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, 32 insertions, 5 deletions

diff --git a/fs/fcntl.c b/fs/fcntl.c
index cb1026181bdc..6c82e5bac039 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -131,7 +131,7 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
 SYSCALL_DEFINE1(dup, unsigned int, fildes)
 {
 	int ret = -EBADF;
-	struct file *file = fget(fildes);
+	struct file *file = fget_raw(fildes);
 
 	if (file) {
 		ret = get_unused_fd();
@@ -426,15 +426,35 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	return err;
 }
 
+static int check_fcntl_cmd(unsigned cmd)
+{
+	switch (cmd) {
+	case F_DUPFD:
+	case F_DUPFD_CLOEXEC:
+	case F_GETFD:
+	case F_SETFD:
+	case F_GETFL:
+		return 1;
+	}
+	return 0;
+}
+
 SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
 {	
 	struct file *filp;
 	long err = -EBADF;
 
-	filp = fget(fd);
+	filp = fget_raw(fd);
 	if (!filp)
 		goto out;
 
+	if (unlikely(filp->f_mode & FMODE_PATH)) {
+		if (!check_fcntl_cmd(cmd)) {
+			fput(filp);
+			goto out;
+		}
+	}
+
 	err = security_file_fcntl(filp, cmd, arg);
 	if (err) {
 		fput(filp);
@@ -456,10 +476,17 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
 	long err;
 
 	err = -EBADF;
-	filp = fget(fd);
+	filp = fget_raw(fd);
 	if (!filp)
 		goto out;
 
+	if (unlikely(filp->f_mode & FMODE_PATH)) {
+		if (!check_fcntl_cmd(cmd)) {
+			fput(filp);
+			goto out;
+		}
+	}
+
 	err = security_file_fcntl(filp, cmd, arg);
 	if (err) {
 		fput(filp);
@@ -808,14 +835,14 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(18 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+	BUILD_BUG_ON(19 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
 		O_RDONLY	| O_WRONLY	| O_RDWR	|
 		O_CREAT		| O_EXCL	| O_NOCTTY	|
 		O_TRUNC		| O_APPEND	| /* O_NONBLOCK	| */
 		__O_SYNC	| O_DSYNC	| FASYNC	|
 		O_DIRECT	| O_LARGEFILE	| O_DIRECTORY	|
 		O_NOFOLLOW	| O_NOATIME	| O_CLOEXEC	|
-		__FMODE_EXEC
+		__FMODE_EXEC	| O_PATH
 		));
 
 	fasync_cache = kmem_cache_create("fasync_cache",