walk(nd);
-		return err;
-	}
-	if (!inode) {
-		path_to_nameidata(path, nd);
-		terminate_walk(nd);
-		return -ENOENT;
+		if (err < 0)
+			goto out_err;
+
+		err = lookup_slow(nd, name, path);
+		if (err < 0)
+			goto out_err;
+
+		inode = path->dentry->d_inode;
 	}
+	err = -ENOENT;
+	if (!inode)
+		goto out_path_put;
+
 	if (should_follow_link(inode, follow)) {
 		if (nd->flags & LOOKUP_RCU) {
 			if (unlikely(unlazy_walk(nd, path->dentry))) {
-				terminate_walk(nd);
-				return -ECHILD;
+				err = -ECHILD;
+				goto out_err;
 			}
 		}
 		BUG_ON(inode != path->dentry->d_inode);
@@ -1324,6 +1349,12 @@ static inline int walk_component(struct nameidata *nd, struct path *path,
 	path_to_nameidata(path, nd);
 	nd->inode = inode;
 	return 0;
+
+out_path_put:
+	path_to_nameidata(path, nd);
+out_err:
+	terminate_walk(nd);
+	return err;
 }
 
 /*
@@ -1620,7 +1651,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 		nd->path = nd->root;
 		nd->inode = inode;
 		if (flags & LOOKUP_RCU) {
-			br_read_lock(vfsmount_lock);
+			br_read_lock(&vfsmount_lock);
 			rcu_read_lock();
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 		} else {
@@ -1633,7 +1664,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 
 	if (*name=='/') {
 		if (flags & LOOKUP_RCU) {
-			br_read_lock(vfsmount_lock);
+			br_read_lock(&vfsmount_lock);
 			rcu_read_lock();
 			set_root_rcu(nd);
 		} else {
@@ -1646,7 +1677,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 			struct fs_struct *fs = current->fs;
 			unsigned seq;
 
-			br_read_lock(vfsmount_lock);
+			br_read_lock(&vfsmount_lock);
 			rcu_read_lock();
 
 			do {
@@ -1682,7 +1713,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 			if (fput_needed)
 				*fp = file;
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
-			br_read_lock(vfsmount_lock);
+			br_read_lock(&vfsmount_lock);
 			rcu_read_lock();
 		} else {
 			path_get(&file->f_path);
@@ -2169,6 +2200,10 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	int want_write = 0;
 	int acc_mode = op->acc_mode;
 	struct file *filp;
+	struct inode *inode;
+	int symlink_ok = 0;
+	struct path save_parent = { .dentry = NULL, .mnt = NULL };
+	bool retried = false;
 	int error;
 
 	nd->flags &= ~LOOKUP_PARENT;
@@ -2200,30 +2235,23 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	}
 
 	if (!(open_flag & O_CREAT)) {
-		int symlink_ok = 0;
 		if (nd->last.name[nd->last.len])
 			nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
 		if (open_flag & O_PATH && !(nd->flags & LOOKUP_FOLLOW))
 			symlink_ok = 1;
 		/* we _can_ be in RCU mode here */
-		error = walk_component(nd, path, &nd->last, LAST_NORM,
-					!symlink_ok);
-		if (error < 0)
-			return ERR_PTR(error);
-		if (error) /* symlink */
-			return NULL;
-		/* sayonara */
-		error = complete_walk(nd);
-		if (error)
-			return ERR_PTR(error);
+		error = lookup_fast(nd, &nd->last, path, &inode);
+		if (unlikely(error)) {
+			if (error < 0)
+				goto exit;
 
-		error = -ENOTDIR;
-		if (nd->flags & LOOKUP_DIRECTORY) {
-			if (!nd->inode->i_op->lookup)
+			error = lookup_slow(nd, &nd->last, path);
+			if (error < 0)
 				goto exit;
+
+			inode = path->dentry->d_inode;
 		}
-		audit_inode(pathname, nd->path.dentry);
-		goto ok;
+		goto finish_lookup;
 	}
 
 	/* create side of things */
@@ -2241,6 +2269,7 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	if (nd->last.name[nd->last.len])
 		goto exit;
 
+retry_lookup:
 	mutex_lock(&dir->d_inode->i_mutex);
 
 	dentry = lookup_hash(nd);
@@ -2302,22 +2331,49 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	if (error)
 		nd->flags |= LOOKUP_JUMPED;
 
+	BUG_ON(nd->flags & LOOKUP_RCU);
+	inode = path->dentry->d_inode;
+finish_lookup:
+	/* we _can_ be in RCU mode here */
 	error = -ENOENT;
-	if (!path->dentry->d_inode)
-		goto exit_dput;
+	if (!inode) {
+		path_to_nameidata(path, nd);
+		goto exit;
+	}
 
-	if (path->dentry->d_inode->i_op->follow_link)
+	if (should_follow_link(inode, !symlink_ok)) {
+		if (nd->flags & LOOKUP_RCU) {
+			if (unlikely(unlazy_walk(nd, path->dentry))) {
+				error = -ECHILD;
+				goto exit;
+			}
+		}
+		BUG_ON(inode != path->dentry->d_inode);
 		return NULL;
+	}
 
-	path_to_nameidata(path, nd);
-	nd->inode = path->dentry->d_inode;
+	if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path->mnt) {
+		path_to_nameidata(path, nd);
+	} else {
+		save_parent.dentry = nd->path.dentry;
+		save_parent.mnt = mntget(path->mnt);
+		nd->path.dentry = path->dentry;
+
+	}
+	nd->inode = inode;
 	/* Why this, you ask?  _Now_ we might have grown LOOKUP_JUMPED... */
 	error = complete_walk(nd);
-	if (error)
+	if (error) {
+		path_put(&save_parent);
 		return ERR_PTR(error);
+	}
 	error = -EISDIR;
-	if (S_ISDIR(nd->inode->i_mode))
+	if ((open_flag & O_CREAT) && S_ISDIR(nd->inode->i_mode))
+		goto exit;
+	error = -ENOTDIR;
+	if ((nd->flags & LOOKUP_DIRECTORY) && !nd->inode->i_op->lookup)
 		goto exit;
+	audit_inode(pathname, nd->path.dentry);
 ok:
 	if (!S_ISREG(nd->inode->i_mode))
 		will_truncate = 0;
@@ -2333,6 +2389,20 @@ common:
 	if (error)
 		goto exit;
 	filp = nameidata_to_filp(nd);
+	if (filp == ERR_PTR(-EOPENSTALE) && save_parent.dentry && !retried) {
+		BUG_ON(save_parent.dentry != dir);
+		path_put(&nd->path);
+		nd->path = save_parent;
+		nd->inode = dir->d_inode;
+		save_parent.mnt = NULL;
+		save_parent.dentry = NULL;
+		if (want_write) {
+			mnt_drop_write(nd->path.mnt);
+			want_write = 0;
+		}
+		retried = true;
+		goto retry_lookup;
+	}
 	if (!IS_ERR(filp)) {
 		error = ima_file_check(filp, op->acc_mode);
 		if (error) {
@@ -2352,7 +2422,8 @@ common:
 out:
 	if (want_write)
 		mnt_drop_write(nd->path.mnt);
-	path_put(&nd->path);
+	path_put(&save_parent);
+	terminate_walk(nd);
 	return filp;
 
 exit_mutex_unlock:
@@ -2415,6 +2486,12 @@ out:
 	if (base)
 		fput(base);
 	release_open_intent(nd);
+	if (filp == ERR_PTR(-EOPENSTALE)) {
+		if (flags & LOOKUP_RCU)
+			filp = ERR_PTR(-ECHILD);
+		else
+			filp = ERR_PTR(-ESTALE);
+	}
 	return filp;
 
 out_filp: