man/man2/mbind.2

.\" Copyright, the authors of the Linux man-pages project
.\"
.\" SPDX-License-Identifier: Linux-man-pages-copyleft-var
.\"
.\" FIXME
.\" Linux 3.8 added MPOL_MF_LAZY, which needs to be documented.
.\" Does it also apply for move_pages()?
.\"
.\"                commit b24f53a0bea38b266d219ee651b22dba727c44ae
.\"                Author: Lee Schermerhorn <lee.schermerhorn@hp.com>
.\"                Date:   Thu Oct 25 14:16:32 2012 +0200
.\"
.TH mbind 2 (date) "Linux man-pages (unreleased)"
.SH NAME
mbind \- set memory policy for a memory range
.SH LIBRARY
NUMA (Non-Uniform Memory Access) policy library
.RI ( libnuma ,\~ \-lnuma )
.SH SYNOPSIS
.nf
.B "#include <numaif.h>"
.P
.BR "long mbind(" "unsigned long size, unsigned long maxnode;"
.BI "           void " addr [ size "], unsigned long " size  ", int " mode ,
.BI "           const unsigned long " nodemask [( maxnode " + ULONG_WIDTH \- 1)"
.B "                                        / ULONG_WIDTH],"
.BI "           unsigned long " maxnode ", unsigned int " flags );
.fi
.SH DESCRIPTION
.BR mbind ()
sets the NUMA memory policy,
which consists of a policy mode and zero or more nodes,
for the memory range starting with
.I addr
and continuing for
.I size
bytes.
The memory policy defines from which node memory is allocated.
.P
If the memory range specified by the
.IR addr " and " size
arguments includes an "anonymous" region of memory\[em]that is
a region of memory created using the
.BR mmap (2)
system call with the
.BR MAP_ANONYMOUS \[em]or
a memory-mapped file, mapped using the
.BR mmap (2)
system call with the
.B MAP_PRIVATE
flag, pages will be allocated only according to the specified
policy when the application writes (stores) to the page.
For anonymous regions, an initial read access will use a shared
page in the kernel containing all zeros.
For a file mapped with
.BR MAP_PRIVATE ,
an initial read access will allocate pages according to the
memory policy of the thread that causes the page to be allocated.
This may not be the thread that called
.BR mbind ().
.P
The specified policy will be ignored for any
.B MAP_SHARED
mappings in the specified memory range.
Rather the pages will be allocated according to the memory policy
of the thread that caused the page to be allocated.
Again, this may not be the thread that called
.BR mbind ().
.P
If the specified memory range includes a shared memory region
created using the
.BR shmget (2)
system call and attached using the
.BR shmat (2)
system call,
pages allocated for the anonymous or shared memory region will
be allocated according to the policy specified, regardless of which
process attached to the shared memory segment causes the allocation.
If, however, the shared memory region was created with the
.B SHM_HUGETLB
flag,
the huge pages will be allocated according to the policy specified
only if the page allocation is caused by the process that calls
.BR mbind ()
for that region.
.P
By default,
.BR mbind ()
has an effect only for new allocations; if the pages inside
the range have been already touched before setting the policy,
then the policy has no effect.
This default behavior may be overridden by the
.B MPOL_MF_MOVE
and
.B MPOL_MF_MOVE_ALL
flags described below.
.P
The
.I mode
argument must specify one of
.BR MPOL_DEFAULT ,
.BR MPOL_BIND ,
.BR MPOL_INTERLEAVE ,
.BR MPOL_WEIGHTED_INTERLEAVE ,
.BR MPOL_PREFERRED ,
.BR MPOL_PREFERRED_MANY ,
or
.B MPOL_LOCAL
(which are described in detail below).
All policy modes except
.B MPOL_DEFAULT
require the caller to specify the node or nodes to which the mode applies,
via the
.I nodemask
argument.
.P
The
.I mode
argument may also include an optional
.IR "mode flag" .
The supported
.I "mode flags"
are:
.TP
.BR MPOL_F_NUMA_BALANCING " (since Linux 5.15)"
.\" commit bda420b985054a3badafef23807c4b4fa38a3dff
.\" commit 6d2aec9e123bb9c49cb5c7fc654f25f81e688e8c
When
.I mode
is
.BR MPOL_BIND ,
enable the kernel NUMA balancing for the task if it is supported by the kernel.
If the flag isn't supported by the kernel, or is used with
.I mode
other than
.BR MPOL_BIND ,
\-1 is returned and
.I errno
is set to
.BR EINVAL .
.TP
.BR MPOL_F_STATIC_NODES " (since Linux-2.6.26)"
A nonempty
.I nodemask
specifies physical node IDs.
Linux does not remap the
.I nodemask
when the thread moves to a different cpuset context,
nor when the set of nodes allowed by the thread's
current cpuset context changes.
.TP
.BR MPOL_F_RELATIVE_NODES " (since Linux-2.6.26)"
A nonempty
.I nodemask
specifies node IDs that are relative to the set of
node IDs allowed by the thread's current cpuset.
.P
.I nodemask
points to a bit mask of nodes containing up to
.I maxnode
bits.
The bit mask size is rounded to the next multiple of
.IR "sizeof(unsigned long)" ,
but the kernel will use bits only up to
.IR maxnode .
A NULL value of
.I nodemask
or a
.I maxnode
value of zero specifies the empty set of nodes.
If the value of
.I maxnode
is zero,
the
.I nodemask
argument is ignored.
Where a
.I nodemask
is required, it must contain at least one node that is on-line,
allowed by the thread's current cpuset context
(unless the
.B MPOL_F_STATIC_NODES
mode flag is specified),
and contains memory.
.P
The
.I mode
argument must include one of the following values:
.TP
.B MPOL_DEFAULT
This mode requests that any nondefault policy be removed,
restoring default behavior.
When applied to a range of memory via
.BR mbind (),
this means to use the thread memory policy,
which may have been set with
.BR set_mempolicy (2).
If the mode of the thread memory policy is also
.BR MPOL_DEFAULT ,
the system-wide default policy will be used.
The system-wide default policy allocates
pages on the node of the CPU that triggers the allocation.
For
.BR MPOL_DEFAULT ,
the
.I nodemask
and
.I maxnode
arguments must be specify the empty set of nodes.
.TP
.B MPOL_BIND
This mode specifies a strict policy that restricts memory allocation to
the nodes specified in
.IR nodemask .
If
.I nodemask
specifies more than one node, page allocations will come from
the node with sufficient free memory that is closest to
the node where the allocation takes place.
Pages will not be allocated from any node not specified in the
IR nodemask .
(Before Linux 2.6.26,
.\" commit 19770b32609b6bf97a3dece2529089494cbfc549
page allocations came from
the node with the lowest numeric node ID first, until that node
contained no free memory.
Allocations then came from the node with the next highest
node ID specified in
.I nodemask
and so forth, until none of the specified nodes contained free memory.)
.TP
.B MPOL_INTERLEAVE
This mode specifies that page allocations be interleaved across the
set of nodes specified in
.IR nodemask .
This optimizes for bandwidth instead of latency
by spreading out pages and memory accesses to those pages across
multiple nodes.
To be effective the memory area should be fairly large,
at least 1\ MB or bigger with a fairly uniform access pattern.
Accesses to a single page of the area will still be limited to
the memory bandwidth of a single node.
.TP
.BR MPOL_WEIGHTED_INTERLEAVE " (since Linux 6.9)"
.\" commit fa3bea4e1f8202d787709b7e3654eb0a99aed758
This mode interleaves page allocations across the nodes specified in
.I nodemask
according to the weights in
.IR /sys/kernel/mm/mempolicy/weighted_interleave .
For example, if bits 0, 2, and 5 are set in
.IR nodemask ,
and the contents of
.IR /sys/kernel/mm/mempolicy/weighted_interleave/node0 ,
.IR /sys/ .\|.\|. /node2 ,
and
.IR /sys/ .\|.\|. /node5
are 4, 7, and 9, respectively,
then pages in this region will be allocated on nodes 0, 2, and 5
in a 4:7:9 ratio.
.TP
.B MPOL_PREFERRED
This mode sets the preferred node for allocation.
The kernel will try to allocate pages from this
node first and fall back to other nodes if the
preferred nodes is low on free memory.
If
.I nodemask
specifies more than one node ID, the first node in the
mask will be selected as the preferred node.
If the
.I nodemask
and
.I maxnode
arguments specify the empty set, then the memory is allocated on
the node of the CPU that triggered the allocation.
.TP
.BR MPOL_PREFERRED_MANY " (since Linux 5.15)"
.\" commit b27abaccf8e8b012f126da0c2a1ab32723ec8b9f
Specifies a set of nodes for allocation; see
.BR set_mempolicy (2)
.TP
.BR MPOL_LOCAL " (since Linux 3.8)"
.\" commit 479e2802d09f1e18a97262c4c6f8f17ae5884bd8
.\" commit f2a07f40dbc603c15f8b06e6ec7f768af67b424f
This mode specifies "local allocation"; the memory is allocated on
the node of the CPU that triggered the allocation (the "local node").
The
.I nodemask
and
.I maxnode
arguments must specify the empty set.
If the "local node" is low on free memory,
the kernel will try to allocate memory from other nodes.
The kernel will allocate memory from the "local node"
whenever memory for this node is available.
If the "local node" is not allowed by the thread's current cpuset context,
the kernel will try to allocate memory from other nodes.
The kernel will allocate memory from the "local node" whenever
it becomes allowed by the thread's current cpuset context.
By contrast,
.B MPOL_DEFAULT
reverts to the memory policy of the thread (which may be set via
.BR set_mempolicy (2));
that policy may be something other than "local allocation".
.P
If
.B MPOL_MF_STRICT
is passed in
.I flags
and
.I mode
is not
.BR MPOL_DEFAULT ,
then the call fails with the error
.B EIO
if the existing pages in the memory range don't follow the policy.
.\" According to the kernel code, the following is not true
.\" --Lee Schermerhorn
.\" In Linux 2.6.16 or later the kernel will also try to move pages
.\" to the requested node with this flag.
.P
If
.B MPOL_MF_MOVE
is specified in
.IR flags ,
then the kernel will attempt to move all the existing pages
in the memory range so that they follow the policy.
Pages that are shared with other processes will not be moved.
If
.B MPOL_MF_STRICT
is also specified, then the call fails with the error
.B EIO
if some pages could not be moved.
If the
.B MPOL_INTERLEAVE
policy was specified,
pages already residing on the specified nodes
will not be moved such that they are interleaved.
.P
If
.B MPOL_MF_MOVE_ALL
is passed in
.IR flags ,
then the kernel will attempt to move all existing pages in the memory range
regardless of whether other processes use the pages.
The calling thread must be privileged
.RB ( CAP_SYS_NICE )
to use this flag.
If
.B MPOL_MF_STRICT
is also specified, then the call fails with the error
.B EIO
if some pages could not be moved.
If the
.B MPOL_INTERLEAVE
policy was specified,
pages already residing on the specified nodes
will not be moved such that they are interleaved.
.\" ---------------------------------------------------------------
.SH RETURN VALUE
On success,
.BR mbind ()
returns 0;
on error, \-1 is returned and
.I errno
is set to indicate the error.
.\" ---------------------------------------------------------------
.SH ERRORS
.\"  I think I got all of the error returns.  --Lee Schermerhorn
.TP
.B EFAULT
Part or all of the memory range specified by
.I nodemask
and
.I maxnode
points outside your accessible address space.
Or, there was an unmapped hole in the specified memory range specified by
.I addr
and
.IR size .
.TP
.B EINVAL
An invalid value was specified for
.I flags
or
.IR mode ;
or
.I addr + size
was less than
.IR addr ;
or
.I addr
is not a multiple of the system page size.
Or,
.I mode
is
.B MPOL_DEFAULT
and
.I nodemask
specified a nonempty set;
or
.I mode
is
.B MPOL_BIND
or
.B MPOL_INTERLEAVE
and
.I nodemask
is empty.
Or,
.I maxnode
exceeds a kernel-imposed limit.
.\" As at 2.6.23, this limit is "a page worth of bits", e.g.,
.\" 8 * 4096 bits, assuming a 4kB page size.
Or,
.I nodemask
specifies one or more node IDs that are
greater than the maximum supported node ID.
Or, none of the node IDs specified by
.I nodemask
are on-line and allowed by the thread's current cpuset context,
or none of the specified nodes contain memory.
Or, the
.I mode
argument specified both
.B MPOL_F_STATIC_NODES
and
.BR MPOL_F_RELATIVE_NODES .
.TP
.B EIO
.B MPOL_MF_STRICT
was specified and an existing page was already on a node
that does not follow the policy;
or
.B MPOL_MF_MOVE
or
.B MPOL_MF_MOVE_ALL
was specified and the kernel was unable to move all existing
pages in the range.
.TP
.B ENOMEM
Insufficient kernel memory was available.
.TP
.B EPERM
The
.I flags
argument included the
.B MPOL_MF_MOVE_ALL
flag and the caller does not have the
.B CAP_SYS_NICE
privilege.
.\" ---------------------------------------------------------------
.SH STANDARDS
Linux.
.SH HISTORY
Linux 2.6.7.
.P
Support for huge page policy was added with Linux 2.6.16.
For interleave policy to be effective on huge page mappings the
policied memory needs to be tens of megabytes or larger.
.P
Before Linux 5.7.
.\" commit dcf1763546d76c372f3136c8d6b2b6e77f140cf0
.B MPOL_MF_STRICT
was ignored on huge page mappings.
.P
.B MPOL_MF_MOVE
and
.B MPOL_MF_MOVE_ALL
are available only on Linux 2.6.16 and later.
.SH NOTES
For information on library support, see
.BR numa (7).
.P
NUMA policy is not supported on a memory-mapped file range
that was mapped with the
.B MAP_SHARED
flag.
.P
The
.B MPOL_DEFAULT
mode can have different effects for
.BR mbind ()
and
.BR set_mempolicy (2).
When
.B MPOL_DEFAULT
is specified for
.BR set_mempolicy (2),
the thread's memory policy reverts to the system default policy
or local allocation.
When
.B MPOL_DEFAULT
is specified for a range of memory using
.BR mbind (),
any pages subsequently allocated for that range will use
the thread's memory policy, as set by
.BR set_mempolicy (2).
This effectively removes the explicit policy from the
specified range, "falling back" to a possibly nondefault
policy.
To select explicit "local allocation" for a memory range,
specify a
.I mode
of
.B MPOL_LOCAL
or
.B MPOL_PREFERRED
with an empty set of nodes.
This method will work for
.BR set_mempolicy (2),
as well.
.SH SEE ALSO
.BR get_mempolicy (2),
.BR getcpu (2),
.BR mmap (2),
.BR set_mempolicy (2),
.BR shmat (2),
.BR shmget (2),
.BR numa (3),
.BR cpuset (7),
.BR numa (7),
.BR numactl (8)