Merge remote-tracking branch 'overlayfs/overlayfs-next'

9 files changed, 219 insertions, 75 deletions

diff --git a/fs/namei.c b/fs/namei.c
index ad74877e1442..7d87699c3e2e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3353,13 +3353,50 @@ out:
 	return error;
 }
 
+struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag)
+{
+	static const struct qstr name = QSTR_INIT("/", 1);
+	struct dentry *child = NULL;
+	struct inode *dir = dentry->d_inode;
+	struct inode *inode;
+	int error;
+
+	/* we want directory to be writable */
+	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+	if (error)
+		goto out_err;
+	error = -EOPNOTSUPP;
+	if (!dir->i_op->tmpfile)
+		goto out_err;
+	error = -ENOMEM;
+	child = d_alloc(dentry, &name);
+	if (unlikely(!child))
+		goto out_err;
+	error = dir->i_op->tmpfile(dir, child, mode);
+	if (error)
+		goto out_err;
+	error = -ENOENT;
+	inode = child->d_inode;
+	if (unlikely(!inode))
+		goto out_err;
+	if (!(open_flag & O_EXCL)) {
+		spin_lock(&inode->i_lock);
+		inode->i_state |= I_LINKABLE;
+		spin_unlock(&inode->i_lock);
+	}
+	return child;
+
+out_err:
+	dput(child);
+	return ERR_PTR(error);
+}
+EXPORT_SYMBOL(vfs_tmpfile);
+
 static int do_tmpfile(struct nameidata *nd, unsigned flags,
 		const struct open_flags *op,
 		struct file *file, int *opened)
 {
-	static const struct qstr name = QSTR_INIT("/", 1);
 	struct dentry *child;
-	struct inode *dir;
 	struct path path;
 	int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path);
 	if (unlikely(error))
@@ -3367,25 +3404,12 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 	error = mnt_want_write(path.mnt);
 	if (unlikely(error))
 		goto out;
-	dir = path.dentry->d_inode;
-	/* we want directory to be writable */
-	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
-	if (error)
-		goto out2;
-	if (!dir->i_op->tmpfile) {
-		error = -EOPNOTSUPP;
-		goto out2;
-	}
-	child = d_alloc(path.dentry, &name);
-	if (unlikely(!child)) {
-		error = -ENOMEM;
+	child = vfs_tmpfile(path.dentry, op->mode, op->open_flag);
+	error = PTR_ERR(child);
+	if (unlikely(IS_ERR(child)))
 		goto out2;
-	}
 	dput(path.dentry);
 	path.dentry = child;
-	error = dir->i_op->tmpfile(dir, child, op->mode);
-	if (error)
-		goto out2;
 	audit_inode(nd->name, child, 0);
 	/* Don't check for other permissions, the inode was just created */
 	error = may_open(&path, 0, op->open_flag);
@@ -3396,14 +3420,8 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 	if (error)
 		goto out2;
 	error = open_check_o_direct(file);
-	if (error) {
+	if (error)
 		fput(file);
-	} else if (!(op->open_flag & O_EXCL)) {
-		struct inode *inode = file_inode(file);
-		spin_lock(&inode->i_lock);
-		inode->i_state |= I_LINKABLE;
-		spin_unlock(&inode->i_lock);
-	}
 out2:
 	mnt_drop_write(path.mnt);
 out:
diff --git a/fs/open.c b/fs/open.c
index 9921f70bc5ca..949cef29c3bb 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -301,12 +301,10 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (S_ISFIFO(inode->i_mode))
 		return -ESPIPE;
 
-	/*
-	 * Let individual file system decide if it supports preallocation
-	 * for directories or not.
-	 */
-	if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode) &&
-	    !S_ISBLK(inode->i_mode))
+	if (S_ISDIR(inode->i_mode))
+		return -EISDIR;
+
+	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
 		return -ENODEV;
 
 	/* Check for wrap through zero too */
@@ -316,7 +314,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (!file->f_op->fallocate)
 		return -EOPNOTSUPP;
 
-	sb_start_write(inode->i_sb);
+	file_start_write(file);
 	ret = file->f_op->fallocate(file, mode, offset, len);
 
 	/*
@@ -329,7 +327,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (ret == 0)
 		fsnotify_modify(file);
 
-	sb_end_write(inode->i_sb);
+	file_end_write(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(vfs_fallocate);
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index f57043dace62..48eb8812ac5b 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -20,6 +20,7 @@
 #include <linux/fdtable.h>
 #include <linux/ratelimit.h>
 #include "overlayfs.h"
+#include "ovl_entry.h"
 
 #define OVL_COPY_UP_CHUNK_SIZE (1 << 20)
 
@@ -232,12 +233,14 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
 
 static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 			      struct dentry *dentry, struct path *lowerpath,
-			      struct kstat *stat, const char *link)
+			      struct kstat *stat, const char *link,
+			      struct kstat *pstat, bool tmpfile)
 {
 	struct inode *wdir = workdir->d_inode;
 	struct inode *udir = upperdir->d_inode;
 	struct dentry *newdentry = NULL;
 	struct dentry *upper = NULL;
+	struct dentry *temp = NULL;
 	int err;
 	const struct cred *old_creds = NULL;
 	struct cred *new_creds = NULL;
@@ -248,25 +251,30 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 		.link = link
 	};
 
-	newdentry = ovl_lookup_temp(workdir, dentry);
-	err = PTR_ERR(newdentry);
-	if (IS_ERR(newdentry))
-		goto out;
-
 	upper = lookup_one_len(dentry->d_name.name, upperdir,
 			       dentry->d_name.len);
 	err = PTR_ERR(upper);
 	if (IS_ERR(upper))
-		goto out1;
+		goto out;
 
 	err = security_inode_copy_up(dentry, &new_creds);
 	if (err < 0)
-		goto out2;
+		goto out1;
 
 	if (new_creds)
 		old_creds = override_creds(new_creds);
 
-	err = ovl_create_real(wdir, newdentry, &cattr, NULL, true);
+	if (tmpfile)
+		temp = ovl_do_tmpfile(upperdir, stat->mode);
+	else
+		temp = ovl_lookup_temp(workdir, dentry);
+	err = PTR_ERR(temp);
+	if (IS_ERR(temp))
+		goto out1;
+
+	err = 0;
+	if (!tmpfile)
+		err = ovl_create_real(wdir, temp, &cattr, NULL, true);
 
 	if (new_creds) {
 		revert_creds(old_creds);
@@ -281,39 +289,55 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 
 		ovl_path_upper(dentry, &upperpath);
 		BUG_ON(upperpath.dentry != NULL);
-		upperpath.dentry = newdentry;
+		upperpath.dentry = temp;
+
+		if (tmpfile) {
+			inode_unlock(udir);
+			err = ovl_copy_up_data(lowerpath, &upperpath,
+					       stat->size);
+			inode_lock_nested(udir, I_MUTEX_PARENT);
+		} else {
+			err = ovl_copy_up_data(lowerpath, &upperpath,
+					       stat->size);
+		}
 
-		err = ovl_copy_up_data(lowerpath, &upperpath, stat->size);
 		if (err)
 			goto out_cleanup;
 	}
 
-	err = ovl_copy_xattr(lowerpath->dentry, newdentry);
+	err = ovl_copy_xattr(lowerpath->dentry, temp);
 	if (err)
 		goto out_cleanup;
 
-	inode_lock(newdentry->d_inode);
-	err = ovl_set_attr(newdentry, stat);
-	inode_unlock(newdentry->d_inode);
+	inode_lock(temp->d_inode);
+	err = ovl_set_attr(temp, stat);
+	inode_unlock(temp->d_inode);
 	if (err)
 		goto out_cleanup;
 
-	err = ovl_do_rename(wdir, newdentry, udir, upper, 0);
+	if (tmpfile)
+		err = ovl_do_link(temp, udir, upper, true);
+	else
+		err = ovl_do_rename(wdir, temp, udir, upper, 0);
 	if (err)
 		goto out_cleanup;
 
+	newdentry = dget(tmpfile ? upper : temp);
 	ovl_dentry_update(dentry, newdentry);
 	ovl_inode_update(d_inode(dentry), d_inode(newdentry));
-	newdentry = NULL;
+
+	/* Restore timestamps on parent (best effort) */
+	ovl_set_timestamps(upperdir, pstat);
 out2:
-	dput(upper);
+	dput(temp);
 out1:
-	dput(newdentry);
+	dput(upper);
 out:
 	return err;
 
 out_cleanup:
-	ovl_cleanup(wdir, newdentry);
+	if (!tmpfile)
+		ovl_cleanup(wdir, temp);
 	goto out2;
 }
 
@@ -337,6 +361,7 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	struct dentry *lowerdentry = lowerpath->dentry;
 	struct dentry *upperdir;
 	const char *link = NULL;
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
 
 	if (WARN_ON(!workdir))
 		return -EROFS;
@@ -356,6 +381,25 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 			return PTR_ERR(link);
 	}
 
+	/* Should we copyup with O_TMPFILE or with workdir? */
+	if (S_ISREG(stat->mode) && ofs->tmpfile) {
+		err = ovl_copy_up_start(dentry);
+		/* err < 0: interrupted, err > 0: raced with another copy-up */
+		if (unlikely(err)) {
+			pr_debug("ovl_copy_up_start(%pd2) = %i\n", dentry, err);
+			if (err > 0)
+				err = 0;
+			goto out_done;
+		}
+
+		inode_lock_nested(upperdir->d_inode, I_MUTEX_PARENT);
+		err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath,
+					 stat, link, &pstat, true);
+		inode_unlock(upperdir->d_inode);
+		ovl_copy_up_end(dentry);
+		goto out_done;
+	}
+
 	err = -EIO;
 	if (lock_rename(workdir, upperdir) != NULL) {
 		pr_err("overlayfs: failed to lock workdir+upperdir\n");
@@ -368,13 +412,10 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	}
 
 	err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath,
-				 stat, link);
-	if (!err) {
-		/* Restore timestamps on parent (best effort) */
-		ovl_set_timestamps(upperdir, &pstat);
-	}
+				 stat, link, &pstat, false);
 out_unlock:
 	unlock_rename(workdir, upperdir);
+out_done:
 	do_delayed_call(&done);
 
 	return err;
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 8af450b0e57a..741dc0b6931f 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -127,6 +127,15 @@ static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry)
 	return err;
 }
 
+static inline struct dentry *ovl_do_tmpfile(struct dentry *dentry, umode_t mode)
+{
+	struct dentry *ret = vfs_tmpfile(dentry, mode, 0);
+	int err = IS_ERR(ret) ? PTR_ERR(ret) : 0;
+
+	pr_debug("tmpfile(%pd2, 0%o) = %i\n", dentry, mode, err);
+	return ret;
+}
+
 static inline struct inode *ovl_inode_real(struct inode *inode, bool *is_upper)
 {
 	unsigned long x = (unsigned long) READ_ONCE(inode->i_private);
@@ -169,6 +178,8 @@ void ovl_dentry_version_inc(struct dentry *dentry);
 u64 ovl_dentry_version_get(struct dentry *dentry);
 bool ovl_is_whiteout(struct dentry *dentry);
 struct file *ovl_path_open(struct path *path, int flags);
+int ovl_copy_up_start(struct dentry *dentry);
+void ovl_copy_up_end(struct dentry *dentry);
 
 /* namei.c */
 int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index d14bca1850d9..59614faa14c3 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -27,6 +27,8 @@ struct ovl_fs {
 	struct ovl_config config;
 	/* creds of process who forced instantiation of super block */
 	const struct cred *creator_cred;
+	bool tmpfile;
+	wait_queue_head_t copyup_wq;
 };
 
 /* private information held for every overlayfs dentry */
@@ -38,6 +40,7 @@ struct ovl_entry {
 			u64 version;
 			const char *redirect;
 			bool opaque;
+			bool copying;
 		};
 		struct rcu_head rcu;
 	};
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 20f48abbb82f..7b2188181367 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -160,6 +160,25 @@ static void ovl_put_super(struct super_block *sb)
 	kfree(ufs);
 }
 
+static int ovl_sync_fs(struct super_block *sb, int wait)
+{
+	struct ovl_fs *ufs = sb->s_fs_info;
+	struct super_block *upper_sb;
+	int ret;
+
+	if (!ufs->upper_mnt)
+		return 0;
+	upper_sb = ufs->upper_mnt->mnt_sb;
+	if (!upper_sb->s_op->sync_fs)
+		return 0;
+
+	/* real inodes have already been synced by sync_filesystem(ovl_sb) */
+	down_read(&upper_sb->s_umount);
+	ret = upper_sb->s_op->sync_fs(upper_sb, wait);
+	up_read(&upper_sb->s_umount);
+	return ret;
+}
+
 /**
  * ovl_statfs
  * @sb: The overlayfs super block
@@ -222,6 +241,7 @@ static int ovl_remount(struct super_block *sb, int *flags, char *data)
 
 static const struct super_operations ovl_super_operations = {
 	.put_super	= ovl_put_super,
+	.sync_fs	= ovl_sync_fs,
 	.statfs		= ovl_statfs,
 	.show_options	= ovl_show_options,
 	.remount_fs	= ovl_remount,
@@ -701,6 +721,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	unsigned int stacklen = 0;
 	unsigned int i;
 	bool remote = false;
+	struct cred *cred;
 	int err;
 
 	err = -ENOMEM;
@@ -708,6 +729,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	if (!ufs)
 		goto out;
 
+	init_waitqueue_head(&ufs->copyup_wq);
 	ufs->config.redirect_dir = ovl_redirect_dir_def;
 	err = ovl_parse_opt((char *) data, &ufs->config);
 	if (err)
@@ -825,6 +847,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		 * creation of workdir in previous step.
 		 */
 		if (ufs->workdir) {
+			struct dentry *temp;
+
 			err = ovl_check_d_type_supported(&workpath);
 			if (err < 0)
 				goto out_put_workdir;
@@ -836,6 +860,14 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 			 */
 			if (!err)
 				pr_warn("overlayfs: upper fs needs to support d_type.\n");
+
+			/* Check if upper/work fs supports O_TMPFILE */
+			temp = ovl_do_tmpfile(ufs->workdir, S_IFREG | 0);
+			ufs->tmpfile = !IS_ERR(temp);
+			if (ufs->tmpfile)
+				dput(temp);
+			else
+				pr_warn("overlayfs: upper fs does not support tmpfile.\n");
 		}
 	}
 
@@ -870,10 +902,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	else
 		sb->s_d_op = &ovl_dentry_operations;
 
-	ufs->creator_cred = prepare_creds();
-	if (!ufs->creator_cred)
+	ufs->creator_cred = cred = prepare_creds();
+	if (!cred)
 		goto out_put_lower_mnt;
 
+	/* Never override disk quota limits or use reserved space */
+	cap_lower(cred->cap_effective, CAP_SYS_RESOURCE);
+
 	err = -ENOMEM;
 	oe = ovl_alloc_entry(numlower);
 	if (!oe)
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 952286f4826c..01157d6e8cfe 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -263,3 +263,33 @@ struct file *ovl_path_open(struct path *path, int flags)
 {
 	return dentry_open(path, flags | O_NOATIME, current_cred());
 }
+
+int ovl_copy_up_start(struct dentry *dentry)
+{
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	struct ovl_entry *oe = dentry->d_fsdata;
+	int err;
+
+	spin_lock(&ofs->copyup_wq.lock);
+	err = wait_event_interruptible_locked(ofs->copyup_wq, !oe->copying);
+	if (!err) {
+		if (oe->__upperdentry)
+			err = 1; /* Already copied up */
+		else
+			oe->copying = true;
+	}
+	spin_unlock(&ofs->copyup_wq.lock);
+
+	return err;
+}
+
+void ovl_copy_up_end(struct dentry *dentry)
+{
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	spin_lock(&ofs->copyup_wq.lock);
+	oe->copying = false;
+	wake_up_locked(&ofs->copyup_wq);
+	spin_unlock(&ofs->copyup_wq.lock);
+}
diff --git a/fs/read_write.c b/fs/read_write.c
index 5816d4c4cab0..820a3f06c46a 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1518,6 +1518,11 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (flags != 0)
 		return -EINVAL;
 
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
 	ret = rw_verify_area(READ, file_in, &pos_in, len);
 	if (unlikely(ret))
 		return ret;
@@ -1538,7 +1543,7 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (len == 0)
 		return 0;
 
-	sb_start_write(inode_out->i_sb);
+	file_start_write(file_out);
 
 	/*
 	 * Try cloning first, this is supported by more file systems, and
@@ -1574,7 +1579,7 @@ done:
 	inc_syscr(current);
 	inc_syscw(current);
 
-	sb_end_write(inode_out->i_sb);
+	file_end_write(file_out);
 
 	return ret;
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2ba074328894..78c81e6f5d76 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1561,6 +1561,9 @@ extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
 extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
 extern int vfs_whiteout(struct inode *, struct dentry *);
 
+extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode,
+				  int open_flag);
+
 /*
  * VFS file helper functions.
  */
@@ -1738,19 +1741,6 @@ extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 extern int vfs_dedupe_file_range(struct file *file,
 				 struct file_dedupe_range *same);
 
-static inline int do_clone_file_range(struct file *file_in, loff_t pos_in,
-				      struct file *file_out, loff_t pos_out,
-				      u64 len)
-{
-	int ret;
-
-	sb_start_write(file_inode(file_out)->i_sb);
-	ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len);
-	sb_end_write(file_inode(file_out)->i_sb);
-
-	return ret;
-}
-
 struct super_operations {
    	struct inode *(*alloc_inode)(struct super_block *sb);
 	void (*destroy_inode)(struct inode *);
@@ -2561,6 +2551,19 @@ static inline void file_end_write(struct file *file)
 	__sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE);
 }
 
+static inline int do_clone_file_range(struct file *file_in, loff_t pos_in,
+				      struct file *file_out, loff_t pos_out,
+				      u64 len)
+{
+	int ret;
+
+	file_start_write(file_out);
+	ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len);
+	file_end_write(file_out);
+
+	return ret;
+}
+
 /*
  * get_write_access() gets write permission for a file.
  * put_write_access() releases this write permission.