2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-24 13:13:57 +08:00
linux-next/fs/open.c
Kirill Smelkov 10dce8af34 fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock
Commit 9c225f2655 ("vfs: atomic f_pos accesses as per POSIX") added
locking for file.f_pos access and in particular made concurrent read and
write not possible - now both those functions take f_pos lock for the
whole run, and so if e.g. a read is blocked waiting for data, write will
deadlock waiting for that read to complete.

This caused regression for stream-like files where previously read and
write could run simultaneously, but after that patch could not do so
anymore. See e.g. commit 581d21a2d0 ("xenbus: fix deadlock on writes
to /proc/xen/xenbus") which fixes such regression for particular case of
/proc/xen/xenbus.

The patch that added f_pos lock in 2014 did so to guarantee POSIX thread
safety for read/write/lseek and added the locking to file descriptors of
all regular files. In 2014 that thread-safety problem was not new as it
was already discussed earlier in 2006.

However even though 2006'th version of Linus's patch was adding f_pos
locking "only for files that are marked seekable with FMODE_LSEEK (thus
avoiding the stream-like objects like pipes and sockets)", the 2014
version - the one that actually made it into the tree as 9c225f2655 -
is doing so irregardless of whether a file is seekable or not.

See

    https://lore.kernel.org/lkml/53022DB1.4070805@gmail.com/
    https://lwn.net/Articles/180387
    https://lwn.net/Articles/180396

for historic context.

The reason that it did so is, probably, that there are many files that
are marked non-seekable, but e.g. their read implementation actually
depends on knowing current position to correctly handle the read. Some
examples:

	kernel/power/user.c		snapshot_read
	fs/debugfs/file.c		u32_array_read
	fs/fuse/control.c		fuse_conn_waiting_read + ...
	drivers/hwmon/asus_atk0110.c	atk_debugfs_ggrp_read
	arch/s390/hypfs/inode.c		hypfs_read_iter
	...

Despite that, many nonseekable_open users implement read and write with
pure stream semantics - they don't depend on passed ppos at all. And for
those cases where read could wait for something inside, it creates a
situation similar to xenbus - the write could be never made to go until
read is done, and read is waiting for some, potentially external, event,
for potentially unbounded time -> deadlock.

Besides xenbus, there are 14 such places in the kernel that I've found
with semantic patch (see below):

	drivers/xen/evtchn.c:667:8-24: ERROR: evtchn_fops: .read() can deadlock .write()
	drivers/isdn/capi/capi.c:963:8-24: ERROR: capi_fops: .read() can deadlock .write()
	drivers/input/evdev.c:527:1-17: ERROR: evdev_fops: .read() can deadlock .write()
	drivers/char/pcmcia/cm4000_cs.c:1685:7-23: ERROR: cm4000_fops: .read() can deadlock .write()
	net/rfkill/core.c:1146:8-24: ERROR: rfkill_fops: .read() can deadlock .write()
	drivers/s390/char/fs3270.c:488:1-17: ERROR: fs3270_fops: .read() can deadlock .write()
	drivers/usb/misc/ldusb.c:310:1-17: ERROR: ld_usb_fops: .read() can deadlock .write()
	drivers/hid/uhid.c:635:1-17: ERROR: uhid_fops: .read() can deadlock .write()
	net/batman-adv/icmp_socket.c:80:1-17: ERROR: batadv_fops: .read() can deadlock .write()
	drivers/media/rc/lirc_dev.c:198:1-17: ERROR: lirc_fops: .read() can deadlock .write()
	drivers/leds/uleds.c:77:1-17: ERROR: uleds_fops: .read() can deadlock .write()
	drivers/input/misc/uinput.c:400:1-17: ERROR: uinput_fops: .read() can deadlock .write()
	drivers/infiniband/core/user_mad.c:985:7-23: ERROR: umad_fops: .read() can deadlock .write()
	drivers/gnss/core.c:45:1-17: ERROR: gnss_fops: .read() can deadlock .write()

In addition to the cases above another regression caused by f_pos
locking is that now FUSE filesystems that implement open with
FOPEN_NONSEEKABLE flag, can no longer implement bidirectional
stream-like files - for the same reason as above e.g. read can deadlock
write locking on file.f_pos in the kernel.

FUSE's FOPEN_NONSEEKABLE was added in 2008 in a7c1b990f7 ("fuse:
implement nonseekable open") to support OSSPD. OSSPD implements /dev/dsp
in userspace with FOPEN_NONSEEKABLE flag, with corresponding read and
write routines not depending on current position at all, and with both
read and write being potentially blocking operations:

See

    https://github.com/libfuse/osspd
    https://lwn.net/Articles/308445

    https://github.com/libfuse/osspd/blob/14a9cff0/osspd.c#L1406
    https://github.com/libfuse/osspd/blob/14a9cff0/osspd.c#L1438-L1477
    https://github.com/libfuse/osspd/blob/14a9cff0/osspd.c#L1479-L1510

Corresponding libfuse example/test also describes FOPEN_NONSEEKABLE as
"somewhat pipe-like files ..." with read handler not using offset.
However that test implements only read without write and cannot exercise
the deadlock scenario:

    https://github.com/libfuse/libfuse/blob/fuse-3.4.2-3-ga1bff7d/example/poll.c#L124-L131
    https://github.com/libfuse/libfuse/blob/fuse-3.4.2-3-ga1bff7d/example/poll.c#L146-L163
    https://github.com/libfuse/libfuse/blob/fuse-3.4.2-3-ga1bff7d/example/poll.c#L209-L216

I've actually hit the read vs write deadlock for real while implementing
my FUSE filesystem where there is /head/watch file, for which open
creates separate bidirectional socket-like stream in between filesystem
and its user with both read and write being later performed
simultaneously. And there it is semantically not easy to split the
stream into two separate read-only and write-only channels:

    https://lab.nexedi.com/kirr/wendelin.core/blob/f13aa600/wcfs/wcfs.go#L88-169

Let's fix this regression. The plan is:

1. We can't change nonseekable_open to include &~FMODE_ATOMIC_POS -
   doing so would break many in-kernel nonseekable_open users which
   actually use ppos in read/write handlers.

2. Add stream_open() to kernel to open stream-like non-seekable file
   descriptors. Read and write on such file descriptors would never use
   nor change ppos. And with that property on stream-like files read and
   write will be running without taking f_pos lock - i.e. read and write
   could be running simultaneously.

3. With semantic patch search and convert to stream_open all in-kernel
   nonseekable_open users for which read and write actually do not
   depend on ppos and where there is no other methods in file_operations
   which assume @offset access.

4. Add FOPEN_STREAM to fs/fuse/ and open in-kernel file-descriptors via
   steam_open if that bit is present in filesystem open reply.

   It was tempting to change fs/fuse/ open handler to use stream_open
   instead of nonseekable_open on just FOPEN_NONSEEKABLE flags, but
   grepping through Debian codesearch shows users of FOPEN_NONSEEKABLE,
   and in particular GVFS which actually uses offset in its read and
   write handlers

	https://codesearch.debian.net/search?q=-%3Enonseekable+%3D
	https://gitlab.gnome.org/GNOME/gvfs/blob/1.40.0-6-gcbc54396/client/gvfsfusedaemon.c#L1080
	https://gitlab.gnome.org/GNOME/gvfs/blob/1.40.0-6-gcbc54396/client/gvfsfusedaemon.c#L1247-1346
	https://gitlab.gnome.org/GNOME/gvfs/blob/1.40.0-6-gcbc54396/client/gvfsfusedaemon.c#L1399-1481

   so if we would do such a change it will break a real user.

5. Add stream_open and FOPEN_STREAM handling to stable kernels starting
   from v3.14+ (the kernel where 9c225f2655 first appeared).

   This will allow to patch OSSPD and other FUSE filesystems that
   provide stream-like files to return FOPEN_STREAM | FOPEN_NONSEEKABLE
   in their open handler and this way avoid the deadlock on all kernel
   versions. This should work because fs/fuse/ ignores unknown open
   flags returned from a filesystem and so passing FOPEN_STREAM to a
   kernel that is not aware of this flag cannot hurt. In turn the kernel
   that is not aware of FOPEN_STREAM will be < v3.14 where just
   FOPEN_NONSEEKABLE is sufficient to implement streams without read vs
   write deadlock.

This patch adds stream_open, converts /proc/xen/xenbus to it and adds
semantic patch to automatically locate in-kernel places that are either
required to be converted due to read vs write deadlock, or that are just
safe to be converted because read and write do not use ppos and there
are no other funky methods in file_operations.

Regarding semantic patch I've verified each generated change manually -
that it is correct to convert - and each other nonseekable_open instance
left - that it is either not correct to convert there, or that it is not
converted due to current stream_open.cocci limitations.

The script also does not convert files that should be valid to convert,
but that currently have .llseek = noop_llseek or generic_file_llseek for
unknown reason despite file being opened with nonseekable_open (e.g.
drivers/input/mousedev.c)

Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Yongzhi Pan <panyongzhi@gmail.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Tejun Heo <tj@kernel.org>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Julia Lawall <Julia.Lawall@lip6.fr>
Cc: Nikolaus Rath <Nikolaus@rath.org>
Cc: Han-Wen Nienhuys <hanwen@google.com>
Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-04-06 07:01:55 -10:00

1236 lines
29 KiB
C

/*
* linux/fs/open.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/fsnotify.h>
#include <linux/module.h>
#include <linux/tty.h>
#include <linux/namei.h>
#include <linux/backing-dev.h>
#include <linux/capability.h>
#include <linux/securebits.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/fcntl.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/fs.h>
#include <linux/personality.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/rcupdate.h>
#include <linux/audit.h>
#include <linux/falloc.h>
#include <linux/fs_struct.h>
#include <linux/ima.h>
#include <linux/dnotify.h>
#include <linux/compat.h>
#include "internal.h"
int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
struct file *filp)
{
int ret;
struct iattr newattrs;
/* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */
if (length < 0)
return -EINVAL;
newattrs.ia_size = length;
newattrs.ia_valid = ATTR_SIZE | time_attrs;
if (filp) {
newattrs.ia_file = filp;
newattrs.ia_valid |= ATTR_FILE;
}
/* Remove suid, sgid, and file capabilities on truncate too */
ret = dentry_needs_remove_privs(dentry);
if (ret < 0)
return ret;
if (ret)
newattrs.ia_valid |= ret | ATTR_FORCE;
inode_lock(dentry->d_inode);
/* Note any delegations or leases have already been broken: */
ret = notify_change(dentry, &newattrs, NULL);
inode_unlock(dentry->d_inode);
return ret;
}
long vfs_truncate(const struct path *path, loff_t length)
{
struct inode *inode;
long error;
inode = path->dentry->d_inode;
/* For directories it's -EISDIR, for other non-regulars - -EINVAL */
if (S_ISDIR(inode->i_mode))
return -EISDIR;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
error = mnt_want_write(path->mnt);
if (error)
goto out;
error = inode_permission(inode, MAY_WRITE);
if (error)
goto mnt_drop_write_and_out;
error = -EPERM;
if (IS_APPEND(inode))
goto mnt_drop_write_and_out;
error = get_write_access(inode);
if (error)
goto mnt_drop_write_and_out;
/*
* Make sure that there are no leases. get_write_access() protects
* against the truncate racing with a lease-granting setlease().
*/
error = break_lease(inode, O_WRONLY);
if (error)
goto put_write_and_out;
error = locks_verify_truncate(inode, NULL, length);
if (!error)
error = security_path_truncate(path);
if (!error)
error = do_truncate(path->dentry, length, 0, NULL);
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)
{
unsigned int lookup_flags = LOOKUP_FOLLOW;
struct path path;
int error;
if (length < 0) /* sorry, but loff_t says... */
return -EINVAL;
retry:
error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
if (!error) {
error = vfs_truncate(&path, length);
path_put(&path);
}
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
return error;
}
SYSCALL_DEFINE2(truncate, const char __user *, path, long, length)
{
return do_sys_truncate(path, length);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length)
{
return do_sys_truncate(path, length);
}
#endif
long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
{
struct inode *inode;
struct dentry *dentry;
struct fd f;
int error;
error = -EINVAL;
if (length < 0)
goto out;
error = -EBADF;
f = fdget(fd);
if (!f.file)
goto out;
/* explicitly opened as large or we are on 64-bit box */
if (f.file->f_flags & O_LARGEFILE)
small = 0;
dentry = f.file->f_path.dentry;
inode = dentry->d_inode;
error = -EINVAL;
if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE))
goto out_putf;
error = -EINVAL;
/* Cannot ftruncate over 2^31 bytes without large file support */
if (small && length > MAX_NON_LFS)
goto out_putf;
error = -EPERM;
/* Check IS_APPEND on real upper inode */
if (IS_APPEND(file_inode(f.file)))
goto out_putf;
sb_start_write(inode->i_sb);
error = locks_verify_truncate(inode, f.file, length);
if (!error)
error = security_path_truncate(&f.file->f_path);
if (!error)
error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, f.file);
sb_end_write(inode->i_sb);
out_putf:
fdput(f);
out:
return error;
}
SYSCALL_DEFINE2(ftruncate, unsigned int, fd, unsigned long, length)
{
return do_sys_ftruncate(fd, length, 1);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_ulong_t, length)
{
return do_sys_ftruncate(fd, length, 1);
}
#endif
/* LFS versions of truncate are only needed on 32 bit machines */
#if BITS_PER_LONG == 32
SYSCALL_DEFINE2(truncate64, const char __user *, path, loff_t, length)
{
return do_sys_truncate(path, length);
}
SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length)
{
return do_sys_ftruncate(fd, length, 0);
}
#endif /* BITS_PER_LONG == 32 */
int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
long ret;
if (offset < 0 || len <= 0)
return -EINVAL;
/* Return error if mode is not supported */
if (mode & ~FALLOC_FL_SUPPORTED_MASK)
return -EOPNOTSUPP;
/* Punch hole and zero range are mutually exclusive */
if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) ==
(FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE))
return -EOPNOTSUPP;
/* Punch hole must have keep size set */
if ((mode & FALLOC_FL_PUNCH_HOLE) &&
!(mode & FALLOC_FL_KEEP_SIZE))
return -EOPNOTSUPP;
/* Collapse range should only be used exclusively. */
if ((mode & FALLOC_FL_COLLAPSE_RANGE) &&
(mode & ~FALLOC_FL_COLLAPSE_RANGE))
return -EINVAL;
/* Insert range should only be used exclusively. */
if ((mode & FALLOC_FL_INSERT_RANGE) &&
(mode & ~FALLOC_FL_INSERT_RANGE))
return -EINVAL;
/* Unshare range should only be used with allocate mode. */
if ((mode & FALLOC_FL_UNSHARE_RANGE) &&
(mode & ~(FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_KEEP_SIZE)))
return -EINVAL;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
/*
* We can only allow pure fallocate on append only files
*/
if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode))
return -EPERM;
if (IS_IMMUTABLE(inode))
return -EPERM;
/*
* We cannot allow any fallocate operation on an active swapfile
*/
if (IS_SWAPFILE(inode))
return -ETXTBSY;
/*
* Revalidate the write permissions, in case security policy has
* changed since the files were opened.
*/
ret = security_file_permission(file, MAY_WRITE);
if (ret)
return ret;
if (S_ISFIFO(inode->i_mode))
return -ESPIPE;
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 */
if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
return -EFBIG;
if (!file->f_op->fallocate)
return -EOPNOTSUPP;
file_start_write(file);
ret = file->f_op->fallocate(file, mode, offset, len);
/*
* Create inotify and fanotify events.
*
* To keep the logic simple always create events if fallocate succeeds.
* This implies that events are even created if the file size remains
* unchanged, e.g. when using flag FALLOC_FL_KEEP_SIZE.
*/
if (ret == 0)
fsnotify_modify(file);
file_end_write(file);
return ret;
}
EXPORT_SYMBOL_GPL(vfs_fallocate);
int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len)
{
struct fd f = fdget(fd);
int error = -EBADF;
if (f.file) {
error = vfs_fallocate(f.file, mode, offset, len);
fdput(f);
}
return error;
}
SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len)
{
return ksys_fallocate(fd, mode, offset, len);
}
/*
* access() needs to use the real uid/gid, not the effective uid/gid.
* We do this by temporarily clearing all FS-related capabilities and
* switching the fsuid/fsgid around to the real ones.
*/
long do_faccessat(int dfd, const char __user *filename, int mode)
{
const struct cred *old_cred;
struct cred *override_cred;
struct path path;
struct inode *inode;
int res;
unsigned int lookup_flags = LOOKUP_FOLLOW;
if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */
return -EINVAL;
override_cred = prepare_creds();
if (!override_cred)
return -ENOMEM;
override_cred->fsuid = override_cred->uid;
override_cred->fsgid = override_cred->gid;
if (!issecure(SECURE_NO_SETUID_FIXUP)) {
/* Clear the capabilities if we switch to a non-root user */
kuid_t root_uid = make_kuid(override_cred->user_ns, 0);
if (!uid_eq(override_cred->uid, root_uid))
cap_clear(override_cred->cap_effective);
else
override_cred->cap_effective =
override_cred->cap_permitted;
}
old_cred = override_creds(override_cred);
retry:
res = user_path_at(dfd, filename, lookup_flags, &path);
if (res)
goto out;
inode = d_backing_inode(path.dentry);
if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) {
/*
* MAY_EXEC on regular files is denied if the fs is mounted
* with the "noexec" flag.
*/
res = -EACCES;
if (path_noexec(&path))
goto out_path_release;
}
res = inode_permission(inode, mode | MAY_ACCESS);
/* SuS v2 requires we report a read only fs too */
if (res || !(mode & S_IWOTH) || special_file(inode->i_mode))
goto out_path_release;
/*
* This is a rare case where using __mnt_is_readonly()
* is OK without a mnt_want/drop_write() pair. Since
* no actual write to the fs is performed here, we do
* not need to telegraph to that to anyone.
*
* By doing this, we accept that this access is
* inherently racy and know that the fs may change
* state before we even see this result.
*/
if (__mnt_is_readonly(path.mnt))
res = -EROFS;
out_path_release:
path_put(&path);
if (retry_estale(res, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
revert_creds(old_cred);
put_cred(override_cred);
return res;
}
SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
{
return do_faccessat(dfd, filename, mode);
}
SYSCALL_DEFINE2(access, const char __user *, filename, int, mode)
{
return do_faccessat(AT_FDCWD, filename, mode);
}
int ksys_chdir(const char __user *filename)
{
struct path path;
int error;
unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
retry:
error = user_path_at(AT_FDCWD, filename, lookup_flags, &path);
if (error)
goto out;
error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
if (error)
goto dput_and_out;
set_fs_pwd(current->fs, &path);
dput_and_out:
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
return error;
}
SYSCALL_DEFINE1(chdir, const char __user *, filename)
{
return ksys_chdir(filename);
}
SYSCALL_DEFINE1(fchdir, unsigned int, fd)
{
struct fd f = fdget_raw(fd);
int error;
error = -EBADF;
if (!f.file)
goto out;
error = -ENOTDIR;
if (!d_can_lookup(f.file->f_path.dentry))
goto out_putf;
error = inode_permission(file_inode(f.file), MAY_EXEC | MAY_CHDIR);
if (!error)
set_fs_pwd(current->fs, &f.file->f_path);
out_putf:
fdput(f);
out:
return error;
}
int ksys_chroot(const char __user *filename)
{
struct path path;
int error;
unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
retry:
error = user_path_at(AT_FDCWD, filename, lookup_flags, &path);
if (error)
goto out;
error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
if (error)
goto dput_and_out;
error = -EPERM;
if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT))
goto dput_and_out;
error = security_path_chroot(&path);
if (error)
goto dput_and_out;
set_fs_root(current->fs, &path);
error = 0;
dput_and_out:
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
return error;
}
SYSCALL_DEFINE1(chroot, const char __user *, filename)
{
return ksys_chroot(filename);
}
static int chmod_common(const struct path *path, umode_t mode)
{
struct inode *inode = path->dentry->d_inode;
struct inode *delegated_inode = NULL;
struct iattr newattrs;
int error;
error = mnt_want_write(path->mnt);
if (error)
return error;
retry_deleg:
inode_lock(inode);
error = security_path_chmod(path, mode);
if (error)
goto out_unlock;
newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
error = notify_change(path->dentry, &newattrs, &delegated_inode);
out_unlock:
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
mnt_drop_write(path->mnt);
return error;
}
int ksys_fchmod(unsigned int fd, umode_t mode)
{
struct fd f = fdget(fd);
int err = -EBADF;
if (f.file) {
audit_file(f.file);
err = chmod_common(&f.file->f_path, mode);
fdput(f);
}
return err;
}
SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
{
return ksys_fchmod(fd, mode);
}
int do_fchmodat(int dfd, const char __user *filename, umode_t mode)
{
struct path path;
int error;
unsigned int lookup_flags = LOOKUP_FOLLOW;
retry:
error = user_path_at(dfd, filename, lookup_flags, &path);
if (!error) {
error = chmod_common(&path, mode);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
}
return error;
}
SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename,
umode_t, mode)
{
return do_fchmodat(dfd, filename, mode);
}
SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)
{
return do_fchmodat(AT_FDCWD, filename, mode);
}
static int chown_common(const struct path *path, uid_t user, gid_t group)
{
struct inode *inode = path->dentry->d_inode;
struct inode *delegated_inode = NULL;
int error;
struct iattr newattrs;
kuid_t uid;
kgid_t gid;
uid = make_kuid(current_user_ns(), user);
gid = make_kgid(current_user_ns(), group);
retry_deleg:
newattrs.ia_valid = ATTR_CTIME;
if (user != (uid_t) -1) {
if (!uid_valid(uid))
return -EINVAL;
newattrs.ia_valid |= ATTR_UID;
newattrs.ia_uid = uid;
}
if (group != (gid_t) -1) {
if (!gid_valid(gid))
return -EINVAL;
newattrs.ia_valid |= ATTR_GID;
newattrs.ia_gid = gid;
}
if (!S_ISDIR(inode->i_mode))
newattrs.ia_valid |=
ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
inode_lock(inode);
error = security_path_chown(path, uid, gid);
if (!error)
error = notify_change(path->dentry, &newattrs, &delegated_inode);
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
return error;
}
int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
int flag)
{
struct path path;
int error = -EINVAL;
int lookup_flags;
if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
goto out;
lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
if (flag & AT_EMPTY_PATH)
lookup_flags |= LOOKUP_EMPTY;
retry:
error = user_path_at(dfd, filename, lookup_flags, &path);
if (error)
goto out;
error = mnt_want_write(path.mnt);
if (error)
goto out_release;
error = chown_common(&path, user, group);
mnt_drop_write(path.mnt);
out_release:
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
return error;
}
SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
gid_t, group, int, flag)
{
return do_fchownat(dfd, filename, user, group, flag);
}
SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group)
{
return do_fchownat(AT_FDCWD, filename, user, group, 0);
}
SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group)
{
return do_fchownat(AT_FDCWD, filename, user, group,
AT_SYMLINK_NOFOLLOW);
}
int ksys_fchown(unsigned int fd, uid_t user, gid_t group)
{
struct fd f = fdget(fd);
int error = -EBADF;
if (!f.file)
goto out;
error = mnt_want_write_file(f.file);
if (error)
goto out_fput;
audit_file(f.file);
error = chown_common(&f.file->f_path, user, group);
mnt_drop_write_file(f.file);
out_fput:
fdput(f);
out:
return error;
}
SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
{
return ksys_fchown(fd, user, group);
}
static int do_dentry_open(struct file *f,
struct inode *inode,
int (*open)(struct inode *, struct file *))
{
static const struct file_operations empty_fops = {};
int error;
path_get(&f->f_path);
f->f_inode = inode;
f->f_mapping = inode->i_mapping;
/* Ensure that we skip any errors that predate opening of the file */
f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
if (unlikely(f->f_flags & O_PATH)) {
f->f_mode = FMODE_PATH | FMODE_OPENED;
f->f_op = &empty_fops;
return 0;
}
/* Any file opened for execve()/uselib() has to be a regular file. */
if (unlikely(f->f_flags & FMODE_EXEC && !S_ISREG(inode->i_mode))) {
error = -EACCES;
goto cleanup_file;
}
if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
error = get_write_access(inode);
if (unlikely(error))
goto cleanup_file;
error = __mnt_want_write(f->f_path.mnt);
if (unlikely(error)) {
put_write_access(inode);
goto cleanup_file;
}
f->f_mode |= FMODE_WRITER;
}
/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))
f->f_mode |= FMODE_ATOMIC_POS;
f->f_op = fops_get(inode->i_fop);
if (unlikely(WARN_ON(!f->f_op))) {
error = -ENODEV;
goto cleanup_all;
}
error = security_file_open(f);
if (error)
goto cleanup_all;
error = break_lease(locks_inode(f), f->f_flags);
if (error)
goto cleanup_all;
/* normally all 3 are set; ->open() can clear them if needed */
f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
if (!open)
open = f->f_op->open;
if (open) {
error = open(inode, f);
if (error)
goto cleanup_all;
}
f->f_mode |= FMODE_OPENED;
if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
i_readcount_inc(inode);
if ((f->f_mode & FMODE_READ) &&
likely(f->f_op->read || f->f_op->read_iter))
f->f_mode |= FMODE_CAN_READ;
if ((f->f_mode & FMODE_WRITE) &&
likely(f->f_op->write || f->f_op->write_iter))
f->f_mode |= FMODE_CAN_WRITE;
f->f_write_hint = WRITE_LIFE_NOT_SET;
f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
/* NB: we're sure to have correct a_ops only after f_op->open */
if (f->f_flags & O_DIRECT) {
if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
return -EINVAL;
}
return 0;
cleanup_all:
if (WARN_ON_ONCE(error > 0))
error = -EINVAL;
fops_put(f->f_op);
if (f->f_mode & FMODE_WRITER) {
put_write_access(inode);
__mnt_drop_write(f->f_path.mnt);
}
cleanup_file:
path_put(&f->f_path);
f->f_path.mnt = NULL;
f->f_path.dentry = NULL;
f->f_inode = NULL;
return error;
}
/**
* finish_open - finish opening a file
* @file: file pointer
* @dentry: pointer to dentry
* @open: open callback
* @opened: state of open
*
* This can be used to finish opening a file passed to i_op->atomic_open().
*
* If the open callback is set to NULL, then the standard f_op->open()
* filesystem callback is substituted.
*
* NB: the dentry reference is _not_ consumed. If, for example, the dentry is
* the return value of d_splice_alias(), then the caller needs to perform dput()
* on it after finish_open().
*
* On successful return @file is a fully instantiated open file. After this, if
* an error occurs in ->atomic_open(), it needs to clean up with fput().
*
* Returns zero on success or -errno if the open failed.
*/
int finish_open(struct file *file, struct dentry *dentry,
int (*open)(struct inode *, struct file *))
{
BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */
file->f_path.dentry = dentry;
return do_dentry_open(file, d_backing_inode(dentry), open);
}
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())
*
* This can be used to set the result of a successful 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.
*/
int finish_no_open(struct file *file, struct dentry *dentry)
{
file->f_path.dentry = dentry;
return 0;
}
EXPORT_SYMBOL(finish_no_open);
char *file_path(struct file *filp, char *buf, int buflen)
{
return d_path(&filp->f_path, buf, buflen);
}
EXPORT_SYMBOL(file_path);
/**
* vfs_open - open the file at the given path
* @path: path to open
* @file: newly allocated file with f_flag initialized
* @cred: credentials to use
*/
int vfs_open(const struct path *path, struct file *file)
{
file->f_path = *path;
return do_dentry_open(file, d_backing_inode(path->dentry), NULL);
}
struct file *dentry_open(const struct path *path, int flags,
const struct cred *cred)
{
int error;
struct file *f;
validate_creds(cred);
/* We must always pass in a valid mount pointer. */
BUG_ON(!path->mnt);
f = alloc_empty_file(flags, cred);
if (!IS_ERR(f)) {
error = vfs_open(path, f);
if (error) {
fput(f);
f = ERR_PTR(error);
}
}
return f;
}
EXPORT_SYMBOL(dentry_open);
struct file *open_with_fake_path(const struct path *path, int flags,
struct inode *inode, const struct cred *cred)
{
struct file *f = alloc_empty_file_noaccount(flags, cred);
if (!IS_ERR(f)) {
int error;
f->f_path = *path;
error = do_dentry_open(f, inode, NULL);
if (error) {
fput(f);
f = ERR_PTR(error);
}
}
return f;
}
EXPORT_SYMBOL(open_with_fake_path);
static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op)
{
int lookup_flags = 0;
int acc_mode = ACC_MODE(flags);
/*
* Clear out all open flags we don't know about so that we don't report
* them in fcntl(F_GETFD) or similar interfaces.
*/
flags &= VALID_OPEN_FLAGS;
if (flags & (O_CREAT | __O_TMPFILE))
op->mode = (mode & S_IALLUGO) | S_IFREG;
else
op->mode = 0;
/* Must never be set by userspace */
flags &= ~FMODE_NONOTIFY & ~O_CLOEXEC;
/*
* O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only
* check for O_DSYNC if the need any syncing at all we enforce it's
* always set instead of having to deal with possibly weird behaviour
* for malicious applications setting only __O_SYNC.
*/
if (flags & __O_SYNC)
flags |= O_DSYNC;
if (flags & __O_TMPFILE) {
if ((flags & O_TMPFILE_MASK) != O_TMPFILE)
return -EINVAL;
if (!(acc_mode & MAY_WRITE))
return -EINVAL;
} else if (flags & O_PATH) {
/*
* If we have O_PATH in the open flag. Then we
* cannot have anything other than the below set of flags
*/
flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH;
acc_mode = 0;
}
op->open_flag = flags;
/* O_TRUNC implies we need access checks for write permissions */
if (flags & O_TRUNC)
acc_mode |= MAY_WRITE;
/* Allow the LSM permission hook to distinguish append
access from general write access. */
if (flags & O_APPEND)
acc_mode |= MAY_APPEND;
op->acc_mode = acc_mode;
op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN;
if (flags & O_CREAT) {
op->intent |= LOOKUP_CREATE;
if (flags & O_EXCL)
op->intent |= LOOKUP_EXCL;
}
if (flags & O_DIRECTORY)
lookup_flags |= LOOKUP_DIRECTORY;
if (!(flags & O_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
op->lookup_flags = lookup_flags;
return 0;
}
/**
* file_open_name - open file and return file pointer
*
* @name: struct filename containing path to open
* @flags: open flags as per the open(2) second argument
* @mode: mode for the new file if O_CREAT is set, else ignored
*
* This is the helper to open a file from kernelspace if you really
* have to. But in generally you should not do this, so please move
* along, nothing to see here..
*/
struct file *file_open_name(struct filename *name, int flags, umode_t mode)
{
struct open_flags op;
int err = build_open_flags(flags, mode, &op);
return err ? ERR_PTR(err) : do_filp_open(AT_FDCWD, name, &op);
}
/**
* filp_open - open file and return file pointer
*
* @filename: path to open
* @flags: open flags as per the open(2) second argument
* @mode: mode for the new file if O_CREAT is set, else ignored
*
* This is the helper to open a file from kernelspace if you really
* have to. But in generally you should not do this, so please move
* along, nothing to see here..
*/
struct file *filp_open(const char *filename, int flags, umode_t mode)
{
struct filename *name = getname_kernel(filename);
struct file *file = ERR_CAST(name);
if (!IS_ERR(name)) {
file = file_open_name(name, flags, mode);
putname(name);
}
return file;
}
EXPORT_SYMBOL(filp_open);
struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
const char *filename, int flags, umode_t mode)
{
struct open_flags op;
int err = build_open_flags(flags, mode, &op);
if (err)
return ERR_PTR(err);
return do_file_open_root(dentry, mnt, filename, &op);
}
EXPORT_SYMBOL(file_open_root);
long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
{
struct open_flags op;
int fd = build_open_flags(flags, mode, &op);
struct filename *tmp;
if (fd)
return fd;
tmp = getname(filename);
if (IS_ERR(tmp))
return PTR_ERR(tmp);
fd = get_unused_fd_flags(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 {
fsnotify_open(f);
fd_install(fd, f);
}
}
putname(tmp);
return fd;
}
SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
{
if (force_o_largefile())
flags |= O_LARGEFILE;
return do_sys_open(AT_FDCWD, filename, flags, mode);
}
SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
umode_t, mode)
{
if (force_o_largefile())
flags |= O_LARGEFILE;
return do_sys_open(dfd, filename, flags, mode);
}
#ifdef CONFIG_COMPAT
/*
* Exactly like sys_open(), except that it doesn't set the
* O_LARGEFILE flag.
*/
COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
{
return do_sys_open(AT_FDCWD, filename, flags, mode);
}
/*
* Exactly like sys_openat(), except that it doesn't set the
* O_LARGEFILE flag.
*/
COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode)
{
return do_sys_open(dfd, filename, flags, mode);
}
#endif
#ifndef __alpha__
/*
* For backward compatibility? Maybe this should be moved
* into arch/i386 instead?
*/
SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode)
{
return ksys_open(pathname, O_CREAT | O_WRONLY | O_TRUNC, mode);
}
#endif
/*
* "id" is the POSIX thread ID. We use the
* files pointer for this..
*/
int filp_close(struct file *filp, fl_owner_t id)
{
int retval = 0;
if (!file_count(filp)) {
printk(KERN_ERR "VFS: Close: file count is 0\n");
return 0;
}
if (filp->f_op->flush)
retval = filp->f_op->flush(filp, id);
if (likely(!(filp->f_mode & FMODE_PATH))) {
dnotify_flush(filp, id);
locks_remove_posix(filp, id);
}
fput(filp);
return retval;
}
EXPORT_SYMBOL(filp_close);
/*
* Careful here! We test whether the file pointer is NULL before
* releasing the fd. This ensures that one clone task can't release
* an fd while another clone is opening it.
*/
SYSCALL_DEFINE1(close, unsigned int, fd)
{
int retval = __close_fd(current->files, fd);
/* can't restart close syscall because file table entry was cleared */
if (unlikely(retval == -ERESTARTSYS ||
retval == -ERESTARTNOINTR ||
retval == -ERESTARTNOHAND ||
retval == -ERESTART_RESTARTBLOCK))
retval = -EINTR;
return retval;
}
/*
* This routine simulates a hangup on the tty, to arrange that users
* are given clean terminals at login time.
*/
SYSCALL_DEFINE0(vhangup)
{
if (capable(CAP_SYS_TTY_CONFIG)) {
tty_vhangup_self();
return 0;
}
return -EPERM;
}
/*
* Called when an inode is about to be open.
* We use this to disallow opening large files on 32bit systems if
* the caller didn't specify O_LARGEFILE. On 64bit systems we force
* on this flag in sys_open.
*/
int generic_file_open(struct inode * inode, struct file * filp)
{
if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
return -EOVERFLOW;
return 0;
}
EXPORT_SYMBOL(generic_file_open);
/*
* This is used by subsystems that don't want seekable
* file descriptors. The function is not supposed to ever fail, the only
* reason it returns an 'int' and not 'void' is so that it can be plugged
* directly into file_operations structure.
*/
int nonseekable_open(struct inode *inode, struct file *filp)
{
filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
return 0;
}
EXPORT_SYMBOL(nonseekable_open);
/*
* stream_open is used by subsystems that want stream-like file descriptors.
* Such file descriptors are not seekable and don't have notion of position
* (file.f_pos is always 0). Contrary to file descriptors of other regular
* files, .read() and .write() can run simultaneously.
*
* stream_open never fails and is marked to return int so that it could be
* directly used as file_operations.open .
*/
int stream_open(struct inode *inode, struct file *filp)
{
filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS);
filp->f_mode |= FMODE_STREAM;
return 0;
}
EXPORT_SYMBOL(stream_open);