1.\" $OpenBSD: mlock.2,v 1.11 2001/03/09 15:15:20 art Exp $ 2.\" $NetBSD: mlock.2,v 1.3 1995/06/24 10:42:03 cgd Exp $ 3.\" 4.\" Copyright (c) 1993 5.\" The Regents of the University of California. All rights reserved. 6.\" 7.\" Redistribution and use in source and binary forms, with or without 8.\" modification, are permitted provided that the following conditions 9.\" are met: 10.\" 1. Redistributions of source code must retain the above copyright 11.\" notice, this list of conditions and the following disclaimer. 12.\" 2. Redistributions in binary form must reproduce the above copyright 13.\" notice, this list of conditions and the following disclaimer in the 14.\" documentation and/or other materials provided with the distribution. 15.\" 3. All advertising materials mentioning features or use of this software 16.\" must display the following acknowledgement: 17.\" This product includes software developed by the University of 18.\" California, Berkeley and its contributors. 19.\" 4. Neither the name of the University nor the names of its contributors 20.\" may be used to endorse or promote products derived from this software 21.\" without specific prior written permission. 22.\" 23.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 24.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 25.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 26.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 27.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 28.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 29.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 30.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 31.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 32.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 33.\" SUCH DAMAGE. 34.\" 35.\" @(#)mlock.2 8.2 (Berkeley) 12/11/93 36.\" 37.Dd June 2, 1993 38.Dt MLOCK 2 39.Os 40.Sh NAME 41.Nm mlock , 42.Nm munlock 43.Nd lock (unlock) physical pages in memory 44.Sh SYNOPSIS 45.Fd #include <sys/types.h> 46.Fd #include <sys/mman.h> 47.Ft int 48.Fn mlock "void *addr" "size_t len" 49.Ft int 50.Fn munlock "void *addr" "size_t len" 51.Sh DESCRIPTION 52The 53.Nm mlock 54system call 55locks into memory the physical pages associated with the virtual address 56range starting at 57.Fa addr 58for 59.Fa len 60bytes. 61The 62.Nm munlock 63call unlocks pages previously locked by one or more 64.Nm mlock 65calls. 66For both, the 67.Fa addr 68parameter should be aligned to a multiple of the page size. 69If the 70.Fa len 71parameter is not a multiple of the page size, it will be rounded up 72to be so. 73The entire range must be allocated. 74.Pp 75After an 76.Nm mlock 77call, the indicated pages will cause neither a non-resident page 78nor address-translation fault until they are unlocked. 79They may still cause protection-violation faults or TLB-miss faults on 80architectures with software-managed TLBs. 81The physical pages remain in memory until all locked mappings for the pages 82are removed. 83Multiple processes may have the same physical pages locked via their own 84virtual address mappings. 85A single process may likewise have pages multiply locked via different virtual 86mappings of the same pages or via nested 87.Nm mlock 88calls on the same address range. 89Unlocking is performed explicitly by 90.Nm munlock 91or implicitly by a call to 92.Nm munmap 93which deallocates the unmapped address range. 94Locked mappings are not inherited by the child process after a 95.Xr fork 2 . 96.Pp 97Since physical memory is a potentially scarce resource, processes are 98limited in how much they can lock down. 99A single process can 100.Nm mlock 101the minimum of 102a system-wide ``wired pages'' limit and 103the per-process 104.Li RLIMIT_MEMLOCK 105resource limit. 106.Sh RETURN VALUES 107A return value of 0 indicates that the call 108succeeded and all pages in the range have either been locked or unlocked. 109A return value of \-1 indicates an error occurred and the locked 110status of all pages in the range remains unchanged. 111In this case, the global location 112.Va errno 113is set to indicate the error. 114.Sh ERRORS 115.Fn mlock 116will fail if: 117.Bl -tag -width Er 118.It Bq Er EINVAL 119The address given is not page aligned or the length is negative. 120.It Bq Er EAGAIN 121Locking the indicated range would exceed either the system or per-process 122limit for locked memory. 123.It Bq Er ENOMEM 124Some portion of the indicated address range is not allocated. 125There was an error faulting/mapping a page. 126.El 127.Fn munlock 128will fail if: 129.Bl -tag -width Er 130.It Bq Er EINVAL 131The address given is not page aligned or the length is negative. 132.It Bq Er ENOMEM 133Some portion of the indicated address range is not allocated. 134Some portion of the indicated address range is not locked. 135.El 136.Sh SEE ALSO 137.Xr fork 2 , 138.Xr mincore 2 , 139.Xr minherit 2 , 140.Xr mlockall 2 , 141.Xr mmap 2 , 142.Xr munmap 2 , 143.Xr setrlimit 2 , 144.Xr getpagesize 3 145.Sh BUGS 146Unlike The Sun implementation, multiple 147.Nm mlock 148calls on the same address range require the corresponding number of 149.Nm munlock 150calls to actually unlock the pages, i.e., 151.Nm mlock 152nests. 153This should be considered a consequence of the implementation 154and not a feature. 155.Pp 156The per-process resource limit is a limit on the amount of virtual 157memory locked, while the system-wide limit is for the number of locked 158physical pages. 159Hence a process with two distinct locked mappings of the same physical page 160counts as 2 pages against the per-process limit and as only a single page 161in the system limit. 162.Sh HISTORY 163The 164.Fn mlock 165and 166.Fn munlock 167functions first appeared in 168.Bx 4.4 . 169