BSD 4_4 development

[unix-history] / usr / share / man / cat2 / munlock.0

MLOCK(2)                    BSD Programmer's Manual                   MLOCK(2)

N\bNA\bAM\bME\bE
    m\bml\blo\boc\bck\bk, m\bmu\bun\bnl\blo\boc\bck\bk - lock (unlock) physical pages in memory

S\bSY\bYN\bNO\bOP\bPS\bSI\bIS\bS
    #\b#i\bin\bnc\bcl\blu\bud\bde\be <\b<s\bsy\bys\bs/\b/t\bty\byp\bpe\bes\bs.\b.h\bh>\b>
    #\b#i\bin\bnc\bcl\blu\bud\bde\be <\b<s\bsy\bys\bs/\b/m\bmm\bma\ban\bn.\b.h\bh>\b>

    _\bi_\bn_\bt
    m\bml\blo\boc\bck\bk(_\bc_\ba_\bd_\bd_\br_\b__\bt _\ba_\bd_\bd_\br, _\bs_\bi_\bz_\be_\b__\bt _\bl_\be_\bn);

    _\bi_\bn_\bt
    m\bmu\bun\bnl\blo\boc\bck\bk(_\bc_\ba_\bd_\bd_\br_\b__\bt _\ba_\bd_\bd_\br, _\bs_\bi_\bz_\be_\b__\bt _\bl_\be_\bn);

D\bDE\bES\bSC\bCR\bRI\bIP\bPT\bTI\bIO\bON\bN
    The m\bml\blo\boc\bck\bk system call locks into memory the physical pages associated
    with the virtual address range starting at _\ba_\bd_\bd_\br for _\bl_\be_\bn bytes.  The
    m\bmu\bun\bnl\blo\boc\bck\bk call unlocks pages previously locked by one or more m\bml\blo\boc\bck\bk calls.
    For both, the _\ba_\bd_\bd_\br parameter should be aligned to a multiple of the page
    size.  If the _\bl_\be_\bn parameter is not a multiple of the page size, it will
    be rounded up to be so.  The entire range must be allocated.

    After an m\bml\blo\boc\bck\bk call, the indicated pages will cause neither a non-
    resident page or address-translation fault until they are unlocked.  They
    may still cause protection-violation faults or TLB-miss faults on archi-
    tectures with software-managed TLBs.  The physical pages remain in memory
    until all locked mappings for the pages are removed.  Multiple processes
    may have the same physical pages locked via their own virtual address
    mappings.  A single process may likewise have pages multiply-locked via
    different virtual mappings of the same pages or via nested m\bml\blo\boc\bck\bk calls on
    the same address range.  Unlocking is performed explicitly by m\bmu\bun\bnl\blo\boc\bck\bk or
    implicitly by a call to m\bmu\bun\bnm\bma\bap\bp which deallocates the unmapped address
    range.  Locked mappings are not inherited by the child process after a
    fork(2).

    Since physical memory is a potentially scarce resource, processes are
    limited in how much they can lock down.  A single process can m\bml\blo\boc\bck\bk the
    minimum of a system-wide ``wired pages'' limit and the per-process
    RLIMIT_MEMLOCK resource limit.

R\bRE\bET\bTU\bUR\bRN\bN V\bVA\bAL\bLU\bUE\bES\bS
    A return value of 0 indicates that the call succeeded and all pages in
    the range have either been locked or unlocked.  A return value of -1 in-
    dicates an error occurred and the locked status of all pages in the range
    remains unchanged.  In this case, the global location _\be_\br_\br_\bn_\bo is set to in-
    dicate the error.

E\bER\bRR\bRO\bOR\bRS\bS
    M\bMl\blo\boc\bck\bk() will fail if:

    [EINVAL]      The address given is not page aligned or the length is neg-
                  ative.

    [EAGAIN]      Locking the indicated range would exceed either the system
                  or per-process limit for locked memory.

    [ENOMEM]      Some portion of the indicated address range is not allocat-
                  ed.  There was an error faulting/mapping a page.
    M\bMu\bun\bnl\blo\boc\bck\bk() will fail if:

    [EINVAL]      The address given is not page aligned or the length is neg-
                  ative.

    [ENOMEM]      Some portion of the indicated address range is not allocat-
                  ed.  Some portion of the indicated address range is not
                  locked.

S\bSE\bEE\bE A\bAL\bLS\bSO\bO
    fork(2),  mmap(2),  munmap(2),  setrlimit(2),  getpagesize(3)

B\bBU\bUG\bGS\bS
    Unlike The Sun implementation, multiple m\bml\blo\boc\bck\bk calls on the same address
    range require the corresponding number of m\bmu\bun\bnl\blo\boc\bck\bk calls to actually un-
    lock the pages, i.e.  m\bml\blo\boc\bck\bk nests.  This should be considered a conse-
    quence of the implementation and not a feature.

    The per-process resource limit is a limit on the amount of virtual memory
    locked, while the system-wide limit is for the number of locked physical
    pages.  Hence a process with two distinct locked mappings of the same
    physical page counts as 2 pages against the per-process limit and as only
    a single page in the system limit.

H\bHI\bIS\bST\bTO\bOR\bRY\bY
    The m\bml\blo\boc\bck\bk() and m\bmu\bun\bnl\blo\boc\bck\bk() functions first appeared in 4.4BSD.

4.4BSD                           June 2, 1993                                2