mmap(2) allocate memory, or map files or devices into memory

LIBRARY

Lb libc

SYNOPSIS

In sys/mman.h Ft void * Fn mmap void *addr size_t len int prot int flags int fd off_t offset

DESCRIPTION

The Fn mmap system call causes the pages starting at Fa addr and continuing for at most Fa len bytes to be mapped from the object described by Fa fd , starting at byte offset Fa offset . If Fa len is not a multiple of the pagesize, the mapped region may extend past the specified range. Any such extension beyond the end of the mapped object will be zero-filled.

If Fa addr is non-zero, it is used as a hint to the system. (As a convenience to the system, the actual address of the region may differ from the address supplied.) If Fa addr is zero, an address will be selected by the system. The actual starting address of the region is returned. A successful Fa mmap deletes any previous mapping in the allocated address range.

The protections (region accessibility) are specified in the Fa prot argument by or 'ing the following values:

PROT_NONE
Pages may not be accessed.
PROT_READ
Pages may be read.
PROT_WRITE
Pages may be written.
PROT_EXEC
Pages may be executed.

The Fa flags argument specifies the type of the mapped object, mapping options and whether modifications made to the mapped copy of the page are private to the process or are to be shared with other references. Sharing, mapping type and options are specified in the Fa flags argument by or 'ing the following values:

MAP_32BIT
Request a region in the first 2GB of the current process's address space. If a suitable region cannot be found, Fn mmap will fail. This flag is only available on 64-bit platforms.
MAP_ALIGNED (Fa n )
Align the region on a requested boundary. If a suitable region cannot be found, Fn mmap will fail. The Fa n argument specifies the binary logarithm of the desired alignment.
MAP_ALIGNED_SUPER
Align the region to maximize the potential use of large (``super'' ) pages. If a suitable region cannot be found, Fn mmap will fail. The system will choose a suitable page size based on the size of mapping. The page size used as well as the alignment of the region may both be affected by properties of the file being mapped. In particular, the physical address of existing pages of a file may require a specific alignment. The region is not guaranteed to be aligned on any specific boundary.
MAP_ANON
Map anonymous memory not associated with any specific file. The file descriptor used for creating MAP_ANON must be -1. The Fa offset argument must be 0.
MAP_ANONYMOUS
This flag is identical to MAP_ANON and is provided for compatibility.
MAP_EXCL
This flag can only be used in combination with MAP_FIXED Please see the definition of MAP_FIXED for the description of its effect.
MAP_FIXED
Do not permit the system to select a different address than the one specified. If the specified address cannot be used, Fn mmap will fail. If MAP_FIXED is specified, Fa addr must be a multiple of the pagesize. If MAP_EXCL is not specified, a successfull MAP_FIXED request replaces any previous mappings for the process' pages in the range from Fa addr to Fa addr + Fa len . In contrast, if MAP_EXCL is specified, the request will fail if a mapping already exists within the range.
MAP_HASSEMAPHORE
Notify the kernel that the region may contain semaphores and that special handling may be necessary.
MAP_INHERIT
This flag never operated as advertised and is no longer supported. Please refer to minherit(2) for further information.
MAP_NOCORE
Region is not included in a core file.
MAP_NOSYNC
Causes data dirtied via this VM map to be flushed to physical media only when necessary (usually by the pager) rather than gratuitously. Typically this prevents the update daemons from flushing pages dirtied through such maps and thus allows efficient sharing of memory across unassociated processes using a file-backed shared memory map. Without this option any VM pages you dirty may be flushed to disk every so often (every 30-60 seconds usually) which can create performance problems if you do not need that to occur (such as when you are using shared file-backed mmap regions for IPC purposes). Note that VM/file system coherency is maintained whether you use MAP_NOSYNC or not. This option is not portable across UNIX platforms (yet), though some may implement the same behavior by default.

WARNING Extending a file with ftruncate(2), thus creating a big hole, and then filling the hole by modifying a shared Fn mmap can lead to severe file fragmentation. In order to avoid such fragmentation you should always pre-allocate the file's backing store by Fn write Ns ing zero's into the newly extended area prior to modifying the area via your Fn mmap . The fragmentation problem is especially sensitive to MAP_NOSYNC pages, because pages may be flushed to disk in a totally random order.

The same applies when using MAP_NOSYNC to implement a file-based shared memory store. It is recommended that you create the backing store by Fn write Ns ing zero's to the backing file rather than Fn ftruncate Ns ing it. You can test file fragmentation by observing the KB/t (kilobytes per transfer) results from an ``iostat 1 '' while reading a large file sequentially, e.g. using ``dd if=filename of=/dev/null bs=32k ''

The fsync(2) system call will flush all dirty data and metadata associated with a file, including dirty NOSYNC VM data, to physical media. The sync(8) command and sync(2) system call generally do not flush dirty NOSYNC VM data. The msync(2) system call is usually not needed since BSD implements a coherent file system buffer cache. However, it may be used to associate dirty VM pages with file system buffers and thus cause them to be flushed to physical media sooner rather than later.

MAP_PREFAULT_READ
Immediately update the calling process's lowest-level virtual address translation structures, such as its page table, so that every memory resident page within the region is mapped for read access. Ordinarily these structures are updated lazily. The effect of this option is to eliminate any soft faults that would otherwise occur on the initial read accesses to the region. Although this option does not preclude Fa prot from including PROT_WRITE it does not eliminate soft faults on the initial write accesses to the region.
MAP_PRIVATE
Modifications are private.
MAP_SHARED
Modifications are shared.
MAP_STACK
MAP_STACK implies MAP_ANON and Fa offset of 0. The Fa fd argument must be -1 and Fa prot must include at least PROT_READ and PROT_WRITE This option creates a memory region that grows to at most Fa len bytes in size, starting from the stack top and growing down. The stack top is the starting address returned by the call, plus Fa len bytes. The bottom of the stack at maximum growth is the starting address returned by the call.

The close(2) system call does not unmap pages, see munmap(2) for further information.

The current design does not allow a process to specify the location of swap space. In the future we may define an additional mapping type, MAP_SWAP in which the file descriptor argument specifies a file or device to which swapping should be done.

NOTES

Although this implementation does not impose any alignment restrictions on the Fa offset argument, a portable program must only use page-aligned values.

Large page mappings require that the pages backing an object be aligned in matching blocks in both the virtual address space and RAM. The system will automatically attempt to use large page mappings when mapping an object that is already backed by large pages in RAM by aligning the mapping request in the virtual address space to match the alignment of the large physical pages. The system may also use large page mappings when mapping portions of an object that are not yet backed by pages in RAM. The MAP_ALIGNED_SUPER flag is an optimization that will align the mapping request to the size of a large page similar to MAP_ALIGNED except that the system will override this alignment if an object already uses large pages so that the mapping will be consistent with the existing large pages. This flag is mostly useful for maximizing the use of large pages on the first mapping of objects that do not yet have pages present in RAM.

RETURN VALUES

Upon successful completion, Fn mmap returns a pointer to the mapped region. Otherwise, a value of MAP_FAILED is returned and errno is set to indicate the error.

ERRORS

The Fn mmap system call will fail if:

Bq Er EACCES
The flag PROT_READ was specified as part of the Fa prot argument and Fa fd was not open for reading. The flags MAP_SHARED and PROT_WRITE were specified as part of the Fa flags and Fa prot argument and Fa fd was not open for writing.
Bq Er EBADF
The Fa fd argument is not a valid open file descriptor.
Bq Er EINVAL
MAP_FIXED was specified and the Fa addr argument was not page aligned, or part of the desired address space resides out of the valid address space for a user process.
Bq Er EINVAL
Both MAP_FIXED and MAP_32BIT were specified and part of the desired address space resides outside of the first 2GB of user address space.
Bq Er EINVAL
The Fa len argument was equal to zero.
Bq Er EINVAL
MAP_ALIGNED was specified and the desired alignment was either larger than the virtual address size of the machine or smaller than a page.
Bq Er EINVAL
MAP_ANON was specified and the Fa fd argument was not -1.
Bq Er EINVAL
MAP_ANON was specified and the Fa offset argument was not 0.
Bq Er EINVAL
Both MAP_FIXED and MAP_EXCL were specified, but the requested region is already used by a mapping.
Bq Er EINVAL
MAP_EXCL was specified, but MAP_FIXED was not.
Bq Er ENODEV
MAP_ANON has not been specified and Fa fd did not reference a regular or character special file.
Bq Er ENOMEM
MAP_FIXED was specified and the Fa addr argument was not available. MAP_ANON was specified and insufficient memory was available.

BUGS

The Fa len argument is limited to the maximum file size or available userland address space. Files may not be able to be made more than 1TB large on 32 bit systems due to file systems restrictions and bugs, but address space is far more restrictive. Larger files may be possible on 64 bit systems.

The previous documented limit of 2GB was a documentation bug. That limit has not existed since Fx 2.2 .