mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-07-23 15:37:49 -04:00
7e0e7bd60d
Pull misc vfs updates from Christian Brauner:
"Features:
- Reduce pipe->mutex contention by pre-allocating pages outside the
lock in anon_pipe_write().
anon_pipe_write() called alloc_page() once per page while holding
pipe->mutex. The allocation can sleep doing direct reclaim and runs
memcg charging, which extends the critical section and stalls any
concurrent reader on the same mutex. Now up to 8 pages are
pre-allocated before the mutex is taken, leftovers are recycled
into the per-pipe tmp_page[] cache before unlock, and any remainder
is released after unlock, keeping the allocator out of the critical
section on both sides. On a writers x readers sweep with 64KB
writes against a 1 MB pipe throughput improves 6-28% and average
write latency drops 5-22%; under memory pressure - when the cost of
holding the mutex across reclaim is highest - throughput improves
21-48% and latency drops 17-33%. The microbenchmark is added to
selftests.
- uaccess/sockptr: fix the ignored_trailing logic in
copy_struct_to_user() to behave as documented and the usize check
in copy_struct_from_sockptr() for user pointers, and add
copy_struct_{from,to}_bounce_buffer() and copy_struct_to_sockptr()
helpers for upcoming users (IPPROTO_SMBDIRECT, IPPROTO_QUIC).
- bpf: add a sleepable bpf_real_inode() kfunc that resolves the real
inode backing a dentry via d_real_inode(). On overlayfs the inode
attached to the dentry doesn't carry the underlying device
information; this is used by the filesystem restriction BPF program
that was merged into systemd.
- docs: add guidelines for submitting new filesystems, motivated by
the maintenance burden abandoned and untestable filesystems impose
on VFS developers, blocking infrastructure work like folio
conversions and iomap migration.
Fixes:
- libfs: set SB_I_NOEXEC and SB_I_NODEV by default in init_pseudo()
and drop the now-redundant assignments in callers. This began as a
one-line dma-buf fix for a path_noexec() warning; a pseudo
filesystem has no reason not to set SB_I_NOEXEC. All init_pseudo()
callers were audited: the only visible effect is on dma-buf where
SB_I_NOEXEC silences the warning.
- Handle set_blocksize() failures in legacy filesystems (bfs, hpfs,
qnx4, jfs, befs, affs, isofs, minix, ntfs3, omfs). Mounting a
device with a sector size > PAGE_SIZE crashed roughly half of them;
the rest had the same missing error handling pattern. Plus a
follow-up releasing the superblock buffer_head when setting the
minix v3 block size fails.
- mount: honour SB_NOUSER in the new mount API.
- fs/fcntl: fix a SOFTIRQ-unsafe lock order in fasync signaling by
switching the process-group paths of send_sigio() and send_sigurg()
from read_lock(&tasklist_lock) to RCU, matching the single-PID
path.
- vfs: add an FS_USERNS_DELEGATABLE flag and set it for NFS, fixing
delegated NFS mounts (fsopen() in a container with the mount
performed by a privileged daemon) that broke when non-init
s_user_ns was tied to FS_USERNS_MOUNT.
- selftests/namespaces: fix a hang in nsid_test where an unreaped
grandchild kept the TAP pipe write-end open, a waitpid(-1) race in
listns_efault_test, and a false FAIL on kernels without listns()
where the tests should SKIP.
- filelock: fix the break_lease() stub signature for
CONFIG_FILE_LOCKING=n.
- init/initramfs_test: wait for the async initramfs unpacking before
running; the test and do_populate_rootfs() share the parser state.
- fs/coredump: reduce redundant log noise in
validate_coredump_safety().
- iomap: pass the correct length to fserror_report_io() in
__iomap_write_begin().
- backing-file: fix the backing_file_open() kerneldoc.
Cleanups:
- initramfs: refactor the cpio hex header parsing to use hex2bin()
instead of the hand-rolled simple_strntoul() which is reverted, and
extend the initramfs KUnit tests to cover header fields with 0x
prefixes.
- Replace __get_free_pages() and friends with kmalloc()/kzalloc()
across quota, proc, ocfs2/dlm, nilfs2, nfs, nfsd, libfs, jfs, jbd2,
isofs, fuse, select, namespace, configfs, binfmt_misc, bfs, and the
do_mounts init code - part of the larger work of replacing page
allocator calls with kmalloc().
- Use clear_and_wake_up_bit() in unlock_buffer() and
journal_end_buffer_io_sync() instead of open-coding the sequence.
- Drop unused VFS exports: unexport drop_super_exclusive(), remove
start_removing_user_path_at(), and fold __start_removing_path()
into start_removing_path().
- fs/read_write: narrow the __kernel_write() export with
EXPORT_SYMBOL_FOR_MODULES().
- vfs: uapi: retire octal and hex constants in favor of (1 << n) for
the O_ flags. Finding a free bit for a new flag across the
architectures was needlessly hard with the mixed bases.
- dcache: add extra sanity checks of dead dentries in dentry_free()
via a new DENTRY_WARN_ONCE() that also prints d_flags.
- iov_iter: use kmemdup_array() in dup_iter() to harden the
allocation against multiplication overflow.
- fs/pipe: write to ->poll_usage only once.
- vfs: remove an always-taken if-branch in find_next_fd().
- dcache: use kmalloc_flex() for struct external_name in __d_alloc().
- namei: use QSTR() instead of QSTR_INIT() in path_pts().
- sync_file_range: delete dead S_ISLNK code.
- Comment fixes: retire a stale comment in fget_task_next() and fix
assorted spelling mistakes"
* tag 'vfs-7.2-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (73 commits)
backing-file: fix backing_file_open() kerneldoc parameter
iomap: pass the correct len to fserror_report_io in __iomap_write_begin
vfs: add FS_USERNS_DELEGATABLE flag and set it for NFS
filelock: fix break_lease() stub signature for CONFIG_FILE_LOCKING=n
vfs: uapi: retire octal and hex numbers in favor of (1 << n) for O_ flags
bpf: add bpf_real_inode() kfunc
fs/read_write: Do not export __kernel_write() to the entire world
libfs: drop redundant SB_I_NOEXEC/SB_I_NODEV in init_pseudo() callers
libfs: set SB_I_NOEXEC and SB_I_NODEV by default in init_pseudo()
mount: honour SB_NOUSER in the new mount API
fs/fcntl: fix SOFTIRQ-unsafe lock order in fasync signaling
selftests/pipe: add pipe_bench microbenchmark
fs/pipe: pre-allocate pages outside pipe->mutex in anon_pipe_write
fs: retire stale comment in fget_task_next()
fs: fix spelling mistakes in comment
bfs: replace get_zeroed_page() with kzalloc()
binfmt_misc: replace __get_free_page() with kmalloc()
configfs: replace __get_free_pages() with kzalloc()
fs/namespace: use __getname() to allocate mntpath buffer
fs/select: replace __get_free_page() with kmalloc()
...
233 lines
6.0 KiB
C
233 lines
6.0 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
|
|
* 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 3
|
|
#define O_RDONLY 0
|
|
#define O_WRONLY (1 << 0)
|
|
#define O_RDWR (1 << 1)
|
|
/* (1 << 2) must not be used -- it collides with flags on alpha, sparc */
|
|
/* (1 << 3) must not be used -- it collides with flags on alpha, mips, parisc, sparc */
|
|
/* (1 << 4) must not be used -- it collides with flags on mips */
|
|
/* (1 << 5) is free */
|
|
#ifndef O_CREAT
|
|
#define O_CREAT (1 << 6) /* not fcntl */
|
|
#endif
|
|
#ifndef O_EXCL
|
|
#define O_EXCL (1 << 7) /* not fcntl */
|
|
#endif
|
|
#ifndef O_NOCTTY
|
|
#define O_NOCTTY (1 << 8) /* not fcntl */
|
|
#endif
|
|
#ifndef O_TRUNC
|
|
#define O_TRUNC (1 << 9) /* not fcntl */
|
|
#endif
|
|
#ifndef O_APPEND
|
|
#define O_APPEND (1 << 10)
|
|
#endif
|
|
#ifndef O_NONBLOCK
|
|
#define O_NONBLOCK (1 << 11)
|
|
#endif
|
|
#ifndef O_DSYNC
|
|
#define O_DSYNC (1 << 12) /* used to be O_SYNC, see below */
|
|
#endif
|
|
#ifndef FASYNC
|
|
#define FASYNC (1 << 13) /* fcntl, for BSD compatibility */
|
|
#endif
|
|
#ifndef O_DIRECT
|
|
#define O_DIRECT (1 << 14) /* direct disk access hint */
|
|
#endif
|
|
#ifndef O_LARGEFILE
|
|
#define O_LARGEFILE (1 << 15)
|
|
#endif
|
|
#ifndef O_DIRECTORY
|
|
#define O_DIRECTORY (1 << 16) /* must be a directory */
|
|
#endif
|
|
#ifndef O_NOFOLLOW
|
|
#define O_NOFOLLOW (1 << 17) /* don't follow links */
|
|
#endif
|
|
#ifndef O_NOATIME
|
|
#define O_NOATIME (1 << 18)
|
|
#endif
|
|
#ifndef O_CLOEXEC
|
|
#define O_CLOEXEC (1 << 19) /* 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 (1 << 20)
|
|
#define O_SYNC (__O_SYNC|O_DSYNC)
|
|
#endif
|
|
|
|
#ifndef O_PATH
|
|
#define O_PATH (1 << 21)
|
|
#endif
|
|
|
|
#ifndef __O_TMPFILE
|
|
#define __O_TMPFILE (1 << 22)
|
|
#endif
|
|
|
|
#ifndef O_EMPTYPATH
|
|
#define O_EMPTYPATH (1 << 26) /* allow empty path */
|
|
#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
|
|
|
|
/* (1 << 23) must not be used -- it collides with flags on alpha, parisc, sparc */
|
|
/* (1 << 24) must not be used -- it collides with flags on alpha, sparc */
|
|
/* (1 << 25) must not be used -- it collides with flags on sparc */
|
|
|
|
#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 */
|