lib/libsys/fcntl.2

.\" Copyright (c) 1983, 1993
.\"	The Regents of the University of California.  All rights reserved.
.\"
.\" Redistribution and use in source and binary forms, with or without
.\" modification, are permitted provided that the following conditions
.\" are met:
.\" 1. Redistributions of source code must retain the above copyright
.\"    notice, this list of conditions and the following disclaimer.
.\" 2. Redistributions in binary form must reproduce the above copyright
.\"    notice, this list of conditions and the following disclaimer in the
.\"    documentation and/or other materials provided with the distribution.
.\" 3. Neither the name of the University nor the names of its contributors
.\"    may be used to endorse or promote products derived from this software
.\"    without specific prior written permission.
.\"
.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
.\" ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
.\" SUCH DAMAGE.
.\"
.Dd June 24, 2025
.Dt FCNTL 2
.Os
.Sh NAME
.Nm fcntl
.Nd file control
.Sh LIBRARY
.Lb libc
.Sh SYNOPSIS
.In fcntl.h
.Ft int
.Fn fcntl "int fd" "int cmd" "..."
.Sh DESCRIPTION
The
.Fn fcntl
system call provides for control over descriptors.
The argument
.Fa fd
is a descriptor to be operated on by
.Fa cmd
as described below.
Depending on the value of
.Fa cmd ,
.Fn fcntl
can take an additional third argument
.Fa arg .
Unless otherwise noted below for a specific operation,
.Fa arg
has type
.Vt int .
.Bl -tag -width F_DUP2FD_CLOEXEC
.It Dv F_DUPFD
Return a new descriptor as follows:
.Pp
.Bl -bullet -compact -offset 4n
.It
Lowest numbered available descriptor greater than or equal to
.Fa arg .
.It
Same object references as the original descriptor.
.It
New descriptor shares the same file offset if the object
was a file.
.It
Same access mode (read, write or read/write).
.It
Same file status flags (i.e., both file descriptors
share the same file status flags).
.It
The close-on-exec flag
.Dv FD_CLOEXEC
associated with the new file descriptor is cleared, so the file descriptor is
to remain open across
.Xr execve 2
system calls.
.It
The fork-on-exec flag
.Dv FD_CLOFORK
associated with the new file descriptor is cleared, so the file descriptor is
to remain open across
.Xr fork 2
system calls.
.It
The
.Dv FD_RESOLVE_BENEATH
flag, described below, will be set if it was set on the original
descriptor.
.El
.It Dv F_DUPFD_CLOEXEC
Like
.Dv F_DUPFD ,
but the
.Dv FD_CLOEXEC
flag associated with the new file descriptor is set, so the file descriptor
is closed when
.Xr execve 2
system call executes.
.It Dv F_DUPFD_CLOFORK
Like
.Dv F_DUPFD ,
but the
.Dv FD_CLOFORK
flag associated with the new file descriptor is set, so the file descriptor
is closed when
.Xr fork 2
system call executes.
.It Dv F_DUP2FD
It is functionally equivalent to
.Bd -literal -offset indent
dup2(fd, arg)
.Ed
.It Dv F_DUP2FD_CLOEXEC
Like
.Dv F_DUP2FD ,
but the
.Dv FD_CLOEXEC
flag associated with the new file descriptor is set.
.Pp
The
.Dv F_DUP2FD
and
.Dv F_DUP2FD_CLOEXEC
constants are not portable, so they should not be used if
portability is needed.
Use
.Fn dup2
instead of
.Dv F_DUP2FD .
.It Dv F_DUP3FD
Used to implement the
.Fn dup3
call.
Do not use it.
.It Dv F_GETFD
Get the flags associated with the file descriptor
.Fa fd .
The following flags are defined:
.Bl -tag -width FD_RESOLVE_BENEATH
.It Dv FD_CLOEXEC
The file will be closed upon execution of
.Fn exec
.Fa ( arg
is ignored).
Otherwise, the file descriptor will remain open.
.It Dv FD_CLOFORK
The file will be closed upon execution of the
.Fn fork
family of system calls.
.It Dv FD_RESOLVE_BENEATH
All path name lookups relative to that file descriptor
will behave as if the lookup had
.Dv O_RESOLVE_BENEATH
or
.Dv AT_RESOLVE_BENEATH
semantics.
It is not permitted to call
.Xr fchdir 2
or
.Xr fchroot 2
on such a file descriptor.
The
.Dv FD_RESOLVE_BENEATH
flag is sticky, meaning that it is preserved by
.Xr dup 2
and similar operations, and opening a directory with
.Xr openat 2
where the directory descriptor has the flag set causes the new directory
descriptor to also have the flag set.
.El
.It Dv F_SETFD
Set flags associated with
.Fa fd .
The available flags are
.Dv FD_CLOEXEC ,
.Dv FD_CLOFORK
and
.Dv FD_RESOLVE_BENEATH .
The
.Dv FD_RESOLVE_BENEATH
flag cannot be cleared once set.
.It Dv F_GETFL
Get descriptor status flags, as described below
.Fa ( arg
is ignored).
.It Dv F_SETFL
Set descriptor status flags to
.Fa arg .
.It Dv F_GETOWN
Get the process ID or process group
currently receiving
.Dv SIGIO
and
.Dv SIGURG
signals; process groups are returned
as negative values
.Fa ( arg
is ignored).
.It Dv F_SETOWN
Set the process or process group
to receive
.Dv SIGIO
and
.Dv SIGURG
signals;
process groups are specified by supplying
.Fa arg
as negative, otherwise
.Fa arg
is interpreted as a process ID.
.It Dv F_READAHEAD
Set or clear the read ahead amount for sequential access to the third
argument,
.Fa arg ,
which is rounded up to the nearest block size.
A zero value in
.Fa arg
turns off read ahead, a negative value restores the system default.
.It Dv F_RDAHEAD
Equivalent to Darwin counterpart which sets read ahead amount of 128KB
when the third argument,
.Fa arg
is non-zero.
A zero value in
.Fa arg
turns off read ahead.
.It Dv F_ADD_SEALS
Add seals to the file as described below, if the underlying filesystem supports
seals.
.It Dv F_GET_SEALS
Get seals associated with the file, if the underlying filesystem supports seals.
.It Dv F_ISUNIONSTACK
Check if the vnode is part of a union stack (either the "union" flag from
.Xr mount 2
or unionfs).
This is a hack not intended to be used outside of libc.
.It Dv F_KINFO
Fills a
.Vt struct kinfo_file
for the file referenced by the specified file descriptor.
The
.Fa arg
argument should point to the storage for
.Vt struct kinfo_file .
The
.Va kf_structsize
member of the passed structure must be initialized with the sizeof of
.Vt struct kinfo_file ,
to allow for the interface versioning and evolution.
.El
.Pp
The flags for the
.Dv F_GETFL
and
.Dv F_SETFL
commands are as follows:
.Bl -tag -width O_NONBLOCKX
.It Dv O_NONBLOCK
Non-blocking I/O; if no data is available to a
.Xr read 2
system call, or if a
.Xr write 2
operation would block,
the read or write call returns -1 with the error
.Er EAGAIN .
.It Dv O_APPEND
Force each write to append at the end of file;
corresponds to the
.Dv O_APPEND
flag of
.Xr open 2 .
.It Dv O_DIRECT
Minimize or eliminate the cache effects of reading and writing.
The system
will attempt to avoid caching the data you read or write.
If it cannot
avoid caching the data, it will minimize the impact the data has on the cache.
Use of this flag can drastically reduce performance if not used with care.
.It Dv O_ASYNC
Enable the
.Dv SIGIO
signal to be sent to the process group
when I/O is possible, e.g.,
upon availability of data to be read.
.It Dv O_SYNC
Enable synchronous writes.
Corresponds to the
.Dv O_SYNC
flag of
.Xr open 2 .
.Dv O_FSYNC
is an historical synonym for
.Dv O_SYNC .
.It Dv O_DSYNC
Enable synchronous data writes.
Corresponds to the
.Dv O_DSYNC
flag of
.Xr open 2 .
.El
.Pp
The seals that may be applied with
.Dv F_ADD_SEALS
are as follows:
.Bl -tag -width F_SEAL_SHRINK
.It Dv F_SEAL_SEAL
Prevent any further seals from being applied to the file.
.It Dv F_SEAL_SHRINK
Prevent the file from being shrunk with
.Xr ftruncate 2 .
.It Dv F_SEAL_GROW
Prevent the file from being enlarged with
.Xr ftruncate 2 .
.It Dv F_SEAL_WRITE
Prevent any further
.Xr write 2
calls to the file.
Any writes in progress will finish before
.Fn fcntl
returns.
If any writeable mappings exist, F_ADD_SEALS will fail and return
.Dv EBUSY .
.El
.Pp
Seals are on a per-inode basis and require support by the underlying filesystem.
If the underlying filesystem does not support seals,
.Dv F_ADD_SEALS
and
.Dv F_GET_SEALS
will fail and return
.Dv EINVAL .
.Pp
Several operations are available for doing advisory file locking;
they all operate on the following structure:
.Bd -literal
struct flock {
	off_t	l_start;	/* starting offset */
	off_t	l_len;		/* len = 0 means until end of file */
	pid_t	l_pid;		/* lock owner */
	short	l_type;		/* lock type: read/write, etc. */
	short	l_whence;	/* type of l_start */
	int	l_sysid;	/* remote system id or zero for local */
};
.Ed
These advisory file locking operations take a pointer to
.Vt struct flock
as the third argument
.Fa arg .
The commands available for advisory record locking are as follows:
.Bl -tag -width F_SETLKWX
.It Dv F_GETLK
Get the first lock that blocks the lock description pointed to by the
third argument,
.Fa arg ,
taken as a pointer to a
.Fa "struct flock"
(see above).
The information retrieved overwrites the information passed to
.Fn fcntl
in the
.Fa flock
structure.
If no lock is found that would prevent this lock from being created,
the structure is left unchanged by this system call except for the
lock type which is set to
.Dv F_UNLCK .
.It Dv F_SETLK
Set or clear a file segment lock according to the lock description
pointed to by the third argument,
.Fa arg ,
taken as a pointer to a
.Fa "struct flock"
(see above).
.Dv F_SETLK
is used to establish shared (or read) locks
.Pq Dv F_RDLCK
or exclusive (or write) locks,
.Pq Dv F_WRLCK ,
as well as remove either type of lock
.Pq Dv F_UNLCK .
If a shared or exclusive lock cannot be set,
.Fn fcntl
returns immediately with
.Er EAGAIN .
.It Dv F_SETLKW
This command is the same as
.Dv F_SETLK
except that if a shared or exclusive lock is blocked by other locks,
the process waits until the request can be satisfied.
If a signal that is to be caught is received while
.Fn fcntl
is waiting for a region, the
.Fn fcntl
will be interrupted if the signal handler has not specified the
.Dv SA_RESTART
(see
.Xr sigaction 2 ) .
.El
.Pp
When a shared lock has been set on a segment of a file,
other processes can set shared locks on that segment
or a portion of it.
A shared lock prevents any other process from setting an exclusive
lock on any portion of the protected area.
A request for a shared lock fails if the file descriptor was not
opened with read access.
.Pp
An exclusive lock prevents any other process from setting a shared lock or
an exclusive lock on any portion of the protected area.
A request for an exclusive lock fails if the file was not
opened with write access.
.Pp
The value of
.Fa l_whence
is
.Dv SEEK_SET ,
.Dv SEEK_CUR ,
or
.Dv SEEK_END
to indicate that the relative offset,
.Fa l_start
bytes, will be measured from the start of the file,
current position, or end of the file, respectively.
The value of
.Fa l_len
is the number of consecutive bytes to be locked.
If
.Fa l_len
is negative,
.Fa l_start
means end edge of the region.
The
.Fa l_pid
and
.Fa l_sysid
fields are only used with
.Dv F_GETLK
to return the process ID of the process holding a blocking lock and
the system ID of the system that owns that process.
Locks created by the local system will have a system ID of zero.
After a successful
.Dv F_GETLK
request, the value of
.Fa l_whence
is
.Dv SEEK_SET .
.Pp
Locks may start and extend beyond the current end of a file,
but may not start or extend before the beginning of the file.
A lock is set to extend to the largest possible value of the
file offset for that file if
.Fa l_len
is set to zero.
If
.Fa l_whence
and
.Fa l_start
point to the beginning of the file, and
.Fa l_len
is zero, the entire file is locked.
If an application wishes only to do entire file locking, the
.Xr flock 2
system call is much more efficient.
.Pp
There is at most one type of lock set for each byte in the file.
Before a successful return from an
.Dv F_SETLK
or an
.Dv F_SETLKW
request when the calling process has previously existing locks
on bytes in the region specified by the request,
the previous lock type for each byte in the specified
region is replaced by the new lock type.
As specified above under the descriptions
of shared locks and exclusive locks, an
.Dv F_SETLK
or an
.Dv F_SETLKW
request fails or blocks respectively when another process has existing
locks on bytes in the specified region and the type of any of those
locks conflicts with the type specified in the request.
.Pp
The queuing for
.Dv F_SETLKW
requests on local files is fair;
that is, while the thread is blocked,
subsequent requests conflicting with its requests will not be granted,
even if these requests do not conflict with existing locks.
.Pp
This interface follows the completely stupid semantics of System V and
.St -p1003.1-88
that require that all locks associated with a file for a given process are
removed when
.Em any
file descriptor for that file is closed by that process.
This semantic means that applications must be aware of any files that
a subroutine library may access.
For example if an application for updating the password file locks the
password file database while making the update, and then calls
.Xr getpwnam 3
to retrieve a record,
the lock will be lost because
.Xr getpwnam 3
opens, reads, and closes the password database.
The database close will release all locks that the process has
associated with the database, even if the library routine never
requested a lock on the database.
Another minor semantic problem with this interface is that
locks are not inherited by a child process created using the
.Xr fork 2
system call.
The
.Xr flock 2
interface has much more rational last close semantics and
allows locks to be inherited by child processes.
The
.Xr flock 2
system call is recommended for applications that want to ensure the integrity
of their locks when using library routines or wish to pass locks
to their children.
.Pp
The
.Fn fcntl ,
.Xr flock 2 ,
and
.Xr lockf 3
locks are compatible.
Processes using different locking interfaces can cooperate
over the same file safely.
However, only one of such interfaces should be used within
the same process.
If a file is locked by a process through
.Xr flock 2 ,
any record within the file will be seen as locked
from the viewpoint of another process using
.Fn fcntl
or
.Xr lockf 3 ,
and vice versa.
Note that
.Fn fcntl F_GETLK
returns \-1 in
.Fa l_pid
if the process holding a blocking lock previously locked the
file descriptor by
.Xr flock 2 .
.Pp
All locks associated with a file for a given process are
removed when the process terminates.
.Pp
All locks obtained before a call to
.Xr execve 2
remain in effect until the new program releases them.
If the new program does not know about the locks, they will not be
released until the program exits.
.Pp
A potential for deadlock occurs if a process controlling a locked region
is put to sleep by attempting to lock the locked region of another process.
This implementation detects that sleeping until a locked region is unlocked
would cause a deadlock and fails with an
.Er EDEADLK
error.
.Sh RETURN VALUES
Upon successful completion, the value returned depends on
.Fa cmd
as follows:
.Bl -tag -width F_GETOWNX -offset indent
.It Dv F_DUPFD
A new file descriptor.
.It Dv F_DUP2FD
A file descriptor equal to
.Fa arg .
.It Dv F_GETFD
Value of flags.
.It Dv F_GETFL
Value of flags.
.It Dv F_GETOWN
Value of file descriptor owner.
.It other
Value other than -1.
.El
.Pp
Otherwise, a value of -1 is returned and
.Va errno
is set to indicate the error.
.Sh ERRORS
The
.Fn fcntl
system call will fail if:
.Bl -tag -width Er
.It Bq Er EAGAIN
The argument
.Fa cmd
is
.Dv F_SETLK ,
the type of lock
.Pq Fa l_type
is a shared lock
.Pq Dv F_RDLCK
or exclusive lock
.Pq Dv F_WRLCK ,
and the segment of a file to be locked is already
exclusive-locked by another process;
or the type is an exclusive lock and some portion of the
segment of a file to be locked is already shared-locked or
exclusive-locked by another process.
.It Bq Er EBADF
The
.Fa fd
argument
is not a valid open file descriptor.
.Pp
The argument
.Fa cmd
is
.Dv F_DUP2FD ,
and
.Fa arg
is not a valid file descriptor.
.Pp
The argument
.Fa cmd
is
.Dv F_SETLK
or
.Dv F_SETLKW ,
the type of lock
.Pq Fa l_type
is a shared lock
.Pq Dv F_RDLCK ,
and
.Fa fd
is not a valid file descriptor open for reading.
.Pp
The argument
.Fa cmd
is
.Dv F_SETLK
or
.Dv F_SETLKW ,
the type of lock
.Pq Fa l_type
is an exclusive lock
.Pq Dv F_WRLCK ,
and
.Fa fd
is not a valid file descriptor open for writing.
.It Bq Er EBUSY
The argument
.Fa cmd
is
.Dv F_ADD_SEALS ,
attempting to set
.Dv F_SEAL_WRITE ,
and writeable mappings of the file exist.
.It Bq Er EDEADLK
The argument
.Fa cmd
is
.Dv F_SETLKW ,
and a deadlock condition was detected.
.It Bq Er EINTR
The argument
.Fa cmd
is
.Dv F_SETLKW ,
and the system call was interrupted by a signal.
.It Bq Er EINVAL
The
.Fa cmd
argument
is
.Dv F_DUPFD
and
.Fa arg
is negative or greater than the maximum allowable number
(see
.Xr getdtablesize 2 ) .
.Pp
The argument
.Fa cmd
is
.Dv F_GETLK ,
.Dv F_SETLK
or
.Dv F_SETLKW
and the data to which
.Fa arg
points is not valid.
.Pp
The argument
.Fa cmd
is
.Dv F_ADD_SEALS
or
.Dv F_GET_SEALS ,
and the underlying filesystem does not support sealing.
.Pp
The argument
.Fa cmd
is invalid.
.It Bq Er EMFILE
The argument
.Fa cmd
is
.Dv F_DUPFD
and the maximum number of file descriptors permitted for the
process are already in use,
or no file descriptors greater than or equal to
.Fa arg
are available.
.It Bq Er ENOTTY
The
.Fa fd
argument is not a valid file descriptor for the requested operation.
This may be the case if
.Fa fd
is a device node, or a descriptor returned by
.Xr kqueue 2 .
.It Bq Er ENOLCK
The argument
.Fa cmd
is
.Dv F_SETLK
or
.Dv F_SETLKW ,
and satisfying the lock or unlock request would result in the
number of locked regions in the system exceeding a system-imposed limit.
.It Bq Er EOPNOTSUPP
The argument
.Fa cmd
is
.Dv F_GETLK ,
.Dv F_SETLK
or
.Dv F_SETLKW
and
.Fa fd
refers to a file for which locking is not supported.
.It Bq Er EOVERFLOW
The argument
.Fa cmd
is
.Dv F_GETLK ,
.Dv F_SETLK
or
.Dv F_SETLKW
and an
.Fa off_t
calculation overflowed.
.It Bq Er EPERM
The
.Fa cmd
argument
is
.Dv F_SETOWN
and
the process ID or process group given as an argument is in a
different session than the caller.
.Pp
The
.Fa cmd
argument
is
.Dv F_ADD_SEALS
and the
.Dv F_SEAL_SEAL
seal has already been set.
.It Bq Er ESRCH
The
.Fa cmd
argument
is
.Dv F_SETOWN
and
the process ID given as argument is not in use.
.El
.Pp
In addition, if
.Fa fd
refers to a descriptor open on a terminal device (as opposed to a
descriptor open on a socket), a
.Fa cmd
of
.Dv F_SETOWN
can fail for the same reasons as in
.Xr tcsetpgrp 3 ,
and a
.Fa cmd
of
.Dv F_GETOWN
for the reasons as stated in
.Xr tcgetpgrp 3 .
.Sh SEE ALSO
.Xr close 2 ,
.Xr dup2 2 ,
.Xr execve 2 ,
.Xr flock 2 ,
.Xr getdtablesize 2 ,
.Xr open 2 ,
.Xr sigaction 2 ,
.Xr lockf 3 ,
.Xr tcgetpgrp 3 ,
.Xr tcsetpgrp 3
.Sh STANDARDS
The
.Dv F_DUP2FD
and
.Dv F_DUP3FD
constants are not portable.
They are provided for compatibility with AIX and Solaris.
.Pp
Per
.St -susv4 ,
a call with
.Dv F_SETLKW
should fail with
.Bq Er EINTR
after any caught signal
and should continue waiting during thread suspension such as a stop signal.
However, in this implementation a call with
.Dv F_SETLKW
is restarted after catching a signal with a
.Dv SA_RESTART
handler or a thread suspension such as a stop signal.
.Sh HISTORY
The
.Fn fcntl
system call appeared in
.Bx 4.2 .
.Pp
The
.Dv F_DUP2FD
constant first appeared in
.Fx 7.1 .
.Pp
The
.Dv F_DUPFD_CLOFORK
and
.Dv F_DUP3FD
flags appeared in
.Fx 15.0 .