pldd.1, bpf.2, chdir.2, clone.2, fanotify_init.2, fanotify_mark.2, intro.2, ipc.2...

[thirdparty/man-pages.git] / man2 / mprotect.2

.\" Copyright (C) 2007 Michael Kerrisk <mtk.manpages@gmail.com>
.\" and Copyright (C) 1995 Michael Shields <shields@tembel.org>.
.\"
.\" %%%LICENSE_START(VERBATIM)
.\" Permission is granted to make and distribute verbatim copies of this
.\" manual provided the copyright notice and this permission notice are
.\" preserved on all copies.
.\"
.\" Permission is granted to copy and distribute modified versions of this
.\" manual under the conditions for verbatim copying, provided that the
.\" entire resulting derived work is distributed under the terms of a
.\" permission notice identical to this one.
.\"
.\" Since the Linux kernel and libraries are constantly changing, this
.\" manual page may be incorrect or out-of-date.  The author(s) assume no
.\" responsibility for errors or omissions, or for damages resulting from
.\" the use of the information contained herein.  The author(s) may not
.\" have taken the same level of care in the production of this manual,
.\" which is licensed free of charge, as they might when working
.\" professionally.
.\"
.\" Formatted or processed versions of this manual, if unaccompanied by
.\" the source, must acknowledge the copyright and author of this work.
.\" %%%LICENSE_END
.\"
.\" Modified 1996-10-22 by Eric S. Raymond <esr@thyrsus.com>
.\" Modified 1997-05-31 by Andries Brouwer <aeb@cwi.nl>
.\" Modified 2003-08-24 by Andries Brouwer <aeb@cwi.nl>
.\" Modified 2004-08-16 by Andi Kleen <ak@muc.de>
.\" 2007-06-02, mtk: Fairly substantial rewrites and additions, and
.\" a much improved example program.
.\"
.TH MPROTECT 2 2019-08-02 "Linux" "Linux Programmer's Manual"
.SH NAME
mprotect, pkey_mprotect \- set protection on a region of memory
.SH SYNOPSIS
.nf
.B #include <sys/mman.h>
.PP
.BI "int mprotect(void *" addr ", size_t " len ", int " prot );

.BR "#define _GNU_SOURCE" "             /* See feature_test_macros(7) */"
.B #include <sys/mman.h>
.PP
.BI "int pkey_mprotect(void *" addr ", size_t " len ", int " prot ", int " pkey ");
.fi
.SH DESCRIPTION
.BR mprotect ()
changes the access protections for the calling process's memory pages
containing any part of the address range in the
interval [\fIaddr\fP,\ \fIaddr\fP+\fIlen\fP\-1].
.I addr
must be aligned to a page boundary.
.PP
If the calling process tries to access memory in a manner
that violates the protections, then the kernel generates a
.B SIGSEGV
signal for the process.
.PP
.I prot
is a combination of the following access flags:
.B PROT_NONE
or a bitwise-or of the other values in the following list:
.TP 1.1i
.B PROT_NONE
The memory cannot be accessed at all.
.TP
.B PROT_READ
The memory can be read.
.TP
.B PROT_WRITE
The memory can be modified.
.TP
.B PROT_EXEC
The memory can be executed.
.TP
.BR PROT_SEM " (since Linux 2.5.7)"
The memory can be used for atomic operations.
This flag was introduced as part of the
.BR futex (2)
implementation (in order to guarantee the ability to perform atomic
operations required by commands such as
.BR FUTEX_WAIT ),
but is not currently used in on any architecture.
.TP
.BR PROT_SAO " (since Linux 2.6.26)"
.\" commit aba46c5027cb59d98052231b36efcbbde9c77a1d
.\" commit ef3d3246a0d06be622867d21af25f997aeeb105f
The memory should have strong access ordering.
This feature is specific to
the PowerPC architecture
(version 2.06 of the architecture specification adds the SAO CPU feature,
and it is available on POWER 7 or PowerPC A2, for example).
.PP
Additionally (since Linux 2.6.0),
.I prot
can have one of the following flags set:
.TP 1.1i
.\" mm/mmap.c:
.\"	vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) |
.\"			mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
.\" And calc_vm_flag_bits converts only GROWSDOWN/DENYWRITE/LOCKED.
.B PROT_GROWSUP
Apply the protection mode up to the end of a mapping
that grows upwards.
(Such mappings are created for the stack area on
architectures\(emfor example, HP-PARISC\(emthat
have an upwardly growing stack.)
.\" The VMA is one that was marked with VM_GROWSUP by the kernel
.\" when the stack was created. Note that (unlike VM_GROWSDOWN),
.\" there is no mmap() flag (analogous to MAP_GROWSDOWN) for
.\" creating a VMA that is marked VM_GROWSUP.
.TP
.B PROT_GROWSDOWN
Apply the protection mode down to the beginning of a mapping
that grows downward
(which should be a stack segment or a segment mapped with the
.B MAP_GROWSDOWN
flag set).
.PP
Like
.BR mprotect (),
.BR pkey_mprotect ()
changes the protection on the pages specified by
.IR addr
and
.IR len .
The
.I pkey
argument specifies the protection key (see
.BR pkeys (7))
to assign to the memory.
The protection key must be allocated with
.BR pkey_alloc (2)
before it is passed to
.BR pkey_mprotect ().
For an example of the use of this system call, see
.BR pkeys (7).
.SH RETURN VALUE
On success,
.BR mprotect ()
and
.BR pkey_mprotect ()
return zero.
On error, these system calls return \-1, and
.I errno
is set appropriately.
.SH ERRORS
.TP
.B EACCES
The memory cannot be given the specified access.
This can happen, for example, if you
.BR mmap (2)
a file to which you have read-only access, then ask
.BR mprotect ()
to mark it
.BR PROT_WRITE .
.TP
.B EINVAL
\fIaddr\fP is not a valid pointer,
or not a multiple of the system page size.
.TP
.BR EINVAL
.RB ( pkey_mprotect ())
\fIpkey\fP has not been allocated with
.BR pkey_alloc (2)
.TP
.BR EINVAL
Both
.BR PROT_GROWSUP
and
.BR PROT_GROWSDOWN
were specified in
.IR prot .
.TP
.BR EINVAL
Invalid flags specified in
.IR prot .
.TP
.BR EINVAL
(PowerPC architecture)
.B PROT_SAO
was specified in
.IR prot ,
but SAO hardware feature is not available.
.TP
.B ENOMEM
Internal kernel structures could not be allocated.
.TP
.B ENOMEM
Addresses in the range
.RI [ addr ,
.IR addr + len \-1]
are invalid for the address space of the process,
or specify one or more pages that are not mapped.
(Before kernel 2.4.19, the error
.BR EFAULT
was incorrectly produced for these cases.)
.TP
.B ENOMEM
Changing the protection of a memory region would result in the total number of
mappings with distinct attributes (e.g., read versus read/write protection)
exceeding the allowed maximum.
.\" I.e., the number of VMAs would exceed the 64 kB maximum
(For example, making the protection of a range
.BR PROT_READ
in the middle of a region currently protected as
.BR PROT_READ|PROT_WRITE
would result in three mappings:
two read/write mappings at each end and a read-only mapping in the middle.)
.SH VERSIONS
.BR pkey_mprotect ()
first appeared in Linux 4.9;
library support was added in glibc 2.27.
.SH CONFORMING TO
.BR mprotect ():
POSIX.1-2001, POSIX.1-2008, SVr4.
.\" SVr4 defines an additional error
.\" code EAGAIN. The SVr4 error conditions don't map neatly onto Linux's.
POSIX says that the behavior of
.BR mprotect ()
is unspecified if it is applied to a region of memory that
was not obtained via
.BR mmap (2).
.PP
.BR pkey_mprotect ()
is a nonportable Linux extension.
.SH NOTES
On Linux, it is always permissible to call
.BR mprotect ()
on any address in a process's address space (except for the
kernel vsyscall area).
In particular, it can be used
to change existing code mappings to be writable.
.PP
Whether
.B PROT_EXEC
has any effect different from
.B PROT_READ
depends on processor architecture, kernel version, and process state.
If
.B READ_IMPLIES_EXEC
is set in the process's personality flags (see
.BR personality (2)),
specifying
.B PROT_READ
will implicitly add
.BR PROT_EXEC .
.PP
On some hardware architectures (e.g., i386),
.B PROT_WRITE
implies
.BR PROT_READ .
.PP
POSIX.1 says that an implementation may permit access
other than that specified in
.IR prot ,
but at a minimum can allow write access only if
.B PROT_WRITE
has been set, and must not allow any access if
.B PROT_NONE
has been set.
.PP
Applications should be careful when mixing use of
.BR mprotect ()
and
.BR pkey_mprotect ().
On x86, when
.BR mprotect ()
is used with
.IR prot
set to
.B PROT_EXEC
a pkey is may be allocated and set on the memory implicitly
by the kernel, but only when the pkey was 0 previously.
.PP
On systems that do not support protection keys in hardware,
.BR pkey_mprotect ()
may still be used, but
.IR pkey
must be set to -1.
When called this way, the operation of
.BR pkey_mprotect ()
is equivalent to
.BR mprotect ().
.SH EXAMPLE
.\" sigaction.2 refers to this example
.PP
The program below demonstrates the use of
.BR mprotect ().
The program allocates four pages of memory, makes the third
of these pages read-only, and then executes a loop that walks upward
through the allocated region modifying bytes.
.PP
An example of what we might see when running the program is the
following:
.PP
.in +4n
.EX
.RB "$" " ./a.out"
Start of region:        0x804c000
Got SIGSEGV at address: 0x804e000
.EE
.in
.SS Program source
\&
.EX
#include <unistd.h>
#include <signal.h>
#include <stdio.h>
#include <malloc.h>
#include <stdlib.h>
#include <errno.h>
#include <sys/mman.h>

#define handle_error(msg) \e
    do { perror(msg); exit(EXIT_FAILURE); } while (0)

static char *buffer;

static void
handler(int sig, siginfo_t *si, void *unused)
{
    /* Note: calling printf() from a signal handler is not safe
       (and should not be done in production programs), since
       printf() is not async\-signal\-safe; see signal-safety(7).
       Nevertheless, we use printf() here as a simple way of
       showing that the handler was called. */

    printf("Got SIGSEGV at address: 0x%lx\en",
            (long) si\->si_addr);
    exit(EXIT_FAILURE);
}

int
main(int argc, char *argv[])
{
    char *p;
    int pagesize;
    struct sigaction sa;

    sa.sa_flags = SA_SIGINFO;
    sigemptyset(&sa.sa_mask);
    sa.sa_sigaction = handler;
    if (sigaction(SIGSEGV, &sa, NULL) == \-1)
        handle_error("sigaction");

    pagesize = sysconf(_SC_PAGE_SIZE);
    if (pagesize == \-1)
        handle_error("sysconf");

    /* Allocate a buffer aligned on a page boundary;
       initial protection is PROT_READ | PROT_WRITE */

    buffer = memalign(pagesize, 4 * pagesize);
    if (buffer == NULL)
        handle_error("memalign");

    printf("Start of region:        0x%lx\en", (long) buffer);

    if (mprotect(buffer + pagesize * 2, pagesize,
                PROT_READ) == \-1)
        handle_error("mprotect");

    for (p = buffer ; ; )
        *(p++) = \(aqa\(aq;

    printf("Loop completed\en");     /* Should never happen */
    exit(EXIT_SUCCESS);
}
.EE
.SH SEE ALSO
.BR mmap (2),
.BR sysconf (3),
.BR pkeys (7)