a5804fcf7b
QEMU's local 9pfs server passes through O_NOATIME from the client. If
the QEMU process doesn't have permissions to use O_NOATIME (namely, it
does not own the file nor have the CAP_FOWNER capability), the open will
fail. This causes issues when from the client's point of view, it
believes it has permissions to use O_NOATIME (e.g., a process running as
root in the virtual machine). Additionally, overlayfs on Linux opens
files on the lower layer using O_NOATIME, so in this case a 9pfs mount
can't be used as a lower layer for overlayfs (cf.
dabfe19719/vmtest/onoatimehack.c
and https://github.com/NixOS/nixpkgs/issues/54509).
Luckily, O_NOATIME is effectively a hint, and is often ignored by, e.g.,
network filesystems. open(2) notes that O_NOATIME "may not be effective
on all filesystems. One example is NFS, where the server maintains the
access time." This means that we can honor it when possible but fall
back to ignoring it.
Acked-by: Christian Schoenebeck <qemu_oss@crudebyte.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Message-Id: <e9bee604e8df528584693a4ec474ded6295ce8ad.1587149256.git.osandov@fb.com>
Signed-off-by: Greg Kurz <groug@kaod.org>
82 lines
2.3 KiB
C
82 lines
2.3 KiB
C
/*
|
|
* 9p utilities
|
|
*
|
|
* Copyright IBM, Corp. 2017
|
|
*
|
|
* Authors:
|
|
* Greg Kurz <groug@kaod.org>
|
|
*
|
|
* This work is licensed under the terms of the GNU GPL, version 2 or later.
|
|
* See the COPYING file in the top-level directory.
|
|
*/
|
|
|
|
#ifndef QEMU_9P_UTIL_H
|
|
#define QEMU_9P_UTIL_H
|
|
|
|
#ifdef O_PATH
|
|
#define O_PATH_9P_UTIL O_PATH
|
|
#else
|
|
#define O_PATH_9P_UTIL 0
|
|
#endif
|
|
|
|
static inline void close_preserve_errno(int fd)
|
|
{
|
|
int serrno = errno;
|
|
close(fd);
|
|
errno = serrno;
|
|
}
|
|
|
|
static inline int openat_dir(int dirfd, const char *name)
|
|
{
|
|
return openat(dirfd, name,
|
|
O_DIRECTORY | O_RDONLY | O_NOFOLLOW | O_PATH_9P_UTIL);
|
|
}
|
|
|
|
static inline int openat_file(int dirfd, const char *name, int flags,
|
|
mode_t mode)
|
|
{
|
|
int fd, serrno, ret;
|
|
|
|
again:
|
|
fd = openat(dirfd, name, flags | O_NOFOLLOW | O_NOCTTY | O_NONBLOCK,
|
|
mode);
|
|
if (fd == -1) {
|
|
if (errno == EPERM && (flags & O_NOATIME)) {
|
|
/*
|
|
* The client passed O_NOATIME but we lack permissions to honor it.
|
|
* Rather than failing the open, fall back without O_NOATIME. This
|
|
* doesn't break the semantics on the client side, as the Linux
|
|
* open(2) man page notes that O_NOATIME "may not be effective on
|
|
* all filesystems". In particular, NFS and other network
|
|
* filesystems ignore it entirely.
|
|
*/
|
|
flags &= ~O_NOATIME;
|
|
goto again;
|
|
}
|
|
return -1;
|
|
}
|
|
|
|
serrno = errno;
|
|
/* O_NONBLOCK was only needed to open the file. Let's drop it. We don't
|
|
* do that with O_PATH since fcntl(F_SETFL) isn't supported, and openat()
|
|
* ignored it anyway.
|
|
*/
|
|
if (!(flags & O_PATH_9P_UTIL)) {
|
|
ret = fcntl(fd, F_SETFL, flags);
|
|
assert(!ret);
|
|
}
|
|
errno = serrno;
|
|
return fd;
|
|
}
|
|
|
|
ssize_t fgetxattrat_nofollow(int dirfd, const char *path, const char *name,
|
|
void *value, size_t size);
|
|
int fsetxattrat_nofollow(int dirfd, const char *path, const char *name,
|
|
void *value, size_t size, int flags);
|
|
ssize_t flistxattrat_nofollow(int dirfd, const char *filename,
|
|
char *list, size_t size);
|
|
ssize_t fremovexattrat_nofollow(int dirfd, const char *filename,
|
|
const char *name);
|
|
|
|
#endif
|