Merge branch 'for-ovl' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs into overlayfs-next

This gives us the open_with_fake_path() helper that is needed for stacked
open files in overlay and mmap in particular.

10 files changed, 99 insertions, 132 deletions

diff --git a/fs/aio.c b/fs/aio.c
index e1d20124ec0e..9eea53887d6c 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -234,13 +234,9 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 	path.mnt = mntget(aio_mnt);
 
 	d_instantiate(path.dentry, inode);
-	file = alloc_file(&path, FMODE_READ | FMODE_WRITE, &aio_ring_fops);
-	if (IS_ERR(file)) {
+	file = alloc_file(&path, O_RDWR, &aio_ring_fops);
+	if (IS_ERR(file))
 		path_put(&path);
-		return file;
-	}
-
-	file->f_flags = O_RDWR;
 	return file;
 }
 
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 3168ee4e77f4..6b235ab1df6c 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -102,12 +102,11 @@ struct file *anon_inode_getfile(const char *name,
 
 	d_instantiate(path.dentry, anon_inode_inode);
 
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
+	file = alloc_file(&path, flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file))
 		goto err_dput;
 	file->f_mapping = anon_inode_inode->i_mapping;
 
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 
 	return file;
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 4b5fff31ef27..aa4a7a23ff99 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -205,7 +205,7 @@ static int load_misc_binary(struct linux_binprm *bprm)
 		goto error;
 
 	if (fmt->flags & MISC_FMT_OPEN_FILE) {
-		interp_file = filp_clone_open(fmt->interp_file);
+		interp_file = file_clone_open(fmt->interp_file);
 		if (!IS_ERR(interp_file))
 			deny_write_access(interp_file);
 	} else {
diff --git a/fs/file_table.c b/fs/file_table.c
index 7ec0b3e5f05d..9b70ed2bbc4e 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -51,6 +51,7 @@ static void file_free_rcu(struct rcu_head *head)
 
 static inline void file_free(struct file *f)
 {
+	security_file_free(f);
 	percpu_counter_dec(&nr_files);
 	call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
 }
@@ -100,9 +101,8 @@ int proc_nr_files(struct ctl_table *table, int write,
  * done, you will imbalance int the mount's writer count
  * and a warning at __fput() time.
  */
-struct file *get_empty_filp(void)
+struct file *alloc_empty_file(int flags, const struct cred *cred)
 {
-	const struct cred *cred = current_cred();
 	static long old_max;
 	struct file *f;
 	int error;
@@ -123,11 +123,10 @@ struct file *get_empty_filp(void)
 	if (unlikely(!f))
 		return ERR_PTR(-ENOMEM);
 
-	percpu_counter_inc(&nr_files);
 	f->f_cred = get_cred(cred);
 	error = security_file_alloc(f);
 	if (unlikely(error)) {
-		file_free(f);
+		file_free_rcu(&f->f_u.fu_rcuhead);
 		return ERR_PTR(error);
 	}
 
@@ -136,7 +135,10 @@ struct file *get_empty_filp(void)
 	spin_lock_init(&f->f_lock);
 	mutex_init(&f->f_pos_lock);
 	eventpoll_init_file(f);
+	f->f_flags = flags;
+	f->f_mode = OPEN_FMODE(flags);
 	/* f->f_version: 0 */
+	percpu_counter_inc(&nr_files);
 	return f;
 
 over:
@@ -152,15 +154,15 @@ over:
  * alloc_file - allocate and initialize a 'struct file'
  *
  * @path: the (dentry, vfsmount) pair for the new file
- * @mode: the mode with which the new file will be opened
+ * @flags: O_... flags with which the new file will be opened
  * @fop: the 'struct file_operations' for the new file
  */
-struct file *alloc_file(const struct path *path, fmode_t mode,
+struct file *alloc_file(const struct path *path, int flags,
 		const struct file_operations *fop)
 {
 	struct file *file;
 
-	file = get_empty_filp();
+	file = alloc_empty_file(flags, current_cred());
 	if (IS_ERR(file))
 		return file;
 
@@ -168,15 +170,15 @@ struct file *alloc_file(const struct path *path, fmode_t mode,
 	file->f_inode = path->dentry->d_inode;
 	file->f_mapping = path->dentry->d_inode->i_mapping;
 	file->f_wb_err = filemap_sample_wb_err(file->f_mapping);
-	if ((mode & FMODE_READ) &&
+	if ((file->f_mode & FMODE_READ) &&
 	     likely(fop->read || fop->read_iter))
-		mode |= FMODE_CAN_READ;
-	if ((mode & FMODE_WRITE) &&
+		file->f_mode |= FMODE_CAN_READ;
+	if ((file->f_mode & FMODE_WRITE) &&
 	     likely(fop->write || fop->write_iter))
-		mode |= FMODE_CAN_WRITE;
-	file->f_mode = mode;
+		file->f_mode |= FMODE_CAN_WRITE;
+	file->f_mode |= FMODE_OPENED;
 	file->f_op = fop;
-	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(path->dentry->d_inode);
 	return file;
 }
@@ -190,6 +192,9 @@ static void __fput(struct file *file)
 	struct vfsmount *mnt = file->f_path.mnt;
 	struct inode *inode = file->f_inode;
 
+	if (unlikely(!(file->f_mode & FMODE_OPENED)))
+		goto out;
+
 	might_sleep();
 
 	fsnotify_close(file);
@@ -207,7 +212,6 @@ static void __fput(struct file *file)
 	}
 	if (file->f_op->release)
 		file->f_op->release(inode, file);
-	security_file_free(file);
 	if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
 		     !(file->f_mode & FMODE_PATH))) {
 		cdev_put(inode->i_cdev);
@@ -220,12 +224,10 @@ static void __fput(struct file *file)
 		put_write_access(inode);
 		__mnt_drop_write(mnt);
 	}
-	file->f_path.dentry = NULL;
-	file->f_path.mnt = NULL;
-	file->f_inode = NULL;
-	file_free(file);
 	dput(dentry);
 	mntput(mnt);
+out:
+	file_free(file);
 }
 
 static LLIST_HEAD(delayed_fput_list);
@@ -300,14 +302,6 @@ void __fput_sync(struct file *file)
 
 EXPORT_SYMBOL(fput);
 
-void put_filp(struct file *file)
-{
-	if (atomic_long_dec_and_test(&file->f_count)) {
-		security_file_free(file);
-		file_free(file);
-	}
-}
-
 void __init files_init(void)
 {
 	filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index d508c7844681..71aed47422e2 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1375,8 +1375,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	inode->i_size = size;
 	clear_nlink(inode);
 
-	file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
-			&hugetlbfs_file_operations);
+	file = alloc_file(&path, O_RDWR, &hugetlbfs_file_operations);
 	if (IS_ERR(file))
 		goto out_dentry; /* inode is already attached */
 
diff --git a/fs/internal.h b/fs/internal.h
index 980d005b21b4..52a346903748 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -93,7 +93,7 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
 /*
  * file_table.c
  */
-extern struct file *get_empty_filp(void);
+extern struct file *alloc_empty_file(int, const struct cred *);
 
 /*
  * super.c
@@ -125,9 +125,7 @@ int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 		int flag);
 
-extern int open_check_o_direct(struct file *f);
-extern int vfs_open(const struct path *, struct file *, const struct cred *);
-extern struct file *filp_clone_open(struct file *);
+extern int vfs_open(const struct path *, struct file *);
 
 /*
  * inode.c
diff --git a/fs/namei.c b/fs/namei.c
index 734cef54fdf8..d152cc05fdc3 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3396,19 +3396,15 @@ finish_open_created:
 	if (error)
 		goto out;
 	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
-	error = vfs_open(&nd->path, file, current_cred());
+	error = vfs_open(&nd->path, file);
 	if (error)
 		goto out;
 	*opened |= FILE_OPENED;
 opened:
-	error = open_check_o_direct(file);
-	if (!error)
-		error = ima_file_check(file, op->acc_mode, *opened);
+	error = ima_file_check(file, op->acc_mode, *opened);
 	if (!error && will_truncate)
 		error = handle_truncate(file);
 out:
-	if (unlikely(error) && (*opened & FILE_OPENED))
-		fput(file);
 	if (unlikely(error > 0)) {
 		WARN_ON(1);
 		error = -EINVAL;
@@ -3481,11 +3477,6 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 		goto out2;
 	file->f_path.mnt = path.mnt;
 	error = finish_open(file, child, NULL, opened);
-	if (error)
-		goto out2;
-	error = open_check_o_direct(file);
-	if (error)
-		fput(file);
 out2:
 	mnt_drop_write(path.mnt);
 out:
@@ -3499,7 +3490,7 @@ static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file)
 	int error = path_lookupat(nd, flags, &path);
 	if (!error) {
 		audit_inode(nd->name, path.dentry, 0);
-		error = vfs_open(&path, file, current_cred());
+		error = vfs_open(&path, file);
 		path_put(&path);
 	}
 	return error;
@@ -3513,12 +3504,10 @@ static struct file *path_openat(struct nameidata *nd,
 	int opened = 0;
 	int error;
 
-	file = get_empty_filp();
+	file = alloc_empty_file(op->open_flag, current_cred());
 	if (IS_ERR(file))
 		return file;
 
-	file->f_flags = op->open_flag;
-
 	if (unlikely(file->f_flags & __O_TMPFILE)) {
 		error = do_tmpfile(nd, flags, op, file, &opened);
 		goto out2;
@@ -3533,7 +3522,7 @@ static struct file *path_openat(struct nameidata *nd,
 
 	s = path_init(nd, flags);
 	if (IS_ERR(s)) {
-		put_filp(file);
+		fput(file);
 		return ERR_CAST(s);
 	}
 	while (!(error = link_path_walk(s, nd)) &&
@@ -3547,20 +3536,20 @@ static struct file *path_openat(struct nameidata *nd,
 	}
 	terminate_walk(nd);
 out2:
-	if (!(opened & FILE_OPENED)) {
-		BUG_ON(!error);
-		put_filp(file);
+	if (likely(!error)) {
+		if (likely(opened & FILE_OPENED))
+			return file;
+		WARN_ON(1);
+		error = -EINVAL;
 	}
-	if (unlikely(error)) {
-		if (error == -EOPENSTALE) {
-			if (flags & LOOKUP_RCU)
-				error = -ECHILD;
-			else
-				error = -ESTALE;
-		}
-		file = ERR_PTR(error);
+	fput(file);
+	if (error == -EOPENSTALE) {
+		if (flags & LOOKUP_RCU)
+			error = -ECHILD;
+		else
+			error = -ESTALE;
 	}
-	return file;
+	return ERR_PTR(error);
 }
 
 struct file *do_filp_open(int dfd, struct filename *pathname,
diff --git a/fs/open.c b/fs/open.c
index d0e955b558ad..dd15711eb658 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -724,27 +724,13 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
 	return ksys_fchown(fd, user, group);
 }
 
-int open_check_o_direct(struct file *f)
-{
-	/* NB: we're sure to have correct a_ops only after f_op->open */
-	if (f->f_flags & O_DIRECT) {
-		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
-			return -EINVAL;
-	}
-	return 0;
-}
-
 static int do_dentry_open(struct file *f,
 			  struct inode *inode,
-			  int (*open)(struct inode *, struct file *),
-			  const struct cred *cred)
+			  int (*open)(struct inode *, struct file *))
 {
 	static const struct file_operations empty_fops = {};
 	int error;
 
-	f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
-				FMODE_PREAD | FMODE_PWRITE;
-
 	path_get(&f->f_path);
 	f->f_inode = inode;
 	f->f_mapping = inode->i_mapping;
@@ -753,7 +739,7 @@ static int do_dentry_open(struct file *f,
 	f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
 
 	if (unlikely(f->f_flags & O_PATH)) {
-		f->f_mode = FMODE_PATH;
+		f->f_mode = FMODE_PATH | FMODE_OPENED;
 		f->f_op = &empty_fops;
 		return 0;
 	}
@@ -780,7 +766,7 @@ static int do_dentry_open(struct file *f,
 		goto cleanup_all;
 	}
 
-	error = security_file_open(f, cred);
+	error = security_file_open(f);
 	if (error)
 		goto cleanup_all;
 
@@ -788,6 +774,8 @@ static int do_dentry_open(struct file *f,
 	if (error)
 		goto cleanup_all;
 
+	/* normally all 3 are set; ->open() can clear them if needed */
+	f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
 	if (!open)
 		open = f->f_op->open;
 	if (open) {
@@ -795,6 +783,7 @@ static int do_dentry_open(struct file *f,
 		if (error)
 			goto cleanup_all;
 	}
+	f->f_mode |= FMODE_OPENED;
 	if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(inode);
 	if ((f->f_mode & FMODE_READ) &&
@@ -809,9 +798,16 @@ static int do_dentry_open(struct file *f,
 
 	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
 
+	/* NB: we're sure to have correct a_ops only after f_op->open */
+	if (f->f_flags & O_DIRECT) {
+		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
+			return -EINVAL;
+	}
 	return 0;
 
 cleanup_all:
+	if (WARN_ON_ONCE(error > 0))
+		error = -EINVAL;
 	fops_put(f->f_op);
 	if (f->f_mode & FMODE_WRITER) {
 		put_write_access(inode);
@@ -854,8 +850,7 @@ int finish_open(struct file *file, struct dentry *dentry,
 	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
 
 	file->f_path.dentry = dentry;
-	error = do_dentry_open(file, d_backing_inode(dentry), open,
-			       current_cred());
+	error = do_dentry_open(file, d_backing_inode(dentry), open);
 	if (!error)
 		*opened |= FILE_OPENED;
 
@@ -896,8 +891,7 @@ EXPORT_SYMBOL(file_path);
  * @file: newly allocated file with f_flag initialized
  * @cred: credentials to use
  */
-int vfs_open(const struct path *path, struct file *file,
-	     const struct cred *cred)
+int vfs_open(const struct path *path, struct file *file)
 {
 	struct dentry *dentry = d_real(path->dentry, NULL, file->f_flags, 0);
 
@@ -905,7 +899,7 @@ int vfs_open(const struct path *path, struct file *file,
 		return PTR_ERR(dentry);
 
 	file->f_path = *path;
-	return do_dentry_open(file, d_backing_inode(dentry), NULL, cred);
+	return do_dentry_open(file, d_backing_inode(dentry), NULL);
 }
 
 struct file *dentry_open(const struct path *path, int flags,
@@ -919,19 +913,11 @@ struct file *dentry_open(const struct path *path, int flags,
 	/* We must always pass in a valid mount pointer. */
 	BUG_ON(!path->mnt);
 
-	f = get_empty_filp();
+	f = alloc_empty_file(flags, cred);
 	if (!IS_ERR(f)) {
-		f->f_flags = flags;
-		error = vfs_open(path, f, cred);
-		if (!error) {
-			/* from now on we need fput() to dispose of f */
-			error = open_check_o_direct(f);
-			if (error) {
-				fput(f);
-				f = ERR_PTR(error);
-			}
-		} else { 
-			put_filp(f);
+		error = vfs_open(path, f);
+		if (error) {
+			fput(f);
 			f = ERR_PTR(error);
 		}
 	}
@@ -939,6 +925,24 @@ struct file *dentry_open(const struct path *path, int flags,
 }
 EXPORT_SYMBOL(dentry_open);
 
+struct file *open_with_fake_path(const struct path *path, int flags,
+				struct inode *inode, const struct cred *cred)
+{
+	struct file *f = alloc_empty_file(flags, cred);
+	if (!IS_ERR(f)) {
+		int error;
+
+		f->f_path = *path;
+		error = do_dentry_open(f, inode, NULL);
+		if (error) {
+			fput(f);
+			f = ERR_PTR(error);
+		}
+	}
+	return f;
+}
+EXPORT_SYMBOL(open_with_fake_path);
+
 static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op)
 {
 	int lookup_flags = 0;
@@ -1063,26 +1067,6 @@ struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 }
 EXPORT_SYMBOL(file_open_root);
 
-struct file *filp_clone_open(struct file *oldfile)
-{
-	struct file *file;
-	int retval;
-
-	file = get_empty_filp();
-	if (IS_ERR(file))
-		return file;
-
-	file->f_flags = oldfile->f_flags;
-	retval = vfs_open(&oldfile->f_path, file, oldfile->f_cred);
-	if (retval) {
-		put_filp(file);
-		return ERR_PTR(retval);
-	}
-
-	return file;
-}
-EXPORT_SYMBOL(filp_clone_open);
-
 long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
 {
 	struct open_flags op;
diff --git a/fs/pipe.c b/fs/pipe.c
index bb0840e234f3..1909422e5a78 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -760,29 +760,28 @@ int create_pipe_files(struct file **res, int flags)
 
 	d_instantiate(path.dentry, inode);
 
-	f = alloc_file(&path, FMODE_WRITE, &pipefifo_fops);
+	f = alloc_file(&path, O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)),
+			&pipefifo_fops);
 	if (IS_ERR(f)) {
 		err = PTR_ERR(f);
 		goto err_dentry;
 	}
 
-	f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT));
 	f->private_data = inode->i_pipe;
 
-	res[0] = alloc_file(&path, FMODE_READ, &pipefifo_fops);
+	res[0] = alloc_file(&path, O_RDONLY | (flags & O_NONBLOCK),
+			&pipefifo_fops);
 	if (IS_ERR(res[0])) {
-		err = PTR_ERR(res[0]);
-		goto err_file;
+		put_pipe_info(inode, inode->i_pipe);
+		fput(f);
+		return PTR_ERR(res[0]);
 	}
 
 	path_get(&path);
 	res[0]->private_data = inode->i_pipe;
-	res[0]->f_flags = O_RDONLY | (flags & O_NONBLOCK);
 	res[1] = f;
 	return 0;
 
-err_file:
-	put_filp(f);
 err_dentry:
 	free_pipe_info(inode->i_pipe);
 	path_put(&path);
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 6ac1c92997ea..bb1c1625b158 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -564,11 +564,20 @@ static int proc_seq_open(struct inode *inode, struct file *file)
 	return seq_open(file, de->seq_ops);
 }
 
+static int proc_seq_release(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *de = PDE(inode);
+
+	if (de->state_size)
+		return seq_release_private(inode, file);
+	return seq_release(inode, file);
+}
+
 static const struct file_operations proc_seq_fops = {
 	.open		= proc_seq_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release,
+	.release	= proc_seq_release,
 };
 
 struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,