New kind of open files - "location only".

New flag for open(2) - O_PATH.  Semantics:
	* pathname is resolved, but the file itself is _NOT_ opened
as far as filesystem is concerned.
	* almost all operations on the resulting descriptors shall
fail with -EBADF.  Exceptions are:
	1) operations on descriptors themselves (i.e.
		close(), dup(), dup2(), dup3(), fcntl(fd, F_DUPFD),
		fcntl(fd, F_DUPFD_CLOEXEC, ...), fcntl(fd, F_GETFD),
		fcntl(fd, F_SETFD, ...))
	2) fcntl(fd, F_GETFL), for a common non-destructive way to
		check if descriptor is open
	3) "dfd" arguments of ...at(2) syscalls, i.e. the starting
		points of pathname resolution
	* closing such descriptor does *NOT* affect dnotify or
posix locks.
	* permissions are checked as usual along the way to file;
no permission checks are applied to the file itself.  Of course,
giving such thing to syscall will result in permission checks (at
the moment it means checking that starting point of ....at() is
a directory and caller has exec permissions on it).

fget() and fget_light() return NULL on such descriptors; use of
fget_raw() and fget_raw_light() is needed to get them.  That protects
existing code from dealing with those things.

There are two things still missing (they come in the next commits):
one is handling of symlinks (right now we refuse to open them that
way; see the next commit for semantics related to those) and another
is descriptor passing via SCM_RIGHTS datagrams.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 48 insertions, 5 deletions

diff --git a/fs/file_table.c b/fs/file_table.c
index eb36b6b17e2..3c16e1ca163 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -276,11 +276,10 @@ struct file *fget(unsigned int fd)
 	rcu_read_lock();
 	file = fcheck_files(files, fd);
 	if (file) {
-		if (!atomic_long_inc_not_zero(&file->f_count)) {
-			/* File object ref couldn't be taken */
-			rcu_read_unlock();
-			return NULL;
-		}
+		/* File object ref couldn't be taken */
+		if (file->f_mode & FMODE_PATH ||
+		    !atomic_long_inc_not_zero(&file->f_count))
+			file = NULL;
 	}
 	rcu_read_unlock();
 
@@ -289,6 +288,23 @@ struct file *fget(unsigned int fd)
 
 EXPORT_SYMBOL(fget);
 
+struct file *fget_raw(unsigned int fd)
+{
+	struct file *file;
+	struct files_struct *files = current->files;
+
+	rcu_read_lock();
+	file = fcheck_files(files, fd);
+	if (file) {
+		/* File object ref couldn't be taken */
+		if (!atomic_long_inc_not_zero(&file->f_count))
+			file = NULL;
+	}
+	rcu_read_unlock();
+
+	return file;
+}
+
 /*
  * Lightweight file lookup - no refcnt increment if fd table isn't shared.
  *
@@ -313,6 +329,33 @@ struct file *fget_light(unsigned int fd, int *fput_needed)
 	*fput_needed = 0;
 	if (atomic_read(&files->count) == 1) {
 		file = fcheck_files(files, fd);
+		if (file && (file->f_mode & FMODE_PATH))
+			file = NULL;
+	} else {
+		rcu_read_lock();
+		file = fcheck_files(files, fd);
+		if (file) {
+			if (!(file->f_mode & FMODE_PATH) &&
+			    atomic_long_inc_not_zero(&file->f_count))
+				*fput_needed = 1;
+			else
+				/* Didn't get the reference, someone's freed */
+				file = NULL;
+		}
+		rcu_read_unlock();
+	}
+
+	return file;
+}
+
+struct file *fget_raw_light(unsigned int fd, int *fput_needed)
+{
+	struct file *file;
+	struct files_struct *files = current->files;
+
+	*fput_needed = 0;
+	if (atomic_read(&files->count) == 1) {
+		file = fcheck_files(files, fd);
 	} else {
 		rcu_read_lock();
 		file = fcheck_files(files, fd);