1 .\" Copyright (c) 1991, 1993
2 .\" The Regents of the University of California. All rights reserved.
4 .\" Redistribution and use in source and binary forms, with or without
5 .\" modification, are permitted provided that the following conditions
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 .\" 4. Neither the name of the University nor the names of its contributors
13 .\" may be used to endorse or promote products derived from this software
14 .\" without specific prior written permission.
16 .\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
17 .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18 .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19 .\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
20 .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
21 .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
22 .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
23 .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
24 .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
25 .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
28 .\" @(#)mmap.2 8.4 (Berkeley) 5/11/95
36 .Nd allocate memory, or map files or devices into memory
42 .Fn mmap "void *addr" "size_t len" "int prot" "int flags" "int fd" "off_t offset"
46 system call causes the pages starting at
48 and continuing for at most
50 bytes to be mapped from the object described by
52 starting at byte offset
56 is not a multiple of the pagesize, the mapped region may extend past the
58 Any such extension beyond the end of the mapped object will be zero-filled.
62 is non-zero, it is used as a hint to the system.
63 (As a convenience to the system, the actual address of the region may differ
64 from the address supplied.)
67 is zero, an address will be selected by the system.
68 The actual starting address of the region is returned.
71 deletes any previous mapping in the allocated address range.
73 The protections (region accessibility) are specified in the
79 .Bl -tag -width PROT_WRITE -compact
81 Pages may not be accessed.
87 Pages may be executed.
92 argument specifies the type of the mapped object, mapping options and
93 whether modifications made to the mapped copy of the page are private
94 to the process or are to be shared with other references.
95 Sharing, mapping type and options are specified in the
100 .Bl -tag -width MAP_PREFAULT_READ
102 Request a region in the first 2GB of the current process's address space.
103 If a suitable region cannot be found,
106 This flag is only available on 64-bit platforms.
107 .It Dv MAP_ALIGNED Ns Pq Fa n
108 Align the region on a requested boundary.
109 If a suitable region cannot be found,
114 argument specifies the binary logarithm of the desired alignment.
115 .It Dv MAP_ALIGNED_SUPER
116 Align the region to maximize the potential use of large
119 If a suitable region cannot be found,
122 The system will choose a suitable page size based on the size of
124 The page size used as well as the alignment of the region may both be
125 affected by properties of the file being mapped.
127 the physical address of existing pages of a file may require a specific
129 The region is not guaranteed to be aligned on any specific boundary.
131 Map anonymous memory not associated with any specific file.
132 The file descriptor used for creating
139 .\"Mapped from a regular file or character-special device memory.
141 This flag is identical to
143 and is provided for compatibility.
145 This flag can only be used in combination with
147 Please see the definition of
149 for the description of its effect.
151 Do not permit the system to select a different address than the one
153 If the specified address cannot be used,
160 must be a multiple of the pagesize.
163 is not specified, a successfull
165 request replaces any previous mappings for the process'
166 pages in the range from
174 is specified, the request will fail if a mapping
175 already exists within the range.
177 Instead of a mapping, create a guard of the specified size.
178 Guards allow a process to create reservations in its address space,
179 which can later be replaced by actual mappings.
182 will not create mappings in the address range of a guard unless
183 the request specifies
185 Guards can be destroyed with
187 Any memory access by a thread to the guarded range results
190 signal to that thread.
192 Region is not included in a core file.
194 Causes data dirtied via this VM map to be flushed to physical media
195 only when necessary (usually by the pager) rather than gratuitously.
196 Typically this prevents the update daemons from flushing pages dirtied
197 through such maps and thus allows efficient sharing of memory across
198 unassociated processes using a file-backed shared memory map.
200 this option any VM pages you dirty may be flushed to disk every so often
201 (every 30-60 seconds usually) which can create performance problems if you
202 do not need that to occur (such as when you are using shared file-backed
203 mmap regions for IPC purposes).
204 Note that VM/file system coherency is
205 maintained whether you use
208 This option is not portable
211 platforms (yet), though some may implement the same behavior
215 Extending a file with
217 thus creating a big hole, and then filling the hole by modifying a shared
219 can lead to severe file fragmentation.
220 In order to avoid such fragmentation you should always pre-allocate the
221 file's backing store by
223 zero's into the newly extended area prior to modifying the area via your
225 The fragmentation problem is especially sensitive to
227 pages, because pages may be flushed to disk in a totally random order.
229 The same applies when using
231 to implement a file-based shared memory store.
232 It is recommended that you create the backing store by
234 zero's to the backing file rather than
237 You can test file fragmentation by observing the KB/t (kilobytes per
238 transfer) results from an
240 while reading a large file sequentially, e.g.\& using
241 .Dq Li dd if=filename of=/dev/null bs=32k .
245 system call will flush all dirty data and metadata associated with a file,
246 including dirty NOSYNC VM data, to physical media.
251 system call generally do not flush dirty NOSYNC VM data.
254 system call is usually not needed since
256 implements a coherent file system buffer cache.
258 used to associate dirty VM pages with file system buffers and thus cause
259 them to be flushed to physical media sooner rather than later.
260 .It Dv MAP_PREFAULT_READ
261 Immediately update the calling process's lowest-level virtual address
262 translation structures, such as its page table, so that every memory
263 resident page within the region is mapped for read access.
264 Ordinarily these structures are updated lazily.
265 The effect of this option is to eliminate any soft faults that would
266 otherwise occur on the initial read accesses to the region.
267 Although this option does not preclude
271 it does not eliminate soft faults on the initial write accesses to the
274 Modifications are private.
276 Modifications are shared.
289 must include at least
295 a memory region that grows to at most
297 bytes in size, starting from the stack top and growing down.
299 stack top is the starting address returned by the call, plus
302 The bottom of the stack at maximum growth is the starting
303 address returned by the call.
308 Guards prevent inadvertent use of the regions into which those
309 stacks can grow without requiring mapping the whole stack in advance.
314 system call does not unmap pages, see
316 for further information.
318 Although this implementation does not impose any alignment restrictions on
321 argument, a portable program must only use page-aligned values.
323 Large page mappings require that the pages backing an object be
324 aligned in matching blocks in both the virtual address space and RAM.
325 The system will automatically attempt to use large page mappings when
326 mapping an object that is already backed by large pages in RAM by
327 aligning the mapping request in the virtual address space to match the
328 alignment of the large physical pages.
329 The system may also use large page mappings when mapping portions of an
330 object that are not yet backed by pages in RAM.
332 .Dv MAP_ALIGNED_SUPER
333 flag is an optimization that will align the mapping request to the
334 size of a large page similar to
336 except that the system will override this alignment if an object already
337 uses large pages so that the mapping will be consistent with the existing
339 This flag is mostly useful for maximizing the use of large pages on the
340 first mapping of objects that do not yet have pages present in RAM.
342 Upon successful completion,
344 returns a pointer to the mapped region.
345 Otherwise, a value of
349 is set to indicate the error.
359 was specified as part of the
363 was not open for reading.
368 were specified as part of the
374 was not open for writing.
379 is not a valid open file descriptor.
381 An invalid value was passed in the
385 An undefined option was set in the
403 At least one of these flags must be included.
406 was specified and the
408 argument was not page aligned, or part of the desired address space
409 resides out of the valid address space for a user process.
415 were specified and part of the desired address space resides outside
416 of the first 2GB of user address space.
424 was specified and the desired alignment was either larger than the
425 virtual address size of the machine or smaller than a page.
428 was specified and the
433 was specified and the
441 were specified, but the requested region is already used by a mapping.
449 was specified, but the
451 argument was not zero, the
453 argument was not -1, or the
459 was specified together with one of the flags
462 .Dv MAP_PREFAULT_READ ,
468 has not been specified and
470 did not reference a regular or character special file.
473 was specified and the
475 argument was not available.
477 was specified and insufficient memory was available.
494 is limited to the maximum file size or available userland address
496 Files may not be able to be made more than 1TB large on 32 bit systems
497 due to file systems restrictions and bugs, but address space is far more
499 Larger files may be possible on 64 bit systems.
501 The previous documented limit of 2GB was a documentation bug.
502 That limit has not existed since