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>
diff --git a/fs/fcntl.c b/fs/fcntl.c
index cb10261..6c82e5b 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -131,7 +131,7 @@
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 @@
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 @@
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 @@
* 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",
diff --git a/fs/file_table.c b/fs/file_table.c
index eb36b6b..3c16e1c 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -276,11 +276,10 @@
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 @@
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 @@
*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);
diff --git a/fs/namei.c b/fs/namei.c
index 33be51a..e1d9f90 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1544,7 +1544,7 @@
} else {
struct dentry *dentry;
- file = fget_light(dfd, &fput_needed);
+ file = fget_raw_light(dfd, &fput_needed);
retval = -EBADF;
if (!file)
goto out_fail;
diff --git a/fs/open.c b/fs/open.c
index 48afc5c..14a51de 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -669,11 +669,16 @@
int (*open)(struct inode *, struct file *),
const struct cred *cred)
{
+ static const struct file_operations empty_fops = {};
struct inode *inode;
int error;
f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
FMODE_PREAD | FMODE_PWRITE;
+
+ if (unlikely(f->f_flags & O_PATH))
+ f->f_mode = FMODE_PATH;
+
inode = dentry->d_inode;
if (f->f_mode & FMODE_WRITE) {
error = __get_file_write_access(inode, mnt);
@@ -687,9 +692,15 @@
f->f_path.dentry = dentry;
f->f_path.mnt = mnt;
f->f_pos = 0;
- f->f_op = fops_get(inode->i_fop);
file_sb_list_add(f, inode->i_sb);
+ if (unlikely(f->f_mode & FMODE_PATH)) {
+ f->f_op = &empty_fops;
+ return f;
+ }
+
+ f->f_op = fops_get(inode->i_fop);
+
error = security_dentry_open(f, cred);
if (error)
goto cleanup_all;
@@ -911,9 +922,18 @@
if (flags & __O_SYNC)
flags |= O_DSYNC;
- op->open_flag = flags;
+ /*
+ * If we have O_PATH in the open flag. Then we
+ * cannot have anything other than the below set of flags
+ */
+ if (flags & O_PATH) {
+ flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH;
+ acc_mode = 0;
+ } else {
+ acc_mode = MAY_OPEN | ACC_MODE(flags);
+ }
- acc_mode = MAY_OPEN | ACC_MODE(flags);
+ op->open_flag = flags;
/* O_TRUNC implies we need access checks for write permissions */
if (flags & O_TRUNC)
@@ -926,7 +946,8 @@
op->acc_mode = acc_mode;
- op->intent = LOOKUP_OPEN;
+ op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN;
+
if (flags & O_CREAT) {
op->intent |= LOOKUP_CREATE;
if (flags & O_EXCL)
@@ -1053,8 +1074,10 @@
if (filp->f_op && filp->f_op->flush)
retval = filp->f_op->flush(filp, id);
- dnotify_flush(filp, id);
- locks_remove_posix(filp, id);
+ if (likely(!(filp->f_mode & FMODE_PATH))) {
+ dnotify_flush(filp, id);
+ locks_remove_posix(filp, id);
+ }
fput(filp);
return retval;
}