1 files changed, 107 insertions, 85 deletions

diff --git a/fs/open.c b/fs/open.c
index e6911101fe71..f328622061c5 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -60,18 +60,21 @@ int do_truncate(struct mnt_idmap *idmap, struct dentry *dentry,
 	if (ret)
 		newattrs.ia_valid |= ret | ATTR_FORCE;
 
-	inode_lock(dentry->d_inode);
+	ret = inode_lock_killable(dentry->d_inode);
+	if (ret)
+		return ret;
+
 	/* Note any delegations or leases have already been broken: */
 	ret = notify_change(idmap, dentry, &newattrs, NULL);
 	inode_unlock(dentry->d_inode);
 	return ret;
 }
 
-long vfs_truncate(const struct path *path, loff_t length)
+int vfs_truncate(const struct path *path, loff_t length)
 {
 	struct mnt_idmap *idmap;
 	struct inode *inode;
-	long error;
+	int error;
 
 	inode = path->dentry->d_inode;
 
@@ -81,14 +84,18 @@ long vfs_truncate(const struct path *path, loff_t length)
 	if (!S_ISREG(inode->i_mode))
 		return -EINVAL;
 
-	error = mnt_want_write(path->mnt);
-	if (error)
-		goto out;
-
 	idmap = mnt_idmap(path->mnt);
 	error = inode_permission(idmap, inode, MAY_WRITE);
 	if (error)
-		goto mnt_drop_write_and_out;
+		return error;
+
+	error = fsnotify_truncate_perm(path, length);
+	if (error)
+		return error;
+
+	error = mnt_want_write(path->mnt);
+	if (error)
+		return error;
 
 	error = -EPERM;
 	if (IS_APPEND(inode))
@@ -114,12 +121,12 @@ put_write_and_out:
 	put_write_access(inode);
 mnt_drop_write_and_out:
 	mnt_drop_write(path->mnt);
-out:
+
 	return error;
 }
 EXPORT_SYMBOL_GPL(vfs_truncate);
 
-long do_sys_truncate(const char __user *pathname, loff_t length)
+int do_sys_truncate(const char __user *pathname, loff_t length)
 {
 	unsigned int lookup_flags = LOOKUP_FOLLOW;
 	struct path path;
@@ -153,7 +160,7 @@ COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length
 }
 #endif
 
-long do_ftruncate(struct file *file, loff_t length, int small)
+int do_ftruncate(struct file *file, loff_t length, int small)
 {
 	struct inode *inode;
 	struct dentry *dentry;
@@ -175,17 +182,21 @@ long do_ftruncate(struct file *file, loff_t length, int small)
 	/* Check IS_APPEND on real upper inode */
 	if (IS_APPEND(file_inode(file)))
 		return -EPERM;
-	sb_start_write(inode->i_sb);
+
 	error = security_file_truncate(file);
-	if (!error)
-		error = do_truncate(file_mnt_idmap(file), dentry, length,
-				    ATTR_MTIME | ATTR_CTIME, file);
-	sb_end_write(inode->i_sb);
+	if (error)
+		return error;
 
-	return error;
+	error = fsnotify_truncate_perm(&file->f_path, length);
+	if (error)
+		return error;
+
+	scoped_guard(super_write, inode->i_sb)
+		return do_truncate(file_mnt_idmap(file), dentry, length,
+				   ATTR_MTIME | ATTR_CTIME, file);
 }
 
-long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
+int do_sys_ftruncate(unsigned int fd, loff_t length, int small)
 {
 	if (length < 0)
 		return -EINVAL;
@@ -240,7 +251,7 @@ COMPAT_SYSCALL_DEFINE3(ftruncate64, unsigned int, fd,
 int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 {
 	struct inode *inode = file_inode(file);
-	long ret;
+	int ret;
 	loff_t sum;
 
 	if (offset < 0 || len <= 0)
@@ -267,6 +278,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		break;
 	case FALLOC_FL_COLLAPSE_RANGE:
 	case FALLOC_FL_INSERT_RANGE:
+	case FALLOC_FL_WRITE_ZEROES:
 		if (mode & FALLOC_FL_KEEP_SIZE)
 			return -EOPNOTSUPP;
 		break;
@@ -402,7 +414,6 @@ static bool access_need_override_creds(int flags)
 
 static const struct cred *access_override_creds(void)
 {
-	const struct cred *old_cred;
 	struct cred *override_cred;
 
 	override_cred = prepare_creds();
@@ -447,16 +458,10 @@ static const struct cred *access_override_creds(void)
 	 * freeing.
 	 */
 	override_cred->non_rcu = 1;
-
-	old_cred = override_creds(override_cred);
-
-	/* override_cred() gets its own ref */
-	put_cred(override_cred);
-
-	return old_cred;
+	return override_creds(override_cred);
 }
 
-static long do_faccessat(int dfd, const char __user *filename, int mode, int flags)
+static int do_faccessat(int dfd, const char __user *filename, int mode, int flags)
 {
 	struct path path;
 	struct inode *inode;
@@ -523,7 +528,7 @@ out_path_release:
 	}
 out:
 	if (old_cred)
-		revert_creds(old_cred);
+		put_cred(revert_creds(old_cred));
 
 	return res;
 }
@@ -623,7 +628,7 @@ out:
 int chmod_common(const struct path *path, umode_t mode)
 {
 	struct inode *inode = path->dentry->d_inode;
-	struct inode *delegated_inode = NULL;
+	struct delegated_inode delegated_inode = { };
 	struct iattr newattrs;
 	int error;
 
@@ -631,7 +636,9 @@ int chmod_common(const struct path *path, umode_t mode)
 	if (error)
 		return error;
 retry_deleg:
-	inode_lock(inode);
+	error = inode_lock_killable(inode);
+	if (error)
+		goto out_mnt_unlock;
 	error = security_path_chmod(path, mode);
 	if (error)
 		goto out_unlock;
@@ -641,11 +648,12 @@ retry_deleg:
 			      &newattrs, &delegated_inode);
 out_unlock:
 	inode_unlock(inode);
-	if (delegated_inode) {
+	if (is_delegated(&delegated_inode)) {
 		error = break_deleg_wait(&delegated_inode);
 		if (!error)
 			goto retry_deleg;
 	}
+out_mnt_unlock:
 	mnt_drop_write(path->mnt);
 	return error;
 }
@@ -745,7 +753,7 @@ int chown_common(const struct path *path, uid_t user, gid_t group)
 	struct mnt_idmap *idmap;
 	struct user_namespace *fs_userns;
 	struct inode *inode = path->dentry->d_inode;
-	struct inode *delegated_inode = NULL;
+	struct delegated_inode delegated_inode = { };
 	int error;
 	struct iattr newattrs;
 	kuid_t uid;
@@ -765,7 +773,9 @@ retry_deleg:
 		return -EINVAL;
 	if ((group != (gid_t)-1) && !setattr_vfsgid(&newattrs, gid))
 		return -EINVAL;
-	inode_lock(inode);
+	error = inode_lock_killable(inode);
+	if (error)
+		return error;
 	if (!S_ISDIR(inode->i_mode))
 		newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV |
 				     setattr_should_drop_sgid(idmap, inode);
@@ -778,7 +788,7 @@ retry_deleg:
 		error = notify_change(idmap, path->dentry, &newattrs,
 				      &delegated_inode);
 	inode_unlock(inode);
-	if (delegated_inode) {
+	if (is_delegated(&delegated_inode)) {
 		error = break_deleg_wait(&delegated_inode);
 		if (!error)
 			goto retry_deleg;
@@ -902,6 +912,7 @@ static int do_dentry_open(struct file *f,
 
 	if (unlikely(f->f_flags & O_PATH)) {
 		f->f_mode = FMODE_PATH | FMODE_OPENED;
+		file_set_fsnotify_mode(f, FMODE_NONOTIFY);
 		f->f_op = &empty_fops;
 		return 0;
 	}
@@ -926,15 +937,21 @@ static int do_dentry_open(struct file *f,
 	}
 
 	error = security_file_open(f);
-	if (error)
+	if (unlikely(error))
 		goto cleanup_all;
 
-	error = fsnotify_open_perm(f);
-	if (error)
+	/*
+	 * Call fsnotify open permission hook and set FMODE_NONOTIFY_* bits
+	 * according to existing permission watches.
+	 * If FMODE_NONOTIFY mode was already set for an fanotify fd or for a
+	 * pseudo file, this call will not change the mode.
+	 */
+	error = fsnotify_open_perm_and_set_mode(f);
+	if (unlikely(error))
 		goto cleanup_all;
 
 	error = break_lease(file_inode(f), f->f_flags);
-	if (error)
+	if (unlikely(error))
 		goto cleanup_all;
 
 	/* normally all 3 are set; ->open() can clear them if needed */
@@ -1002,8 +1019,8 @@ cleanup_all:
 	put_file_access(f);
 cleanup_file:
 	path_put(&f->f_path);
-	f->f_path.mnt = NULL;
-	f->f_path.dentry = NULL;
+	f->__f_path.mnt = NULL;
+	f->__f_path.dentry = NULL;
 	f->f_inode = NULL;
 	return error;
 }
@@ -1030,7 +1047,7 @@ int finish_open(struct file *file, struct dentry *dentry,
 {
 	BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */
 
-	file->f_path.dentry = dentry;
+	file->__f_path.dentry = dentry;
 	return do_dentry_open(file, open);
 }
 EXPORT_SYMBOL(finish_open);
@@ -1039,19 +1056,21 @@ EXPORT_SYMBOL(finish_open);
  * finish_no_open - finish ->atomic_open() without opening the file
  *
  * @file: file pointer
- * @dentry: dentry or NULL (as returned from ->lookup())
+ * @dentry: dentry, ERR_PTR(-E...) or NULL (as returned from ->lookup())
  *
- * This can be used to set the result of a successful lookup in ->atomic_open().
+ * This can be used to set the result of a lookup in ->atomic_open().
  *
  * NB: unlike finish_open() this function does consume the dentry reference and
  * the caller need not dput() it.
  *
- * Returns "0" which must be the return value of ->atomic_open() after having
- * called this function.
+ * Returns 0 or -E..., which must be the return value of ->atomic_open() after
+ * having called this function.
  */
 int finish_no_open(struct file *file, struct dentry *dentry)
 {
-	file->f_path.dentry = dentry;
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+	file->__f_path.dentry = dentry;
 	return 0;
 }
 EXPORT_SYMBOL(finish_no_open);
@@ -1071,7 +1090,7 @@ int vfs_open(const struct path *path, struct file *file)
 {
 	int ret;
 
-	file->f_path = *path;
+	file->__f_path = *path;
 	ret = do_dentry_open(file, NULL);
 	if (!ret) {
 		/*
@@ -1105,6 +1124,23 @@ struct file *dentry_open(const struct path *path, int flags,
 }
 EXPORT_SYMBOL(dentry_open);
 
+struct file *dentry_open_nonotify(const struct path *path, int flags,
+				  const struct cred *cred)
+{
+	struct file *f = alloc_empty_file(flags, cred);
+	if (!IS_ERR(f)) {
+		int error;
+
+		file_set_fsnotify_mode(f, FMODE_NONOTIFY);
+		error = vfs_open(path, f);
+		if (error) {
+			fput(f);
+			f = ERR_PTR(error);
+		}
+	}
+	return f;
+}
+
 /**
  * dentry_create - Create and open a file
  * @path: path to create
@@ -1132,9 +1168,7 @@ struct file *dentry_create(const struct path *path, int flags, umode_t mode,
 	if (IS_ERR(f))
 		return f;
 
-	error = vfs_create(mnt_idmap(path->mnt),
-			   d_inode(path->dentry->d_parent),
-			   path->dentry, mode, true);
+	error = vfs_create(mnt_idmap(path->mnt), path->dentry, mode, NULL);
 	if (!error)
 		error = vfs_open(path, f);
 
@@ -1168,14 +1202,11 @@ struct file *kernel_file_open(const struct path *path, int flags,
 	if (IS_ERR(f))
 		return f;
 
-	f->f_path = *path;
-	error = do_dentry_open(f, NULL);
+	error = vfs_open(path, f);
 	if (error) {
 		fput(f);
 		return ERR_PTR(error);
 	}
-
-	fsnotify_open(f);
 	return f;
 }
 EXPORT_SYMBOL_GPL(kernel_file_open);
@@ -1202,7 +1233,7 @@ inline struct open_how build_open_how(int flags, umode_t mode)
 inline int build_open_flags(const struct open_how *how, struct open_flags *op)
 {
 	u64 flags = how->flags;
-	u64 strip = __FMODE_NONOTIFY | O_CLOEXEC;
+	u64 strip = O_CLOEXEC;
 	int lookup_flags = 0;
 	int acc_mode = ACC_MODE(flags);
 
@@ -1210,9 +1241,7 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op)
 			 "struct open_flags doesn't yet handle flags > 32 bits");
 
 	/*
-	 * Strip flags that either shouldn't be set by userspace like
-	 * FMODE_NONOTIFY or that aren't relevant in determining struct
-	 * open_flags like O_CLOEXEC.
+	 * Strip flags that aren't relevant in determining struct open_flags.
 	 */
 	flags &= ~strip;
 
@@ -1383,35 +1412,25 @@ struct file *file_open_root(const struct path *root,
 }
 EXPORT_SYMBOL(file_open_root);
 
-static long do_sys_openat2(int dfd, const char __user *filename,
-			   struct open_how *how)
+static int do_sys_openat2(int dfd, const char __user *filename,
+			  struct open_how *how)
 {
 	struct open_flags op;
-	int fd = build_open_flags(how, &op);
-	struct filename *tmp;
+	struct filename *tmp __free(putname) = NULL;
+	int err;
 
-	if (fd)
-		return fd;
+	err = build_open_flags(how, &op);
+	if (unlikely(err))
+		return err;
 
 	tmp = getname(filename);
 	if (IS_ERR(tmp))
 		return PTR_ERR(tmp);
 
-	fd = get_unused_fd_flags(how->flags);
-	if (fd >= 0) {
-		struct file *f = do_filp_open(dfd, tmp, &op);
-		if (IS_ERR(f)) {
-			put_unused_fd(fd);
-			fd = PTR_ERR(f);
-		} else {
-			fd_install(fd, f);
-		}
-	}
-	putname(tmp);
-	return fd;
+	return FD_ADD(how->flags, do_filp_open(dfd, tmp, &op));
 }
 
-long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
+int do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
 {
 	struct open_how how = build_open_how(flags, mode);
 	return do_sys_openat2(dfd, filename, &how);
@@ -1504,7 +1523,7 @@ static int filp_flush(struct file *filp, fl_owner_t id)
 {
 	int retval = 0;
 
-	if (CHECK_DATA_CORRUPTION(file_count(filp) == 0,
+	if (CHECK_DATA_CORRUPTION(file_count(filp) == 0, filp,
 			"VFS: Close: file count is 0 (f_op=%ps)",
 			filp->f_op)) {
 		return 0;
@@ -1525,7 +1544,7 @@ int filp_close(struct file *filp, fl_owner_t id)
 	int retval;
 
 	retval = filp_flush(filp, id);
-	fput(filp);
+	fput_close(filp);
 
 	return retval;
 }
@@ -1551,13 +1570,16 @@ SYSCALL_DEFINE1(close, unsigned int, fd)
 	 * We're returning to user space. Don't bother
 	 * with any delayed fput() cases.
 	 */
-	__fput_sync(file);
+	fput_close_sync(file);
+
+	if (likely(retval == 0))
+		return 0;
 
 	/* can't restart close syscall because file table entry was cleared */
-	if (unlikely(retval == -ERESTARTSYS ||
-		     retval == -ERESTARTNOINTR ||
-		     retval == -ERESTARTNOHAND ||
-		     retval == -ERESTART_RESTARTBLOCK))
+	if (retval == -ERESTARTSYS ||
+	    retval == -ERESTARTNOINTR ||
+	    retval == -ERESTARTNOHAND ||
+	    retval == -ERESTART_RESTARTBLOCK)
 		retval = -EINTR;
 
 	return retval;