mirror of
https://github.com/torvalds/linux
synced 2024-09-06 18:01:05 +00:00
![Christian Brauner](/assets/img/avatar_default.png)
After a couple of years and multiple LTS releases we received a report that the behavior of O_DIRECTORY | O_CREAT changed starting with v5.7. On kernels prior to v5.7 combinations of O_DIRECTORY, O_CREAT, O_EXCL had the following semantics: (1) open("/tmp/d", O_DIRECTORY | O_CREAT) * d doesn't exist: create regular file * d exists and is a regular file: ENOTDIR * d exists and is a directory: EISDIR (2) open("/tmp/d", O_DIRECTORY | O_CREAT | O_EXCL) * d doesn't exist: create regular file * d exists and is a regular file: EEXIST * d exists and is a directory: EEXIST (3) open("/tmp/d", O_DIRECTORY | O_EXCL) * d doesn't exist: ENOENT * d exists and is a regular file: ENOTDIR * d exists and is a directory: open directory On kernels since to v5.7 combinations of O_DIRECTORY, O_CREAT, O_EXCL have the following semantics: (1) open("/tmp/d", O_DIRECTORY | O_CREAT) * d doesn't exist: ENOTDIR (create regular file) * d exists and is a regular file: ENOTDIR * d exists and is a directory: EISDIR (2) open("/tmp/d", O_DIRECTORY | O_CREAT | O_EXCL) * d doesn't exist: ENOTDIR (create regular file) * d exists and is a regular file: EEXIST * d exists and is a directory: EEXIST (3) open("/tmp/d", O_DIRECTORY | O_EXCL) * d doesn't exist: ENOENT * d exists and is a regular file: ENOTDIR * d exists and is a directory: open directory This is a fairly substantial semantic change that userspace didn't notice until Pedro took the time to deliberately figure out corner cases. Since no one noticed this breakage we can somewhat safely assume that O_DIRECTORY | O_CREAT combinations are likely unused. The v5.7 breakage is especially weird because while ENOTDIR is returned indicating failure a regular file is actually created. This doesn't make a lot of sense. Time was spent finding potential users of this combination. Searching on codesearch.debian.net showed that codebases often express semantical expectations about O_DIRECTORY | O_CREAT which are completely contrary to what our code has done and currently does. The expectation often is that this particular combination would create and open a directory. This suggests users who tried to use that combination would stumble upon the counterintuitive behavior no matter if pre-v5.7 or post v5.7 and quickly realize neither semantics give them what they want. For some examples see the code examples in [1] to [3] and the discussion in [4]. There are various ways to address this issue. The lazy/simple option would be to restore the pre-v5.7 behavior and to just live with that bug forever. But since there's a real chance that the O_DIRECTORY | O_CREAT quirk isn't relied upon we should try to get away with murder(ing bad semantics) first. If we need to Frankenstein pre-v5.7 behavior later so be it. So let's simply return EINVAL categorically for O_DIRECTORY | O_CREAT combinations. In addition to cleaning up the old bug this also opens up the possiblity to make that flag combination do something more intuitive in the future. Starting with this commit the following semantics apply: (1) open("/tmp/d", O_DIRECTORY | O_CREAT) * d doesn't exist: EINVAL * d exists and is a regular file: EINVAL * d exists and is a directory: EINVAL (2) open("/tmp/d", O_DIRECTORY | O_CREAT | O_EXCL) * d doesn't exist: EINVAL * d exists and is a regular file: EINVAL * d exists and is a directory: EINVAL (3) open("/tmp/d", O_DIRECTORY | O_EXCL) * d doesn't exist: ENOENT * d exists and is a regular file: ENOTDIR * d exists and is a directory: open directory One additional note, O_TMPFILE is implemented as: #define __O_TMPFILE 020000000 #define O_TMPFILE (__O_TMPFILE | O_DIRECTORY) #define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT) For older kernels it was important to return an explicit error when O_TMPFILE wasn't supported. So O_TMPFILE requires that O_DIRECTORY is raised alongside __O_TMPFILE. It also enforced that O_CREAT wasn't specified. Since O_DIRECTORY | O_CREAT could be used to create a regular allowing that combination together with __O_TMPFILE would've meant that false positives were possible, i.e., that a regular file was created instead of a O_TMPFILE. This could've been used to trick userspace into thinking it operated on a O_TMPFILE when it wasn't. Now that we block O_DIRECTORY | O_CREAT completely the check for O_CREAT in the __O_TMPFILE branch via if ((flags & O_TMPFILE_MASK) != O_TMPFILE) can be dropped. Instead we can simply check verify that O_DIRECTORY is raised via if (!(flags & O_DIRECTORY)) and explain this in two comments. As Aleksa pointed out O_PATH is unaffected by this change since it always returned EINVAL if O_CREAT was specified - with or without O_DIRECTORY. Link: https://lore.kernel.org/lkml/20230320071442.172228-1-pedro.falcato@gmail.com Link: https://sources.debian.org/src/flatpak/1.14.4-1/subprojects/libglnx/glnx-dirfd.c/?hl=324#L324 [1] Link: https://sources.debian.org/src/flatpak-builder/1.2.3-1/subprojects/libglnx/glnx-shutil.c/?hl=251#L251 [2] Link: https://sources.debian.org/src/ostree/2022.7-2/libglnx/glnx-dirfd.c/?hl=324#L324 [3] Link: https://www.openwall.com/lists/oss-security/2014/11/26/14 [4] Reported-by: Pedro Falcato <pedro.falcato@gmail.com> Cc: Aleksa Sarai <cyphar@cyphar.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Christian Brauner <brauner@kernel.org>
222 lines
5.5 KiB
C
222 lines
5.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
|
|
#ifndef _ASM_GENERIC_FCNTL_H
|
|
#define _ASM_GENERIC_FCNTL_H
|
|
|
|
#include <linux/types.h>
|
|
|
|
/*
|
|
* FMODE_EXEC is 0x20
|
|
* FMODE_NONOTIFY is 0x4000000
|
|
* These cannot be used by userspace O_* until internal and external open
|
|
* flags are split.
|
|
* -Eric Paris
|
|
*/
|
|
|
|
/*
|
|
* When introducing new O_* bits, please check its uniqueness in fcntl_init().
|
|
*/
|
|
|
|
#define O_ACCMODE 00000003
|
|
#define O_RDONLY 00000000
|
|
#define O_WRONLY 00000001
|
|
#define O_RDWR 00000002
|
|
#ifndef O_CREAT
|
|
#define O_CREAT 00000100 /* not fcntl */
|
|
#endif
|
|
#ifndef O_EXCL
|
|
#define O_EXCL 00000200 /* not fcntl */
|
|
#endif
|
|
#ifndef O_NOCTTY
|
|
#define O_NOCTTY 00000400 /* not fcntl */
|
|
#endif
|
|
#ifndef O_TRUNC
|
|
#define O_TRUNC 00001000 /* not fcntl */
|
|
#endif
|
|
#ifndef O_APPEND
|
|
#define O_APPEND 00002000
|
|
#endif
|
|
#ifndef O_NONBLOCK
|
|
#define O_NONBLOCK 00004000
|
|
#endif
|
|
#ifndef O_DSYNC
|
|
#define O_DSYNC 00010000 /* used to be O_SYNC, see below */
|
|
#endif
|
|
#ifndef FASYNC
|
|
#define FASYNC 00020000 /* fcntl, for BSD compatibility */
|
|
#endif
|
|
#ifndef O_DIRECT
|
|
#define O_DIRECT 00040000 /* direct disk access hint */
|
|
#endif
|
|
#ifndef O_LARGEFILE
|
|
#define O_LARGEFILE 00100000
|
|
#endif
|
|
#ifndef O_DIRECTORY
|
|
#define O_DIRECTORY 00200000 /* must be a directory */
|
|
#endif
|
|
#ifndef O_NOFOLLOW
|
|
#define O_NOFOLLOW 00400000 /* don't follow links */
|
|
#endif
|
|
#ifndef O_NOATIME
|
|
#define O_NOATIME 01000000
|
|
#endif
|
|
#ifndef O_CLOEXEC
|
|
#define O_CLOEXEC 02000000 /* set close_on_exec */
|
|
#endif
|
|
|
|
/*
|
|
* Before Linux 2.6.33 only O_DSYNC semantics were implemented, but using
|
|
* the O_SYNC flag. We continue to use the existing numerical value
|
|
* for O_DSYNC semantics now, but using the correct symbolic name for it.
|
|
* This new value is used to request true Posix O_SYNC semantics. It is
|
|
* defined in this strange way to make sure applications compiled against
|
|
* new headers get at least O_DSYNC semantics on older kernels.
|
|
*
|
|
* This has the nice side-effect that we can simply test for O_DSYNC
|
|
* wherever we do not care if O_DSYNC or O_SYNC is used.
|
|
*
|
|
* Note: __O_SYNC must never be used directly.
|
|
*/
|
|
#ifndef O_SYNC
|
|
#define __O_SYNC 04000000
|
|
#define O_SYNC (__O_SYNC|O_DSYNC)
|
|
#endif
|
|
|
|
#ifndef O_PATH
|
|
#define O_PATH 010000000
|
|
#endif
|
|
|
|
#ifndef __O_TMPFILE
|
|
#define __O_TMPFILE 020000000
|
|
#endif
|
|
|
|
/* a horrid kludge trying to make sure that this will fail on old kernels */
|
|
#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
|
|
|
|
#ifndef O_NDELAY
|
|
#define O_NDELAY O_NONBLOCK
|
|
#endif
|
|
|
|
#define F_DUPFD 0 /* dup */
|
|
#define F_GETFD 1 /* get close_on_exec */
|
|
#define F_SETFD 2 /* set/clear close_on_exec */
|
|
#define F_GETFL 3 /* get file->f_flags */
|
|
#define F_SETFL 4 /* set file->f_flags */
|
|
#ifndef F_GETLK
|
|
#define F_GETLK 5
|
|
#define F_SETLK 6
|
|
#define F_SETLKW 7
|
|
#endif
|
|
#ifndef F_SETOWN
|
|
#define F_SETOWN 8 /* for sockets. */
|
|
#define F_GETOWN 9 /* for sockets. */
|
|
#endif
|
|
#ifndef F_SETSIG
|
|
#define F_SETSIG 10 /* for sockets. */
|
|
#define F_GETSIG 11 /* for sockets. */
|
|
#endif
|
|
|
|
#if __BITS_PER_LONG == 32 || defined(__KERNEL__)
|
|
#ifndef F_GETLK64
|
|
#define F_GETLK64 12 /* using 'struct flock64' */
|
|
#define F_SETLK64 13
|
|
#define F_SETLKW64 14
|
|
#endif
|
|
#endif /* __BITS_PER_LONG == 32 || defined(__KERNEL__) */
|
|
|
|
#ifndef F_SETOWN_EX
|
|
#define F_SETOWN_EX 15
|
|
#define F_GETOWN_EX 16
|
|
#endif
|
|
|
|
#ifndef F_GETOWNER_UIDS
|
|
#define F_GETOWNER_UIDS 17
|
|
#endif
|
|
|
|
/*
|
|
* Open File Description Locks
|
|
*
|
|
* Usually record locks held by a process are released on *any* close and are
|
|
* not inherited across a fork().
|
|
*
|
|
* These cmd values will set locks that conflict with process-associated
|
|
* record locks, but are "owned" by the open file description, not the
|
|
* process. This means that they are inherited across fork() like BSD (flock)
|
|
* locks, and they are only released automatically when the last reference to
|
|
* the the open file against which they were acquired is put.
|
|
*/
|
|
#define F_OFD_GETLK 36
|
|
#define F_OFD_SETLK 37
|
|
#define F_OFD_SETLKW 38
|
|
|
|
#define F_OWNER_TID 0
|
|
#define F_OWNER_PID 1
|
|
#define F_OWNER_PGRP 2
|
|
|
|
struct f_owner_ex {
|
|
int type;
|
|
__kernel_pid_t pid;
|
|
};
|
|
|
|
/* for F_[GET|SET]FL */
|
|
#define FD_CLOEXEC 1 /* actually anything with low bit set goes */
|
|
|
|
/* for posix fcntl() and lockf() */
|
|
#ifndef F_RDLCK
|
|
#define F_RDLCK 0
|
|
#define F_WRLCK 1
|
|
#define F_UNLCK 2
|
|
#endif
|
|
|
|
/* for old implementation of bsd flock () */
|
|
#ifndef F_EXLCK
|
|
#define F_EXLCK 4 /* or 3 */
|
|
#define F_SHLCK 8 /* or 4 */
|
|
#endif
|
|
|
|
/* operations for bsd flock(), also used by the kernel implementation */
|
|
#define LOCK_SH 1 /* shared lock */
|
|
#define LOCK_EX 2 /* exclusive lock */
|
|
#define LOCK_NB 4 /* or'd with one of the above to prevent
|
|
blocking */
|
|
#define LOCK_UN 8 /* remove lock */
|
|
|
|
/*
|
|
* LOCK_MAND support has been removed from the kernel. We leave the symbols
|
|
* here to not break legacy builds, but these should not be used in new code.
|
|
*/
|
|
#define LOCK_MAND 32 /* This is a mandatory flock ... */
|
|
#define LOCK_READ 64 /* which allows concurrent read operations */
|
|
#define LOCK_WRITE 128 /* which allows concurrent write operations */
|
|
#define LOCK_RW 192 /* which allows concurrent read & write ops */
|
|
|
|
#define F_LINUX_SPECIFIC_BASE 1024
|
|
|
|
#ifndef HAVE_ARCH_STRUCT_FLOCK
|
|
struct flock {
|
|
short l_type;
|
|
short l_whence;
|
|
__kernel_off_t l_start;
|
|
__kernel_off_t l_len;
|
|
__kernel_pid_t l_pid;
|
|
#ifdef __ARCH_FLOCK_EXTRA_SYSID
|
|
__ARCH_FLOCK_EXTRA_SYSID
|
|
#endif
|
|
#ifdef __ARCH_FLOCK_PAD
|
|
__ARCH_FLOCK_PAD
|
|
#endif
|
|
};
|
|
|
|
struct flock64 {
|
|
short l_type;
|
|
short l_whence;
|
|
__kernel_loff_t l_start;
|
|
__kernel_loff_t l_len;
|
|
__kernel_pid_t l_pid;
|
|
#ifdef __ARCH_FLOCK64_PAD
|
|
__ARCH_FLOCK64_PAD
|
|
#endif
|
|
};
|
|
#endif /* HAVE_ARCH_STRUCT_FLOCK */
|
|
|
|
#endif /* _ASM_GENERIC_FCNTL_H */
|