| blob | db400b5b080ca64f0064b6e8764817bd4f7d41eb |
1 .\" Copyright (c) 1993
2 .\" The Regents of the University of California. All rights reserved.
3 .\"
4 .\" Redistribution and use in source and binary forms, with or without
5 .\" modification, are permitted provided that the following conditions
6 .\" are met:
7 .\" 1. Redistributions of source code must retain the above copyright
8 .\" notice, this list of conditions and the following disclaimer.
9 .\" 2. Redistributions in binary form must reproduce the above copyright
10 .\" notice, this list of conditions and the following disclaimer in the
11 .\" documentation and/or other materials provided with the distribution.
12 .\" 3. All advertising materials mentioning features or use of this software
13 .\" must display the following acknowledgement:
14 .\" This product includes software developed by the University of
15 .\" California, Berkeley and its contributors.
16 .\" 4. Neither the name of the University nor the names of its contributors
17 .\" may be used to endorse or promote products derived from this software
18 .\" without specific prior written permission.
19 .\"
20 .\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
21 .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
22 .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
23 .\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
24 .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
25 .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
26 .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
27 .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
28 .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
29 .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
30 .\" SUCH DAMAGE.
31 .\"
32 .\" @(#)mlock.2 8.2 (Berkeley) 12/11/93
33 .\" $FreeBSD: src/lib/libc/sys/mlock.2,v 1.6.2.5 2001/12/14 18:34:01 ru Exp $
34 .\" $DragonFly: src/lib/libc/sys/mlock.2,v 1.4 2006/02/17 19:35:06 swildner Exp $
35 .\"
36 .Dd May 18, 2004
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 LIBRARY
44 .Lb libc
45 .Sh SYNOPSIS
46 .In sys/types.h
47 .In sys/mman.h
48 .Ft int
49 .Fn mlock "const void *addr" "size_t len"
50 .Ft int
51 .Fn munlock "const void *addr" "size_t len"
52 .Sh DESCRIPTION
53 The
54 .Fn mlock
55 system call
56 locks into memory the physical pages associated with the virtual address
57 range starting at
58 .Fa addr
59 for
60 .Fa len
61 bytes.
62 The
63 .Fn munlock
64 call unlocks pages previously locked by one or more
65 .Fn mlock
66 calls.
67 For both, the
68 .Fa addr
69 parameter should be aligned to a multiple of the page size.
70 If the
71 .Fa len
72 parameter is not a multiple of the page size, it will be rounded up
73 to be so.
74 The entire range must be allocated.
75 .Pp
76 After an
77 .Fn mlock
78 call, the indicated pages will cause neither a non-resident page
79 nor address-translation fault until they are unlocked.
80 They may still cause protection-violation faults or TLB-miss faults on
81 architectures with software-managed TLBs.
82 The physical pages remain in memory until all locked mappings for the pages
83 are removed.
84 Multiple processes may have the same physical pages locked via their own
85 virtual address mappings.
86 A single process may likewise have pages multiply-locked via different virtual
87 mappings of the same pages or via nested
88 .Fn mlock
89 calls on the same address range.
90 Unlocking is performed explicitly by
91 .Fn munlock
92 or implicitly by a call to
93 .Fn munmap
94 which deallocates the unmapped address range.
95 Locked mappings are not inherited by the child process after a
96 .Xr fork 2 .
97 .Pp
98 Since physical memory is a potentially scarce resource, processes are
99 limited in how much they can lock down.
100 A single process can
101 .Fn mlock
102 the minimum of
103 a system-wide ``wired pages'' limit and
104 the per-process
105 .Li RLIMIT_MEMLOCK
106 resource limit.
107 .Pp
108 These calls are only available to the super-user.
109 .Sh RETURN VALUES
110 .Rv -std
111 .Pp
112 If the call succeeds, all pages in the range become locked (unlocked);
113 otherwise the locked status of all pages in the range remains unchanged.
114 .Sh ERRORS
115 .Fn Mlock
116 will fail if:
117 .Bl -tag -width Er
118 .It Bq Er EPERM
119 The caller is not the super-user.
120 .It Bq Er EINVAL
121 The address given is not page aligned or the length is negative.
122 .It Bq Er EAGAIN
123 Locking the indicated range would exceed either the system or per-process
124 limit for locked memory.
125 .It Bq Er ENOMEM
126 Some portion of the indicated address range is not allocated.
127 There was an error faulting/mapping a page.
128 .El
129 .Fn Munlock
130 will fail if:
131 .Bl -tag -width Er
132 .It Bq Er EPERM
133 The caller is not the super-user.
134 .It Bq Er EINVAL
135 The address given is not page aligned or the length is negative.
136 .It Bq Er ENOMEM
137 Some portion of the indicated address range is not allocated.
138 Some portion of the indicated address range is not locked.
139 .El
140 .Sh "SEE ALSO"
141 .Xr fork 2 ,
142 .Xr mincore 2 ,
143 .Xr minherit 2 ,
144 .Xr mmap 2 ,
145 .Xr munmap 2 ,
146 .Xr setrlimit 2 ,
147 .Xr getpagesize 3
148 .Sh HISTORY
149 The
150 .Fn mlock
151 and
152 .Fn munlock
153 functions first appeared in
154 .Bx 4.4 .
155 .Sh BUGS
156 The per-process resource limit is a limit on the amount of virtual
157 memory locked, while the system-wide limit is for the number of locked
158 physical pages.
159 Hence a process with two distinct locked mappings of the same physical page
160 counts as 2 pages against the per-process limit and as only a single page
161 in the system limit.
162 .Pp
163 The per-process resource limit is not currently supported.