1.\" $NetBSD: mlock.2,v 1.4 1997/10/16 23:21:50 christos Exp $ 2.\" 3.\" Copyright (c) 1993 4.\" The Regents of the University of California. All rights reserved. 5.\" 6.\" Redistribution and use in source and binary forms, with or without 7.\" modification, are permitted provided that the following conditions 8.\" are met: 9.\" 1. Redistributions of source code must retain the above copyright 10.\" notice, this list of conditions and the following disclaimer. 11.\" 2. Redistributions in binary form must reproduce the above copyright 12.\" notice, this list of conditions and the following disclaimer in the 13.\" documentation and/or other materials provided with the distribution. 14.\" 3. All advertising materials mentioning features or use of this software 15.\" must display the following acknowledgement: 16.\" This product includes software developed by the University of 17.\" California, Berkeley and its contributors. 18.\" 4. Neither the name of the University nor the names of its contributors 19.\" may be used to endorse or promote products derived from this software 20.\" without specific prior written permission. 21.\" 22.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 23.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 24.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 25.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 26.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 27.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 28.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 29.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 30.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 31.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 32.\" SUCH DAMAGE. 33.\" 34.\" @(#)mlock.2 8.2 (Berkeley) 12/11/93 35.\" 36.Dd June 2, 1993 37.Dt MLOCK 2 38.Os 39.Sh NAME 40.Nm mlock , 41.Nm munlock 42.Nd lock (unlock) physical pages in memory 43.Sh SYNOPSIS 44.Fd #include <sys/types.h> 45.Fd #include <sys/mman.h> 46.Ft int 47.Fn mlock "void *addr" "size_t len" 48.Ft int 49.Fn munlock "void *addr" "size_t len" 50.Sh DESCRIPTION 51The 52.Nm mlock 53system call 54locks into memory the physical pages associated with the virtual address 55range starting at 56.Fa addr 57for 58.Fa len 59bytes. 60The 61.Nm munlock 62call unlocks pages previously locked by one or more 63.Nm mlock 64calls. 65For both, the 66.Fa addr 67parameter should be aligned to a multiple of the page size. 68If the 69.Fa len 70parameter is not a multiple of the page size, it will be rounded up 71to be so. 72The entire range must be allocated. 73.Pp 74After an 75.Nm mlock 76call, the indicated pages will cause neither a non-resident page 77nor address-translation fault until they are unlocked. 78They may still cause protection-violation faults or TLB-miss faults on 79architectures with software-managed TLBs. 80The physical pages remain in memory until all locked mappings for the pages 81are removed. 82Multiple processes may have the same physical pages locked via their own 83virtual address mappings. 84A single process may likewise have pages multiply-locked via different virtual 85mappings of the same pages or via nested 86.Nm mlock 87calls on the same address range. 88Unlocking is performed explicitly by 89.Nm munlock 90or implicitly by a call to 91.Nm munmap 92which deallocates the unmapped address range. 93Locked mappings are not inherited by the child process after a 94.Xr fork 2 . 95.Pp 96Since physical memory is a potentially scarce resource, processes are 97limited in how much they can lock down. 98A single process can 99.Nm mlock 100the minimum of 101a system-wide ``wired pages'' limit and 102the per-process 103.Li RLIMIT_MEMLOCK 104resource limit. 105.Sh RETURN VALUES 106A return value of 0 indicates that the call 107succeeded and all pages in the range have either been locked or unlocked. 108A return value of -1 indicates an error occurred and the locked 109status of all pages in the range remains unchanged. 110In this case, the global location 111.Va errno 112is set to indicate the error. 113.Sh ERRORS 114.Fn Mlock 115will fail if: 116.Bl -tag -width Er 117.It Bq Er EINVAL 118The address given is not page aligned or the length is negative. 119.It Bq Er EAGAIN 120Locking the indicated range would exceed either the system or per-process 121limit for locked memory. 122.It Bq Er ENOMEM 123Some portion of the indicated address range is not allocated. 124There was an error faulting/mapping a page. 125.El 126.Fn Munlock 127will fail if: 128.Bl -tag -width Er 129.It Bq Er EINVAL 130The address given is not page aligned or the length is negative. 131.It Bq Er ENOMEM 132Some portion of the indicated address range is not allocated. 133Some portion of the indicated address range is not locked. 134.El 135.Sh "SEE ALSO" 136.Xr fork 2 , 137.Xr mincore 2 , 138.Xr mmap 2 , 139.Xr munmap 2 , 140.Xr setrlimit 2 , 141.Xr getpagesize 3 142.Sh BUGS 143Unlike The Sun implementation, multiple 144.Nm mlock 145calls on the same address range require the corresponding number of 146.Nm munlock 147calls to actually unlock the pages, i.e. 148.Nm mlock 149nests. 150This should be considered a consequence of the implementation 151and not a feature. 152.Pp 153The per-process resource limit is a limit on the amount of virtual 154memory locked, while the system-wide limit is for the number of locked 155physical pages. 156Hence a process with two distinct locked mappings of the same physical page 157counts as 2 pages against the per-process limit and as only a single page 158in the system limit. 159.Sh HISTORY 160The 161.Fn mlock 162and 163.Fn munlock 164functions first appeared in 4.4BSD. 165