2005-04-17 00:20:36 +02:00
|
|
|
/*
|
|
|
|
* Simple NUMA memory policy for the Linux kernel.
|
|
|
|
*
|
|
|
|
* Copyright 2003,2004 Andi Kleen, SuSE Labs.
|
2005-10-30 02:16:59 +01:00
|
|
|
* (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc.
|
2005-04-17 00:20:36 +02:00
|
|
|
* Subject to the GNU Public License, version 2.
|
|
|
|
*
|
|
|
|
* NUMA policy allows the user to give hints in which node(s) memory should
|
|
|
|
* be allocated.
|
|
|
|
*
|
|
|
|
* Support four policies per VMA and per process:
|
|
|
|
*
|
|
|
|
* The VMA policy has priority over the process policy for a page fault.
|
|
|
|
*
|
|
|
|
* interleave Allocate memory interleaved over a set of nodes,
|
|
|
|
* with normal fallback if it fails.
|
|
|
|
* For VMA based allocations this interleaves based on the
|
|
|
|
* offset into the backing object or offset into the mapping
|
|
|
|
* for anonymous memory. For process policy an process counter
|
|
|
|
* is used.
|
2005-10-30 02:16:59 +01:00
|
|
|
*
|
2005-04-17 00:20:36 +02:00
|
|
|
* bind Only allocate memory on a specific set of nodes,
|
|
|
|
* no fallback.
|
2005-10-30 02:16:59 +01:00
|
|
|
* FIXME: memory is allocated starting with the first node
|
|
|
|
* to the last. It would be better if bind would truly restrict
|
|
|
|
* the allocation to memory nodes instead
|
|
|
|
*
|
2005-04-17 00:20:36 +02:00
|
|
|
* preferred Try a specific node first before normal fallback.
|
|
|
|
* As a special case node -1 here means do the allocation
|
|
|
|
* on the local CPU. This is normally identical to default,
|
|
|
|
* but useful to set in a VMA when you have a non default
|
|
|
|
* process policy.
|
2005-10-30 02:16:59 +01:00
|
|
|
*
|
2005-04-17 00:20:36 +02:00
|
|
|
* default Allocate on the local node first, or when on a VMA
|
|
|
|
* use the process policy. This is what Linux always did
|
|
|
|
* in a NUMA aware kernel and still does by, ahem, default.
|
|
|
|
*
|
|
|
|
* The process policy is applied for most non interrupt memory allocations
|
|
|
|
* in that process' context. Interrupts ignore the policies and always
|
|
|
|
* try to allocate on the local CPU. The VMA policy is only applied for memory
|
|
|
|
* allocations for a VMA in the VM.
|
|
|
|
*
|
|
|
|
* Currently there are a few corner cases in swapping where the policy
|
|
|
|
* is not applied, but the majority should be handled. When process policy
|
|
|
|
* is used it is not remembered over swap outs/swap ins.
|
|
|
|
*
|
|
|
|
* Only the highest zone in the zone hierarchy gets policied. Allocations
|
|
|
|
* requesting a lower zone just use default policy. This implies that
|
|
|
|
* on systems with highmem kernel lowmem allocation don't get policied.
|
|
|
|
* Same with GFP_DMA allocations.
|
|
|
|
*
|
|
|
|
* For shmfs/tmpfs/hugetlbfs shared memory the policy is shared between
|
|
|
|
* all users and remembered even when nobody has memory mapped.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* Notebook:
|
|
|
|
fix mmap readahead to honour policy and enable policy for any page cache
|
|
|
|
object
|
|
|
|
statistics for bigpages
|
|
|
|
global policy for page cache? currently it uses process policy. Requires
|
|
|
|
first item above.
|
|
|
|
handle mremap for shared memory (currently ignored for the policy)
|
|
|
|
grows down?
|
|
|
|
make bind policy root only? It can trigger oom much faster and the
|
|
|
|
kernel is not always grateful with that.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/mempolicy.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/highmem.h>
|
|
|
|
#include <linux/hugetlb.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/nodemask.h>
|
|
|
|
#include <linux/cpuset.h>
|
|
|
|
#include <linux/gfp.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/string.h>
|
|
|
|
#include <linux/module.h>
|
2007-10-19 08:40:14 +02:00
|
|
|
#include <linux/nsproxy.h>
|
2005-04-17 00:20:36 +02:00
|
|
|
#include <linux/interrupt.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/compat.h>
|
2006-01-08 10:00:50 +01:00
|
|
|
#include <linux/swap.h>
|
2006-01-08 10:01:02 +01:00
|
|
|
#include <linux/seq_file.h>
|
|
|
|
#include <linux/proc_fs.h>
|
2006-03-22 09:09:12 +01:00
|
|
|
#include <linux/migrate.h>
|
ksm: memory hotremove migration only
The previous patch enables page migration of ksm pages, but that soon gets
into trouble: not surprising, since we're using the ksm page lock to lock
operations on its stable_node, but page migration switches the page whose
lock is to be used for that. Another layer of locking would fix it, but
do we need that yet?
Do we actually need page migration of ksm pages? Yes, memory hotremove
needs to offline sections of memory: and since we stopped allocating ksm
pages with GFP_HIGHUSER, they will tend to be GFP_HIGHUSER_MOVABLE
candidates for migration.
But KSM is currently unconscious of NUMA issues, happily merging pages
from different NUMA nodes: at present the rule must be, not to use
MADV_MERGEABLE where you care about NUMA. So no, NUMA page migration of
ksm pages does not make sense yet.
So, to complete support for ksm swapping we need to make hotremove safe.
ksm_memory_callback() take ksm_thread_mutex when MEM_GOING_OFFLINE and
release it when MEM_OFFLINE or MEM_CANCEL_OFFLINE. But if mapped pages
are freed before migration reaches them, stable_nodes may be left still
pointing to struct pages which have been removed from the system: the
stable_node needs to identify a page by pfn rather than page pointer, then
it can safely prune them when MEM_OFFLINE.
And make NUMA migration skip PageKsm pages where it skips PageReserved.
But it's only when we reach unmap_and_move() that the page lock is taken
and we can be sure that raised pagecount has prevented a PageAnon from
being upgraded: so add offlining arg to migrate_pages(), to migrate ksm
page when offlining (has sufficient locking) but reject it otherwise.
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Izik Eidus <ieidus@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Chris Wright <chrisw@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 02:59:33 +01:00
|
|
|
#include <linux/ksm.h>
|
2006-06-23 11:03:53 +02:00
|
|
|
#include <linux/rmap.h>
|
2006-06-23 11:04:02 +02:00
|
|
|
#include <linux/security.h>
|
2007-10-16 10:26:26 +02:00
|
|
|
#include <linux/syscalls.h>
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
#include <linux/ctype.h>
|
2009-12-15 02:58:11 +01:00
|
|
|
#include <linux/mm_inline.h>
|
2006-01-08 10:00:50 +01:00
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
#include <asm/tlbflush.h>
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
|
vmscan: move isolate_lru_page() to vmscan.c
On large memory systems, the VM can spend way too much time scanning
through pages that it cannot (or should not) evict from memory. Not only
does it use up CPU time, but it also provokes lock contention and can
leave large systems under memory presure in a catatonic state.
This patch series improves VM scalability by:
1) putting filesystem backed, swap backed and unevictable pages
onto their own LRUs, so the system only scans the pages that it
can/should evict from memory
2) switching to two handed clock replacement for the anonymous LRUs,
so the number of pages that need to be scanned when the system
starts swapping is bound to a reasonable number
3) keeping unevictable pages off the LRU completely, so the
VM does not waste CPU time scanning them. ramfs, ramdisk,
SHM_LOCKED shared memory segments and mlock()ed VMA pages
are keept on the unevictable list.
This patch:
isolate_lru_page logically belongs to be in vmscan.c than migrate.c.
It is tough, because we don't need that function without memory migration
so there is a valid argument to have it in migrate.c. However a
subsequent patch needs to make use of it in the core mm, so we can happily
move it to vmscan.c.
Also, make the function a little more generic by not requiring that it
adds an isolated page to a given list. Callers can do that.
Note that we now have '__isolate_lru_page()', that does
something quite different, visible outside of vmscan.c
for use with memory controller. Methinks we need to
rationalize these names/purposes. --lts
[akpm@linux-foundation.org: fix mm/memory_hotplug.c build]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 05:26:09 +02:00
|
|
|
#include "internal.h"
|
|
|
|
|
2006-01-08 10:01:01 +01:00
|
|
|
/* Internal flags */
|
2006-01-08 10:00:50 +01:00
|
|
|
#define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */
|
2006-01-08 10:01:01 +01:00
|
|
|
#define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */
|
2006-01-08 10:01:02 +01:00
|
|
|
#define MPOL_MF_STATS (MPOL_MF_INTERNAL << 2) /* Gather statistics */
|
2006-01-08 10:00:50 +01:00
|
|
|
|
2006-03-22 09:08:13 +01:00
|
|
|
static struct kmem_cache *policy_cache;
|
|
|
|
static struct kmem_cache *sn_cache;
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
/* Highest zone. An specific allocation for a zone below that is not
|
|
|
|
policied. */
|
2007-02-10 10:43:07 +01:00
|
|
|
enum zone_type policy_zone = 0;
|
2005-04-17 00:20:36 +02:00
|
|
|
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
/*
|
|
|
|
* run-time system-wide default policy => local allocation
|
|
|
|
*/
|
2005-07-06 19:56:03 +02:00
|
|
|
struct mempolicy default_policy = {
|
2005-04-17 00:20:36 +02:00
|
|
|
.refcnt = ATOMIC_INIT(1), /* never free it */
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
.mode = MPOL_PREFERRED,
|
2008-04-28 11:13:21 +02:00
|
|
|
.flags = MPOL_F_LOCAL,
|
2005-04-17 00:20:36 +02:00
|
|
|
};
|
|
|
|
|
2008-04-28 11:12:33 +02:00
|
|
|
static const struct mempolicy_operations {
|
|
|
|
int (*create)(struct mempolicy *pol, const nodemask_t *nodes);
|
|
|
|
void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes);
|
|
|
|
} mpol_ops[MPOL_MAX];
|
|
|
|
|
2008-04-28 11:12:18 +02:00
|
|
|
/* Check that the nodemask contains at least one populated zone */
|
2008-04-28 11:12:33 +02:00
|
|
|
static int is_valid_nodemask(const nodemask_t *nodemask)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
2008-04-28 11:12:18 +02:00
|
|
|
int nd, k;
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2008-04-28 11:12:18 +02:00
|
|
|
/* Check that there is something useful in this mask */
|
|
|
|
k = policy_zone;
|
|
|
|
|
|
|
|
for_each_node_mask(nd, *nodemask) {
|
|
|
|
struct zone *z;
|
|
|
|
|
|
|
|
for (k = 0; k <= policy_zone; k++) {
|
|
|
|
z = &NODE_DATA(nd)->node_zones[k];
|
|
|
|
if (z->present_pages > 0)
|
|
|
|
return 1;
|
2006-02-17 01:39:16 +01:00
|
|
|
}
|
2007-02-20 22:57:49 +01:00
|
|
|
}
|
2008-04-28 11:12:18 +02:00
|
|
|
|
|
|
|
return 0;
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
mempolicy: add MPOL_F_STATIC_NODES flag
Add an optional mempolicy mode flag, MPOL_F_STATIC_NODES, that suppresses the
node remap when the policy is rebound.
Adds another member to struct mempolicy, nodemask_t user_nodemask, as part of
a union with cpuset_mems_allowed:
struct mempolicy {
...
union {
nodemask_t cpuset_mems_allowed;
nodemask_t user_nodemask;
} w;
}
that stores the the nodemask that the user passed when he or she created the
mempolicy via set_mempolicy() or mbind(). When using MPOL_F_STATIC_NODES,
which is passed with any mempolicy mode, the user's passed nodemask
intersected with the VMA or task's allowed nodes is always used when
determining the preferred node, setting the MPOL_BIND zonelist, or creating
the interleave nodemask. This happens whenever the policy is rebound,
including when a task's cpuset assignment changes or the cpuset's mems are
changed.
This creates an interesting side-effect in that it allows the mempolicy
"intent" to lie dormant and uneffected until it has access to the node(s) that
it desires. For example, if you currently ask for an interleaved policy over
a set of nodes that you do not have access to, the mempolicy is not created
and the task continues to use the previous policy. With this change, however,
it is possible to create the same mempolicy; it is only effected when access
to nodes in the nodemask is acquired.
It is also possible to mount tmpfs with the static nodemask behavior when
specifying a node or nodemask. To do this, simply add "=static" immediately
following the mempolicy mode at mount time:
mount -o remount mpol=interleave=static:1-3
Also removes mpol_check_policy() and folds its logic into mpol_new() since it
is now obsoleted. The unused vma_mpol_equal() is also removed.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:27 +02:00
|
|
|
static inline int mpol_store_user_nodemask(const struct mempolicy *pol)
|
|
|
|
{
|
mempolicy: add MPOL_F_RELATIVE_NODES flag
Adds another optional mode flag, MPOL_F_RELATIVE_NODES, that specifies
nodemasks passed via set_mempolicy() or mbind() should be considered relative
to the current task's mems_allowed.
When the mempolicy is created, the passed nodemask is folded and mapped onto
the current task's mems_allowed. For example, consider a task using
set_mempolicy() to pass MPOL_INTERLEAVE | MPOL_F_RELATIVE_NODES with a
nodemask of 1-3. If current's mems_allowed is 4-7, the effected nodemask is
5-7 (the second, third, and fourth node of mems_allowed).
If the same task is attached to a cpuset, the mempolicy nodemask is rebound
each time the mems are changed. Some possible rebinds and results are:
mems result
1-3 1-3
1-7 2-4
1,5-6 1,5-6
1,5-7 5-7
Likewise, the zonelist built for MPOL_BIND acts on the set of zones assigned
to the resultant nodemask from the relative remap.
In the MPOL_PREFERRED case, the preferred node is remapped from the currently
effected nodemask to the relative nodemask.
This mempolicy mode flag was conceived of by Paul Jackson <pj@sgi.com>.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:30 +02:00
|
|
|
return pol->flags & (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig,
|
|
|
|
const nodemask_t *rel)
|
|
|
|
{
|
|
|
|
nodemask_t tmp;
|
|
|
|
nodes_fold(tmp, *orig, nodes_weight(*rel));
|
|
|
|
nodes_onto(*ret, tmp, *rel);
|
mempolicy: add MPOL_F_STATIC_NODES flag
Add an optional mempolicy mode flag, MPOL_F_STATIC_NODES, that suppresses the
node remap when the policy is rebound.
Adds another member to struct mempolicy, nodemask_t user_nodemask, as part of
a union with cpuset_mems_allowed:
struct mempolicy {
...
union {
nodemask_t cpuset_mems_allowed;
nodemask_t user_nodemask;
} w;
}
that stores the the nodemask that the user passed when he or she created the
mempolicy via set_mempolicy() or mbind(). When using MPOL_F_STATIC_NODES,
which is passed with any mempolicy mode, the user's passed nodemask
intersected with the VMA or task's allowed nodes is always used when
determining the preferred node, setting the MPOL_BIND zonelist, or creating
the interleave nodemask. This happens whenever the policy is rebound,
including when a task's cpuset assignment changes or the cpuset's mems are
changed.
This creates an interesting side-effect in that it allows the mempolicy
"intent" to lie dormant and uneffected until it has access to the node(s) that
it desires. For example, if you currently ask for an interleaved policy over
a set of nodes that you do not have access to, the mempolicy is not created
and the task continues to use the previous policy. With this change, however,
it is possible to create the same mempolicy; it is only effected when access
to nodes in the nodemask is acquired.
It is also possible to mount tmpfs with the static nodemask behavior when
specifying a node or nodemask. To do this, simply add "=static" immediately
following the mempolicy mode at mount time:
mount -o remount mpol=interleave=static:1-3
Also removes mpol_check_policy() and folds its logic into mpol_new() since it
is now obsoleted. The unused vma_mpol_equal() is also removed.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:27 +02:00
|
|
|
}
|
|
|
|
|
2008-04-28 11:12:33 +02:00
|
|
|
static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes)
|
|
|
|
{
|
|
|
|
if (nodes_empty(*nodes))
|
|
|
|
return -EINVAL;
|
|
|
|
pol->v.nodes = *nodes;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
|
|
|
|
{
|
|
|
|
if (!nodes)
|
2008-04-28 11:13:21 +02:00
|
|
|
pol->flags |= MPOL_F_LOCAL; /* local allocation */
|
2008-04-28 11:12:33 +02:00
|
|
|
else if (nodes_empty(*nodes))
|
|
|
|
return -EINVAL; /* no allowed nodes */
|
|
|
|
else
|
|
|
|
pol->v.preferred_node = first_node(*nodes);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
|
|
|
|
{
|
|
|
|
if (!is_valid_nodemask(nodes))
|
|
|
|
return -EINVAL;
|
|
|
|
pol->v.nodes = *nodes;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
/*
|
|
|
|
* mpol_set_nodemask is called after mpol_new() to set up the nodemask, if
|
|
|
|
* any, for the new policy. mpol_new() has already validated the nodes
|
|
|
|
* parameter with respect to the policy mode and flags. But, we need to
|
|
|
|
* handle an empty nodemask with MPOL_PREFERRED here.
|
|
|
|
*
|
|
|
|
* Must be called holding task's alloc_lock to protect task's mems_allowed
|
|
|
|
* and mempolicy. May also be called holding the mmap_semaphore for write.
|
|
|
|
*/
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
static int mpol_set_nodemask(struct mempolicy *pol,
|
|
|
|
const nodemask_t *nodes, struct nodemask_scratch *nsc)
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
/* if mode is MPOL_DEFAULT, pol is NULL. This is right. */
|
|
|
|
if (pol == NULL)
|
|
|
|
return 0;
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
/* Check N_HIGH_MEMORY */
|
|
|
|
nodes_and(nsc->mask1,
|
|
|
|
cpuset_current_mems_allowed, node_states[N_HIGH_MEMORY]);
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
|
|
|
|
VM_BUG_ON(!nodes);
|
|
|
|
if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes))
|
|
|
|
nodes = NULL; /* explicit local allocation */
|
|
|
|
else {
|
|
|
|
if (pol->flags & MPOL_F_RELATIVE_NODES)
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
mpol_relative_nodemask(&nsc->mask2, nodes,&nsc->mask1);
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
else
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
nodes_and(nsc->mask2, *nodes, nsc->mask1);
|
|
|
|
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
if (mpol_store_user_nodemask(pol))
|
|
|
|
pol->w.user_nodemask = *nodes;
|
|
|
|
else
|
|
|
|
pol->w.cpuset_mems_allowed =
|
|
|
|
cpuset_current_mems_allowed;
|
|
|
|
}
|
|
|
|
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
if (nodes)
|
|
|
|
ret = mpol_ops[pol->mode].create(pol, &nsc->mask2);
|
|
|
|
else
|
|
|
|
ret = mpol_ops[pol->mode].create(pol, NULL);
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This function just creates a new policy, does some check and simple
|
|
|
|
* initialization. You must invoke mpol_set_nodemask() to set nodes.
|
|
|
|
*/
|
2008-04-28 11:12:25 +02:00
|
|
|
static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
|
|
|
|
nodemask_t *nodes)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
struct mempolicy *policy;
|
|
|
|
|
2008-04-28 11:12:25 +02:00
|
|
|
pr_debug("setting mode %d flags %d nodes[0] %lx\n",
|
|
|
|
mode, flags, nodes ? nodes_addr(*nodes)[0] : -1);
|
2007-07-16 08:38:16 +02:00
|
|
|
|
2008-04-28 11:12:34 +02:00
|
|
|
if (mode == MPOL_DEFAULT) {
|
|
|
|
if (nodes && !nodes_empty(*nodes))
|
2008-04-28 11:12:33 +02:00
|
|
|
return ERR_PTR(-EINVAL);
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
return NULL; /* simply delete any existing policy */
|
2008-04-28 11:12:33 +02:00
|
|
|
}
|
2008-04-28 11:12:34 +02:00
|
|
|
VM_BUG_ON(!nodes);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or
|
|
|
|
* MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation).
|
|
|
|
* All other modes require a valid pointer to a non-empty nodemask.
|
|
|
|
*/
|
|
|
|
if (mode == MPOL_PREFERRED) {
|
|
|
|
if (nodes_empty(*nodes)) {
|
|
|
|
if (((flags & MPOL_F_STATIC_NODES) ||
|
|
|
|
(flags & MPOL_F_RELATIVE_NODES)))
|
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
}
|
|
|
|
} else if (nodes_empty(*nodes))
|
|
|
|
return ERR_PTR(-EINVAL);
|
2005-04-17 00:20:36 +02:00
|
|
|
policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
|
|
|
|
if (!policy)
|
|
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
atomic_set(&policy->refcnt, 1);
|
2008-04-28 11:13:12 +02:00
|
|
|
policy->mode = mode;
|
2008-04-28 11:12:34 +02:00
|
|
|
policy->flags = flags;
|
2008-04-28 11:12:33 +02:00
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
return policy;
|
2008-04-28 11:12:33 +02:00
|
|
|
}
|
|
|
|
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
/* Slow path of a mpol destructor. */
|
|
|
|
void __mpol_put(struct mempolicy *p)
|
|
|
|
{
|
|
|
|
if (!atomic_dec_and_test(&p->refcnt))
|
|
|
|
return;
|
|
|
|
kmem_cache_free(policy_cache, p);
|
|
|
|
}
|
|
|
|
|
2008-04-28 11:12:33 +02:00
|
|
|
static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static void mpol_rebind_nodemask(struct mempolicy *pol,
|
|
|
|
const nodemask_t *nodes)
|
|
|
|
{
|
|
|
|
nodemask_t tmp;
|
|
|
|
|
|
|
|
if (pol->flags & MPOL_F_STATIC_NODES)
|
|
|
|
nodes_and(tmp, pol->w.user_nodemask, *nodes);
|
|
|
|
else if (pol->flags & MPOL_F_RELATIVE_NODES)
|
|
|
|
mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
|
|
|
|
else {
|
|
|
|
nodes_remap(tmp, pol->v.nodes, pol->w.cpuset_mems_allowed,
|
|
|
|
*nodes);
|
|
|
|
pol->w.cpuset_mems_allowed = *nodes;
|
|
|
|
}
|
mempolicy: add MPOL_F_STATIC_NODES flag
Add an optional mempolicy mode flag, MPOL_F_STATIC_NODES, that suppresses the
node remap when the policy is rebound.
Adds another member to struct mempolicy, nodemask_t user_nodemask, as part of
a union with cpuset_mems_allowed:
struct mempolicy {
...
union {
nodemask_t cpuset_mems_allowed;
nodemask_t user_nodemask;
} w;
}
that stores the the nodemask that the user passed when he or she created the
mempolicy via set_mempolicy() or mbind(). When using MPOL_F_STATIC_NODES,
which is passed with any mempolicy mode, the user's passed nodemask
intersected with the VMA or task's allowed nodes is always used when
determining the preferred node, setting the MPOL_BIND zonelist, or creating
the interleave nodemask. This happens whenever the policy is rebound,
including when a task's cpuset assignment changes or the cpuset's mems are
changed.
This creates an interesting side-effect in that it allows the mempolicy
"intent" to lie dormant and uneffected until it has access to the node(s) that
it desires. For example, if you currently ask for an interleaved policy over
a set of nodes that you do not have access to, the mempolicy is not created
and the task continues to use the previous policy. With this change, however,
it is possible to create the same mempolicy; it is only effected when access
to nodes in the nodemask is acquired.
It is also possible to mount tmpfs with the static nodemask behavior when
specifying a node or nodemask. To do this, simply add "=static" immediately
following the mempolicy mode at mount time:
mount -o remount mpol=interleave=static:1-3
Also removes mpol_check_policy() and folds its logic into mpol_new() since it
is now obsoleted. The unused vma_mpol_equal() is also removed.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:27 +02:00
|
|
|
|
2008-04-28 11:12:33 +02:00
|
|
|
pol->v.nodes = tmp;
|
|
|
|
if (!node_isset(current->il_next, tmp)) {
|
|
|
|
current->il_next = next_node(current->il_next, tmp);
|
|
|
|
if (current->il_next >= MAX_NUMNODES)
|
|
|
|
current->il_next = first_node(tmp);
|
|
|
|
if (current->il_next >= MAX_NUMNODES)
|
|
|
|
current->il_next = numa_node_id();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void mpol_rebind_preferred(struct mempolicy *pol,
|
|
|
|
const nodemask_t *nodes)
|
|
|
|
{
|
|
|
|
nodemask_t tmp;
|
|
|
|
|
|
|
|
if (pol->flags & MPOL_F_STATIC_NODES) {
|
|
|
|
int node = first_node(pol->w.user_nodemask);
|
|
|
|
|
2008-04-28 11:13:21 +02:00
|
|
|
if (node_isset(node, *nodes)) {
|
2008-04-28 11:12:33 +02:00
|
|
|
pol->v.preferred_node = node;
|
2008-04-28 11:13:21 +02:00
|
|
|
pol->flags &= ~MPOL_F_LOCAL;
|
|
|
|
} else
|
|
|
|
pol->flags |= MPOL_F_LOCAL;
|
2008-04-28 11:12:33 +02:00
|
|
|
} else if (pol->flags & MPOL_F_RELATIVE_NODES) {
|
|
|
|
mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
|
|
|
|
pol->v.preferred_node = first_node(tmp);
|
2008-04-28 11:13:21 +02:00
|
|
|
} else if (!(pol->flags & MPOL_F_LOCAL)) {
|
2008-04-28 11:12:33 +02:00
|
|
|
pol->v.preferred_node = node_remap(pol->v.preferred_node,
|
|
|
|
pol->w.cpuset_mems_allowed,
|
|
|
|
*nodes);
|
|
|
|
pol->w.cpuset_mems_allowed = *nodes;
|
|
|
|
}
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
2008-04-28 11:12:32 +02:00
|
|
|
/* Migrate a policy to a different set of nodes */
|
|
|
|
static void mpol_rebind_policy(struct mempolicy *pol,
|
|
|
|
const nodemask_t *newmask)
|
|
|
|
{
|
|
|
|
if (!pol)
|
|
|
|
return;
|
|
|
|
if (!mpol_store_user_nodemask(pol) &&
|
|
|
|
nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
|
|
|
|
return;
|
2008-04-28 11:13:12 +02:00
|
|
|
mpol_ops[pol->mode].rebind(pol, newmask);
|
2008-04-28 11:12:32 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Wrapper for mpol_rebind_policy() that just requires task
|
|
|
|
* pointer, and updates task mempolicy.
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
*
|
|
|
|
* Called with task's alloc_lock held.
|
2008-04-28 11:12:32 +02:00
|
|
|
*/
|
|
|
|
|
|
|
|
void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new)
|
|
|
|
{
|
|
|
|
mpol_rebind_policy(tsk->mempolicy, new);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Rebind each vma in mm to new nodemask.
|
|
|
|
*
|
|
|
|
* Call holding a reference to mm. Takes mm->mmap_sem during call.
|
|
|
|
*/
|
|
|
|
|
|
|
|
void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
|
|
|
|
{
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
|
|
|
|
down_write(&mm->mmap_sem);
|
|
|
|
for (vma = mm->mmap; vma; vma = vma->vm_next)
|
|
|
|
mpol_rebind_policy(vma->vm_policy, new);
|
|
|
|
up_write(&mm->mmap_sem);
|
|
|
|
}
|
|
|
|
|
2008-04-28 11:12:33 +02:00
|
|
|
static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
|
|
|
|
[MPOL_DEFAULT] = {
|
|
|
|
.rebind = mpol_rebind_default,
|
|
|
|
},
|
|
|
|
[MPOL_INTERLEAVE] = {
|
|
|
|
.create = mpol_new_interleave,
|
|
|
|
.rebind = mpol_rebind_nodemask,
|
|
|
|
},
|
|
|
|
[MPOL_PREFERRED] = {
|
|
|
|
.create = mpol_new_preferred,
|
|
|
|
.rebind = mpol_rebind_preferred,
|
|
|
|
},
|
|
|
|
[MPOL_BIND] = {
|
|
|
|
.create = mpol_new_bind,
|
|
|
|
.rebind = mpol_rebind_nodemask,
|
|
|
|
},
|
|
|
|
};
|
|
|
|
|
2006-03-07 00:42:53 +01:00
|
|
|
static void gather_stats(struct page *, void *, int pte_dirty);
|
2006-01-19 02:42:29 +01:00
|
|
|
static void migrate_page_add(struct page *page, struct list_head *pagelist,
|
|
|
|
unsigned long flags);
|
2006-01-08 10:01:02 +01:00
|
|
|
|
2006-01-08 10:01:01 +01:00
|
|
|
/* Scan through pages checking if pages follow certain conditions. */
|
2005-10-30 02:16:12 +01:00
|
|
|
static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
|
2006-01-08 10:00:50 +01:00
|
|
|
unsigned long addr, unsigned long end,
|
|
|
|
const nodemask_t *nodes, unsigned long flags,
|
2006-01-08 10:01:01 +01:00
|
|
|
void *private)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
2005-06-22 02:15:07 +02:00
|
|
|
pte_t *orig_pte;
|
|
|
|
pte_t *pte;
|
2005-10-30 02:16:27 +01:00
|
|
|
spinlock_t *ptl;
|
2005-06-22 02:15:06 +02:00
|
|
|
|
2005-10-30 02:16:27 +01:00
|
|
|
orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
|
2005-06-22 02:15:07 +02:00
|
|
|
do {
|
2005-11-28 23:34:23 +01:00
|
|
|
struct page *page;
|
2006-12-07 05:33:03 +01:00
|
|
|
int nid;
|
2005-06-22 02:15:07 +02:00
|
|
|
|
|
|
|
if (!pte_present(*pte))
|
2005-04-17 00:20:36 +02:00
|
|
|
continue;
|
2005-11-28 23:34:23 +01:00
|
|
|
page = vm_normal_page(vma, addr, *pte);
|
|
|
|
if (!page)
|
2005-04-17 00:20:36 +02:00
|
|
|
continue;
|
2006-01-19 02:42:27 +01:00
|
|
|
/*
|
ksm: memory hotremove migration only
The previous patch enables page migration of ksm pages, but that soon gets
into trouble: not surprising, since we're using the ksm page lock to lock
operations on its stable_node, but page migration switches the page whose
lock is to be used for that. Another layer of locking would fix it, but
do we need that yet?
Do we actually need page migration of ksm pages? Yes, memory hotremove
needs to offline sections of memory: and since we stopped allocating ksm
pages with GFP_HIGHUSER, they will tend to be GFP_HIGHUSER_MOVABLE
candidates for migration.
But KSM is currently unconscious of NUMA issues, happily merging pages
from different NUMA nodes: at present the rule must be, not to use
MADV_MERGEABLE where you care about NUMA. So no, NUMA page migration of
ksm pages does not make sense yet.
So, to complete support for ksm swapping we need to make hotremove safe.
ksm_memory_callback() take ksm_thread_mutex when MEM_GOING_OFFLINE and
release it when MEM_OFFLINE or MEM_CANCEL_OFFLINE. But if mapped pages
are freed before migration reaches them, stable_nodes may be left still
pointing to struct pages which have been removed from the system: the
stable_node needs to identify a page by pfn rather than page pointer, then
it can safely prune them when MEM_OFFLINE.
And make NUMA migration skip PageKsm pages where it skips PageReserved.
But it's only when we reach unmap_and_move() that the page lock is taken
and we can be sure that raised pagecount has prevented a PageAnon from
being upgraded: so add offlining arg to migrate_pages(), to migrate ksm
page when offlining (has sufficient locking) but reject it otherwise.
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Izik Eidus <ieidus@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Chris Wright <chrisw@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 02:59:33 +01:00
|
|
|
* vm_normal_page() filters out zero pages, but there might
|
|
|
|
* still be PageReserved pages to skip, perhaps in a VDSO.
|
|
|
|
* And we cannot move PageKsm pages sensibly or safely yet.
|
2006-01-19 02:42:27 +01:00
|
|
|
*/
|
ksm: memory hotremove migration only
The previous patch enables page migration of ksm pages, but that soon gets
into trouble: not surprising, since we're using the ksm page lock to lock
operations on its stable_node, but page migration switches the page whose
lock is to be used for that. Another layer of locking would fix it, but
do we need that yet?
Do we actually need page migration of ksm pages? Yes, memory hotremove
needs to offline sections of memory: and since we stopped allocating ksm
pages with GFP_HIGHUSER, they will tend to be GFP_HIGHUSER_MOVABLE
candidates for migration.
But KSM is currently unconscious of NUMA issues, happily merging pages
from different NUMA nodes: at present the rule must be, not to use
MADV_MERGEABLE where you care about NUMA. So no, NUMA page migration of
ksm pages does not make sense yet.
So, to complete support for ksm swapping we need to make hotremove safe.
ksm_memory_callback() take ksm_thread_mutex when MEM_GOING_OFFLINE and
release it when MEM_OFFLINE or MEM_CANCEL_OFFLINE. But if mapped pages
are freed before migration reaches them, stable_nodes may be left still
pointing to struct pages which have been removed from the system: the
stable_node needs to identify a page by pfn rather than page pointer, then
it can safely prune them when MEM_OFFLINE.
And make NUMA migration skip PageKsm pages where it skips PageReserved.
But it's only when we reach unmap_and_move() that the page lock is taken
and we can be sure that raised pagecount has prevented a PageAnon from
being upgraded: so add offlining arg to migrate_pages(), to migrate ksm
page when offlining (has sufficient locking) but reject it otherwise.
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Izik Eidus <ieidus@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Chris Wright <chrisw@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 02:59:33 +01:00
|
|
|
if (PageReserved(page) || PageKsm(page))
|
2006-01-12 10:05:20 +01:00
|
|
|
continue;
|
2005-11-28 23:34:23 +01:00
|
|
|
nid = page_to_nid(page);
|
2006-01-08 10:01:01 +01:00
|
|
|
if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
|
|
|
|
continue;
|
|
|
|
|
2006-01-08 10:01:02 +01:00
|
|
|
if (flags & MPOL_MF_STATS)
|
2006-03-07 00:42:53 +01:00
|
|
|
gather_stats(page, private, pte_dirty(*pte));
|
2006-01-19 02:42:27 +01:00
|
|
|
else if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
|
2006-01-19 02:42:29 +01:00
|
|
|
migrate_page_add(page, private, flags);
|
2006-01-08 10:01:01 +01:00
|
|
|
else
|
|
|
|
break;
|
2005-06-22 02:15:07 +02:00
|
|
|
} while (pte++, addr += PAGE_SIZE, addr != end);
|
2005-10-30 02:16:27 +01:00
|
|
|
pte_unmap_unlock(orig_pte, ptl);
|
2005-06-22 02:15:07 +02:00
|
|
|
return addr != end;
|
|
|
|
}
|
|
|
|
|
2005-10-30 02:16:12 +01:00
|
|
|
static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud,
|
2006-01-08 10:00:50 +01:00
|
|
|
unsigned long addr, unsigned long end,
|
|
|
|
const nodemask_t *nodes, unsigned long flags,
|
2006-01-08 10:01:01 +01:00
|
|
|
void *private)
|
2005-06-22 02:15:07 +02:00
|
|
|
{
|
|
|
|
pmd_t *pmd;
|
|
|
|
unsigned long next;
|
|
|
|
|
|
|
|
pmd = pmd_offset(pud, addr);
|
|
|
|
do {
|
|
|
|
next = pmd_addr_end(addr, end);
|
|
|
|
if (pmd_none_or_clear_bad(pmd))
|
|
|
|
continue;
|
2006-01-08 10:00:50 +01:00
|
|
|
if (check_pte_range(vma, pmd, addr, next, nodes,
|
2006-01-08 10:01:01 +01:00
|
|
|
flags, private))
|
2005-06-22 02:15:07 +02:00
|
|
|
return -EIO;
|
|
|
|
} while (pmd++, addr = next, addr != end);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2005-10-30 02:16:12 +01:00
|
|
|
static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
|
2006-01-08 10:00:50 +01:00
|
|
|
unsigned long addr, unsigned long end,
|
|
|
|
const nodemask_t *nodes, unsigned long flags,
|
2006-01-08 10:01:01 +01:00
|
|
|
void *private)
|
2005-06-22 02:15:07 +02:00
|
|
|
{
|
|
|
|
pud_t *pud;
|
|
|
|
unsigned long next;
|
|
|
|
|
|
|
|
pud = pud_offset(pgd, addr);
|
|
|
|
do {
|
|
|
|
next = pud_addr_end(addr, end);
|
|
|
|
if (pud_none_or_clear_bad(pud))
|
|
|
|
continue;
|
2006-01-08 10:00:50 +01:00
|
|
|
if (check_pmd_range(vma, pud, addr, next, nodes,
|
2006-01-08 10:01:01 +01:00
|
|
|
flags, private))
|
2005-06-22 02:15:07 +02:00
|
|
|
return -EIO;
|
|
|
|
} while (pud++, addr = next, addr != end);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2005-10-30 02:16:12 +01:00
|
|
|
static inline int check_pgd_range(struct vm_area_struct *vma,
|
2006-01-08 10:00:50 +01:00
|
|
|
unsigned long addr, unsigned long end,
|
|
|
|
const nodemask_t *nodes, unsigned long flags,
|
2006-01-08 10:01:01 +01:00
|
|
|
void *private)
|
2005-06-22 02:15:07 +02:00
|
|
|
{
|
|
|
|
pgd_t *pgd;
|
|
|
|
unsigned long next;
|
|
|
|
|
2005-10-30 02:16:12 +01:00
|
|
|
pgd = pgd_offset(vma->vm_mm, addr);
|
2005-06-22 02:15:07 +02:00
|
|
|
do {
|
|
|
|
next = pgd_addr_end(addr, end);
|
|
|
|
if (pgd_none_or_clear_bad(pgd))
|
|
|
|
continue;
|
2006-01-08 10:00:50 +01:00
|
|
|
if (check_pud_range(vma, pgd, addr, next, nodes,
|
2006-01-08 10:01:01 +01:00
|
|
|
flags, private))
|
2005-06-22 02:15:07 +02:00
|
|
|
return -EIO;
|
|
|
|
} while (pgd++, addr = next, addr != end);
|
|
|
|
return 0;
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
2006-01-08 10:00:50 +01:00
|
|
|
/*
|
|
|
|
* Check if all pages in a range are on a set of nodes.
|
|
|
|
* If pagelist != NULL then isolate pages from the LRU and
|
|
|
|
* put them on the pagelist.
|
|
|
|
*/
|
2005-04-17 00:20:36 +02:00
|
|
|
static struct vm_area_struct *
|
|
|
|
check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
|
2006-01-08 10:01:01 +01:00
|
|
|
const nodemask_t *nodes, unsigned long flags, void *private)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
int err;
|
|
|
|
struct vm_area_struct *first, *vma, *prev;
|
|
|
|
|
2006-01-19 02:42:27 +01:00
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
first = find_vma(mm, start);
|
|
|
|
if (!first)
|
|
|
|
return ERR_PTR(-EFAULT);
|
|
|
|
prev = NULL;
|
|
|
|
for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
|
2006-01-08 10:00:50 +01:00
|
|
|
if (!(flags & MPOL_MF_DISCONTIG_OK)) {
|
|
|
|
if (!vma->vm_next && vma->vm_end < end)
|
|
|
|
return ERR_PTR(-EFAULT);
|
|
|
|
if (prev && prev->vm_end < vma->vm_start)
|
|
|
|
return ERR_PTR(-EFAULT);
|
|
|
|
}
|
|
|
|
if (!is_vm_hugetlb_page(vma) &&
|
|
|
|
((flags & MPOL_MF_STRICT) ||
|
|
|
|
((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
|
|
|
|
vma_migratable(vma)))) {
|
2005-09-13 10:25:08 +02:00
|
|
|
unsigned long endvma = vma->vm_end;
|
2006-01-08 10:00:50 +01:00
|
|
|
|
2005-09-13 10:25:08 +02:00
|
|
|
if (endvma > end)
|
|
|
|
endvma = end;
|
|
|
|
if (vma->vm_start > start)
|
|
|
|
start = vma->vm_start;
|
2006-01-08 10:00:50 +01:00
|
|
|
err = check_pgd_range(vma, start, endvma, nodes,
|
2006-01-08 10:01:01 +01:00
|
|
|
flags, private);
|
2005-04-17 00:20:36 +02:00
|
|
|
if (err) {
|
|
|
|
first = ERR_PTR(err);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
prev = vma;
|
|
|
|
}
|
|
|
|
return first;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Apply policy to a single VMA */
|
|
|
|
static int policy_vma(struct vm_area_struct *vma, struct mempolicy *new)
|
|
|
|
{
|
|
|
|
int err = 0;
|
|
|
|
struct mempolicy *old = vma->vm_policy;
|
|
|
|
|
2007-07-16 08:38:16 +02:00
|
|
|
pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
|
2005-04-17 00:20:36 +02:00
|
|
|
vma->vm_start, vma->vm_end, vma->vm_pgoff,
|
|
|
|
vma->vm_ops, vma->vm_file,
|
|
|
|
vma->vm_ops ? vma->vm_ops->set_policy : NULL);
|
|
|
|
|
|
|
|
if (vma->vm_ops && vma->vm_ops->set_policy)
|
|
|
|
err = vma->vm_ops->set_policy(vma, new);
|
|
|
|
if (!err) {
|
|
|
|
mpol_get(new);
|
|
|
|
vma->vm_policy = new;
|
2008-04-28 11:13:08 +02:00
|
|
|
mpol_put(old);
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Step 2: apply policy to a range and do splits. */
|
|
|
|
static int mbind_range(struct vm_area_struct *vma, unsigned long start,
|
|
|
|
unsigned long end, struct mempolicy *new)
|
|
|
|
{
|
|
|
|
struct vm_area_struct *next;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
err = 0;
|
|
|
|
for (; vma && vma->vm_start < end; vma = next) {
|
|
|
|
next = vma->vm_next;
|
|
|
|
if (vma->vm_start < start)
|
|
|
|
err = split_vma(vma->vm_mm, vma, start, 1);
|
|
|
|
if (!err && vma->vm_end > end)
|
|
|
|
err = split_vma(vma->vm_mm, vma, end, 0);
|
|
|
|
if (!err)
|
|
|
|
err = policy_vma(vma, new);
|
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2006-03-24 12:16:08 +01:00
|
|
|
/*
|
|
|
|
* Update task->flags PF_MEMPOLICY bit: set iff non-default
|
|
|
|
* mempolicy. Allows more rapid checking of this (combined perhaps
|
|
|
|
* with other PF_* flag bits) on memory allocation hot code paths.
|
|
|
|
*
|
|
|
|
* If called from outside this file, the task 'p' should -only- be
|
|
|
|
* a newly forked child not yet visible on the task list, because
|
|
|
|
* manipulating the task flags of a visible task is not safe.
|
|
|
|
*
|
|
|
|
* The above limitation is why this routine has the funny name
|
|
|
|
* mpol_fix_fork_child_flag().
|
|
|
|
*
|
|
|
|
* It is also safe to call this with a task pointer of current,
|
|
|
|
* which the static wrapper mpol_set_task_struct_flag() does,
|
|
|
|
* for use within this file.
|
|
|
|
*/
|
|
|
|
|
|
|
|
void mpol_fix_fork_child_flag(struct task_struct *p)
|
|
|
|
{
|
|
|
|
if (p->mempolicy)
|
|
|
|
p->flags |= PF_MEMPOLICY;
|
|
|
|
else
|
|
|
|
p->flags &= ~PF_MEMPOLICY;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void mpol_set_task_struct_flag(void)
|
|
|
|
{
|
|
|
|
mpol_fix_fork_child_flag(current);
|
|
|
|
}
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
/* Set the process memory policy */
|
2008-04-28 11:12:25 +02:00
|
|
|
static long do_set_mempolicy(unsigned short mode, unsigned short flags,
|
|
|
|
nodemask_t *nodes)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
struct mempolicy *new, *old;
|
2008-04-28 11:13:10 +02:00
|
|
|
struct mm_struct *mm = current->mm;
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
NODEMASK_SCRATCH(scratch);
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
int ret;
|
2005-04-17 00:20:36 +02:00
|
|
|
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
if (!scratch)
|
|
|
|
return -ENOMEM;
|
2008-04-28 11:13:10 +02:00
|
|
|
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
new = mpol_new(mode, flags, nodes);
|
|
|
|
if (IS_ERR(new)) {
|
|
|
|
ret = PTR_ERR(new);
|
|
|
|
goto out;
|
|
|
|
}
|
2008-04-28 11:13:10 +02:00
|
|
|
/*
|
|
|
|
* prevent changing our mempolicy while show_numa_maps()
|
|
|
|
* is using it.
|
|
|
|
* Note: do_set_mempolicy() can be called at init time
|
|
|
|
* with no 'mm'.
|
|
|
|
*/
|
|
|
|
if (mm)
|
|
|
|
down_write(&mm->mmap_sem);
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
task_lock(current);
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
ret = mpol_set_nodemask(new, nodes, scratch);
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
if (ret) {
|
|
|
|
task_unlock(current);
|
|
|
|
if (mm)
|
|
|
|
up_write(&mm->mmap_sem);
|
|
|
|
mpol_put(new);
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
goto out;
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
}
|
|
|
|
old = current->mempolicy;
|
2005-04-17 00:20:36 +02:00
|
|
|
current->mempolicy = new;
|
2006-03-24 12:16:08 +01:00
|
|
|
mpol_set_task_struct_flag();
|
2008-04-28 11:13:12 +02:00
|
|
|
if (new && new->mode == MPOL_INTERLEAVE &&
|
mempolicy: add MPOL_F_STATIC_NODES flag
Add an optional mempolicy mode flag, MPOL_F_STATIC_NODES, that suppresses the
node remap when the policy is rebound.
Adds another member to struct mempolicy, nodemask_t user_nodemask, as part of
a union with cpuset_mems_allowed:
struct mempolicy {
...
union {
nodemask_t cpuset_mems_allowed;
nodemask_t user_nodemask;
} w;
}
that stores the the nodemask that the user passed when he or she created the
mempolicy via set_mempolicy() or mbind(). When using MPOL_F_STATIC_NODES,
which is passed with any mempolicy mode, the user's passed nodemask
intersected with the VMA or task's allowed nodes is always used when
determining the preferred node, setting the MPOL_BIND zonelist, or creating
the interleave nodemask. This happens whenever the policy is rebound,
including when a task's cpuset assignment changes or the cpuset's mems are
changed.
This creates an interesting side-effect in that it allows the mempolicy
"intent" to lie dormant and uneffected until it has access to the node(s) that
it desires. For example, if you currently ask for an interleaved policy over
a set of nodes that you do not have access to, the mempolicy is not created
and the task continues to use the previous policy. With this change, however,
it is possible to create the same mempolicy; it is only effected when access
to nodes in the nodemask is acquired.
It is also possible to mount tmpfs with the static nodemask behavior when
specifying a node or nodemask. To do this, simply add "=static" immediately
following the mempolicy mode at mount time:
mount -o remount mpol=interleave=static:1-3
Also removes mpol_check_policy() and folds its logic into mpol_new() since it
is now obsoleted. The unused vma_mpol_equal() is also removed.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:27 +02:00
|
|
|
nodes_weight(new->v.nodes))
|
2005-10-30 02:15:48 +01:00
|
|
|
current->il_next = first_node(new->v.nodes);
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
task_unlock(current);
|
2008-04-28 11:13:10 +02:00
|
|
|
if (mm)
|
|
|
|
up_write(&mm->mmap_sem);
|
|
|
|
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
mpol_put(old);
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
ret = 0;
|
|
|
|
out:
|
|
|
|
NODEMASK_SCRATCH_FREE(scratch);
|
|
|
|
return ret;
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
/*
|
|
|
|
* Return nodemask for policy for get_mempolicy() query
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
*
|
|
|
|
* Called with task's alloc_lock held
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
*/
|
|
|
|
static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
2005-10-30 02:15:48 +01:00
|
|
|
nodes_clear(*nodes);
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
if (p == &default_policy)
|
|
|
|
return;
|
|
|
|
|
2008-04-28 11:13:12 +02:00
|
|
|
switch (p->mode) {
|
2008-04-28 11:12:18 +02:00
|
|
|
case MPOL_BIND:
|
|
|
|
/* Fall through */
|
2005-04-17 00:20:36 +02:00
|
|
|
case MPOL_INTERLEAVE:
|
2005-10-30 02:15:48 +01:00
|
|
|
*nodes = p->v.nodes;
|
2005-04-17 00:20:36 +02:00
|
|
|
break;
|
|
|
|
case MPOL_PREFERRED:
|
2008-04-28 11:13:21 +02:00
|
|
|
if (!(p->flags & MPOL_F_LOCAL))
|
2005-10-30 02:15:48 +01:00
|
|
|
node_set(p->v.preferred_node, *nodes);
|
mempolicy: mPOL_PREFERRED cleanups for "local allocation"
Here are a couple of "cleanups" for MPOL_PREFERRED behavior when
v.preferred_node < 0 -- i.e., "local allocation":
1) [do_]get_mempolicy() calls the now renamed get_policy_nodemask()
to fetch the nodemask associated with a policy. Currently,
get_policy_nodemask() returns the set of nodes with memory, when
the policy 'mode' is 'PREFERRED, and the preferred_node is < 0.
Change to return an empty nodemask, as this is what was specified
to achieve "local allocation".
2) When a task is moved into a [new] cpuset, mpol_rebind_policy() is
called to adjust any task and vma policy nodes to be valid in the
new cpuset. However, when the policy is MPOL_PREFERRED, and the
preferred_node is <0, no rebind is necessary. The "local allocation"
indication is valid in any cpuset. Existing code will "do the right
thing" because node_remap() will just return the argument node when
it is outside of the valid range of node ids. However, I think it is
clearer and cleaner to skip the remap explicitly in this case.
3) mpol_to_str() produces a printable, "human readable" string from a
struct mempolicy. For MPOL_PREFERRED with preferred_node <0, show
"local", as this indicates local allocation, as the task migrates
among nodes. Note that this matches the usage of "local allocation"
in libnuma() and numactl. Without this change, I believe that node_set()
[via set_bit()] will set bit 31, resulting in a misleading display.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:20 +02:00
|
|
|
/* else return empty node mask for local allocation */
|
2005-04-17 00:20:36 +02:00
|
|
|
break;
|
|
|
|
default:
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int lookup_node(struct mm_struct *mm, unsigned long addr)
|
|
|
|
{
|
|
|
|
struct page *p;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
err = get_user_pages(current, mm, addr & PAGE_MASK, 1, 0, 0, &p, NULL);
|
|
|
|
if (err >= 0) {
|
|
|
|
err = page_to_nid(p);
|
|
|
|
put_page(p);
|
|
|
|
}
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Retrieve NUMA policy */
|
2007-10-16 10:26:26 +02:00
|
|
|
static long do_get_mempolicy(int *policy, nodemask_t *nmask,
|
|
|
|
unsigned long addr, unsigned long flags)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
2005-10-30 02:16:59 +01:00
|
|
|
int err;
|
2005-04-17 00:20:36 +02:00
|
|
|
struct mm_struct *mm = current->mm;
|
|
|
|
struct vm_area_struct *vma = NULL;
|
|
|
|
struct mempolicy *pol = current->mempolicy;
|
|
|
|
|
2007-10-16 10:24:51 +02:00
|
|
|
if (flags &
|
|
|
|
~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED))
|
2005-04-17 00:20:36 +02:00
|
|
|
return -EINVAL;
|
2007-10-16 10:24:51 +02:00
|
|
|
|
|
|
|
if (flags & MPOL_F_MEMS_ALLOWED) {
|
|
|
|
if (flags & (MPOL_F_NODE|MPOL_F_ADDR))
|
|
|
|
return -EINVAL;
|
|
|
|
*policy = 0; /* just so it's initialized */
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
task_lock(current);
|
2007-10-16 10:24:51 +02:00
|
|
|
*nmask = cpuset_current_mems_allowed;
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
task_unlock(current);
|
2007-10-16 10:24:51 +02:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
if (flags & MPOL_F_ADDR) {
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
/*
|
|
|
|
* Do NOT fall back to task policy if the
|
|
|
|
* vma/shared policy at addr is NULL. We
|
|
|
|
* want to return MPOL_DEFAULT in this case.
|
|
|
|
*/
|
2005-04-17 00:20:36 +02:00
|
|
|
down_read(&mm->mmap_sem);
|
|
|
|
vma = find_vma_intersection(mm, addr, addr+1);
|
|
|
|
if (!vma) {
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
return -EFAULT;
|
|
|
|
}
|
|
|
|
if (vma->vm_ops && vma->vm_ops->get_policy)
|
|
|
|
pol = vma->vm_ops->get_policy(vma, addr);
|
|
|
|
else
|
|
|
|
pol = vma->vm_policy;
|
|
|
|
} else if (addr)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (!pol)
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
pol = &default_policy; /* indicates default behavior */
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
if (flags & MPOL_F_NODE) {
|
|
|
|
if (flags & MPOL_F_ADDR) {
|
|
|
|
err = lookup_node(mm, addr);
|
|
|
|
if (err < 0)
|
|
|
|
goto out;
|
2005-10-30 02:16:59 +01:00
|
|
|
*policy = err;
|
2005-04-17 00:20:36 +02:00
|
|
|
} else if (pol == current->mempolicy &&
|
2008-04-28 11:13:12 +02:00
|
|
|
pol->mode == MPOL_INTERLEAVE) {
|
2005-10-30 02:16:59 +01:00
|
|
|
*policy = current->il_next;
|
2005-04-17 00:20:36 +02:00
|
|
|
} else {
|
|
|
|
err = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
} else {
|
|
|
|
*policy = pol == &default_policy ? MPOL_DEFAULT :
|
|
|
|
pol->mode;
|
2008-07-04 21:24:13 +02:00
|
|
|
/*
|
|
|
|
* Internal mempolicy flags must be masked off before exposing
|
|
|
|
* the policy to userspace.
|
|
|
|
*/
|
|
|
|
*policy |= (pol->flags & MPOL_MODE_FLAGS);
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
}
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
if (vma) {
|
|
|
|
up_read(¤t->mm->mmap_sem);
|
|
|
|
vma = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
err = 0;
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
if (nmask) {
|
|
|
|
task_lock(current);
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
get_policy_nodemask(pol, nmask);
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
task_unlock(current);
|
|
|
|
}
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
out:
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
mpol_cond_put(pol);
|
2005-04-17 00:20:36 +02:00
|
|
|
if (vma)
|
|
|
|
up_read(¤t->mm->mmap_sem);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2006-03-22 09:09:12 +01:00
|
|
|
#ifdef CONFIG_MIGRATION
|
2006-01-08 10:01:04 +01:00
|
|
|
/*
|
|
|
|
* page migration
|
|
|
|
*/
|
2006-01-19 02:42:29 +01:00
|
|
|
static void migrate_page_add(struct page *page, struct list_head *pagelist,
|
|
|
|
unsigned long flags)
|
2006-01-08 10:01:04 +01:00
|
|
|
{
|
|
|
|
/*
|
2006-01-19 02:42:29 +01:00
|
|
|
* Avoid migrating a page that is shared with others.
|
2006-01-08 10:01:04 +01:00
|
|
|
*/
|
vmscan: move isolate_lru_page() to vmscan.c
On large memory systems, the VM can spend way too much time scanning
through pages that it cannot (or should not) evict from memory. Not only
does it use up CPU time, but it also provokes lock contention and can
leave large systems under memory presure in a catatonic state.
This patch series improves VM scalability by:
1) putting filesystem backed, swap backed and unevictable pages
onto their own LRUs, so the system only scans the pages that it
can/should evict from memory
2) switching to two handed clock replacement for the anonymous LRUs,
so the number of pages that need to be scanned when the system
starts swapping is bound to a reasonable number
3) keeping unevictable pages off the LRU completely, so the
VM does not waste CPU time scanning them. ramfs, ramdisk,
SHM_LOCKED shared memory segments and mlock()ed VMA pages
are keept on the unevictable list.
This patch:
isolate_lru_page logically belongs to be in vmscan.c than migrate.c.
It is tough, because we don't need that function without memory migration
so there is a valid argument to have it in migrate.c. However a
subsequent patch needs to make use of it in the core mm, so we can happily
move it to vmscan.c.
Also, make the function a little more generic by not requiring that it
adds an isolated page to a given list. Callers can do that.
Note that we now have '__isolate_lru_page()', that does
something quite different, visible outside of vmscan.c
for use with memory controller. Methinks we need to
rationalize these names/purposes. --lts
[akpm@linux-foundation.org: fix mm/memory_hotplug.c build]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 05:26:09 +02:00
|
|
|
if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) {
|
|
|
|
if (!isolate_lru_page(page)) {
|
|
|
|
list_add_tail(&page->lru, pagelist);
|
2009-12-15 02:58:11 +01:00
|
|
|
inc_zone_page_state(page, NR_ISOLATED_ANON +
|
|
|
|
page_is_file_cache(page));
|
vmscan: move isolate_lru_page() to vmscan.c
On large memory systems, the VM can spend way too much time scanning
through pages that it cannot (or should not) evict from memory. Not only
does it use up CPU time, but it also provokes lock contention and can
leave large systems under memory presure in a catatonic state.
This patch series improves VM scalability by:
1) putting filesystem backed, swap backed and unevictable pages
onto their own LRUs, so the system only scans the pages that it
can/should evict from memory
2) switching to two handed clock replacement for the anonymous LRUs,
so the number of pages that need to be scanned when the system
starts swapping is bound to a reasonable number
3) keeping unevictable pages off the LRU completely, so the
VM does not waste CPU time scanning them. ramfs, ramdisk,
SHM_LOCKED shared memory segments and mlock()ed VMA pages
are keept on the unevictable list.
This patch:
isolate_lru_page logically belongs to be in vmscan.c than migrate.c.
It is tough, because we don't need that function without memory migration
so there is a valid argument to have it in migrate.c. However a
subsequent patch needs to make use of it in the core mm, so we can happily
move it to vmscan.c.
Also, make the function a little more generic by not requiring that it
adds an isolated page to a given list. Callers can do that.
Note that we now have '__isolate_lru_page()', that does
something quite different, visible outside of vmscan.c
for use with memory controller. Methinks we need to
rationalize these names/purposes. --lts
[akpm@linux-foundation.org: fix mm/memory_hotplug.c build]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 05:26:09 +02:00
|
|
|
}
|
|
|
|
}
|
2006-02-01 12:05:40 +01:00
|
|
|
}
|
2006-01-08 10:01:04 +01:00
|
|
|
|
2006-06-23 11:03:55 +02:00
|
|
|
static struct page *new_node_page(struct page *page, unsigned long node, int **x)
|
2006-06-23 11:03:53 +02:00
|
|
|
{
|
2009-06-17 00:31:54 +02:00
|
|
|
return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0);
|
2006-06-23 11:03:53 +02:00
|
|
|
}
|
|
|
|
|
2006-02-01 12:05:40 +01:00
|
|
|
/*
|
|
|
|
* Migrate pages from one node to a target node.
|
|
|
|
* Returns error or the number of pages not migrated.
|
|
|
|
*/
|
2007-10-16 10:26:26 +02:00
|
|
|
static int migrate_to_node(struct mm_struct *mm, int source, int dest,
|
|
|
|
int flags)
|
2006-02-01 12:05:40 +01:00
|
|
|
{
|
|
|
|
nodemask_t nmask;
|
|
|
|
LIST_HEAD(pagelist);
|
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
nodes_clear(nmask);
|
|
|
|
node_set(source, nmask);
|
2006-01-08 10:01:04 +01:00
|
|
|
|
2006-02-01 12:05:40 +01:00
|
|
|
check_range(mm, mm->mmap->vm_start, TASK_SIZE, &nmask,
|
|
|
|
flags | MPOL_MF_DISCONTIG_OK, &pagelist);
|
|
|
|
|
2006-06-23 11:03:52 +02:00
|
|
|
if (!list_empty(&pagelist))
|
ksm: memory hotremove migration only
The previous patch enables page migration of ksm pages, but that soon gets
into trouble: not surprising, since we're using the ksm page lock to lock
operations on its stable_node, but page migration switches the page whose
lock is to be used for that. Another layer of locking would fix it, but
do we need that yet?
Do we actually need page migration of ksm pages? Yes, memory hotremove
needs to offline sections of memory: and since we stopped allocating ksm
pages with GFP_HIGHUSER, they will tend to be GFP_HIGHUSER_MOVABLE
candidates for migration.
But KSM is currently unconscious of NUMA issues, happily merging pages
from different NUMA nodes: at present the rule must be, not to use
MADV_MERGEABLE where you care about NUMA. So no, NUMA page migration of
ksm pages does not make sense yet.
So, to complete support for ksm swapping we need to make hotremove safe.
ksm_memory_callback() take ksm_thread_mutex when MEM_GOING_OFFLINE and
release it when MEM_OFFLINE or MEM_CANCEL_OFFLINE. But if mapped pages
are freed before migration reaches them, stable_nodes may be left still
pointing to struct pages which have been removed from the system: the
stable_node needs to identify a page by pfn rather than page pointer, then
it can safely prune them when MEM_OFFLINE.
And make NUMA migration skip PageKsm pages where it skips PageReserved.
But it's only when we reach unmap_and_move() that the page lock is taken
and we can be sure that raised pagecount has prevented a PageAnon from
being upgraded: so add offlining arg to migrate_pages(), to migrate ksm
page when offlining (has sufficient locking) but reject it otherwise.
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Izik Eidus <ieidus@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Chris Wright <chrisw@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 02:59:33 +01:00
|
|
|
err = migrate_pages(&pagelist, new_node_page, dest, 0);
|
2006-06-23 11:03:53 +02:00
|
|
|
|
2006-02-01 12:05:40 +01:00
|
|
|
return err;
|
2006-01-08 10:01:04 +01:00
|
|
|
}
|
|
|
|
|
2006-01-08 10:00:51 +01:00
|
|
|
/*
|
2006-02-01 12:05:40 +01:00
|
|
|
* Move pages between the two nodesets so as to preserve the physical
|
|
|
|
* layout as much as possible.
|
2006-01-08 10:00:51 +01:00
|
|
|
*
|
|
|
|
* Returns the number of page that could not be moved.
|
|
|
|
*/
|
|
|
|
int do_migrate_pages(struct mm_struct *mm,
|
|
|
|
const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
|
|
|
|
{
|
2006-02-01 12:05:40 +01:00
|
|
|
int busy = 0;
|
2008-11-06 21:53:30 +01:00
|
|
|
int err;
|
2006-02-01 12:05:40 +01:00
|
|
|
nodemask_t tmp;
|
2006-01-08 10:00:51 +01:00
|
|
|
|
2008-11-06 21:53:30 +01:00
|
|
|
err = migrate_prep();
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
|
mempolicy: mPOL_PREFERRED cleanups for "local allocation"
Here are a couple of "cleanups" for MPOL_PREFERRED behavior when
v.preferred_node < 0 -- i.e., "local allocation":
1) [do_]get_mempolicy() calls the now renamed get_policy_nodemask()
to fetch the nodemask associated with a policy. Currently,
get_policy_nodemask() returns the set of nodes with memory, when
the policy 'mode' is 'PREFERRED, and the preferred_node is < 0.
Change to return an empty nodemask, as this is what was specified
to achieve "local allocation".
2) When a task is moved into a [new] cpuset, mpol_rebind_policy() is
called to adjust any task and vma policy nodes to be valid in the
new cpuset. However, when the policy is MPOL_PREFERRED, and the
preferred_node is <0, no rebind is necessary. The "local allocation"
indication is valid in any cpuset. Existing code will "do the right
thing" because node_remap() will just return the argument node when
it is outside of the valid range of node ids. However, I think it is
clearer and cleaner to skip the remap explicitly in this case.
3) mpol_to_str() produces a printable, "human readable" string from a
struct mempolicy. For MPOL_PREFERRED with preferred_node <0, show
"local", as this indicates local allocation, as the task migrates
among nodes. Note that this matches the usage of "local allocation"
in libnuma() and numactl. Without this change, I believe that node_set()
[via set_bit()] will set bit 31, resulting in a misleading display.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:20 +02:00
|
|
|
down_read(&mm->mmap_sem);
|
2006-01-08 10:00:51 +01:00
|
|
|
|
2006-06-25 14:46:48 +02:00
|
|
|
err = migrate_vmas(mm, from_nodes, to_nodes, flags);
|
|
|
|
if (err)
|
|
|
|
goto out;
|
|
|
|
|
2006-02-01 12:05:40 +01:00
|
|
|
/*
|
|
|
|
* Find a 'source' bit set in 'tmp' whose corresponding 'dest'
|
|
|
|
* bit in 'to' is not also set in 'tmp'. Clear the found 'source'
|
|
|
|
* bit in 'tmp', and return that <source, dest> pair for migration.
|
|
|
|
* The pair of nodemasks 'to' and 'from' define the map.
|
|
|
|
*
|
|
|
|
* If no pair of bits is found that way, fallback to picking some
|
|
|
|
* pair of 'source' and 'dest' bits that are not the same. If the
|
|
|
|
* 'source' and 'dest' bits are the same, this represents a node
|
|
|
|
* that will be migrating to itself, so no pages need move.
|
|
|
|
*
|
|
|
|
* If no bits are left in 'tmp', or if all remaining bits left
|
|
|
|
* in 'tmp' correspond to the same bit in 'to', return false
|
|
|
|
* (nothing left to migrate).
|
|
|
|
*
|
|
|
|
* This lets us pick a pair of nodes to migrate between, such that
|
|
|
|
* if possible the dest node is not already occupied by some other
|
|
|
|
* source node, minimizing the risk of overloading the memory on a
|
|
|
|
* node that would happen if we migrated incoming memory to a node
|
|
|
|
* before migrating outgoing memory source that same node.
|
|
|
|
*
|
|
|
|
* A single scan of tmp is sufficient. As we go, we remember the
|
|
|
|
* most recent <s, d> pair that moved (s != d). If we find a pair
|
|
|
|
* that not only moved, but what's better, moved to an empty slot
|
|
|
|
* (d is not set in tmp), then we break out then, with that pair.
|
|
|
|
* Otherwise when we finish scannng from_tmp, we at least have the
|
|
|
|
* most recent <s, d> pair that moved. If we get all the way through
|
|
|
|
* the scan of tmp without finding any node that moved, much less
|
|
|
|
* moved to an empty node, then there is nothing left worth migrating.
|
|
|
|
*/
|
2006-01-08 10:00:55 +01:00
|
|
|
|
2006-02-01 12:05:40 +01:00
|
|
|
tmp = *from_nodes;
|
|
|
|
while (!nodes_empty(tmp)) {
|
|
|
|
int s,d;
|
|
|
|
int source = -1;
|
|
|
|
int dest = 0;
|
|
|
|
|
|
|
|
for_each_node_mask(s, tmp) {
|
|
|
|
d = node_remap(s, *from_nodes, *to_nodes);
|
|
|
|
if (s == d)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
source = s; /* Node moved. Memorize */
|
|
|
|
dest = d;
|
|
|
|
|
|
|
|
/* dest not in remaining from nodes? */
|
|
|
|
if (!node_isset(dest, tmp))
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (source == -1)
|
|
|
|
break;
|
|
|
|
|
|
|
|
node_clear(source, tmp);
|
|
|
|
err = migrate_to_node(mm, source, dest, flags);
|
|
|
|
if (err > 0)
|
|
|
|
busy += err;
|
|
|
|
if (err < 0)
|
|
|
|
break;
|
2006-01-08 10:00:51 +01:00
|
|
|
}
|
2006-06-25 14:46:48 +02:00
|
|
|
out:
|
2006-01-08 10:00:51 +01:00
|
|
|
up_read(&mm->mmap_sem);
|
2006-02-01 12:05:40 +01:00
|
|
|
if (err < 0)
|
|
|
|
return err;
|
|
|
|
return busy;
|
2006-03-22 09:09:12 +01:00
|
|
|
|
|
|
|
}
|
|
|
|
|
Migration: find correct vma in new_vma_page()
We hit the BUG_ON() in mm/rmap.c:vma_address() when trying to migrate via
mbind(MPOL_MF_MOVE) a non-anon region that spans multiple vmas. For
anon-regions, we just fail to migrate any pages beyond the 1st vma in the
range.
This occurs because do_mbind() collects a list of pages to migrate by
calling check_range(). check_range() walks the task's mm, spanning vmas as
necessary, to collect the migratable pages into a list. Then, do_mbind()
calls migrate_pages() passing the list of pages, a function to allocate new
pages based on vma policy [new_vma_page()], and a pointer to the first vma
of the range.
For each page in the list, new_vma_page() calls page_address_in_vma()
passing the page and the vma [first in range] to obtain the address to get
for alloc_page_vma(). The page address is needed to get interleaving
policy correct. If the pages in the list come from multiple vmas,
eventually, new_page_address() will pass that page to page_address_in_vma()
with the incorrect vma. For !PageAnon pages, this will result in a bug
check in rmap.c:vma_address(). For anon pages, vma_address() will just
return EFAULT and fail the migration.
This patch modifies new_vma_page() to check the return value from
page_address_in_vma(). If the return value is EFAULT, new_vma_page()
searchs forward via vm_next for the vma that maps the page--i.e., that does
not return EFAULT. This assumes that the pages in the list handed to
migrate_pages() is in address order. This is currently case. The patch
documents this assumption in a new comment block for new_vma_page().
If new_vma_page() cannot locate the vma mapping the page in a forward
search in the mm, it will pass a NULL vma to alloc_page_vma(). This will
result in the allocation using the task policy, if any, else system default
policy. This situation is unlikely, but the patch documents this behavior
with a comment.
Note, this patch results in restarting from the first vma in a multi-vma
range each time new_vma_page() is called. If this is not acceptable, we
can make the vma argument a pointer, both in new_vma_page() and it's caller
unmap_and_move() so that the value held by the loop in migrate_pages()
always passes down the last vma in which a page was found. This will
require changes to all new_page_t functions passed to migrate_pages(). Is
this necessary?
For this patch to work, we can't bug check in vma_address() for pages
outside the argument vma. This patch removes the BUG_ON(). All other
callers [besides new_vma_page()] already check the return status.
Tested on x86_64, 4 node NUMA platform.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-11-15 01:59:10 +01:00
|
|
|
/*
|
|
|
|
* Allocate a new page for page migration based on vma policy.
|
|
|
|
* Start assuming that page is mapped by vma pointed to by @private.
|
|
|
|
* Search forward from there, if not. N.B., this assumes that the
|
|
|
|
* list of pages handed to migrate_pages()--which is how we get here--
|
|
|
|
* is in virtual address order.
|
|
|
|
*/
|
2006-06-23 11:03:55 +02:00
|
|
|
static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
|
2006-06-23 11:03:53 +02:00
|
|
|
{
|
|
|
|
struct vm_area_struct *vma = (struct vm_area_struct *)private;
|
Migration: find correct vma in new_vma_page()
We hit the BUG_ON() in mm/rmap.c:vma_address() when trying to migrate via
mbind(MPOL_MF_MOVE) a non-anon region that spans multiple vmas. For
anon-regions, we just fail to migrate any pages beyond the 1st vma in the
range.
This occurs because do_mbind() collects a list of pages to migrate by
calling check_range(). check_range() walks the task's mm, spanning vmas as
necessary, to collect the migratable pages into a list. Then, do_mbind()
calls migrate_pages() passing the list of pages, a function to allocate new
pages based on vma policy [new_vma_page()], and a pointer to the first vma
of the range.
For each page in the list, new_vma_page() calls page_address_in_vma()
passing the page and the vma [first in range] to obtain the address to get
for alloc_page_vma(). The page address is needed to get interleaving
policy correct. If the pages in the list come from multiple vmas,
eventually, new_page_address() will pass that page to page_address_in_vma()
with the incorrect vma. For !PageAnon pages, this will result in a bug
check in rmap.c:vma_address(). For anon pages, vma_address() will just
return EFAULT and fail the migration.
This patch modifies new_vma_page() to check the return value from
page_address_in_vma(). If the return value is EFAULT, new_vma_page()
searchs forward via vm_next for the vma that maps the page--i.e., that does
not return EFAULT. This assumes that the pages in the list handed to
migrate_pages() is in address order. This is currently case. The patch
documents this assumption in a new comment block for new_vma_page().
If new_vma_page() cannot locate the vma mapping the page in a forward
search in the mm, it will pass a NULL vma to alloc_page_vma(). This will
result in the allocation using the task policy, if any, else system default
policy. This situation is unlikely, but the patch documents this behavior
with a comment.
Note, this patch results in restarting from the first vma in a multi-vma
range each time new_vma_page() is called. If this is not acceptable, we
can make the vma argument a pointer, both in new_vma_page() and it's caller
unmap_and_move() so that the value held by the loop in migrate_pages()
always passes down the last vma in which a page was found. This will
require changes to all new_page_t functions passed to migrate_pages(). Is
this necessary?
For this patch to work, we can't bug check in vma_address() for pages
outside the argument vma. This patch removes the BUG_ON(). All other
callers [besides new_vma_page()] already check the return status.
Tested on x86_64, 4 node NUMA platform.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-11-15 01:59:10 +01:00
|
|
|
unsigned long uninitialized_var(address);
|
2006-06-23 11:03:53 +02:00
|
|
|
|
Migration: find correct vma in new_vma_page()
We hit the BUG_ON() in mm/rmap.c:vma_address() when trying to migrate via
mbind(MPOL_MF_MOVE) a non-anon region that spans multiple vmas. For
anon-regions, we just fail to migrate any pages beyond the 1st vma in the
range.
This occurs because do_mbind() collects a list of pages to migrate by
calling check_range(). check_range() walks the task's mm, spanning vmas as
necessary, to collect the migratable pages into a list. Then, do_mbind()
calls migrate_pages() passing the list of pages, a function to allocate new
pages based on vma policy [new_vma_page()], and a pointer to the first vma
of the range.
For each page in the list, new_vma_page() calls page_address_in_vma()
passing the page and the vma [first in range] to obtain the address to get
for alloc_page_vma(). The page address is needed to get interleaving
policy correct. If the pages in the list come from multiple vmas,
eventually, new_page_address() will pass that page to page_address_in_vma()
with the incorrect vma. For !PageAnon pages, this will result in a bug
check in rmap.c:vma_address(). For anon pages, vma_address() will just
return EFAULT and fail the migration.
This patch modifies new_vma_page() to check the return value from
page_address_in_vma(). If the return value is EFAULT, new_vma_page()
searchs forward via vm_next for the vma that maps the page--i.e., that does
not return EFAULT. This assumes that the pages in the list handed to
migrate_pages() is in address order. This is currently case. The patch
documents this assumption in a new comment block for new_vma_page().
If new_vma_page() cannot locate the vma mapping the page in a forward
search in the mm, it will pass a NULL vma to alloc_page_vma(). This will
result in the allocation using the task policy, if any, else system default
policy. This situation is unlikely, but the patch documents this behavior
with a comment.
Note, this patch results in restarting from the first vma in a multi-vma
range each time new_vma_page() is called. If this is not acceptable, we
can make the vma argument a pointer, both in new_vma_page() and it's caller
unmap_and_move() so that the value held by the loop in migrate_pages()
always passes down the last vma in which a page was found. This will
require changes to all new_page_t functions passed to migrate_pages(). Is
this necessary?
For this patch to work, we can't bug check in vma_address() for pages
outside the argument vma. This patch removes the BUG_ON(). All other
callers [besides new_vma_page()] already check the return status.
Tested on x86_64, 4 node NUMA platform.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-11-15 01:59:10 +01:00
|
|
|
while (vma) {
|
|
|
|
address = page_address_in_vma(page, vma);
|
|
|
|
if (address != -EFAULT)
|
|
|
|
break;
|
|
|
|
vma = vma->vm_next;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* if !vma, alloc_page_vma() will use task or system default policy
|
|
|
|
*/
|
|
|
|
return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
|
2006-06-23 11:03:53 +02:00
|
|
|
}
|
2006-03-22 09:09:12 +01:00
|
|
|
#else
|
|
|
|
|
|
|
|
static void migrate_page_add(struct page *page, struct list_head *pagelist,
|
|
|
|
unsigned long flags)
|
|
|
|
{
|
2006-01-08 10:00:51 +01:00
|
|
|
}
|
|
|
|
|
2006-03-22 09:09:12 +01:00
|
|
|
int do_migrate_pages(struct mm_struct *mm,
|
|
|
|
const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
|
|
|
|
{
|
|
|
|
return -ENOSYS;
|
|
|
|
}
|
2006-06-23 11:03:53 +02:00
|
|
|
|
2006-10-11 10:21:28 +02:00
|
|
|
static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
|
2006-06-23 11:03:53 +02:00
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
2006-03-22 09:09:12 +01:00
|
|
|
#endif
|
|
|
|
|
2007-10-16 10:26:26 +02:00
|
|
|
static long do_mbind(unsigned long start, unsigned long len,
|
2008-04-28 11:12:25 +02:00
|
|
|
unsigned short mode, unsigned short mode_flags,
|
|
|
|
nodemask_t *nmask, unsigned long flags)
|
2006-01-08 10:01:04 +01:00
|
|
|
{
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
struct mm_struct *mm = current->mm;
|
|
|
|
struct mempolicy *new;
|
|
|
|
unsigned long end;
|
|
|
|
int err;
|
|
|
|
LIST_HEAD(pagelist);
|
|
|
|
|
mempolicy: convert MPOL constants to enum
The mempolicy mode constants, MPOL_DEFAULT, MPOL_PREFERRED, MPOL_BIND, and
MPOL_INTERLEAVE, are better declared as part of an enum since they are
sequentially numbered and cannot be combined.
The policy member of struct mempolicy is also converted from type short to
type unsigned short. A negative policy does not have any legitimate meaning,
so it is possible to change its type in preparation for adding optional mode
flags later.
The equivalent member of struct shmem_sb_info is also changed from int to
unsigned short.
For compatibility, the policy formal to get_mempolicy() remains as a pointer
to an int:
int get_mempolicy(int *policy, unsigned long *nmask,
unsigned long maxnode, unsigned long addr,
unsigned long flags);
although the only possible values is the range of type unsigned short.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:23 +02:00
|
|
|
if (flags & ~(unsigned long)(MPOL_MF_STRICT |
|
|
|
|
MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
|
2006-01-08 10:01:04 +01:00
|
|
|
return -EINVAL;
|
2006-03-15 04:50:21 +01:00
|
|
|
if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
|
2006-01-08 10:01:04 +01:00
|
|
|
return -EPERM;
|
|
|
|
|
|
|
|
if (start & ~PAGE_MASK)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (mode == MPOL_DEFAULT)
|
|
|
|
flags &= ~MPOL_MF_STRICT;
|
|
|
|
|
|
|
|
len = (len + PAGE_SIZE - 1) & PAGE_MASK;
|
|
|
|
end = start + len;
|
|
|
|
|
|
|
|
if (end < start)
|
|
|
|
return -EINVAL;
|
|
|
|
if (end == start)
|
|
|
|
return 0;
|
|
|
|
|
2008-04-28 11:12:25 +02:00
|
|
|
new = mpol_new(mode, mode_flags, nmask);
|
2006-01-08 10:01:04 +01:00
|
|
|
if (IS_ERR(new))
|
|
|
|
return PTR_ERR(new);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If we are using the default policy then operation
|
|
|
|
* on discontinuous address spaces is okay after all
|
|
|
|
*/
|
|
|
|
if (!new)
|
|
|
|
flags |= MPOL_MF_DISCONTIG_OK;
|
|
|
|
|
2008-04-28 11:12:25 +02:00
|
|
|
pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n",
|
|
|
|
start, start + len, mode, mode_flags,
|
|
|
|
nmask ? nodes_addr(*nmask)[0] : -1);
|
2006-01-08 10:01:04 +01:00
|
|
|
|
2008-11-06 21:53:30 +01:00
|
|
|
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
|
|
|
|
|
|
|
|
err = migrate_prep();
|
|
|
|
if (err)
|
2009-10-27 00:49:59 +01:00
|
|
|
goto mpol_out;
|
2008-11-06 21:53:30 +01:00
|
|
|
}
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
{
|
|
|
|
NODEMASK_SCRATCH(scratch);
|
|
|
|
if (scratch) {
|
|
|
|
down_write(&mm->mmap_sem);
|
|
|
|
task_lock(current);
|
|
|
|
err = mpol_set_nodemask(new, nmask, scratch);
|
|
|
|
task_unlock(current);
|
|
|
|
if (err)
|
|
|
|
up_write(&mm->mmap_sem);
|
|
|
|
} else
|
|
|
|
err = -ENOMEM;
|
|
|
|
NODEMASK_SCRATCH_FREE(scratch);
|
|
|
|
}
|
2009-10-27 00:49:59 +01:00
|
|
|
if (err)
|
|
|
|
goto mpol_out;
|
|
|
|
|
2006-01-08 10:01:04 +01:00
|
|
|
vma = check_range(mm, start, end, nmask,
|
|
|
|
flags | MPOL_MF_INVERT, &pagelist);
|
|
|
|
|
|
|
|
err = PTR_ERR(vma);
|
|
|
|
if (!IS_ERR(vma)) {
|
|
|
|
int nr_failed = 0;
|
|
|
|
|
|
|
|
err = mbind_range(vma, start, end, new);
|
2006-02-01 12:05:40 +01:00
|
|
|
|
2006-01-08 10:01:04 +01:00
|
|
|
if (!list_empty(&pagelist))
|
2006-06-23 11:03:53 +02:00
|
|
|
nr_failed = migrate_pages(&pagelist, new_vma_page,
|
ksm: memory hotremove migration only
The previous patch enables page migration of ksm pages, but that soon gets
into trouble: not surprising, since we're using the ksm page lock to lock
operations on its stable_node, but page migration switches the page whose
lock is to be used for that. Another layer of locking would fix it, but
do we need that yet?
Do we actually need page migration of ksm pages? Yes, memory hotremove
needs to offline sections of memory: and since we stopped allocating ksm
pages with GFP_HIGHUSER, they will tend to be GFP_HIGHUSER_MOVABLE
candidates for migration.
But KSM is currently unconscious of NUMA issues, happily merging pages
from different NUMA nodes: at present the rule must be, not to use
MADV_MERGEABLE where you care about NUMA. So no, NUMA page migration of
ksm pages does not make sense yet.
So, to complete support for ksm swapping we need to make hotremove safe.
ksm_memory_callback() take ksm_thread_mutex when MEM_GOING_OFFLINE and
release it when MEM_OFFLINE or MEM_CANCEL_OFFLINE. But if mapped pages
are freed before migration reaches them, stable_nodes may be left still
pointing to struct pages which have been removed from the system: the
stable_node needs to identify a page by pfn rather than page pointer, then
it can safely prune them when MEM_OFFLINE.
And make NUMA migration skip PageKsm pages where it skips PageReserved.
But it's only when we reach unmap_and_move() that the page lock is taken
and we can be sure that raised pagecount has prevented a PageAnon from
being upgraded: so add offlining arg to migrate_pages(), to migrate ksm
page when offlining (has sufficient locking) but reject it otherwise.
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Izik Eidus <ieidus@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Chris Wright <chrisw@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 02:59:33 +01:00
|
|
|
(unsigned long)vma, 0);
|
2006-01-08 10:01:04 +01:00
|
|
|
|
|
|
|
if (!err && nr_failed && (flags & MPOL_MF_STRICT))
|
|
|
|
err = -EIO;
|
mbind(): fix leak of never putback pages
If mbind() receives an invalid address, do_mbind leaks a page. The
following test program detects this leak.
This patch fixes it.
migrate_efault.c
=======================================
#include <numaif.h>
#include <numa.h>
#include <sys/mman.h>
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <string.h>
static unsigned long pagesize;
static void* make_hole_mapping(void)
{
void* addr;
addr = mmap(NULL, pagesize*3, PROT_READ|PROT_WRITE,
MAP_ANON|MAP_PRIVATE, 0, 0);
if (addr == MAP_FAILED)
return NULL;
/* make page populate */
memset(addr, 0, pagesize*3);
/* make memory hole */
munmap(addr+pagesize, pagesize);
return addr;
}
int main(int argc, char** argv)
{
void* addr;
int ch;
int node;
struct bitmask *nmask = numa_allocate_nodemask();
int err;
int node_set = 0;
while ((ch = getopt(argc, argv, "n:")) != -1){
switch (ch){
case 'n':
node = strtol(optarg, NULL, 0);
numa_bitmask_setbit(nmask, node);
node_set = 1;
break;
default:
;
}
}
argc -= optind;
argv += optind;
if (!node_set)
numa_bitmask_setbit(nmask, 0);
pagesize = getpagesize();
addr = make_hole_mapping();
err = mbind(addr, pagesize*3, MPOL_BIND, nmask->maskp, nmask->size, MPOL_MF_MOVE_ALL);
if (err)
perror("mbind ");
return 0;
}
=======================================
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Christoph Lameter <cl@linux-foundation.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-10-27 00:49:58 +01:00
|
|
|
} else
|
|
|
|
putback_lru_pages(&pagelist);
|
2006-03-22 09:09:12 +01:00
|
|
|
|
2006-01-08 10:01:04 +01:00
|
|
|
up_write(&mm->mmap_sem);
|
2009-10-27 00:49:59 +01:00
|
|
|
mpol_out:
|
2008-04-28 11:13:08 +02:00
|
|
|
mpol_put(new);
|
2006-01-08 10:01:04 +01:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2005-10-30 02:16:59 +01:00
|
|
|
/*
|
|
|
|
* User space interface with variable sized bitmaps for nodelists.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* Copy a node mask from user space. */
|
2006-01-08 10:00:51 +01:00
|
|
|
static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask,
|
2005-10-30 02:16:59 +01:00
|
|
|
unsigned long maxnode)
|
|
|
|
{
|
|
|
|
unsigned long k;
|
|
|
|
unsigned long nlongs;
|
|
|
|
unsigned long endmask;
|
|
|
|
|
|
|
|
--maxnode;
|
|
|
|
nodes_clear(*nodes);
|
|
|
|
if (maxnode == 0 || !nmask)
|
|
|
|
return 0;
|
2006-02-21 03:27:59 +01:00
|
|
|
if (maxnode > PAGE_SIZE*BITS_PER_BYTE)
|
2006-02-17 22:59:36 +01:00
|
|
|
return -EINVAL;
|
2005-10-30 02:16:59 +01:00
|
|
|
|
|
|
|
nlongs = BITS_TO_LONGS(maxnode);
|
|
|
|
if ((maxnode % BITS_PER_LONG) == 0)
|
|
|
|
endmask = ~0UL;
|
|
|
|
else
|
|
|
|
endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1;
|
|
|
|
|
|
|
|
/* When the user specified more nodes than supported just check
|
|
|
|
if the non supported part is all zero. */
|
|
|
|
if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) {
|
|
|
|
if (nlongs > PAGE_SIZE/sizeof(long))
|
|
|
|
return -EINVAL;
|
|
|
|
for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) {
|
|
|
|
unsigned long t;
|
|
|
|
if (get_user(t, nmask + k))
|
|
|
|
return -EFAULT;
|
|
|
|
if (k == nlongs - 1) {
|
|
|
|
if (t & endmask)
|
|
|
|
return -EINVAL;
|
|
|
|
} else if (t)
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
nlongs = BITS_TO_LONGS(MAX_NUMNODES);
|
|
|
|
endmask = ~0UL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long)))
|
|
|
|
return -EFAULT;
|
|
|
|
nodes_addr(*nodes)[nlongs-1] &= endmask;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Copy a kernel node mask to user space */
|
|
|
|
static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
|
|
|
|
nodemask_t *nodes)
|
|
|
|
{
|
|
|
|
unsigned long copy = ALIGN(maxnode-1, 64) / 8;
|
|
|
|
const int nbytes = BITS_TO_LONGS(MAX_NUMNODES) * sizeof(long);
|
|
|
|
|
|
|
|
if (copy > nbytes) {
|
|
|
|
if (copy > PAGE_SIZE)
|
|
|
|
return -EINVAL;
|
|
|
|
if (clear_user((char __user *)mask + nbytes, copy - nbytes))
|
|
|
|
return -EFAULT;
|
|
|
|
copy = nbytes;
|
|
|
|
}
|
|
|
|
return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0;
|
|
|
|
}
|
|
|
|
|
2009-01-14 14:14:30 +01:00
|
|
|
SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
|
|
|
|
unsigned long, mode, unsigned long __user *, nmask,
|
|
|
|
unsigned long, maxnode, unsigned, flags)
|
2005-10-30 02:16:59 +01:00
|
|
|
{
|
|
|
|
nodemask_t nodes;
|
|
|
|
int err;
|
2008-04-28 11:12:25 +02:00
|
|
|
unsigned short mode_flags;
|
2005-10-30 02:16:59 +01:00
|
|
|
|
2008-04-28 11:12:25 +02:00
|
|
|
mode_flags = mode & MPOL_MODE_FLAGS;
|
|
|
|
mode &= ~MPOL_MODE_FLAGS;
|
mempolicy: convert MPOL constants to enum
The mempolicy mode constants, MPOL_DEFAULT, MPOL_PREFERRED, MPOL_BIND, and
MPOL_INTERLEAVE, are better declared as part of an enum since they are
sequentially numbered and cannot be combined.
The policy member of struct mempolicy is also converted from type short to
type unsigned short. A negative policy does not have any legitimate meaning,
so it is possible to change its type in preparation for adding optional mode
flags later.
The equivalent member of struct shmem_sb_info is also changed from int to
unsigned short.
For compatibility, the policy formal to get_mempolicy() remains as a pointer
to an int:
int get_mempolicy(int *policy, unsigned long *nmask,
unsigned long maxnode, unsigned long addr,
unsigned long flags);
although the only possible values is the range of type unsigned short.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:23 +02:00
|
|
|
if (mode >= MPOL_MAX)
|
|
|
|
return -EINVAL;
|
mempolicy: add MPOL_F_RELATIVE_NODES flag
Adds another optional mode flag, MPOL_F_RELATIVE_NODES, that specifies
nodemasks passed via set_mempolicy() or mbind() should be considered relative
to the current task's mems_allowed.
When the mempolicy is created, the passed nodemask is folded and mapped onto
the current task's mems_allowed. For example, consider a task using
set_mempolicy() to pass MPOL_INTERLEAVE | MPOL_F_RELATIVE_NODES with a
nodemask of 1-3. If current's mems_allowed is 4-7, the effected nodemask is
5-7 (the second, third, and fourth node of mems_allowed).
If the same task is attached to a cpuset, the mempolicy nodemask is rebound
each time the mems are changed. Some possible rebinds and results are:
mems result
1-3 1-3
1-7 2-4
1,5-6 1,5-6
1,5-7 5-7
Likewise, the zonelist built for MPOL_BIND acts on the set of zones assigned
to the resultant nodemask from the relative remap.
In the MPOL_PREFERRED case, the preferred node is remapped from the currently
effected nodemask to the relative nodemask.
This mempolicy mode flag was conceived of by Paul Jackson <pj@sgi.com>.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:30 +02:00
|
|
|
if ((mode_flags & MPOL_F_STATIC_NODES) &&
|
|
|
|
(mode_flags & MPOL_F_RELATIVE_NODES))
|
|
|
|
return -EINVAL;
|
2005-10-30 02:16:59 +01:00
|
|
|
err = get_nodes(&nodes, nmask, maxnode);
|
|
|
|
if (err)
|
|
|
|
return err;
|
2008-04-28 11:12:25 +02:00
|
|
|
return do_mbind(start, len, mode, mode_flags, &nodes, flags);
|
2005-10-30 02:16:59 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Set the process memory policy */
|
2009-01-14 14:14:30 +01:00
|
|
|
SYSCALL_DEFINE3(set_mempolicy, int, mode, unsigned long __user *, nmask,
|
|
|
|
unsigned long, maxnode)
|
2005-10-30 02:16:59 +01:00
|
|
|
{
|
|
|
|
int err;
|
|
|
|
nodemask_t nodes;
|
2008-04-28 11:12:25 +02:00
|
|
|
unsigned short flags;
|
2005-10-30 02:16:59 +01:00
|
|
|
|
2008-04-28 11:12:25 +02:00
|
|
|
flags = mode & MPOL_MODE_FLAGS;
|
|
|
|
mode &= ~MPOL_MODE_FLAGS;
|
|
|
|
if ((unsigned int)mode >= MPOL_MAX)
|
2005-10-30 02:16:59 +01:00
|
|
|
return -EINVAL;
|
mempolicy: add MPOL_F_RELATIVE_NODES flag
Adds another optional mode flag, MPOL_F_RELATIVE_NODES, that specifies
nodemasks passed via set_mempolicy() or mbind() should be considered relative
to the current task's mems_allowed.
When the mempolicy is created, the passed nodemask is folded and mapped onto
the current task's mems_allowed. For example, consider a task using
set_mempolicy() to pass MPOL_INTERLEAVE | MPOL_F_RELATIVE_NODES with a
nodemask of 1-3. If current's mems_allowed is 4-7, the effected nodemask is
5-7 (the second, third, and fourth node of mems_allowed).
If the same task is attached to a cpuset, the mempolicy nodemask is rebound
each time the mems are changed. Some possible rebinds and results are:
mems result
1-3 1-3
1-7 2-4
1,5-6 1,5-6
1,5-7 5-7
Likewise, the zonelist built for MPOL_BIND acts on the set of zones assigned
to the resultant nodemask from the relative remap.
In the MPOL_PREFERRED case, the preferred node is remapped from the currently
effected nodemask to the relative nodemask.
This mempolicy mode flag was conceived of by Paul Jackson <pj@sgi.com>.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:30 +02:00
|
|
|
if ((flags & MPOL_F_STATIC_NODES) && (flags & MPOL_F_RELATIVE_NODES))
|
|
|
|
return -EINVAL;
|
2005-10-30 02:16:59 +01:00
|
|
|
err = get_nodes(&nodes, nmask, maxnode);
|
|
|
|
if (err)
|
|
|
|
return err;
|
2008-04-28 11:12:25 +02:00
|
|
|
return do_set_mempolicy(mode, flags, &nodes);
|
2005-10-30 02:16:59 +01:00
|
|
|
}
|
|
|
|
|
2009-01-14 14:14:30 +01:00
|
|
|
SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
|
|
|
|
const unsigned long __user *, old_nodes,
|
|
|
|
const unsigned long __user *, new_nodes)
|
2006-01-08 10:00:51 +01:00
|
|
|
{
|
2008-11-14 00:39:19 +01:00
|
|
|
const struct cred *cred = current_cred(), *tcred;
|
2006-01-08 10:00:51 +01:00
|
|
|
struct mm_struct *mm;
|
|
|
|
struct task_struct *task;
|
|
|
|
nodemask_t old;
|
|
|
|
nodemask_t new;
|
|
|
|
nodemask_t task_nodes;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
err = get_nodes(&old, old_nodes, maxnode);
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
|
|
|
|
err = get_nodes(&new, new_nodes, maxnode);
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
|
|
|
|
/* Find the mm_struct */
|
|
|
|
read_lock(&tasklist_lock);
|
2007-10-19 08:40:16 +02:00
|
|
|
task = pid ? find_task_by_vpid(pid) : current;
|
2006-01-08 10:00:51 +01:00
|
|
|
if (!task) {
|
|
|
|
read_unlock(&tasklist_lock);
|
|
|
|
return -ESRCH;
|
|
|
|
}
|
|
|
|
mm = get_task_mm(task);
|
|
|
|
read_unlock(&tasklist_lock);
|
|
|
|
|
|
|
|
if (!mm)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check if this process has the right to modify the specified
|
|
|
|
* process. The right exists if the process has administrative
|
2006-03-28 11:56:53 +02:00
|
|
|
* capabilities, superuser privileges or the same
|
2006-01-08 10:00:51 +01:00
|
|
|
* userid as the target process.
|
|
|
|
*/
|
2008-11-14 00:39:19 +01:00
|
|
|
rcu_read_lock();
|
|
|
|
tcred = __task_cred(task);
|
2008-11-14 00:39:16 +01:00
|
|
|
if (cred->euid != tcred->suid && cred->euid != tcred->uid &&
|
|
|
|
cred->uid != tcred->suid && cred->uid != tcred->uid &&
|
2006-03-15 04:50:21 +01:00
|
|
|
!capable(CAP_SYS_NICE)) {
|
2008-11-14 00:39:19 +01:00
|
|
|
rcu_read_unlock();
|
2006-01-08 10:00:51 +01:00
|
|
|
err = -EPERM;
|
|
|
|
goto out;
|
|
|
|
}
|
2008-11-14 00:39:19 +01:00
|
|
|
rcu_read_unlock();
|
2006-01-08 10:00:51 +01:00
|
|
|
|
|
|
|
task_nodes = cpuset_mems_allowed(task);
|
|
|
|
/* Is the user allowed to access the target nodes? */
|
2006-03-15 04:50:21 +01:00
|
|
|
if (!nodes_subset(new, task_nodes) && !capable(CAP_SYS_NICE)) {
|
2006-01-08 10:00:51 +01:00
|
|
|
err = -EPERM;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2007-10-16 10:25:39 +02:00
|
|
|
if (!nodes_subset(new, node_states[N_HIGH_MEMORY])) {
|
2007-08-31 09:12:08 +02:00
|
|
|
err = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2006-06-23 11:04:02 +02:00
|
|
|
err = security_task_movememory(task);
|
|
|
|
if (err)
|
|
|
|
goto out;
|
|
|
|
|
2006-03-01 01:58:57 +01:00
|
|
|
err = do_migrate_pages(mm, &old, &new,
|
2006-03-15 04:50:21 +01:00
|
|
|
capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
|
2006-01-08 10:00:51 +01:00
|
|
|
out:
|
|
|
|
mmput(mm);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2005-10-30 02:16:59 +01:00
|
|
|
/* Retrieve NUMA policy */
|
2009-01-14 14:14:30 +01:00
|
|
|
SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
|
|
|
|
unsigned long __user *, nmask, unsigned long, maxnode,
|
|
|
|
unsigned long, addr, unsigned long, flags)
|
2005-10-30 02:16:59 +01:00
|
|
|
{
|
2007-10-16 10:26:26 +02:00
|
|
|
int err;
|
|
|
|
int uninitialized_var(pval);
|
2005-10-30 02:16:59 +01:00
|
|
|
nodemask_t nodes;
|
|
|
|
|
|
|
|
if (nmask != NULL && maxnode < MAX_NUMNODES)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
err = do_get_mempolicy(&pval, &nodes, addr, flags);
|
|
|
|
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
|
|
|
|
if (policy && put_user(pval, policy))
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
if (nmask)
|
|
|
|
err = copy_nodes_to_user(nmask, maxnode, &nodes);
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
#ifdef CONFIG_COMPAT
|
|
|
|
|
|
|
|
asmlinkage long compat_sys_get_mempolicy(int __user *policy,
|
|
|
|
compat_ulong_t __user *nmask,
|
|
|
|
compat_ulong_t maxnode,
|
|
|
|
compat_ulong_t addr, compat_ulong_t flags)
|
|
|
|
{
|
|
|
|
long err;
|
|
|
|
unsigned long __user *nm = NULL;
|
|
|
|
unsigned long nr_bits, alloc_size;
|
|
|
|
DECLARE_BITMAP(bm, MAX_NUMNODES);
|
|
|
|
|
|
|
|
nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
|
|
|
|
alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
|
|
|
|
|
|
|
|
if (nmask)
|
|
|
|
nm = compat_alloc_user_space(alloc_size);
|
|
|
|
|
|
|
|
err = sys_get_mempolicy(policy, nm, nr_bits+1, addr, flags);
|
|
|
|
|
|
|
|
if (!err && nmask) {
|
|
|
|
err = copy_from_user(bm, nm, alloc_size);
|
|
|
|
/* ensure entire bitmap is zeroed */
|
|
|
|
err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8);
|
|
|
|
err |= compat_put_bitmap(nmask, bm, nr_bits);
|
|
|
|
}
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
|
|
|
|
compat_ulong_t maxnode)
|
|
|
|
{
|
|
|
|
long err = 0;
|
|
|
|
unsigned long __user *nm = NULL;
|
|
|
|
unsigned long nr_bits, alloc_size;
|
|
|
|
DECLARE_BITMAP(bm, MAX_NUMNODES);
|
|
|
|
|
|
|
|
nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
|
|
|
|
alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
|
|
|
|
|
|
|
|
if (nmask) {
|
|
|
|
err = compat_get_bitmap(bm, nmask, nr_bits);
|
|
|
|
nm = compat_alloc_user_space(alloc_size);
|
|
|
|
err |= copy_to_user(nm, bm, alloc_size);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (err)
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
return sys_set_mempolicy(mode, nm, nr_bits+1);
|
|
|
|
}
|
|
|
|
|
|
|
|
asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
|
|
|
|
compat_ulong_t mode, compat_ulong_t __user *nmask,
|
|
|
|
compat_ulong_t maxnode, compat_ulong_t flags)
|
|
|
|
{
|
|
|
|
long err = 0;
|
|
|
|
unsigned long __user *nm = NULL;
|
|
|
|
unsigned long nr_bits, alloc_size;
|
2005-10-30 02:15:48 +01:00
|
|
|
nodemask_t bm;
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
|
|
|
|
alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
|
|
|
|
|
|
|
|
if (nmask) {
|
2005-10-30 02:15:48 +01:00
|
|
|
err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits);
|
2005-04-17 00:20:36 +02:00
|
|
|
nm = compat_alloc_user_space(alloc_size);
|
2005-10-30 02:15:48 +01:00
|
|
|
err |= copy_to_user(nm, nodes_addr(bm), alloc_size);
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
if (err)
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif
|
|
|
|
|
Fix NUMA Memory Policy Reference Counting
This patch proposes fixes to the reference counting of memory policy in the
page allocation paths and in show_numa_map(). Extracted from my "Memory
Policy Cleanups and Enhancements" series as stand-alone.
Shared policy lookup [shmem] has always added a reference to the policy,
but this was never unrefed after page allocation or after formatting the
numa map data.
Default system policy should not require additional ref counting, nor
should the current task's task policy. However, show_numa_map() calls
get_vma_policy() to examine what may be [likely is] another task's policy.
The latter case needs protection against freeing of the policy.
This patch adds a reference count to a mempolicy returned by
get_vma_policy() when the policy is a vma policy or another task's
mempolicy. Again, shared policy is already reference counted on lookup. A
matching "unref" [__mpol_free()] is performed in alloc_page_vma() for
shared and vma policies, and in show_numa_map() for shared and another
task's mempolicy. We can call __mpol_free() directly, saving an admittedly
inexpensive inline NULL test, because we know we have a non-NULL policy.
Handling policy ref counts for hugepages is a bit trickier.
huge_zonelist() returns a zone list that might come from a shared or vma
'BIND policy. In this case, we should hold the reference until after the
huge page allocation in dequeue_hugepage(). The patch modifies
huge_zonelist() to return a pointer to the mempolicy if it needs to be
unref'd after allocation.
Kernel Build [16cpu, 32GB, ia64] - average of 10 runs:
w/o patch w/ refcount patch
Avg Std Devn Avg Std Devn
Real: 100.59 0.38 100.63 0.43
User: 1209.60 0.37 1209.91 0.31
System: 81.52 0.42 81.64 0.34
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 07:46:47 +02:00
|
|
|
/*
|
|
|
|
* get_vma_policy(@task, @vma, @addr)
|
|
|
|
* @task - task for fallback if vma policy == default
|
|
|
|
* @vma - virtual memory area whose policy is sought
|
|
|
|
* @addr - address in @vma for shared policy lookup
|
|
|
|
*
|
|
|
|
* Returns effective policy for a VMA at specified address.
|
|
|
|
* Falls back to @task or system default policy, as necessary.
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
* Current or other task's task mempolicy and non-shared vma policies
|
|
|
|
* are protected by the task's mmap_sem, which must be held for read by
|
|
|
|
* the caller.
|
|
|
|
* Shared policies [those marked as MPOL_F_SHARED] require an extra reference
|
|
|
|
* count--added by the get_policy() vm_op, as appropriate--to protect against
|
|
|
|
* freeing by another task. It is the caller's responsibility to free the
|
|
|
|
* extra reference for shared policies.
|
Fix NUMA Memory Policy Reference Counting
This patch proposes fixes to the reference counting of memory policy in the
page allocation paths and in show_numa_map(). Extracted from my "Memory
Policy Cleanups and Enhancements" series as stand-alone.
Shared policy lookup [shmem] has always added a reference to the policy,
but this was never unrefed after page allocation or after formatting the
numa map data.
Default system policy should not require additional ref counting, nor
should the current task's task policy. However, show_numa_map() calls
get_vma_policy() to examine what may be [likely is] another task's policy.
The latter case needs protection against freeing of the policy.
This patch adds a reference count to a mempolicy returned by
get_vma_policy() when the policy is a vma policy or another task's
mempolicy. Again, shared policy is already reference counted on lookup. A
matching "unref" [__mpol_free()] is performed in alloc_page_vma() for
shared and vma policies, and in show_numa_map() for shared and another
task's mempolicy. We can call __mpol_free() directly, saving an admittedly
inexpensive inline NULL test, because we know we have a non-NULL policy.
Handling policy ref counts for hugepages is a bit trickier.
huge_zonelist() returns a zone list that might come from a shared or vma
'BIND policy. In this case, we should hold the reference until after the
huge page allocation in dequeue_hugepage(). The patch modifies
huge_zonelist() to return a pointer to the mempolicy if it needs to be
unref'd after allocation.
Kernel Build [16cpu, 32GB, ia64] - average of 10 runs:
w/o patch w/ refcount patch
Avg Std Devn Avg Std Devn
Real: 100.59 0.38 100.63 0.43
User: 1209.60 0.37 1209.91 0.31
System: 81.52 0.42 81.64 0.34
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 07:46:47 +02:00
|
|
|
*/
|
2008-04-28 11:13:11 +02:00
|
|
|
static struct mempolicy *get_vma_policy(struct task_struct *task,
|
2006-01-08 10:01:03 +01:00
|
|
|
struct vm_area_struct *vma, unsigned long addr)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
2005-09-04 00:54:45 +02:00
|
|
|
struct mempolicy *pol = task->mempolicy;
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
if (vma) {
|
Fix NUMA Memory Policy Reference Counting
This patch proposes fixes to the reference counting of memory policy in the
page allocation paths and in show_numa_map(). Extracted from my "Memory
Policy Cleanups and Enhancements" series as stand-alone.
Shared policy lookup [shmem] has always added a reference to the policy,
but this was never unrefed after page allocation or after formatting the
numa map data.
Default system policy should not require additional ref counting, nor
should the current task's task policy. However, show_numa_map() calls
get_vma_policy() to examine what may be [likely is] another task's policy.
The latter case needs protection against freeing of the policy.
This patch adds a reference count to a mempolicy returned by
get_vma_policy() when the policy is a vma policy or another task's
mempolicy. Again, shared policy is already reference counted on lookup. A
matching "unref" [__mpol_free()] is performed in alloc_page_vma() for
shared and vma policies, and in show_numa_map() for shared and another
task's mempolicy. We can call __mpol_free() directly, saving an admittedly
inexpensive inline NULL test, because we know we have a non-NULL policy.
Handling policy ref counts for hugepages is a bit trickier.
huge_zonelist() returns a zone list that might come from a shared or vma
'BIND policy. In this case, we should hold the reference until after the
huge page allocation in dequeue_hugepage(). The patch modifies
huge_zonelist() to return a pointer to the mempolicy if it needs to be
unref'd after allocation.
Kernel Build [16cpu, 32GB, ia64] - average of 10 runs:
w/o patch w/ refcount patch
Avg Std Devn Avg Std Devn
Real: 100.59 0.38 100.63 0.43
User: 1209.60 0.37 1209.91 0.31
System: 81.52 0.42 81.64 0.34
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 07:46:47 +02:00
|
|
|
if (vma->vm_ops && vma->vm_ops->get_policy) {
|
2008-04-28 11:13:11 +02:00
|
|
|
struct mempolicy *vpol = vma->vm_ops->get_policy(vma,
|
|
|
|
addr);
|
|
|
|
if (vpol)
|
|
|
|
pol = vpol;
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
} else if (vma->vm_policy)
|
2005-04-17 00:20:36 +02:00
|
|
|
pol = vma->vm_policy;
|
|
|
|
}
|
|
|
|
if (!pol)
|
|
|
|
pol = &default_policy;
|
|
|
|
return pol;
|
|
|
|
}
|
|
|
|
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
/*
|
|
|
|
* Return a nodemask representing a mempolicy for filtering nodes for
|
|
|
|
* page allocation
|
|
|
|
*/
|
|
|
|
static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
|
2008-04-28 11:12:18 +02:00
|
|
|
{
|
|
|
|
/* Lower zones don't get a nodemask applied for MPOL_BIND */
|
2008-04-28 11:13:12 +02:00
|
|
|
if (unlikely(policy->mode == MPOL_BIND) &&
|
2008-04-28 11:12:18 +02:00
|
|
|
gfp_zone(gfp) >= policy_zone &&
|
|
|
|
cpuset_nodemask_valid_mems_allowed(&policy->v.nodes))
|
|
|
|
return &policy->v.nodes;
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
/* Return a zonelist indicated by gfp for node representing a mempolicy */
|
|
|
|
static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
2008-04-28 11:13:21 +02:00
|
|
|
int nd = numa_node_id();
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2008-04-28 11:13:12 +02:00
|
|
|
switch (policy->mode) {
|
2005-04-17 00:20:36 +02:00
|
|
|
case MPOL_PREFERRED:
|
2008-04-28 11:13:21 +02:00
|
|
|
if (!(policy->flags & MPOL_F_LOCAL))
|
|
|
|
nd = policy->v.preferred_node;
|
2005-04-17 00:20:36 +02:00
|
|
|
break;
|
|
|
|
case MPOL_BIND:
|
2008-04-28 11:12:18 +02:00
|
|
|
/*
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
* Normally, MPOL_BIND allocations are node-local within the
|
|
|
|
* allowed nodemask. However, if __GFP_THISNODE is set and the
|
|
|
|
* current node is part of the mask, we use the zonelist for
|
|
|
|
* the first node in the mask instead.
|
2008-04-28 11:12:18 +02:00
|
|
|
*/
|
|
|
|
if (unlikely(gfp & __GFP_THISNODE) &&
|
|
|
|
unlikely(!node_isset(nd, policy->v.nodes)))
|
|
|
|
nd = first_node(policy->v.nodes);
|
|
|
|
break;
|
2005-04-17 00:20:36 +02:00
|
|
|
case MPOL_INTERLEAVE: /* should not happen */
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
BUG();
|
|
|
|
}
|
2008-04-28 11:12:14 +02:00
|
|
|
return node_zonelist(nd, gfp);
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Do dynamic interleaving for a process */
|
|
|
|
static unsigned interleave_nodes(struct mempolicy *policy)
|
|
|
|
{
|
|
|
|
unsigned nid, next;
|
|
|
|
struct task_struct *me = current;
|
|
|
|
|
|
|
|
nid = me->il_next;
|
2005-10-30 02:15:48 +01:00
|
|
|
next = next_node(nid, policy->v.nodes);
|
2005-04-17 00:20:36 +02:00
|
|
|
if (next >= MAX_NUMNODES)
|
2005-10-30 02:15:48 +01:00
|
|
|
next = first_node(policy->v.nodes);
|
mempolicy: add MPOL_F_STATIC_NODES flag
Add an optional mempolicy mode flag, MPOL_F_STATIC_NODES, that suppresses the
node remap when the policy is rebound.
Adds another member to struct mempolicy, nodemask_t user_nodemask, as part of
a union with cpuset_mems_allowed:
struct mempolicy {
...
union {
nodemask_t cpuset_mems_allowed;
nodemask_t user_nodemask;
} w;
}
that stores the the nodemask that the user passed when he or she created the
mempolicy via set_mempolicy() or mbind(). When using MPOL_F_STATIC_NODES,
which is passed with any mempolicy mode, the user's passed nodemask
intersected with the VMA or task's allowed nodes is always used when
determining the preferred node, setting the MPOL_BIND zonelist, or creating
the interleave nodemask. This happens whenever the policy is rebound,
including when a task's cpuset assignment changes or the cpuset's mems are
changed.
This creates an interesting side-effect in that it allows the mempolicy
"intent" to lie dormant and uneffected until it has access to the node(s) that
it desires. For example, if you currently ask for an interleaved policy over
a set of nodes that you do not have access to, the mempolicy is not created
and the task continues to use the previous policy. With this change, however,
it is possible to create the same mempolicy; it is only effected when access
to nodes in the nodemask is acquired.
It is also possible to mount tmpfs with the static nodemask behavior when
specifying a node or nodemask. To do this, simply add "=static" immediately
following the mempolicy mode at mount time:
mount -o remount mpol=interleave=static:1-3
Also removes mpol_check_policy() and folds its logic into mpol_new() since it
is now obsoleted. The unused vma_mpol_equal() is also removed.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:27 +02:00
|
|
|
if (next < MAX_NUMNODES)
|
|
|
|
me->il_next = next;
|
2005-04-17 00:20:36 +02:00
|
|
|
return nid;
|
|
|
|
}
|
|
|
|
|
2006-01-19 02:42:36 +01:00
|
|
|
/*
|
|
|
|
* Depending on the memory policy provide a node from which to allocate the
|
|
|
|
* next slab entry.
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
* @policy must be protected by freeing by the caller. If @policy is
|
|
|
|
* the current task's mempolicy, this protection is implicit, as only the
|
|
|
|
* task can change it's policy. The system default policy requires no
|
|
|
|
* such protection.
|
2006-01-19 02:42:36 +01:00
|
|
|
*/
|
|
|
|
unsigned slab_node(struct mempolicy *policy)
|
|
|
|
{
|
2008-04-28 11:13:21 +02:00
|
|
|
if (!policy || policy->flags & MPOL_F_LOCAL)
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
return numa_node_id();
|
|
|
|
|
|
|
|
switch (policy->mode) {
|
|
|
|
case MPOL_PREFERRED:
|
2008-04-28 11:13:21 +02:00
|
|
|
/*
|
|
|
|
* handled MPOL_F_LOCAL above
|
|
|
|
*/
|
|
|
|
return policy->v.preferred_node;
|
2006-09-27 10:50:08 +02:00
|
|
|
|
2006-01-19 02:42:36 +01:00
|
|
|
case MPOL_INTERLEAVE:
|
|
|
|
return interleave_nodes(policy);
|
|
|
|
|
2008-04-28 11:12:17 +02:00
|
|
|
case MPOL_BIND: {
|
2006-01-19 02:42:36 +01:00
|
|
|
/*
|
|
|
|
* Follow bind policy behavior and start allocation at the
|
|
|
|
* first node.
|
|
|
|
*/
|
2008-04-28 11:12:18 +02:00
|
|
|
struct zonelist *zonelist;
|
|
|
|
struct zone *zone;
|
|
|
|
enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL);
|
|
|
|
zonelist = &NODE_DATA(numa_node_id())->node_zonelists[0];
|
|
|
|
(void)first_zones_zonelist(zonelist, highest_zoneidx,
|
|
|
|
&policy->v.nodes,
|
|
|
|
&zone);
|
|
|
|
return zone->node;
|
2008-04-28 11:12:17 +02:00
|
|
|
}
|
2006-01-19 02:42:36 +01:00
|
|
|
|
|
|
|
default:
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
BUG();
|
2006-01-19 02:42:36 +01:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
/* Do static interleaving for a VMA with known offset. */
|
|
|
|
static unsigned offset_il_node(struct mempolicy *pol,
|
|
|
|
struct vm_area_struct *vma, unsigned long off)
|
|
|
|
{
|
2005-10-30 02:15:48 +01:00
|
|
|
unsigned nnodes = nodes_weight(pol->v.nodes);
|
mempolicy: add MPOL_F_STATIC_NODES flag
Add an optional mempolicy mode flag, MPOL_F_STATIC_NODES, that suppresses the
node remap when the policy is rebound.
Adds another member to struct mempolicy, nodemask_t user_nodemask, as part of
a union with cpuset_mems_allowed:
struct mempolicy {
...
union {
nodemask_t cpuset_mems_allowed;
nodemask_t user_nodemask;
} w;
}
that stores the the nodemask that the user passed when he or she created the
mempolicy via set_mempolicy() or mbind(). When using MPOL_F_STATIC_NODES,
which is passed with any mempolicy mode, the user's passed nodemask
intersected with the VMA or task's allowed nodes is always used when
determining the preferred node, setting the MPOL_BIND zonelist, or creating
the interleave nodemask. This happens whenever the policy is rebound,
including when a task's cpuset assignment changes or the cpuset's mems are
changed.
This creates an interesting side-effect in that it allows the mempolicy
"intent" to lie dormant and uneffected until it has access to the node(s) that
it desires. For example, if you currently ask for an interleaved policy over
a set of nodes that you do not have access to, the mempolicy is not created
and the task continues to use the previous policy. With this change, however,
it is possible to create the same mempolicy; it is only effected when access
to nodes in the nodemask is acquired.
It is also possible to mount tmpfs with the static nodemask behavior when
specifying a node or nodemask. To do this, simply add "=static" immediately
following the mempolicy mode at mount time:
mount -o remount mpol=interleave=static:1-3
Also removes mpol_check_policy() and folds its logic into mpol_new() since it
is now obsoleted. The unused vma_mpol_equal() is also removed.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:27 +02:00
|
|
|
unsigned target;
|
2005-04-17 00:20:36 +02:00
|
|
|
int c;
|
|
|
|
int nid = -1;
|
|
|
|
|
mempolicy: add MPOL_F_STATIC_NODES flag
Add an optional mempolicy mode flag, MPOL_F_STATIC_NODES, that suppresses the
node remap when the policy is rebound.
Adds another member to struct mempolicy, nodemask_t user_nodemask, as part of
a union with cpuset_mems_allowed:
struct mempolicy {
...
union {
nodemask_t cpuset_mems_allowed;
nodemask_t user_nodemask;
} w;
}
that stores the the nodemask that the user passed when he or she created the
mempolicy via set_mempolicy() or mbind(). When using MPOL_F_STATIC_NODES,
which is passed with any mempolicy mode, the user's passed nodemask
intersected with the VMA or task's allowed nodes is always used when
determining the preferred node, setting the MPOL_BIND zonelist, or creating
the interleave nodemask. This happens whenever the policy is rebound,
including when a task's cpuset assignment changes or the cpuset's mems are
changed.
This creates an interesting side-effect in that it allows the mempolicy
"intent" to lie dormant and uneffected until it has access to the node(s) that
it desires. For example, if you currently ask for an interleaved policy over
a set of nodes that you do not have access to, the mempolicy is not created
and the task continues to use the previous policy. With this change, however,
it is possible to create the same mempolicy; it is only effected when access
to nodes in the nodemask is acquired.
It is also possible to mount tmpfs with the static nodemask behavior when
specifying a node or nodemask. To do this, simply add "=static" immediately
following the mempolicy mode at mount time:
mount -o remount mpol=interleave=static:1-3
Also removes mpol_check_policy() and folds its logic into mpol_new() since it
is now obsoleted. The unused vma_mpol_equal() is also removed.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:27 +02:00
|
|
|
if (!nnodes)
|
|
|
|
return numa_node_id();
|
|
|
|
target = (unsigned int)off % nnodes;
|
2005-04-17 00:20:36 +02:00
|
|
|
c = 0;
|
|
|
|
do {
|
2005-10-30 02:15:48 +01:00
|
|
|
nid = next_node(nid, pol->v.nodes);
|
2005-04-17 00:20:36 +02:00
|
|
|
c++;
|
|
|
|
} while (c <= target);
|
|
|
|
return nid;
|
|
|
|
}
|
|
|
|
|
2006-01-06 09:10:46 +01:00
|
|
|
/* Determine a node number for interleave */
|
|
|
|
static inline unsigned interleave_nid(struct mempolicy *pol,
|
|
|
|
struct vm_area_struct *vma, unsigned long addr, int shift)
|
|
|
|
{
|
|
|
|
if (vma) {
|
|
|
|
unsigned long off;
|
|
|
|
|
2006-09-01 06:27:53 +02:00
|
|
|
/*
|
|
|
|
* for small pages, there is no difference between
|
|
|
|
* shift and PAGE_SHIFT, so the bit-shift is safe.
|
|
|
|
* for huge pages, since vm_pgoff is in units of small
|
|
|
|
* pages, we need to shift off the always 0 bits to get
|
|
|
|
* a useful offset.
|
|
|
|
*/
|
|
|
|
BUG_ON(shift < PAGE_SHIFT);
|
|
|
|
off = vma->vm_pgoff >> (shift - PAGE_SHIFT);
|
2006-01-06 09:10:46 +01:00
|
|
|
off += (addr - vma->vm_start) >> shift;
|
|
|
|
return offset_il_node(pol, vma, off);
|
|
|
|
} else
|
|
|
|
return interleave_nodes(pol);
|
|
|
|
}
|
|
|
|
|
2006-02-03 21:51:14 +01:00
|
|
|
#ifdef CONFIG_HUGETLBFS
|
Fix NUMA Memory Policy Reference Counting
This patch proposes fixes to the reference counting of memory policy in the
page allocation paths and in show_numa_map(). Extracted from my "Memory
Policy Cleanups and Enhancements" series as stand-alone.
Shared policy lookup [shmem] has always added a reference to the policy,
but this was never unrefed after page allocation or after formatting the
numa map data.
Default system policy should not require additional ref counting, nor
should the current task's task policy. However, show_numa_map() calls
get_vma_policy() to examine what may be [likely is] another task's policy.
The latter case needs protection against freeing of the policy.
This patch adds a reference count to a mempolicy returned by
get_vma_policy() when the policy is a vma policy or another task's
mempolicy. Again, shared policy is already reference counted on lookup. A
matching "unref" [__mpol_free()] is performed in alloc_page_vma() for
shared and vma policies, and in show_numa_map() for shared and another
task's mempolicy. We can call __mpol_free() directly, saving an admittedly
inexpensive inline NULL test, because we know we have a non-NULL policy.
Handling policy ref counts for hugepages is a bit trickier.
huge_zonelist() returns a zone list that might come from a shared or vma
'BIND policy. In this case, we should hold the reference until after the
huge page allocation in dequeue_hugepage(). The patch modifies
huge_zonelist() to return a pointer to the mempolicy if it needs to be
unref'd after allocation.
Kernel Build [16cpu, 32GB, ia64] - average of 10 runs:
w/o patch w/ refcount patch
Avg Std Devn Avg Std Devn
Real: 100.59 0.38 100.63 0.43
User: 1209.60 0.37 1209.91 0.31
System: 81.52 0.42 81.64 0.34
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 07:46:47 +02:00
|
|
|
/*
|
|
|
|
* huge_zonelist(@vma, @addr, @gfp_flags, @mpol)
|
|
|
|
* @vma = virtual memory area whose policy is sought
|
|
|
|
* @addr = address in @vma for shared policy lookup and interleave policy
|
|
|
|
* @gfp_flags = for requested zone
|
2008-04-28 11:12:18 +02:00
|
|
|
* @mpol = pointer to mempolicy pointer for reference counted mempolicy
|
|
|
|
* @nodemask = pointer to nodemask pointer for MPOL_BIND nodemask
|
Fix NUMA Memory Policy Reference Counting
This patch proposes fixes to the reference counting of memory policy in the
page allocation paths and in show_numa_map(). Extracted from my "Memory
Policy Cleanups and Enhancements" series as stand-alone.
Shared policy lookup [shmem] has always added a reference to the policy,
but this was never unrefed after page allocation or after formatting the
numa map data.
Default system policy should not require additional ref counting, nor
should the current task's task policy. However, show_numa_map() calls
get_vma_policy() to examine what may be [likely is] another task's policy.
The latter case needs protection against freeing of the policy.
This patch adds a reference count to a mempolicy returned by
get_vma_policy() when the policy is a vma policy or another task's
mempolicy. Again, shared policy is already reference counted on lookup. A
matching "unref" [__mpol_free()] is performed in alloc_page_vma() for
shared and vma policies, and in show_numa_map() for shared and another
task's mempolicy. We can call __mpol_free() directly, saving an admittedly
inexpensive inline NULL test, because we know we have a non-NULL policy.
Handling policy ref counts for hugepages is a bit trickier.
huge_zonelist() returns a zone list that might come from a shared or vma
'BIND policy. In this case, we should hold the reference until after the
huge page allocation in dequeue_hugepage(). The patch modifies
huge_zonelist() to return a pointer to the mempolicy if it needs to be
unref'd after allocation.
Kernel Build [16cpu, 32GB, ia64] - average of 10 runs:
w/o patch w/ refcount patch
Avg Std Devn Avg Std Devn
Real: 100.59 0.38 100.63 0.43
User: 1209.60 0.37 1209.91 0.31
System: 81.52 0.42 81.64 0.34
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 07:46:47 +02:00
|
|
|
*
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
* Returns a zonelist suitable for a huge page allocation and a pointer
|
|
|
|
* to the struct mempolicy for conditional unref after allocation.
|
|
|
|
* If the effective policy is 'BIND, returns a pointer to the mempolicy's
|
|
|
|
* @nodemask for filtering the zonelist.
|
Fix NUMA Memory Policy Reference Counting
This patch proposes fixes to the reference counting of memory policy in the
page allocation paths and in show_numa_map(). Extracted from my "Memory
Policy Cleanups and Enhancements" series as stand-alone.
Shared policy lookup [shmem] has always added a reference to the policy,
but this was never unrefed after page allocation or after formatting the
numa map data.
Default system policy should not require additional ref counting, nor
should the current task's task policy. However, show_numa_map() calls
get_vma_policy() to examine what may be [likely is] another task's policy.
The latter case needs protection against freeing of the policy.
This patch adds a reference count to a mempolicy returned by
get_vma_policy() when the policy is a vma policy or another task's
mempolicy. Again, shared policy is already reference counted on lookup. A
matching "unref" [__mpol_free()] is performed in alloc_page_vma() for
shared and vma policies, and in show_numa_map() for shared and another
task's mempolicy. We can call __mpol_free() directly, saving an admittedly
inexpensive inline NULL test, because we know we have a non-NULL policy.
Handling policy ref counts for hugepages is a bit trickier.
huge_zonelist() returns a zone list that might come from a shared or vma
'BIND policy. In this case, we should hold the reference until after the
huge page allocation in dequeue_hugepage(). The patch modifies
huge_zonelist() to return a pointer to the mempolicy if it needs to be
unref'd after allocation.
Kernel Build [16cpu, 32GB, ia64] - average of 10 runs:
w/o patch w/ refcount patch
Avg Std Devn Avg Std Devn
Real: 100.59 0.38 100.63 0.43
User: 1209.60 0.37 1209.91 0.31
System: 81.52 0.42 81.64 0.34
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 07:46:47 +02:00
|
|
|
*/
|
2007-07-17 13:03:13 +02:00
|
|
|
struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
|
2008-04-28 11:12:18 +02:00
|
|
|
gfp_t gfp_flags, struct mempolicy **mpol,
|
|
|
|
nodemask_t **nodemask)
|
2006-01-06 09:10:46 +01:00
|
|
|
{
|
Fix NUMA Memory Policy Reference Counting
This patch proposes fixes to the reference counting of memory policy in the
page allocation paths and in show_numa_map(). Extracted from my "Memory
Policy Cleanups and Enhancements" series as stand-alone.
Shared policy lookup [shmem] has always added a reference to the policy,
but this was never unrefed after page allocation or after formatting the
numa map data.
Default system policy should not require additional ref counting, nor
should the current task's task policy. However, show_numa_map() calls
get_vma_policy() to examine what may be [likely is] another task's policy.
The latter case needs protection against freeing of the policy.
This patch adds a reference count to a mempolicy returned by
get_vma_policy() when the policy is a vma policy or another task's
mempolicy. Again, shared policy is already reference counted on lookup. A
matching "unref" [__mpol_free()] is performed in alloc_page_vma() for
shared and vma policies, and in show_numa_map() for shared and another
task's mempolicy. We can call __mpol_free() directly, saving an admittedly
inexpensive inline NULL test, because we know we have a non-NULL policy.
Handling policy ref counts for hugepages is a bit trickier.
huge_zonelist() returns a zone list that might come from a shared or vma
'BIND policy. In this case, we should hold the reference until after the
huge page allocation in dequeue_hugepage(). The patch modifies
huge_zonelist() to return a pointer to the mempolicy if it needs to be
unref'd after allocation.
Kernel Build [16cpu, 32GB, ia64] - average of 10 runs:
w/o patch w/ refcount patch
Avg Std Devn Avg Std Devn
Real: 100.59 0.38 100.63 0.43
User: 1209.60 0.37 1209.91 0.31
System: 81.52 0.42 81.64 0.34
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 07:46:47 +02:00
|
|
|
struct zonelist *zl;
|
2006-01-06 09:10:46 +01:00
|
|
|
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
*mpol = get_vma_policy(current, vma, addr);
|
2008-04-28 11:12:18 +02:00
|
|
|
*nodemask = NULL; /* assume !MPOL_BIND */
|
2006-01-06 09:10:46 +01:00
|
|
|
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) {
|
|
|
|
zl = node_zonelist(interleave_nid(*mpol, vma, addr,
|
2008-07-24 06:27:41 +02:00
|
|
|
huge_page_shift(hstate_vma(vma))), gfp_flags);
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
} else {
|
|
|
|
zl = policy_zonelist(gfp_flags, *mpol);
|
|
|
|
if ((*mpol)->mode == MPOL_BIND)
|
|
|
|
*nodemask = &(*mpol)->v.nodes;
|
Fix NUMA Memory Policy Reference Counting
This patch proposes fixes to the reference counting of memory policy in the
page allocation paths and in show_numa_map(). Extracted from my "Memory
Policy Cleanups and Enhancements" series as stand-alone.
Shared policy lookup [shmem] has always added a reference to the policy,
but this was never unrefed after page allocation or after formatting the
numa map data.
Default system policy should not require additional ref counting, nor
should the current task's task policy. However, show_numa_map() calls
get_vma_policy() to examine what may be [likely is] another task's policy.
The latter case needs protection against freeing of the policy.
This patch adds a reference count to a mempolicy returned by
get_vma_policy() when the policy is a vma policy or another task's
mempolicy. Again, shared policy is already reference counted on lookup. A
matching "unref" [__mpol_free()] is performed in alloc_page_vma() for
shared and vma policies, and in show_numa_map() for shared and another
task's mempolicy. We can call __mpol_free() directly, saving an admittedly
inexpensive inline NULL test, because we know we have a non-NULL policy.
Handling policy ref counts for hugepages is a bit trickier.
huge_zonelist() returns a zone list that might come from a shared or vma
'BIND policy. In this case, we should hold the reference until after the
huge page allocation in dequeue_hugepage(). The patch modifies
huge_zonelist() to return a pointer to the mempolicy if it needs to be
unref'd after allocation.
Kernel Build [16cpu, 32GB, ia64] - average of 10 runs:
w/o patch w/ refcount patch
Avg Std Devn Avg Std Devn
Real: 100.59 0.38 100.63 0.43
User: 1209.60 0.37 1209.91 0.31
System: 81.52 0.42 81.64 0.34
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 07:46:47 +02:00
|
|
|
}
|
|
|
|
return zl;
|
2006-01-06 09:10:46 +01:00
|
|
|
}
|
hugetlb: derive huge pages nodes allowed from task mempolicy
This patch derives a "nodes_allowed" node mask from the numa mempolicy of
the task modifying the number of persistent huge pages to control the
allocation, freeing and adjusting of surplus huge pages when the pool page
count is modified via the new sysctl or sysfs attribute
"nr_hugepages_mempolicy". The nodes_allowed mask is derived as follows:
* For "default" [NULL] task mempolicy, a NULL nodemask_t pointer
is produced. This will cause the hugetlb subsystem to use
node_online_map as the "nodes_allowed". This preserves the
behavior before this patch.
* For "preferred" mempolicy, including explicit local allocation,
a nodemask with the single preferred node will be produced.
"local" policy will NOT track any internode migrations of the
task adjusting nr_hugepages.
* For "bind" and "interleave" policy, the mempolicy's nodemask
will be used.
* Other than to inform the construction of the nodes_allowed node
mask, the actual mempolicy mode is ignored. That is, all modes
behave like interleave over the resulting nodes_allowed mask
with no "fallback".
See the updated documentation [next patch] for more information
about the implications of this patch.
Examples:
Starting with:
Node 0 HugePages_Total: 0
Node 1 HugePages_Total: 0
Node 2 HugePages_Total: 0
Node 3 HugePages_Total: 0
Default behavior [with or without this patch] balances persistent
hugepage allocation across nodes [with sufficient contiguous memory]:
sysctl vm.nr_hugepages[_mempolicy]=32
yields:
Node 0 HugePages_Total: 8
Node 1 HugePages_Total: 8
Node 2 HugePages_Total: 8
Node 3 HugePages_Total: 8
Of course, we only have nr_hugepages_mempolicy with the patch,
but with default mempolicy, nr_hugepages_mempolicy behaves the
same as nr_hugepages.
Applying mempolicy--e.g., with numactl [using '-m' a.k.a.
'--membind' because it allows multiple nodes to be specified
and it's easy to type]--we can allocate huge pages on
individual nodes or sets of nodes. So, starting from the
condition above, with 8 huge pages per node, add 8 more to
node 2 using:
numactl -m 2 sysctl vm.nr_hugepages_mempolicy=40
This yields:
Node 0 HugePages_Total: 8
Node 1 HugePages_Total: 8
Node 2 HugePages_Total: 16
Node 3 HugePages_Total: 8
The incremental 8 huge pages were restricted to node 2 by the
specified mempolicy.
Similarly, we can use mempolicy to free persistent huge pages
from specified nodes:
numactl -m 0,1 sysctl vm.nr_hugepages_mempolicy=32
yields:
Node 0 HugePages_Total: 4
Node 1 HugePages_Total: 4
Node 2 HugePages_Total: 16
Node 3 HugePages_Total: 8
The 8 huge pages freed were balanced over nodes 0 and 1.
[rientjes@google.com: accomodate reworked NODEMASK_ALLOC]
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: Andi Kleen <andi@firstfloor.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Randy Dunlap <randy.dunlap@oracle.com>
Cc: Nishanth Aravamudan <nacc@us.ibm.com>
Cc: Adam Litke <agl@us.ibm.com>
Cc: Andy Whitcroft <apw@canonical.com>
Cc: Eric Whitney <eric.whitney@hp.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 02:58:21 +01:00
|
|
|
|
|
|
|
/*
|
|
|
|
* init_nodemask_of_mempolicy
|
|
|
|
*
|
|
|
|
* If the current task's mempolicy is "default" [NULL], return 'false'
|
|
|
|
* to indicate default policy. Otherwise, extract the policy nodemask
|
|
|
|
* for 'bind' or 'interleave' policy into the argument nodemask, or
|
|
|
|
* initialize the argument nodemask to contain the single node for
|
|
|
|
* 'preferred' or 'local' policy and return 'true' to indicate presence
|
|
|
|
* of non-default mempolicy.
|
|
|
|
*
|
|
|
|
* We don't bother with reference counting the mempolicy [mpol_get/put]
|
|
|
|
* because the current task is examining it's own mempolicy and a task's
|
|
|
|
* mempolicy is only ever changed by the task itself.
|
|
|
|
*
|
|
|
|
* N.B., it is the caller's responsibility to free a returned nodemask.
|
|
|
|
*/
|
|
|
|
bool init_nodemask_of_mempolicy(nodemask_t *mask)
|
|
|
|
{
|
|
|
|
struct mempolicy *mempolicy;
|
|
|
|
int nid;
|
|
|
|
|
|
|
|
if (!(mask && current->mempolicy))
|
|
|
|
return false;
|
|
|
|
|
|
|
|
mempolicy = current->mempolicy;
|
|
|
|
switch (mempolicy->mode) {
|
|
|
|
case MPOL_PREFERRED:
|
|
|
|
if (mempolicy->flags & MPOL_F_LOCAL)
|
|
|
|
nid = numa_node_id();
|
|
|
|
else
|
|
|
|
nid = mempolicy->v.preferred_node;
|
|
|
|
init_nodemask_of_node(mask, nid);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case MPOL_BIND:
|
|
|
|
/* Fall through */
|
|
|
|
case MPOL_INTERLEAVE:
|
|
|
|
*mask = mempolicy->v.nodes;
|
|
|
|
break;
|
|
|
|
|
|
|
|
default:
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
2006-02-03 21:51:14 +01:00
|
|
|
#endif
|
2006-01-06 09:10:46 +01:00
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
/* Allocate a page in interleaved policy.
|
|
|
|
Own path because it needs to do special accounting. */
|
2005-10-30 02:15:49 +01:00
|
|
|
static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
|
|
|
|
unsigned nid)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
struct zonelist *zl;
|
|
|
|
struct page *page;
|
|
|
|
|
2008-04-28 11:12:14 +02:00
|
|
|
zl = node_zonelist(nid, gfp);
|
2005-04-17 00:20:36 +02:00
|
|
|
page = __alloc_pages(gfp, order, zl);
|
2008-04-28 11:12:17 +02:00
|
|
|
if (page && page_zone(page) == zonelist_zone(&zl->_zonerefs[0]))
|
2006-06-30 10:55:44 +02:00
|
|
|
inc_zone_page_state(page, NUMA_INTERLEAVE_HIT);
|
2005-04-17 00:20:36 +02:00
|
|
|
return page;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* alloc_page_vma - Allocate a page for a VMA.
|
|
|
|
*
|
|
|
|
* @gfp:
|
|
|
|
* %GFP_USER user allocation.
|
|
|
|
* %GFP_KERNEL kernel allocations,
|
|
|
|
* %GFP_HIGHMEM highmem/user allocations,
|
|
|
|
* %GFP_FS allocation should not call back into a file system.
|
|
|
|
* %GFP_ATOMIC don't sleep.
|
|
|
|
*
|
|
|
|
* @vma: Pointer to VMA or NULL if not available.
|
|
|
|
* @addr: Virtual Address of the allocation. Must be inside the VMA.
|
|
|
|
*
|
|
|
|
* This function allocates a page from the kernel page pool and applies
|
|
|
|
* a NUMA policy associated with the VMA or the current process.
|
|
|
|
* When VMA is not NULL caller must hold down_read on the mmap_sem of the
|
|
|
|
* mm_struct of the VMA to prevent it from going away. Should be used for
|
|
|
|
* all allocations for pages that will be mapped into
|
|
|
|
* user space. Returns NULL when no page can be allocated.
|
|
|
|
*
|
|
|
|
* Should be called with the mm_sem of the vma hold.
|
|
|
|
*/
|
|
|
|
struct page *
|
2005-10-07 08:46:04 +02:00
|
|
|
alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
2005-09-04 00:54:45 +02:00
|
|
|
struct mempolicy *pol = get_vma_policy(current, vma, addr);
|
Fix NUMA Memory Policy Reference Counting
This patch proposes fixes to the reference counting of memory policy in the
page allocation paths and in show_numa_map(). Extracted from my "Memory
Policy Cleanups and Enhancements" series as stand-alone.
Shared policy lookup [shmem] has always added a reference to the policy,
but this was never unrefed after page allocation or after formatting the
numa map data.
Default system policy should not require additional ref counting, nor
should the current task's task policy. However, show_numa_map() calls
get_vma_policy() to examine what may be [likely is] another task's policy.
The latter case needs protection against freeing of the policy.
This patch adds a reference count to a mempolicy returned by
get_vma_policy() when the policy is a vma policy or another task's
mempolicy. Again, shared policy is already reference counted on lookup. A
matching "unref" [__mpol_free()] is performed in alloc_page_vma() for
shared and vma policies, and in show_numa_map() for shared and another
task's mempolicy. We can call __mpol_free() directly, saving an admittedly
inexpensive inline NULL test, because we know we have a non-NULL policy.
Handling policy ref counts for hugepages is a bit trickier.
huge_zonelist() returns a zone list that might come from a shared or vma
'BIND policy. In this case, we should hold the reference until after the
huge page allocation in dequeue_hugepage(). The patch modifies
huge_zonelist() to return a pointer to the mempolicy if it needs to be
unref'd after allocation.
Kernel Build [16cpu, 32GB, ia64] - average of 10 runs:
w/o patch w/ refcount patch
Avg Std Devn Avg Std Devn
Real: 100.59 0.38 100.63 0.43
User: 1209.60 0.37 1209.91 0.31
System: 81.52 0.42 81.64 0.34
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 07:46:47 +02:00
|
|
|
struct zonelist *zl;
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2008-04-28 11:13:12 +02:00
|
|
|
if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
|
2005-04-17 00:20:36 +02:00
|
|
|
unsigned nid;
|
2006-01-06 09:10:46 +01:00
|
|
|
|
|
|
|
nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
mpol_cond_put(pol);
|
2005-04-17 00:20:36 +02:00
|
|
|
return alloc_page_interleave(gfp, 0, nid);
|
|
|
|
}
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
zl = policy_zonelist(gfp, pol);
|
|
|
|
if (unlikely(mpol_needs_cond_ref(pol))) {
|
Fix NUMA Memory Policy Reference Counting
This patch proposes fixes to the reference counting of memory policy in the
page allocation paths and in show_numa_map(). Extracted from my "Memory
Policy Cleanups and Enhancements" series as stand-alone.
Shared policy lookup [shmem] has always added a reference to the policy,
but this was never unrefed after page allocation or after formatting the
numa map data.
Default system policy should not require additional ref counting, nor
should the current task's task policy. However, show_numa_map() calls
get_vma_policy() to examine what may be [likely is] another task's policy.
The latter case needs protection against freeing of the policy.
This patch adds a reference count to a mempolicy returned by
get_vma_policy() when the policy is a vma policy or another task's
mempolicy. Again, shared policy is already reference counted on lookup. A
matching "unref" [__mpol_free()] is performed in alloc_page_vma() for
shared and vma policies, and in show_numa_map() for shared and another
task's mempolicy. We can call __mpol_free() directly, saving an admittedly
inexpensive inline NULL test, because we know we have a non-NULL policy.
Handling policy ref counts for hugepages is a bit trickier.
huge_zonelist() returns a zone list that might come from a shared or vma
'BIND policy. In this case, we should hold the reference until after the
huge page allocation in dequeue_hugepage(). The patch modifies
huge_zonelist() to return a pointer to the mempolicy if it needs to be
unref'd after allocation.
Kernel Build [16cpu, 32GB, ia64] - average of 10 runs:
w/o patch w/ refcount patch
Avg Std Devn Avg Std Devn
Real: 100.59 0.38 100.63 0.43
User: 1209.60 0.37 1209.91 0.31
System: 81.52 0.42 81.64 0.34
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 07:46:47 +02:00
|
|
|
/*
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
* slow path: ref counted shared policy
|
Fix NUMA Memory Policy Reference Counting
This patch proposes fixes to the reference counting of memory policy in the
page allocation paths and in show_numa_map(). Extracted from my "Memory
Policy Cleanups and Enhancements" series as stand-alone.
Shared policy lookup [shmem] has always added a reference to the policy,
but this was never unrefed after page allocation or after formatting the
numa map data.
Default system policy should not require additional ref counting, nor
should the current task's task policy. However, show_numa_map() calls
get_vma_policy() to examine what may be [likely is] another task's policy.
The latter case needs protection against freeing of the policy.
This patch adds a reference count to a mempolicy returned by
get_vma_policy() when the policy is a vma policy or another task's
mempolicy. Again, shared policy is already reference counted on lookup. A
matching "unref" [__mpol_free()] is performed in alloc_page_vma() for
shared and vma policies, and in show_numa_map() for shared and another
task's mempolicy. We can call __mpol_free() directly, saving an admittedly
inexpensive inline NULL test, because we know we have a non-NULL policy.
Handling policy ref counts for hugepages is a bit trickier.
huge_zonelist() returns a zone list that might come from a shared or vma
'BIND policy. In this case, we should hold the reference until after the
huge page allocation in dequeue_hugepage(). The patch modifies
huge_zonelist() to return a pointer to the mempolicy if it needs to be
unref'd after allocation.
Kernel Build [16cpu, 32GB, ia64] - average of 10 runs:
w/o patch w/ refcount patch
Avg Std Devn Avg Std Devn
Real: 100.59 0.38 100.63 0.43
User: 1209.60 0.37 1209.91 0.31
System: 81.52 0.42 81.64 0.34
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 07:46:47 +02:00
|
|
|
*/
|
2008-04-28 11:12:18 +02:00
|
|
|
struct page *page = __alloc_pages_nodemask(gfp, 0,
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
zl, policy_nodemask(gfp, pol));
|
2008-04-28 11:13:08 +02:00
|
|
|
__mpol_put(pol);
|
Fix NUMA Memory Policy Reference Counting
This patch proposes fixes to the reference counting of memory policy in the
page allocation paths and in show_numa_map(). Extracted from my "Memory
Policy Cleanups and Enhancements" series as stand-alone.
Shared policy lookup [shmem] has always added a reference to the policy,
but this was never unrefed after page allocation or after formatting the
numa map data.
Default system policy should not require additional ref counting, nor
should the current task's task policy. However, show_numa_map() calls
get_vma_policy() to examine what may be [likely is] another task's policy.
The latter case needs protection against freeing of the policy.
This patch adds a reference count to a mempolicy returned by
get_vma_policy() when the policy is a vma policy or another task's
mempolicy. Again, shared policy is already reference counted on lookup. A
matching "unref" [__mpol_free()] is performed in alloc_page_vma() for
shared and vma policies, and in show_numa_map() for shared and another
task's mempolicy. We can call __mpol_free() directly, saving an admittedly
inexpensive inline NULL test, because we know we have a non-NULL policy.
Handling policy ref counts for hugepages is a bit trickier.
huge_zonelist() returns a zone list that might come from a shared or vma
'BIND policy. In this case, we should hold the reference until after the
huge page allocation in dequeue_hugepage(). The patch modifies
huge_zonelist() to return a pointer to the mempolicy if it needs to be
unref'd after allocation.
Kernel Build [16cpu, 32GB, ia64] - average of 10 runs:
w/o patch w/ refcount patch
Avg Std Devn Avg Std Devn
Real: 100.59 0.38 100.63 0.43
User: 1209.60 0.37 1209.91 0.31
System: 81.52 0.42 81.64 0.34
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 07:46:47 +02:00
|
|
|
return page;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* fast path: default or task policy
|
|
|
|
*/
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
return __alloc_pages_nodemask(gfp, 0, zl, policy_nodemask(gfp, pol));
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* alloc_pages_current - Allocate pages.
|
|
|
|
*
|
|
|
|
* @gfp:
|
|
|
|
* %GFP_USER user allocation,
|
|
|
|
* %GFP_KERNEL kernel allocation,
|
|
|
|
* %GFP_HIGHMEM highmem allocation,
|
|
|
|
* %GFP_FS don't call back into a file system.
|
|
|
|
* %GFP_ATOMIC don't sleep.
|
|
|
|
* @order: Power of two of allocation size in pages. 0 is a single page.
|
|
|
|
*
|
|
|
|
* Allocate a page from the kernel page pool. When not in
|
|
|
|
* interrupt context and apply the current process NUMA policy.
|
|
|
|
* Returns NULL when no page can be allocated.
|
|
|
|
*
|
2006-01-08 10:01:54 +01:00
|
|
|
* Don't call cpuset_update_task_memory_state() unless
|
2005-04-17 00:20:36 +02:00
|
|
|
* 1) it's ok to take cpuset_sem (can WAIT), and
|
|
|
|
* 2) allocating for current task (not interrupt).
|
|
|
|
*/
|
2005-10-07 08:46:04 +02:00
|
|
|
struct page *alloc_pages_current(gfp_t gfp, unsigned order)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
struct mempolicy *pol = current->mempolicy;
|
|
|
|
|
2006-09-26 08:31:40 +02:00
|
|
|
if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
|
2005-04-17 00:20:36 +02:00
|
|
|
pol = &default_policy;
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* No reference counting needed for current->mempolicy
|
|
|
|
* nor system default_policy
|
|
|
|
*/
|
2008-04-28 11:13:12 +02:00
|
|
|
if (pol->mode == MPOL_INTERLEAVE)
|
2005-04-17 00:20:36 +02:00
|
|
|
return alloc_page_interleave(gfp, order, interleave_nodes(pol));
|
2008-04-28 11:12:18 +02:00
|
|
|
return __alloc_pages_nodemask(gfp, order,
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
policy_zonelist(gfp, pol), policy_nodemask(gfp, pol));
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(alloc_pages_current);
|
|
|
|
|
[PATCH] cpuset: rebind vma mempolicies fix
Fix more of longstanding bug in cpuset/mempolicy interaction.
NUMA mempolicies (mm/mempolicy.c) are constrained by the current tasks cpuset
to just the Memory Nodes allowed by that cpuset. The kernel maintains
internal state for each mempolicy, tracking what nodes are used for the
MPOL_INTERLEAVE, MPOL_BIND or MPOL_PREFERRED policies.
When a tasks cpuset memory placement changes, whether because the cpuset
changed, or because the task was attached to a different cpuset, then the
tasks mempolicies have to be rebound to the new cpuset placement, so as to
preserve the cpuset-relative numbering of the nodes in that policy.
An earlier fix handled such mempolicy rebinding for mempolicies attached to a
task.
This fix rebinds mempolicies attached to vma's (address ranges in a tasks
address space.) Due to the need to hold the task->mm->mmap_sem semaphore while
updating vma's, the rebinding of vma mempolicies has to be done when the
cpuset memory placement is changed, at which time mmap_sem can be safely
acquired. The tasks mempolicy is rebound later, when the task next attempts
to allocate memory and notices that its task->cpuset_mems_generation is
out-of-date with its cpusets mems_generation.
Because walking the tasklist to find all tasks attached to a changing cpuset
requires holding tasklist_lock, a spinlock, one cannot update the vma's of the
affected tasks while doing the tasklist scan. In general, one cannot acquire
a semaphore (which can sleep) while already holding a spinlock (such as
tasklist_lock). So a list of mm references has to be built up during the
tasklist scan, then the tasklist lock dropped, then for each mm, its mmap_sem
acquired, and the vma's in that mm rebound.
Once the tasklist lock is dropped, affected tasks may fork new tasks, before
their mm's are rebound. A kernel global 'cpuset_being_rebound' is set to
point to the cpuset being rebound (there can only be one; cpuset modifications
are done under a global 'manage_sem' semaphore), and the mpol_copy code that
is used to copy a tasks mempolicies during fork catches such forking tasks,
and ensures their children are also rebound.
When a task is moved to a different cpuset, it is easier, as there is only one
task involved. It's mm->vma's are scanned, using the same
mpol_rebind_policy() as used above.
It may happen that both the mpol_copy hook and the update done via the
tasklist scan update the same mm twice. This is ok, as the mempolicies of
each vma in an mm keep track of what mems_allowed they are relative to, and
safely no-op a second request to rebind to the same nodes.
Signed-off-by: Paul Jackson <pj@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 10:01:59 +01:00
|
|
|
/*
|
2008-04-28 11:13:09 +02:00
|
|
|
* If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it
|
[PATCH] cpuset: rebind vma mempolicies fix
Fix more of longstanding bug in cpuset/mempolicy interaction.
NUMA mempolicies (mm/mempolicy.c) are constrained by the current tasks cpuset
to just the Memory Nodes allowed by that cpuset. The kernel maintains
internal state for each mempolicy, tracking what nodes are used for the
MPOL_INTERLEAVE, MPOL_BIND or MPOL_PREFERRED policies.
When a tasks cpuset memory placement changes, whether because the cpuset
changed, or because the task was attached to a different cpuset, then the
tasks mempolicies have to be rebound to the new cpuset placement, so as to
preserve the cpuset-relative numbering of the nodes in that policy.
An earlier fix handled such mempolicy rebinding for mempolicies attached to a
task.
This fix rebinds mempolicies attached to vma's (address ranges in a tasks
address space.) Due to the need to hold the task->mm->mmap_sem semaphore while
updating vma's, the rebinding of vma mempolicies has to be done when the
cpuset memory placement is changed, at which time mmap_sem can be safely
acquired. The tasks mempolicy is rebound later, when the task next attempts
to allocate memory and notices that its task->cpuset_mems_generation is
out-of-date with its cpusets mems_generation.
Because walking the tasklist to find all tasks attached to a changing cpuset
requires holding tasklist_lock, a spinlock, one cannot update the vma's of the
affected tasks while doing the tasklist scan. In general, one cannot acquire
a semaphore (which can sleep) while already holding a spinlock (such as
tasklist_lock). So a list of mm references has to be built up during the
tasklist scan, then the tasklist lock dropped, then for each mm, its mmap_sem
acquired, and the vma's in that mm rebound.
Once the tasklist lock is dropped, affected tasks may fork new tasks, before
their mm's are rebound. A kernel global 'cpuset_being_rebound' is set to
point to the cpuset being rebound (there can only be one; cpuset modifications
are done under a global 'manage_sem' semaphore), and the mpol_copy code that
is used to copy a tasks mempolicies during fork catches such forking tasks,
and ensures their children are also rebound.
When a task is moved to a different cpuset, it is easier, as there is only one
task involved. It's mm->vma's are scanned, using the same
mpol_rebind_policy() as used above.
It may happen that both the mpol_copy hook and the update done via the
tasklist scan update the same mm twice. This is ok, as the mempolicies of
each vma in an mm keep track of what mems_allowed they are relative to, and
safely no-op a second request to rebind to the same nodes.
Signed-off-by: Paul Jackson <pj@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 10:01:59 +01:00
|
|
|
* rebinds the mempolicy its copying by calling mpol_rebind_policy()
|
|
|
|
* with the mems_allowed returned by cpuset_mems_allowed(). This
|
|
|
|
* keeps mempolicies cpuset relative after its cpuset moves. See
|
|
|
|
* further kernel/cpuset.c update_nodemask().
|
|
|
|
*/
|
|
|
|
|
2008-04-28 11:13:09 +02:00
|
|
|
/* Slow path of a mempolicy duplicate */
|
|
|
|
struct mempolicy *__mpol_dup(struct mempolicy *old)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
|
|
|
|
|
|
|
|
if (!new)
|
|
|
|
return ERR_PTR(-ENOMEM);
|
[PATCH] cpuset: rebind vma mempolicies fix
Fix more of longstanding bug in cpuset/mempolicy interaction.
NUMA mempolicies (mm/mempolicy.c) are constrained by the current tasks cpuset
to just the Memory Nodes allowed by that cpuset. The kernel maintains
internal state for each mempolicy, tracking what nodes are used for the
MPOL_INTERLEAVE, MPOL_BIND or MPOL_PREFERRED policies.
When a tasks cpuset memory placement changes, whether because the cpuset
changed, or because the task was attached to a different cpuset, then the
tasks mempolicies have to be rebound to the new cpuset placement, so as to
preserve the cpuset-relative numbering of the nodes in that policy.
An earlier fix handled such mempolicy rebinding for mempolicies attached to a
task.
This fix rebinds mempolicies attached to vma's (address ranges in a tasks
address space.) Due to the need to hold the task->mm->mmap_sem semaphore while
updating vma's, the rebinding of vma mempolicies has to be done when the
cpuset memory placement is changed, at which time mmap_sem can be safely
acquired. The tasks mempolicy is rebound later, when the task next attempts
to allocate memory and notices that its task->cpuset_mems_generation is
out-of-date with its cpusets mems_generation.
Because walking the tasklist to find all tasks attached to a changing cpuset
requires holding tasklist_lock, a spinlock, one cannot update the vma's of the
affected tasks while doing the tasklist scan. In general, one cannot acquire
a semaphore (which can sleep) while already holding a spinlock (such as
tasklist_lock). So a list of mm references has to be built up during the
tasklist scan, then the tasklist lock dropped, then for each mm, its mmap_sem
acquired, and the vma's in that mm rebound.
Once the tasklist lock is dropped, affected tasks may fork new tasks, before
their mm's are rebound. A kernel global 'cpuset_being_rebound' is set to
point to the cpuset being rebound (there can only be one; cpuset modifications
are done under a global 'manage_sem' semaphore), and the mpol_copy code that
is used to copy a tasks mempolicies during fork catches such forking tasks,
and ensures their children are also rebound.
When a task is moved to a different cpuset, it is easier, as there is only one
task involved. It's mm->vma's are scanned, using the same
mpol_rebind_policy() as used above.
It may happen that both the mpol_copy hook and the update done via the
tasklist scan update the same mm twice. This is ok, as the mempolicies of
each vma in an mm keep track of what mems_allowed they are relative to, and
safely no-op a second request to rebind to the same nodes.
Signed-off-by: Paul Jackson <pj@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 10:01:59 +01:00
|
|
|
if (current_cpuset_is_being_rebound()) {
|
|
|
|
nodemask_t mems = cpuset_mems_allowed(current);
|
|
|
|
mpol_rebind_policy(old, &mems);
|
|
|
|
}
|
2005-04-17 00:20:36 +02:00
|
|
|
*new = *old;
|
|
|
|
atomic_set(&new->refcnt, 1);
|
|
|
|
return new;
|
|
|
|
}
|
|
|
|
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
/*
|
|
|
|
* If *frompol needs [has] an extra ref, copy *frompol to *tompol ,
|
|
|
|
* eliminate the * MPOL_F_* flags that require conditional ref and
|
|
|
|
* [NOTE!!!] drop the extra ref. Not safe to reference *frompol directly
|
|
|
|
* after return. Use the returned value.
|
|
|
|
*
|
|
|
|
* Allows use of a mempolicy for, e.g., multiple allocations with a single
|
|
|
|
* policy lookup, even if the policy needs/has extra ref on lookup.
|
|
|
|
* shmem_readahead needs this.
|
|
|
|
*/
|
|
|
|
struct mempolicy *__mpol_cond_copy(struct mempolicy *tompol,
|
|
|
|
struct mempolicy *frompol)
|
|
|
|
{
|
|
|
|
if (!mpol_needs_cond_ref(frompol))
|
|
|
|
return frompol;
|
|
|
|
|
|
|
|
*tompol = *frompol;
|
|
|
|
tompol->flags &= ~MPOL_F_SHARED; /* copy doesn't need unref */
|
|
|
|
__mpol_put(frompol);
|
|
|
|
return tompol;
|
|
|
|
}
|
|
|
|
|
mempolicy: add MPOL_F_STATIC_NODES flag
Add an optional mempolicy mode flag, MPOL_F_STATIC_NODES, that suppresses the
node remap when the policy is rebound.
Adds another member to struct mempolicy, nodemask_t user_nodemask, as part of
a union with cpuset_mems_allowed:
struct mempolicy {
...
union {
nodemask_t cpuset_mems_allowed;
nodemask_t user_nodemask;
} w;
}
that stores the the nodemask that the user passed when he or she created the
mempolicy via set_mempolicy() or mbind(). When using MPOL_F_STATIC_NODES,
which is passed with any mempolicy mode, the user's passed nodemask
intersected with the VMA or task's allowed nodes is always used when
determining the preferred node, setting the MPOL_BIND zonelist, or creating
the interleave nodemask. This happens whenever the policy is rebound,
including when a task's cpuset assignment changes or the cpuset's mems are
changed.
This creates an interesting side-effect in that it allows the mempolicy
"intent" to lie dormant and uneffected until it has access to the node(s) that
it desires. For example, if you currently ask for an interleaved policy over
a set of nodes that you do not have access to, the mempolicy is not created
and the task continues to use the previous policy. With this change, however,
it is possible to create the same mempolicy; it is only effected when access
to nodes in the nodemask is acquired.
It is also possible to mount tmpfs with the static nodemask behavior when
specifying a node or nodemask. To do this, simply add "=static" immediately
following the mempolicy mode at mount time:
mount -o remount mpol=interleave=static:1-3
Also removes mpol_check_policy() and folds its logic into mpol_new() since it
is now obsoleted. The unused vma_mpol_equal() is also removed.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:27 +02:00
|
|
|
static int mpol_match_intent(const struct mempolicy *a,
|
|
|
|
const struct mempolicy *b)
|
|
|
|
{
|
|
|
|
if (a->flags != b->flags)
|
|
|
|
return 0;
|
|
|
|
if (!mpol_store_user_nodemask(a))
|
|
|
|
return 1;
|
|
|
|
return nodes_equal(a->w.user_nodemask, b->w.user_nodemask);
|
|
|
|
}
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
/* Slow path of a mempolicy comparison */
|
|
|
|
int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
|
|
|
|
{
|
|
|
|
if (!a || !b)
|
|
|
|
return 0;
|
2008-04-28 11:13:12 +02:00
|
|
|
if (a->mode != b->mode)
|
2005-04-17 00:20:36 +02:00
|
|
|
return 0;
|
2008-04-28 11:13:12 +02:00
|
|
|
if (a->mode != MPOL_DEFAULT && !mpol_match_intent(a, b))
|
mempolicy: add MPOL_F_STATIC_NODES flag
Add an optional mempolicy mode flag, MPOL_F_STATIC_NODES, that suppresses the
node remap when the policy is rebound.
Adds another member to struct mempolicy, nodemask_t user_nodemask, as part of
a union with cpuset_mems_allowed:
struct mempolicy {
...
union {
nodemask_t cpuset_mems_allowed;
nodemask_t user_nodemask;
} w;
}
that stores the the nodemask that the user passed when he or she created the
mempolicy via set_mempolicy() or mbind(). When using MPOL_F_STATIC_NODES,
which is passed with any mempolicy mode, the user's passed nodemask
intersected with the VMA or task's allowed nodes is always used when
determining the preferred node, setting the MPOL_BIND zonelist, or creating
the interleave nodemask. This happens whenever the policy is rebound,
including when a task's cpuset assignment changes or the cpuset's mems are
changed.
This creates an interesting side-effect in that it allows the mempolicy
"intent" to lie dormant and uneffected until it has access to the node(s) that
it desires. For example, if you currently ask for an interleaved policy over
a set of nodes that you do not have access to, the mempolicy is not created
and the task continues to use the previous policy. With this change, however,
it is possible to create the same mempolicy; it is only effected when access
to nodes in the nodemask is acquired.
It is also possible to mount tmpfs with the static nodemask behavior when
specifying a node or nodemask. To do this, simply add "=static" immediately
following the mempolicy mode at mount time:
mount -o remount mpol=interleave=static:1-3
Also removes mpol_check_policy() and folds its logic into mpol_new() since it
is now obsoleted. The unused vma_mpol_equal() is also removed.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:27 +02:00
|
|
|
return 0;
|
2008-04-28 11:13:12 +02:00
|
|
|
switch (a->mode) {
|
2008-04-28 11:12:18 +02:00
|
|
|
case MPOL_BIND:
|
|
|
|
/* Fall through */
|
2005-04-17 00:20:36 +02:00
|
|
|
case MPOL_INTERLEAVE:
|
2005-10-30 02:15:48 +01:00
|
|
|
return nodes_equal(a->v.nodes, b->v.nodes);
|
2005-04-17 00:20:36 +02:00
|
|
|
case MPOL_PREFERRED:
|
2008-04-28 11:13:21 +02:00
|
|
|
return a->v.preferred_node == b->v.preferred_node &&
|
|
|
|
a->flags == b->flags;
|
2005-04-17 00:20:36 +02:00
|
|
|
default:
|
|
|
|
BUG();
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Shared memory backing store policy support.
|
|
|
|
*
|
|
|
|
* Remember policies even when nobody has shared memory mapped.
|
|
|
|
* The policies are kept in Red-Black tree linked from the inode.
|
|
|
|
* They are protected by the sp->lock spinlock, which should be held
|
|
|
|
* for any accesses to the tree.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* lookup first element intersecting start-end */
|
|
|
|
/* Caller holds sp->lock */
|
|
|
|
static struct sp_node *
|
|
|
|
sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
|
|
|
|
{
|
|
|
|
struct rb_node *n = sp->root.rb_node;
|
|
|
|
|
|
|
|
while (n) {
|
|
|
|
struct sp_node *p = rb_entry(n, struct sp_node, nd);
|
|
|
|
|
|
|
|
if (start >= p->end)
|
|
|
|
n = n->rb_right;
|
|
|
|
else if (end <= p->start)
|
|
|
|
n = n->rb_left;
|
|
|
|
else
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (!n)
|
|
|
|
return NULL;
|
|
|
|
for (;;) {
|
|
|
|
struct sp_node *w = NULL;
|
|
|
|
struct rb_node *prev = rb_prev(n);
|
|
|
|
if (!prev)
|
|
|
|
break;
|
|
|
|
w = rb_entry(prev, struct sp_node, nd);
|
|
|
|
if (w->end <= start)
|
|
|
|
break;
|
|
|
|
n = prev;
|
|
|
|
}
|
|
|
|
return rb_entry(n, struct sp_node, nd);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Insert a new shared policy into the list. */
|
|
|
|
/* Caller holds sp->lock */
|
|
|
|
static void sp_insert(struct shared_policy *sp, struct sp_node *new)
|
|
|
|
{
|
|
|
|
struct rb_node **p = &sp->root.rb_node;
|
|
|
|
struct rb_node *parent = NULL;
|
|
|
|
struct sp_node *nd;
|
|
|
|
|
|
|
|
while (*p) {
|
|
|
|
parent = *p;
|
|
|
|
nd = rb_entry(parent, struct sp_node, nd);
|
|
|
|
if (new->start < nd->start)
|
|
|
|
p = &(*p)->rb_left;
|
|
|
|
else if (new->end > nd->end)
|
|
|
|
p = &(*p)->rb_right;
|
|
|
|
else
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
rb_link_node(&new->nd, parent, p);
|
|
|
|
rb_insert_color(&new->nd, &sp->root);
|
2007-07-16 08:38:16 +02:00
|
|
|
pr_debug("inserting %lx-%lx: %d\n", new->start, new->end,
|
2008-04-28 11:13:12 +02:00
|
|
|
new->policy ? new->policy->mode : 0);
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Find shared policy intersecting idx */
|
|
|
|
struct mempolicy *
|
|
|
|
mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
|
|
|
|
{
|
|
|
|
struct mempolicy *pol = NULL;
|
|
|
|
struct sp_node *sn;
|
|
|
|
|
|
|
|
if (!sp->root.rb_node)
|
|
|
|
return NULL;
|
|
|
|
spin_lock(&sp->lock);
|
|
|
|
sn = sp_lookup(sp, idx, idx+1);
|
|
|
|
if (sn) {
|
|
|
|
mpol_get(sn->policy);
|
|
|
|
pol = sn->policy;
|
|
|
|
}
|
|
|
|
spin_unlock(&sp->lock);
|
|
|
|
return pol;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void sp_delete(struct shared_policy *sp, struct sp_node *n)
|
|
|
|
{
|
2007-07-16 08:38:16 +02:00
|
|
|
pr_debug("deleting %lx-l%lx\n", n->start, n->end);
|
2005-04-17 00:20:36 +02:00
|
|
|
rb_erase(&n->nd, &sp->root);
|
2008-04-28 11:13:08 +02:00
|
|
|
mpol_put(n->policy);
|
2005-04-17 00:20:36 +02:00
|
|
|
kmem_cache_free(sn_cache, n);
|
|
|
|
}
|
|
|
|
|
2007-10-16 10:26:26 +02:00
|
|
|
static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
|
|
|
|
struct mempolicy *pol)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
struct sp_node *n = kmem_cache_alloc(sn_cache, GFP_KERNEL);
|
|
|
|
|
|
|
|
if (!n)
|
|
|
|
return NULL;
|
|
|
|
n->start = start;
|
|
|
|
n->end = end;
|
|
|
|
mpol_get(pol);
|
2008-04-28 11:13:13 +02:00
|
|
|
pol->flags |= MPOL_F_SHARED; /* for unref */
|
2005-04-17 00:20:36 +02:00
|
|
|
n->policy = pol;
|
|
|
|
return n;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Replace a policy range. */
|
|
|
|
static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
|
|
|
|
unsigned long end, struct sp_node *new)
|
|
|
|
{
|
|
|
|
struct sp_node *n, *new2 = NULL;
|
|
|
|
|
|
|
|
restart:
|
|
|
|
spin_lock(&sp->lock);
|
|
|
|
n = sp_lookup(sp, start, end);
|
|
|
|
/* Take care of old policies in the same range. */
|
|
|
|
while (n && n->start < end) {
|
|
|
|
struct rb_node *next = rb_next(&n->nd);
|
|
|
|
if (n->start >= start) {
|
|
|
|
if (n->end <= end)
|
|
|
|
sp_delete(sp, n);
|
|
|
|
else
|
|
|
|
n->start = end;
|
|
|
|
} else {
|
|
|
|
/* Old policy spanning whole new range. */
|
|
|
|
if (n->end > end) {
|
|
|
|
if (!new2) {
|
|
|
|
spin_unlock(&sp->lock);
|
|
|
|
new2 = sp_alloc(end, n->end, n->policy);
|
|
|
|
if (!new2)
|
|
|
|
return -ENOMEM;
|
|
|
|
goto restart;
|
|
|
|
}
|
|
|
|
n->end = start;
|
|
|
|
sp_insert(sp, new2);
|
|
|
|
new2 = NULL;
|
|
|
|
break;
|
|
|
|
} else
|
|
|
|
n->end = start;
|
|
|
|
}
|
|
|
|
if (!next)
|
|
|
|
break;
|
|
|
|
n = rb_entry(next, struct sp_node, nd);
|
|
|
|
}
|
|
|
|
if (new)
|
|
|
|
sp_insert(sp, new);
|
|
|
|
spin_unlock(&sp->lock);
|
|
|
|
if (new2) {
|
2008-04-28 11:13:08 +02:00
|
|
|
mpol_put(new2->policy);
|
2005-04-17 00:20:36 +02:00
|
|
|
kmem_cache_free(sn_cache, new2);
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
/**
|
|
|
|
* mpol_shared_policy_init - initialize shared policy for inode
|
|
|
|
* @sp: pointer to inode shared policy
|
|
|
|
* @mpol: struct mempolicy to install
|
|
|
|
*
|
|
|
|
* Install non-NULL @mpol in inode's shared policy rb-tree.
|
|
|
|
* On entry, the current task has a reference on a non-NULL @mpol.
|
|
|
|
* This must be released on exit.
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
* This is called at get_inode() calls and we can use GFP_KERNEL.
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
*/
|
|
|
|
void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
|
|
|
|
{
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
int ret;
|
|
|
|
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
sp->root = RB_ROOT; /* empty tree == default mempolicy */
|
|
|
|
spin_lock_init(&sp->lock);
|
|
|
|
|
|
|
|
if (mpol) {
|
|
|
|
struct vm_area_struct pvma;
|
|
|
|
struct mempolicy *new;
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
NODEMASK_SCRATCH(scratch);
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
if (!scratch)
|
|
|
|
return;
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
/* contextualize the tmpfs mount point mempolicy */
|
|
|
|
new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask);
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
if (IS_ERR(new)) {
|
|
|
|
mpol_put(mpol); /* drop our ref on sb mpol */
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
NODEMASK_SCRATCH_FREE(scratch);
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
return; /* no valid nodemask intersection */
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
task_lock(current);
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch);
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
task_unlock(current);
|
|
|
|
mpol_put(mpol); /* drop our ref on sb mpol */
|
|
|
|
if (ret) {
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
NODEMASK_SCRATCH_FREE(scratch);
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
mpol_put(new);
|
|
|
|
return;
|
|
|
|
}
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
|
|
|
|
/* Create pseudo-vma that contains just the policy */
|
|
|
|
memset(&pvma, 0, sizeof(struct vm_area_struct));
|
|
|
|
pvma.vm_end = TASK_SIZE; /* policy covers entire file */
|
|
|
|
mpol_set_shared_policy(sp, &pvma, new); /* adds ref */
|
|
|
|
mpol_put(new); /* drop initial ref */
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
NODEMASK_SCRATCH_FREE(scratch);
|
2006-01-14 22:20:48 +01:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
int mpol_set_shared_policy(struct shared_policy *info,
|
|
|
|
struct vm_area_struct *vma, struct mempolicy *npol)
|
|
|
|
{
|
|
|
|
int err;
|
|
|
|
struct sp_node *new = NULL;
|
|
|
|
unsigned long sz = vma_pages(vma);
|
|
|
|
|
2008-04-28 11:12:25 +02:00
|
|
|
pr_debug("set_shared_policy %lx sz %lu %d %d %lx\n",
|
2005-04-17 00:20:36 +02:00
|
|
|
vma->vm_pgoff,
|
2008-04-28 11:13:12 +02:00
|
|
|
sz, npol ? npol->mode : -1,
|
2008-04-28 11:12:25 +02:00
|
|
|
npol ? npol->flags : -1,
|
2007-07-16 08:38:16 +02:00
|
|
|
npol ? nodes_addr(npol->v.nodes)[0] : -1);
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
if (npol) {
|
|
|
|
new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol);
|
|
|
|
if (!new)
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new);
|
|
|
|
if (err && new)
|
|
|
|
kmem_cache_free(sn_cache, new);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Free a backing policy store on inode delete. */
|
|
|
|
void mpol_free_shared_policy(struct shared_policy *p)
|
|
|
|
{
|
|
|
|
struct sp_node *n;
|
|
|
|
struct rb_node *next;
|
|
|
|
|
|
|
|
if (!p->root.rb_node)
|
|
|
|
return;
|
|
|
|
spin_lock(&p->lock);
|
|
|
|
next = rb_first(&p->root);
|
|
|
|
while (next) {
|
|
|
|
n = rb_entry(next, struct sp_node, nd);
|
|
|
|
next = rb_next(&n->nd);
|
2005-07-27 20:43:50 +02:00
|
|
|
rb_erase(&n->nd, &p->root);
|
2008-04-28 11:13:08 +02:00
|
|
|
mpol_put(n->policy);
|
2005-04-17 00:20:36 +02:00
|
|
|
kmem_cache_free(sn_cache, n);
|
|
|
|
}
|
|
|
|
spin_unlock(&p->lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* assumes fs == KERNEL_DS */
|
|
|
|
void __init numa_policy_init(void)
|
|
|
|
{
|
2007-07-16 08:38:15 +02:00
|
|
|
nodemask_t interleave_nodes;
|
|
|
|
unsigned long largest = 0;
|
|
|
|
int nid, prefer = 0;
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
policy_cache = kmem_cache_create("numa_policy",
|
|
|
|
sizeof(struct mempolicy),
|
2007-07-20 03:11:58 +02:00
|
|
|
0, SLAB_PANIC, NULL);
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
sn_cache = kmem_cache_create("shared_policy_node",
|
|
|
|
sizeof(struct sp_node),
|
2007-07-20 03:11:58 +02:00
|
|
|
0, SLAB_PANIC, NULL);
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2007-07-16 08:38:15 +02:00
|
|
|
/*
|
|
|
|
* Set interleaving policy for system init. Interleaving is only
|
|
|
|
* enabled across suitably sized nodes (default is >= 16MB), or
|
|
|
|
* fall back to the largest node if they're all smaller.
|
|
|
|
*/
|
|
|
|
nodes_clear(interleave_nodes);
|
2007-10-16 10:25:35 +02:00
|
|
|
for_each_node_state(nid, N_HIGH_MEMORY) {
|
2007-07-16 08:38:15 +02:00
|
|
|
unsigned long total_pages = node_present_pages(nid);
|
|
|
|
|
|
|
|
/* Preserve the largest node */
|
|
|
|
if (largest < total_pages) {
|
|
|
|
largest = total_pages;
|
|
|
|
prefer = nid;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Interleave this node? */
|
|
|
|
if ((total_pages << PAGE_SHIFT) >= (16 << 20))
|
|
|
|
node_set(nid, interleave_nodes);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* All too small, use the largest */
|
|
|
|
if (unlikely(nodes_empty(interleave_nodes)))
|
|
|
|
node_set(prefer, interleave_nodes);
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2008-04-28 11:12:25 +02:00
|
|
|
if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes))
|
2005-04-17 00:20:36 +02:00
|
|
|
printk("numa_policy_init: interleaving failed\n");
|
|
|
|
}
|
|
|
|
|
2005-10-30 02:16:59 +01:00
|
|
|
/* Reset policy of current process to default */
|
2005-04-17 00:20:36 +02:00
|
|
|
void numa_default_policy(void)
|
|
|
|
{
|
2008-04-28 11:12:25 +02:00
|
|
|
do_set_mempolicy(MPOL_DEFAULT, 0, NULL);
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
[PATCH] cpusets: automatic numa mempolicy rebinding
This patch automatically updates a tasks NUMA mempolicy when its cpuset
memory placement changes. It does so within the context of the task,
without any need to support low level external mempolicy manipulation.
If a system is not using cpusets, or if running on a system with just the
root (all-encompassing) cpuset, then this remap is a no-op. Only when a
task is moved between cpusets, or a cpusets memory placement is changed
does the following apply. Otherwise, the main routine below,
rebind_policy() is not even called.
When mixing cpusets, scheduler affinity, and NUMA mempolicies, the
essential role of cpusets is to place jobs (several related tasks) on a set
of CPUs and Memory Nodes, the essential role of sched_setaffinity is to
manage a jobs processor placement within its allowed cpuset, and the
essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs
memory placement within its allowed cpuset.
However, CPU affinity and NUMA memory placement are managed within the
kernel using absolute system wide numbering, not cpuset relative numbering.
This is ok until a job is migrated to a different cpuset, or what's the
same, a jobs cpuset is moved to different CPUs and Memory Nodes.
Then the CPU affinity and NUMA memory placement of the tasks in the job
need to be updated, to preserve their cpuset-relative position. This can
be done for CPU affinity using sched_setaffinity() from user code, as one
task can modify anothers CPU affinity. This cannot be done from an
external task for NUMA memory placement, as that can only be modified in
the context of the task using it.
However, it easy enough to remap a tasks NUMA mempolicy automatically when
a task is migrated, using the existing cpuset mechanism to trigger a
refresh of a tasks memory placement after its cpuset has changed. All that
is needed is the old and new nodemask, and notice to the task that it needs
to rebind its mempolicy. The tasks mems_allowed has the old mask, the
tasks cpuset has the new mask, and the existing
cpuset_update_current_mems_allowed() mechanism provides the notice. The
bitmap/cpumask/nodemask remap operators provide the cpuset relative
calculations.
This patch leaves open a couple of issues:
1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies:
These mempolicies may reference nodes outside of those allowed to
the current task by its cpuset. Tasks are migrated as part of jobs,
which reside on what might be several cpusets in a subtree. When such
a job is migrated, all NUMA memory policy references to nodes within
that cpuset subtree should be translated, and references to any nodes
outside that subtree should be left untouched. A future patch will
provide the cpuset mechanism needed to mark such subtrees. With that
patch, we will be able to correctly migrate these other memory policies
across a job migration.
2) Updating cpuset, affinity and memory policies in user space:
This is harder. Any placement state stored in user space using
system-wide numbering will be invalidated across a migration. More
work will be required to provide user code with a migration-safe means
to manage its cpuset relative placement, while preserving the current
API's that pass system wide numbers, not cpuset relative numbers across
the kernel-user boundary.
Signed-off-by: Paul Jackson <pj@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 00:02:36 +01:00
|
|
|
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
/*
|
|
|
|
* Parse and format mempolicy from/to strings
|
|
|
|
*/
|
|
|
|
|
2006-01-08 10:01:02 +01:00
|
|
|
/*
|
2008-04-28 11:13:21 +02:00
|
|
|
* "local" is pseudo-policy: MPOL_PREFERRED with MPOL_F_LOCAL flag
|
2008-04-28 11:13:24 +02:00
|
|
|
* Used only for mpol_parse_str() and mpol_to_str()
|
2006-01-08 10:01:02 +01:00
|
|
|
*/
|
mempolicy: mPOL_PREFERRED cleanups for "local allocation"
Here are a couple of "cleanups" for MPOL_PREFERRED behavior when
v.preferred_node < 0 -- i.e., "local allocation":
1) [do_]get_mempolicy() calls the now renamed get_policy_nodemask()
to fetch the nodemask associated with a policy. Currently,
get_policy_nodemask() returns the set of nodes with memory, when
the policy 'mode' is 'PREFERRED, and the preferred_node is < 0.
Change to return an empty nodemask, as this is what was specified
to achieve "local allocation".
2) When a task is moved into a [new] cpuset, mpol_rebind_policy() is
called to adjust any task and vma policy nodes to be valid in the
new cpuset. However, when the policy is MPOL_PREFERRED, and the
preferred_node is <0, no rebind is necessary. The "local allocation"
indication is valid in any cpuset. Existing code will "do the right
thing" because node_remap() will just return the argument node when
it is outside of the valid range of node ids. However, I think it is
clearer and cleaner to skip the remap explicitly in this case.
3) mpol_to_str() produces a printable, "human readable" string from a
struct mempolicy. For MPOL_PREFERRED with preferred_node <0, show
"local", as this indicates local allocation, as the task migrates
among nodes. Note that this matches the usage of "local allocation"
in libnuma() and numactl. Without this change, I believe that node_set()
[via set_bit()] will set bit 31, resulting in a misleading display.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:20 +02:00
|
|
|
#define MPOL_LOCAL (MPOL_INTERLEAVE + 1)
|
2006-12-07 05:40:36 +01:00
|
|
|
static const char * const policy_types[] =
|
mempolicy: mPOL_PREFERRED cleanups for "local allocation"
Here are a couple of "cleanups" for MPOL_PREFERRED behavior when
v.preferred_node < 0 -- i.e., "local allocation":
1) [do_]get_mempolicy() calls the now renamed get_policy_nodemask()
to fetch the nodemask associated with a policy. Currently,
get_policy_nodemask() returns the set of nodes with memory, when
the policy 'mode' is 'PREFERRED, and the preferred_node is < 0.
Change to return an empty nodemask, as this is what was specified
to achieve "local allocation".
2) When a task is moved into a [new] cpuset, mpol_rebind_policy() is
called to adjust any task and vma policy nodes to be valid in the
new cpuset. However, when the policy is MPOL_PREFERRED, and the
preferred_node is <0, no rebind is necessary. The "local allocation"
indication is valid in any cpuset. Existing code will "do the right
thing" because node_remap() will just return the argument node when
it is outside of the valid range of node ids. However, I think it is
clearer and cleaner to skip the remap explicitly in this case.
3) mpol_to_str() produces a printable, "human readable" string from a
struct mempolicy. For MPOL_PREFERRED with preferred_node <0, show
"local", as this indicates local allocation, as the task migrates
among nodes. Note that this matches the usage of "local allocation"
in libnuma() and numactl. Without this change, I believe that node_set()
[via set_bit()] will set bit 31, resulting in a misleading display.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:20 +02:00
|
|
|
{ "default", "prefer", "bind", "interleave", "local" };
|
2006-01-08 10:01:02 +01:00
|
|
|
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
|
|
|
|
#ifdef CONFIG_TMPFS
|
|
|
|
/**
|
|
|
|
* mpol_parse_str - parse string to mempolicy
|
|
|
|
* @str: string containing mempolicy to parse
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
* @mpol: pointer to struct mempolicy pointer, returned on success.
|
|
|
|
* @no_context: flag whether to "contextualize" the mempolicy
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
*
|
|
|
|
* Format of input:
|
|
|
|
* <mode>[=<flags>][:<nodelist>]
|
|
|
|
*
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
* if @no_context is true, save the input nodemask in w.user_nodemask in
|
|
|
|
* the returned mempolicy. This will be used to "clone" the mempolicy in
|
|
|
|
* a specific context [cpuset] at a later time. Used to parse tmpfs mpol
|
|
|
|
* mount option. Note that if 'static' or 'relative' mode flags were
|
|
|
|
* specified, the input nodemask will already have been saved. Saving
|
|
|
|
* it again is redundant, but safe.
|
|
|
|
*
|
|
|
|
* On success, returns 0, else 1
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
*/
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
{
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
struct mempolicy *new = NULL;
|
|
|
|
unsigned short uninitialized_var(mode);
|
|
|
|
unsigned short uninitialized_var(mode_flags);
|
|
|
|
nodemask_t nodes;
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
char *nodelist = strchr(str, ':');
|
|
|
|
char *flags = strchr(str, '=');
|
|
|
|
int i;
|
|
|
|
int err = 1;
|
|
|
|
|
|
|
|
if (nodelist) {
|
|
|
|
/* NUL-terminate mode or flags string */
|
|
|
|
*nodelist++ = '\0';
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
if (nodelist_parse(nodelist, nodes))
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
goto out;
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
if (!nodes_subset(nodes, node_states[N_HIGH_MEMORY]))
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
goto out;
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
} else
|
|
|
|
nodes_clear(nodes);
|
|
|
|
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
if (flags)
|
|
|
|
*flags++ = '\0'; /* terminate mode string */
|
|
|
|
|
2008-04-28 11:13:24 +02:00
|
|
|
for (i = 0; i <= MPOL_LOCAL; i++) {
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
if (!strcmp(str, policy_types[i])) {
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
mode = i;
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
2008-04-28 11:13:24 +02:00
|
|
|
if (i > MPOL_LOCAL)
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
goto out;
|
|
|
|
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
switch (mode) {
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
case MPOL_PREFERRED:
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
/*
|
|
|
|
* Insist on a nodelist of one node only
|
|
|
|
*/
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
if (nodelist) {
|
|
|
|
char *rest = nodelist;
|
|
|
|
while (isdigit(*rest))
|
|
|
|
rest++;
|
|
|
|
if (!*rest)
|
|
|
|
err = 0;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case MPOL_INTERLEAVE:
|
|
|
|
/*
|
|
|
|
* Default to online nodes with memory if no nodelist
|
|
|
|
*/
|
|
|
|
if (!nodelist)
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
nodes = node_states[N_HIGH_MEMORY];
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
err = 0;
|
2008-04-28 11:13:24 +02:00
|
|
|
break;
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
case MPOL_LOCAL:
|
2008-04-28 11:13:24 +02:00
|
|
|
/*
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
* Don't allow a nodelist; mpol_new() checks flags
|
2008-04-28 11:13:24 +02:00
|
|
|
*/
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
if (nodelist)
|
2008-04-28 11:13:24 +02:00
|
|
|
goto out;
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
mode = MPOL_PREFERRED;
|
2008-04-28 11:13:24 +02:00
|
|
|
break;
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* case MPOL_BIND: mpol_new() enforces non-empty nodemask.
|
|
|
|
* case MPOL_DEFAULT: mpol_new() enforces empty nodemask, ignores flags.
|
|
|
|
*/
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
}
|
|
|
|
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
mode_flags = 0;
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
if (flags) {
|
|
|
|
/*
|
|
|
|
* Currently, we only support two mutually exclusive
|
|
|
|
* mode flags.
|
|
|
|
*/
|
|
|
|
if (!strcmp(flags, "static"))
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
mode_flags |= MPOL_F_STATIC_NODES;
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
else if (!strcmp(flags, "relative"))
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
mode_flags |= MPOL_F_RELATIVE_NODES;
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
else
|
|
|
|
err = 1;
|
|
|
|
}
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
|
|
|
|
new = mpol_new(mode, mode_flags, &nodes);
|
|
|
|
if (IS_ERR(new))
|
|
|
|
err = 1;
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
else {
|
|
|
|
int ret;
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
NODEMASK_SCRATCH(scratch);
|
|
|
|
if (scratch) {
|
|
|
|
task_lock(current);
|
|
|
|
ret = mpol_set_nodemask(new, &nodes, scratch);
|
|
|
|
task_unlock(current);
|
|
|
|
} else
|
|
|
|
ret = -ENOMEM;
|
|
|
|
NODEMASK_SCRATCH_FREE(scratch);
|
|
|
|
if (ret) {
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
err = 1;
|
mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware
At first, init_task's mems_allowed is initialized as this.
init_task->mems_allowed == node_state[N_POSSIBLE]
And cpuset's top_cpuset mask is initialized as this
top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY]
Before 2.6.29:
policy's mems_allowed is initialized as this.
1. update tasks->mems_allowed by its cpuset->mems_allowed.
2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask)
Updating task's mems_allowed in reference to top_cpuset's one.
cpuset's mems_allowed is aware of N_HIGH_MEMORY, always.
In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c
("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed
is initialized as this.
1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask)
Here, if task is in top_cpuset, task->mems_allowed is not updated from
init's one. Assume user excutes command as #numactrl --interleave=all
,....
policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK)
Then, policy's mems_allowd can includes a possible node, which has no pgdat.
MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this
directly.
NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL
Then, what's we need is making policy->mems_allowed be aware of
N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will
be on statck. Because I know cpumask has a new interface of
CPUMASK_ALLOC(), I added it to node.
This patch stands on old behavior. But I feel this fix itself is just a
Band-Aid. But to do fundametal fix, we have to take care of memory
hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I
think.)
mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask
should be includes only online nodes.
In old behavior, this is guaranteed by frequent reference to cpuset's
code. Now, most of them are removed and mempolicy has to check it by
itself.
To do check, a few nodemask_t will be used for calculating nodemask. But,
size of nodemask_t can be big and it's not good to allocate them on stack.
Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.
NODEMASK_ALLOC/FREE shoudl be there.
[akpm@linux-foundation.org: cleanups & tweaks]
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-07 00:07:33 +02:00
|
|
|
mpol_put(new);
|
|
|
|
} else if (no_context) {
|
cpuset,mm: update tasks' mems_allowed in time
Fix allocating page cache/slab object on the unallowed node when memory
spread is set by updating tasks' mems_allowed after its cpuset's mems is
changed.
In order to update tasks' mems_allowed in time, we must modify the code of
memory policy. Because the memory policy is applied in the process's
context originally. After applying this patch, one task directly
manipulates anothers mems_allowed, and we use alloc_lock in the
task_struct to protect mems_allowed and memory policy of the task.
But in the fast path, we didn't use lock to protect them, because adding a
lock may lead to performance regression. But if we don't add a lock,the
task might see no nodes when changing cpuset's mems_allowed to some
non-overlapping set. In order to avoid it, we set all new allowed nodes,
then clear newly disallowed ones.
[lee.schermerhorn@hp.com:
The rework of mpol_new() to extract the adjusting of the node mask to
apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind()
with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local
allocation. Fix this by adding the check for MPOL_PREFERRED and empty
node mask to mpol_new_mpolicy().
Remove the now unneeded 'nodes = NULL' from mpol_new().
Note that mpol_new_mempolicy() is always called with a non-NULL
'nodes' parameter now that it has been removed from mpol_new().
Therefore, we don't need to test nodes for NULL before testing it for
'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to
verify this assumption.]
[lee.schermerhorn@hp.com:
I don't think the function name 'mpol_new_mempolicy' is descriptive
enough to differentiate it from mpol_new().
This function applies cpuset set context, usually constraining nodes
to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag
is set, it also translates the nodes. So I settled on
'mpol_set_nodemask()', because the comment block for mpol_new() mentions
that we need to call this function to "set nodes".
Some additional minor line length, whitespace and typo cleanup.]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Paul Menage <menage@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 00:31:49 +02:00
|
|
|
/* save for contextualization */
|
|
|
|
new->w.user_nodemask = nodes;
|
|
|
|
}
|
|
|
|
}
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
out:
|
|
|
|
/* Restore string for error message */
|
|
|
|
if (nodelist)
|
|
|
|
*--nodelist = ':';
|
|
|
|
if (flags)
|
|
|
|
*--flags = '=';
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
if (!err)
|
|
|
|
*mpol = new;
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_TMPFS */
|
|
|
|
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
/**
|
|
|
|
* mpol_to_str - format a mempolicy structure for printing
|
|
|
|
* @buffer: to contain formatted mempolicy string
|
|
|
|
* @maxlen: length of @buffer
|
|
|
|
* @pol: pointer to mempolicy to be formatted
|
|
|
|
* @no_context: "context free" mempolicy - use nodemask in w.user_nodemask
|
|
|
|
*
|
2006-01-08 10:01:02 +01:00
|
|
|
* Convert a mempolicy into a string.
|
|
|
|
* Returns the number of characters in buffer (if positive)
|
|
|
|
* or an error (negative)
|
|
|
|
*/
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
|
2006-01-08 10:01:02 +01:00
|
|
|
{
|
|
|
|
char *p = buffer;
|
|
|
|
int l;
|
|
|
|
nodemask_t nodes;
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
unsigned short mode;
|
mempolicy: add MPOL_F_STATIC_NODES flag
Add an optional mempolicy mode flag, MPOL_F_STATIC_NODES, that suppresses the
node remap when the policy is rebound.
Adds another member to struct mempolicy, nodemask_t user_nodemask, as part of
a union with cpuset_mems_allowed:
struct mempolicy {
...
union {
nodemask_t cpuset_mems_allowed;
nodemask_t user_nodemask;
} w;
}
that stores the the nodemask that the user passed when he or she created the
mempolicy via set_mempolicy() or mbind(). When using MPOL_F_STATIC_NODES,
which is passed with any mempolicy mode, the user's passed nodemask
intersected with the VMA or task's allowed nodes is always used when
determining the preferred node, setting the MPOL_BIND zonelist, or creating
the interleave nodemask. This happens whenever the policy is rebound,
including when a task's cpuset assignment changes or the cpuset's mems are
changed.
This creates an interesting side-effect in that it allows the mempolicy
"intent" to lie dormant and uneffected until it has access to the node(s) that
it desires. For example, if you currently ask for an interleaved policy over
a set of nodes that you do not have access to, the mempolicy is not created
and the task continues to use the previous policy. With this change, however,
it is possible to create the same mempolicy; it is only effected when access
to nodes in the nodemask is acquired.
It is also possible to mount tmpfs with the static nodemask behavior when
specifying a node or nodemask. To do this, simply add "=static" immediately
following the mempolicy mode at mount time:
mount -o remount mpol=interleave=static:1-3
Also removes mpol_check_policy() and folds its logic into mpol_new() since it
is now obsoleted. The unused vma_mpol_equal() is also removed.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:27 +02:00
|
|
|
unsigned short flags = pol ? pol->flags : 0;
|
2006-01-08 10:01:02 +01:00
|
|
|
|
mempolicy: clean-up mpol-to-str() mempolicy formatting
mpol-to-str() formats memory policies into printable strings. Currently this
is only used to display "numa_maps". A subsequent patch will use
mpol_to_str() for formatting tmpfs [shmem] mpol mount options, allowing us to
remove essentially duplicate code in mm/shmem.c. This patch cleans up
mpol_to_str() generally and in preparation for that patch.
1) show_numa_maps() is not checking the return code from mpol_to_str().
There's not a lot we can do in this context if mpol_to_str() did return the
error [insufficient space in buffer]. Proposed "solution": just check,
under DEBUG_VM, that callers are providing sufficient buffer space for the
policy, flags, and a few nodes. This way, we'll get some display.
show_numa_maps() is providing a 50-byte buffer, so it won't trip this
check. 50-bytes should be sufficient unless one has a large number of
nodes in a very sparse nodemask.
2) The display of the new mode flags ["static" & "relative"] was set up to
display multiple flags, separated by a "bar" '|'. However, this support is
incomplete--e.g., need_bar was never incremented; and currently, these two
flags are mutually exclusive. So remove the "bar" support, for now, and
only display one flag.
3) Use snprint() to format flags, so as not to overflow the buffer. Not
that it's ever happed, AFAIK.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:22 +02:00
|
|
|
/*
|
|
|
|
* Sanity check: room for longest mode, flag and some nodes
|
|
|
|
*/
|
|
|
|
VM_BUG_ON(maxlen < strlen("interleave") + strlen("relative") + 16);
|
|
|
|
|
mempolicy: use MPOL_PREFERRED for system-wide default policy
Currently, when one specifies MPOL_DEFAULT via a NUMA memory policy API
[set_mempolicy(), mbind() and internal versions], the kernel simply installs a
NULL struct mempolicy pointer in the appropriate context: task policy, vma
policy, or shared policy. This causes any use of that policy to "fall back"
to the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in the system
default policy. This requires extra checks/cases for MPOL_DEFAULT in many
mempolicy.c functions.
There is another, "preferred" way to specify local allocation via the APIs.
That is using the MPOL_PREFERRED policy mode with an empty nodemask.
Internally, the empty nodemask gets converted to a preferred_node id of '-1'.
All internal usage of MPOL_PREFERRED will convert the '-1' to the id of the
node local to the cpu where the allocation occurs.
System default policy, except during boot, is hard-coded to "local
allocation". By using the MPOL_PREFERRED mode with a negative value of
preferred node for system default policy, MPOL_DEFAULT will never occur in the
'policy' member of a struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in the allocation
paths.
In slab_node() return local node id when policy pointer is NULL. No need to
set a pol value to take the switch default. Replace switch default with
BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including internal
calls to do_set_mempolicy() and in the display of policy in
/proc/<pid>/numa_maps. It always means "fall back" to the the next most
specific policy scope. This simplifies the description of memory policies
quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when
the requested policy [task or vma/shared] is NULL. These are the values one
would supply via set_mempolicy() or mbind() to achieve that condition--default
behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:18 +02:00
|
|
|
if (!pol || pol == &default_policy)
|
|
|
|
mode = MPOL_DEFAULT;
|
|
|
|
else
|
|
|
|
mode = pol->mode;
|
|
|
|
|
2006-01-08 10:01:02 +01:00
|
|
|
switch (mode) {
|
|
|
|
case MPOL_DEFAULT:
|
|
|
|
nodes_clear(nodes);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case MPOL_PREFERRED:
|
|
|
|
nodes_clear(nodes);
|
2008-04-28 11:13:21 +02:00
|
|
|
if (flags & MPOL_F_LOCAL)
|
mempolicy: mPOL_PREFERRED cleanups for "local allocation"
Here are a couple of "cleanups" for MPOL_PREFERRED behavior when
v.preferred_node < 0 -- i.e., "local allocation":
1) [do_]get_mempolicy() calls the now renamed get_policy_nodemask()
to fetch the nodemask associated with a policy. Currently,
get_policy_nodemask() returns the set of nodes with memory, when
the policy 'mode' is 'PREFERRED, and the preferred_node is < 0.
Change to return an empty nodemask, as this is what was specified
to achieve "local allocation".
2) When a task is moved into a [new] cpuset, mpol_rebind_policy() is
called to adjust any task and vma policy nodes to be valid in the
new cpuset. However, when the policy is MPOL_PREFERRED, and the
preferred_node is <0, no rebind is necessary. The "local allocation"
indication is valid in any cpuset. Existing code will "do the right
thing" because node_remap() will just return the argument node when
it is outside of the valid range of node ids. However, I think it is
clearer and cleaner to skip the remap explicitly in this case.
3) mpol_to_str() produces a printable, "human readable" string from a
struct mempolicy. For MPOL_PREFERRED with preferred_node <0, show
"local", as this indicates local allocation, as the task migrates
among nodes. Note that this matches the usage of "local allocation"
in libnuma() and numactl. Without this change, I believe that node_set()
[via set_bit()] will set bit 31, resulting in a misleading display.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:20 +02:00
|
|
|
mode = MPOL_LOCAL; /* pseudo-policy */
|
|
|
|
else
|
2008-04-28 11:13:21 +02:00
|
|
|
node_set(pol->v.preferred_node, nodes);
|
2006-01-08 10:01:02 +01:00
|
|
|
break;
|
|
|
|
|
|
|
|
case MPOL_BIND:
|
2008-04-28 11:12:18 +02:00
|
|
|
/* Fall through */
|
2006-01-08 10:01:02 +01:00
|
|
|
case MPOL_INTERLEAVE:
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
if (no_context)
|
|
|
|
nodes = pol->w.user_nodemask;
|
|
|
|
else
|
|
|
|
nodes = pol->v.nodes;
|
2006-01-08 10:01:02 +01:00
|
|
|
break;
|
|
|
|
|
|
|
|
default:
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
|
|
|
|
l = strlen(policy_types[mode]);
|
mempolicy: mPOL_PREFERRED cleanups for "local allocation"
Here are a couple of "cleanups" for MPOL_PREFERRED behavior when
v.preferred_node < 0 -- i.e., "local allocation":
1) [do_]get_mempolicy() calls the now renamed get_policy_nodemask()
to fetch the nodemask associated with a policy. Currently,
get_policy_nodemask() returns the set of nodes with memory, when
the policy 'mode' is 'PREFERRED, and the preferred_node is < 0.
Change to return an empty nodemask, as this is what was specified
to achieve "local allocation".
2) When a task is moved into a [new] cpuset, mpol_rebind_policy() is
called to adjust any task and vma policy nodes to be valid in the
new cpuset. However, when the policy is MPOL_PREFERRED, and the
preferred_node is <0, no rebind is necessary. The "local allocation"
indication is valid in any cpuset. Existing code will "do the right
thing" because node_remap() will just return the argument node when
it is outside of the valid range of node ids. However, I think it is
clearer and cleaner to skip the remap explicitly in this case.
3) mpol_to_str() produces a printable, "human readable" string from a
struct mempolicy. For MPOL_PREFERRED with preferred_node <0, show
"local", as this indicates local allocation, as the task migrates
among nodes. Note that this matches the usage of "local allocation"
in libnuma() and numactl. Without this change, I believe that node_set()
[via set_bit()] will set bit 31, resulting in a misleading display.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:20 +02:00
|
|
|
if (buffer + maxlen < p + l + 1)
|
|
|
|
return -ENOSPC;
|
2006-01-08 10:01:02 +01:00
|
|
|
|
|
|
|
strcpy(p, policy_types[mode]);
|
|
|
|
p += l;
|
|
|
|
|
2008-04-28 11:13:21 +02:00
|
|
|
if (flags & MPOL_MODE_FLAGS) {
|
mempolicy: add MPOL_F_STATIC_NODES flag
Add an optional mempolicy mode flag, MPOL_F_STATIC_NODES, that suppresses the
node remap when the policy is rebound.
Adds another member to struct mempolicy, nodemask_t user_nodemask, as part of
a union with cpuset_mems_allowed:
struct mempolicy {
...
union {
nodemask_t cpuset_mems_allowed;
nodemask_t user_nodemask;
} w;
}
that stores the the nodemask that the user passed when he or she created the
mempolicy via set_mempolicy() or mbind(). When using MPOL_F_STATIC_NODES,
which is passed with any mempolicy mode, the user's passed nodemask
intersected with the VMA or task's allowed nodes is always used when
determining the preferred node, setting the MPOL_BIND zonelist, or creating
the interleave nodemask. This happens whenever the policy is rebound,
including when a task's cpuset assignment changes or the cpuset's mems are
changed.
This creates an interesting side-effect in that it allows the mempolicy
"intent" to lie dormant and uneffected until it has access to the node(s) that
it desires. For example, if you currently ask for an interleaved policy over
a set of nodes that you do not have access to, the mempolicy is not created
and the task continues to use the previous policy. With this change, however,
it is possible to create the same mempolicy; it is only effected when access
to nodes in the nodemask is acquired.
It is also possible to mount tmpfs with the static nodemask behavior when
specifying a node or nodemask. To do this, simply add "=static" immediately
following the mempolicy mode at mount time:
mount -o remount mpol=interleave=static:1-3
Also removes mpol_check_policy() and folds its logic into mpol_new() since it
is now obsoleted. The unused vma_mpol_equal() is also removed.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:27 +02:00
|
|
|
if (buffer + maxlen < p + 2)
|
|
|
|
return -ENOSPC;
|
|
|
|
*p++ = '=';
|
|
|
|
|
mempolicy: clean-up mpol-to-str() mempolicy formatting
mpol-to-str() formats memory policies into printable strings. Currently this
is only used to display "numa_maps". A subsequent patch will use
mpol_to_str() for formatting tmpfs [shmem] mpol mount options, allowing us to
remove essentially duplicate code in mm/shmem.c. This patch cleans up
mpol_to_str() generally and in preparation for that patch.
1) show_numa_maps() is not checking the return code from mpol_to_str().
There's not a lot we can do in this context if mpol_to_str() did return the
error [insufficient space in buffer]. Proposed "solution": just check,
under DEBUG_VM, that callers are providing sufficient buffer space for the
policy, flags, and a few nodes. This way, we'll get some display.
show_numa_maps() is providing a 50-byte buffer, so it won't trip this
check. 50-bytes should be sufficient unless one has a large number of
nodes in a very sparse nodemask.
2) The display of the new mode flags ["static" & "relative"] was set up to
display multiple flags, separated by a "bar" '|'. However, this support is
incomplete--e.g., need_bar was never incremented; and currently, these two
flags are mutually exclusive. So remove the "bar" support, for now, and
only display one flag.
3) Use snprint() to format flags, so as not to overflow the buffer. Not
that it's ever happed, AFAIK.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:22 +02:00
|
|
|
/*
|
|
|
|
* Currently, the only defined flags are mutually exclusive
|
|
|
|
*/
|
mempolicy: add MPOL_F_STATIC_NODES flag
Add an optional mempolicy mode flag, MPOL_F_STATIC_NODES, that suppresses the
node remap when the policy is rebound.
Adds another member to struct mempolicy, nodemask_t user_nodemask, as part of
a union with cpuset_mems_allowed:
struct mempolicy {
...
union {
nodemask_t cpuset_mems_allowed;
nodemask_t user_nodemask;
} w;
}
that stores the the nodemask that the user passed when he or she created the
mempolicy via set_mempolicy() or mbind(). When using MPOL_F_STATIC_NODES,
which is passed with any mempolicy mode, the user's passed nodemask
intersected with the VMA or task's allowed nodes is always used when
determining the preferred node, setting the MPOL_BIND zonelist, or creating
the interleave nodemask. This happens whenever the policy is rebound,
including when a task's cpuset assignment changes or the cpuset's mems are
changed.
This creates an interesting side-effect in that it allows the mempolicy
"intent" to lie dormant and uneffected until it has access to the node(s) that
it desires. For example, if you currently ask for an interleaved policy over
a set of nodes that you do not have access to, the mempolicy is not created
and the task continues to use the previous policy. With this change, however,
it is possible to create the same mempolicy; it is only effected when access
to nodes in the nodemask is acquired.
It is also possible to mount tmpfs with the static nodemask behavior when
specifying a node or nodemask. To do this, simply add "=static" immediately
following the mempolicy mode at mount time:
mount -o remount mpol=interleave=static:1-3
Also removes mpol_check_policy() and folds its logic into mpol_new() since it
is now obsoleted. The unused vma_mpol_equal() is also removed.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:27 +02:00
|
|
|
if (flags & MPOL_F_STATIC_NODES)
|
mempolicy: clean-up mpol-to-str() mempolicy formatting
mpol-to-str() formats memory policies into printable strings. Currently this
is only used to display "numa_maps". A subsequent patch will use
mpol_to_str() for formatting tmpfs [shmem] mpol mount options, allowing us to
remove essentially duplicate code in mm/shmem.c. This patch cleans up
mpol_to_str() generally and in preparation for that patch.
1) show_numa_maps() is not checking the return code from mpol_to_str().
There's not a lot we can do in this context if mpol_to_str() did return the
error [insufficient space in buffer]. Proposed "solution": just check,
under DEBUG_VM, that callers are providing sufficient buffer space for the
policy, flags, and a few nodes. This way, we'll get some display.
show_numa_maps() is providing a 50-byte buffer, so it won't trip this
check. 50-bytes should be sufficient unless one has a large number of
nodes in a very sparse nodemask.
2) The display of the new mode flags ["static" & "relative"] was set up to
display multiple flags, separated by a "bar" '|'. However, this support is
incomplete--e.g., need_bar was never incremented; and currently, these two
flags are mutually exclusive. So remove the "bar" support, for now, and
only display one flag.
3) Use snprint() to format flags, so as not to overflow the buffer. Not
that it's ever happed, AFAIK.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:22 +02:00
|
|
|
p += snprintf(p, buffer + maxlen - p, "static");
|
|
|
|
else if (flags & MPOL_F_RELATIVE_NODES)
|
|
|
|
p += snprintf(p, buffer + maxlen - p, "relative");
|
mempolicy: add MPOL_F_STATIC_NODES flag
Add an optional mempolicy mode flag, MPOL_F_STATIC_NODES, that suppresses the
node remap when the policy is rebound.
Adds another member to struct mempolicy, nodemask_t user_nodemask, as part of
a union with cpuset_mems_allowed:
struct mempolicy {
...
union {
nodemask_t cpuset_mems_allowed;
nodemask_t user_nodemask;
} w;
}
that stores the the nodemask that the user passed when he or she created the
mempolicy via set_mempolicy() or mbind(). When using MPOL_F_STATIC_NODES,
which is passed with any mempolicy mode, the user's passed nodemask
intersected with the VMA or task's allowed nodes is always used when
determining the preferred node, setting the MPOL_BIND zonelist, or creating
the interleave nodemask. This happens whenever the policy is rebound,
including when a task's cpuset assignment changes or the cpuset's mems are
changed.
This creates an interesting side-effect in that it allows the mempolicy
"intent" to lie dormant and uneffected until it has access to the node(s) that
it desires. For example, if you currently ask for an interleaved policy over
a set of nodes that you do not have access to, the mempolicy is not created
and the task continues to use the previous policy. With this change, however,
it is possible to create the same mempolicy; it is only effected when access
to nodes in the nodemask is acquired.
It is also possible to mount tmpfs with the static nodemask behavior when
specifying a node or nodemask. To do this, simply add "=static" immediately
following the mempolicy mode at mount time:
mount -o remount mpol=interleave=static:1-3
Also removes mpol_check_policy() and folds its logic into mpol_new() since it
is now obsoleted. The unused vma_mpol_equal() is also removed.
Cc: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:12:27 +02:00
|
|
|
}
|
|
|
|
|
2006-01-08 10:01:02 +01:00
|
|
|
if (!nodes_empty(nodes)) {
|
|
|
|
if (buffer + maxlen < p + 2)
|
|
|
|
return -ENOSPC;
|
mempolicy: rework shmem mpol parsing and display
mm/shmem.c currently contains functions to parse and display memory policy
strings for the tmpfs 'mpol' mount option. Move this to mm/mempolicy.c with
the rest of the mempolicy support. With subsequent patches, we'll be able to
remove knowledge of the details [mode, flags, policy, ...] completely from
shmem.c
1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in
mm/mempolicy.c. Rework to use the policy_types[] array [used by
mpol_to_str()] to look up mode by name.
2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()
expects a pointer to a struct mempolicy, so temporarily construct one.
This will be replaced with a reference to a struct mempolicy in the tmpfs
superblock in a subsequent patch.
NOTE 1: I changed mpol_to_str() to use a colon ':' rather than an equal
sign '=' as the nodemask delimiter to match mpol_parse_str() and the
tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This
is a user visible change to numa_maps, but then the addition of the mode
flags already changed the display. It makes sense to me to have the mounts
and numa_maps display the policy in the same format. However, if anyone
objects strongly, I can pass the desired nodemask delimeter as an arg to
mpol_to_str().
Note 2: Like show_numa_map(), I don't check the return code from
mpol_to_str(). I do use a longer buffer than the one provided by
show_numa_map(), which seems to have sufficed so far.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:23 +02:00
|
|
|
*p++ = ':';
|
2006-01-08 10:01:02 +01:00
|
|
|
p += nodelist_scnprintf(p, buffer + maxlen - p, nodes);
|
|
|
|
}
|
|
|
|
return p - buffer;
|
|
|
|
}
|
|
|
|
|
|
|
|
struct numa_maps {
|
|
|
|
unsigned long pages;
|
|
|
|
unsigned long anon;
|
2006-03-07 00:42:53 +01:00
|
|
|
unsigned long active;
|
|
|
|
unsigned long writeback;
|
2006-01-08 10:01:02 +01:00
|
|
|
unsigned long mapcount_max;
|
2006-03-07 00:42:53 +01:00
|
|
|
unsigned long dirty;
|
|
|
|
unsigned long swapcache;
|
2006-01-08 10:01:02 +01:00
|
|
|
unsigned long node[MAX_NUMNODES];
|
|
|
|
};
|
|
|
|
|
2006-03-07 00:42:53 +01:00
|
|
|
static void gather_stats(struct page *page, void *private, int pte_dirty)
|
2006-01-08 10:01:02 +01:00
|
|
|
{
|
|
|
|
struct numa_maps *md = private;
|
|
|
|
int count = page_mapcount(page);
|
|
|
|
|
2006-03-07 00:42:53 +01:00
|
|
|
md->pages++;
|
|
|
|
if (pte_dirty || PageDirty(page))
|
|
|
|
md->dirty++;
|
2006-01-08 10:01:02 +01:00
|
|
|
|
2006-03-07 00:42:53 +01:00
|
|
|
if (PageSwapCache(page))
|
|
|
|
md->swapcache++;
|
2006-01-08 10:01:02 +01:00
|
|
|
|
Unevictable LRU Infrastructure
When the system contains lots of mlocked or otherwise unevictable pages,
the pageout code (kswapd) can spend lots of time scanning over these
pages. Worse still, the presence of lots of unevictable pages can confuse
kswapd into thinking that more aggressive pageout modes are required,
resulting in all kinds of bad behaviour.
Infrastructure to manage pages excluded from reclaim--i.e., hidden from
vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to
maintain "unevictable" pages on a separate per-zone LRU list, to "hide"
them from vmscan.
Kosaki Motohiro added the support for the memory controller unevictable
lru list.
Pages on the unevictable list have both PG_unevictable and PG_lru set.
Thus, PG_unevictable is analogous to and mutually exclusive with
PG_active--it specifies which LRU list the page is on.
The unevictable infrastructure is enabled by a new mm Kconfig option
[CONFIG_]UNEVICTABLE_LRU.
A new function 'page_evictable(page, vma)' in vmscan.c tests whether or
not a page may be evictable. Subsequent patches will add the various
!evictable tests. We'll want to keep these tests light-weight for use in
shrink_active_list() and, possibly, the fault path.
To avoid races between tasks putting pages [back] onto an LRU list and
tasks that might be moving the page from non-evictable to evictable state,
the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()'
-- tests the "evictability" of a page after placing it on the LRU, before
dropping the reference. If the page has become unevictable,
putback_lru_page() will redo the 'putback', thus moving the page to the
unevictable list. This way, we avoid "stranding" evictable pages on the
unevictable list.
[akpm@linux-foundation.org: fix fallout from out-of-order merge]
[riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build]
[nishimura@mxp.nes.nec.co.jp: remove redundant mapping check]
[kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework]
[kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c]
[kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure]
[kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch]
[kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 05:26:39 +02:00
|
|
|
if (PageActive(page) || PageUnevictable(page))
|
2006-03-07 00:42:53 +01:00
|
|
|
md->active++;
|
|
|
|
|
|
|
|
if (PageWriteback(page))
|
|
|
|
md->writeback++;
|
2006-01-08 10:01:02 +01:00
|
|
|
|
|
|
|
if (PageAnon(page))
|
|
|
|
md->anon++;
|
|
|
|
|
2006-03-07 00:42:53 +01:00
|
|
|
if (count > md->mapcount_max)
|
|
|
|
md->mapcount_max = count;
|
|
|
|
|
2006-01-08 10:01:02 +01:00
|
|
|
md->node[page_to_nid(page)]++;
|
|
|
|
}
|
|
|
|
|
2006-03-08 06:55:22 +01:00
|
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
2006-03-07 00:42:53 +01:00
|
|
|
static void check_huge_range(struct vm_area_struct *vma,
|
|
|
|
unsigned long start, unsigned long end,
|
|
|
|
struct numa_maps *md)
|
|
|
|
{
|
|
|
|
unsigned long addr;
|
|
|
|
struct page *page;
|
2008-07-24 06:27:41 +02:00
|
|
|
struct hstate *h = hstate_vma(vma);
|
|
|
|
unsigned long sz = huge_page_size(h);
|
2006-03-07 00:42:53 +01:00
|
|
|
|
2008-07-24 06:27:41 +02:00
|
|
|
for (addr = start; addr < end; addr += sz) {
|
|
|
|
pte_t *ptep = huge_pte_offset(vma->vm_mm,
|
|
|
|
addr & huge_page_mask(h));
|
2006-03-07 00:42:53 +01:00
|
|
|
pte_t pte;
|
|
|
|
|
|
|
|
if (!ptep)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
pte = *ptep;
|
|
|
|
if (pte_none(pte))
|
|
|
|
continue;
|
|
|
|
|
|
|
|
page = pte_page(pte);
|
|
|
|
if (!page)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
gather_stats(page, md, pte_dirty(*ptep));
|
|
|
|
}
|
|
|
|
}
|
2006-03-08 06:55:22 +01:00
|
|
|
#else
|
|
|
|
static inline void check_huge_range(struct vm_area_struct *vma,
|
|
|
|
unsigned long start, unsigned long end,
|
|
|
|
struct numa_maps *md)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#endif
|
2006-03-07 00:42:53 +01:00
|
|
|
|
mempolicy: mPOL_PREFERRED cleanups for "local allocation"
Here are a couple of "cleanups" for MPOL_PREFERRED behavior when
v.preferred_node < 0 -- i.e., "local allocation":
1) [do_]get_mempolicy() calls the now renamed get_policy_nodemask()
to fetch the nodemask associated with a policy. Currently,
get_policy_nodemask() returns the set of nodes with memory, when
the policy 'mode' is 'PREFERRED, and the preferred_node is < 0.
Change to return an empty nodemask, as this is what was specified
to achieve "local allocation".
2) When a task is moved into a [new] cpuset, mpol_rebind_policy() is
called to adjust any task and vma policy nodes to be valid in the
new cpuset. However, when the policy is MPOL_PREFERRED, and the
preferred_node is <0, no rebind is necessary. The "local allocation"
indication is valid in any cpuset. Existing code will "do the right
thing" because node_remap() will just return the argument node when
it is outside of the valid range of node ids. However, I think it is
clearer and cleaner to skip the remap explicitly in this case.
3) mpol_to_str() produces a printable, "human readable" string from a
struct mempolicy. For MPOL_PREFERRED with preferred_node <0, show
"local", as this indicates local allocation, as the task migrates
among nodes. Note that this matches the usage of "local allocation"
in libnuma() and numactl. Without this change, I believe that node_set()
[via set_bit()] will set bit 31, resulting in a misleading display.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:20 +02:00
|
|
|
/*
|
|
|
|
* Display pages allocated per node and memory policy via /proc.
|
|
|
|
*/
|
2006-01-08 10:01:02 +01:00
|
|
|
int show_numa_map(struct seq_file *m, void *v)
|
|
|
|
{
|
2006-06-26 09:25:55 +02:00
|
|
|
struct proc_maps_private *priv = m->private;
|
2006-01-08 10:01:02 +01:00
|
|
|
struct vm_area_struct *vma = v;
|
|
|
|
struct numa_maps *md;
|
2006-03-07 00:42:53 +01:00
|
|
|
struct file *file = vma->vm_file;
|
|
|
|
struct mm_struct *mm = vma->vm_mm;
|
Fix NUMA Memory Policy Reference Counting
This patch proposes fixes to the reference counting of memory policy in the
page allocation paths and in show_numa_map(). Extracted from my "Memory
Policy Cleanups and Enhancements" series as stand-alone.
Shared policy lookup [shmem] has always added a reference to the policy,
but this was never unrefed after page allocation or after formatting the
numa map data.
Default system policy should not require additional ref counting, nor
should the current task's task policy. However, show_numa_map() calls
get_vma_policy() to examine what may be [likely is] another task's policy.
The latter case needs protection against freeing of the policy.
This patch adds a reference count to a mempolicy returned by
get_vma_policy() when the policy is a vma policy or another task's
mempolicy. Again, shared policy is already reference counted on lookup. A
matching "unref" [__mpol_free()] is performed in alloc_page_vma() for
shared and vma policies, and in show_numa_map() for shared and another
task's mempolicy. We can call __mpol_free() directly, saving an admittedly
inexpensive inline NULL test, because we know we have a non-NULL policy.
Handling policy ref counts for hugepages is a bit trickier.
huge_zonelist() returns a zone list that might come from a shared or vma
'BIND policy. In this case, we should hold the reference until after the
huge page allocation in dequeue_hugepage(). The patch modifies
huge_zonelist() to return a pointer to the mempolicy if it needs to be
unref'd after allocation.
Kernel Build [16cpu, 32GB, ia64] - average of 10 runs:
w/o patch w/ refcount patch
Avg Std Devn Avg Std Devn
Real: 100.59 0.38 100.63 0.43
User: 1209.60 0.37 1209.91 0.31
System: 81.52 0.42 81.64 0.34
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 07:46:47 +02:00
|
|
|
struct mempolicy *pol;
|
2006-01-08 10:01:02 +01:00
|
|
|
int n;
|
|
|
|
char buffer[50];
|
|
|
|
|
2006-03-07 00:42:53 +01:00
|
|
|
if (!mm)
|
2006-01-08 10:01:02 +01:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
md = kzalloc(sizeof(struct numa_maps), GFP_KERNEL);
|
|
|
|
if (!md)
|
|
|
|
return 0;
|
|
|
|
|
Fix NUMA Memory Policy Reference Counting
This patch proposes fixes to the reference counting of memory policy in the
page allocation paths and in show_numa_map(). Extracted from my "Memory
Policy Cleanups and Enhancements" series as stand-alone.
Shared policy lookup [shmem] has always added a reference to the policy,
but this was never unrefed after page allocation or after formatting the
numa map data.
Default system policy should not require additional ref counting, nor
should the current task's task policy. However, show_numa_map() calls
get_vma_policy() to examine what may be [likely is] another task's policy.
The latter case needs protection against freeing of the policy.
This patch adds a reference count to a mempolicy returned by
get_vma_policy() when the policy is a vma policy or another task's
mempolicy. Again, shared policy is already reference counted on lookup. A
matching "unref" [__mpol_free()] is performed in alloc_page_vma() for
shared and vma policies, and in show_numa_map() for shared and another
task's mempolicy. We can call __mpol_free() directly, saving an admittedly
inexpensive inline NULL test, because we know we have a non-NULL policy.
Handling policy ref counts for hugepages is a bit trickier.
huge_zonelist() returns a zone list that might come from a shared or vma
'BIND policy. In this case, we should hold the reference until after the
huge page allocation in dequeue_hugepage(). The patch modifies
huge_zonelist() to return a pointer to the mempolicy if it needs to be
unref'd after allocation.
Kernel Build [16cpu, 32GB, ia64] - average of 10 runs:
w/o patch w/ refcount patch
Avg Std Devn Avg Std Devn
Real: 100.59 0.38 100.63 0.43
User: 1209.60 0.37 1209.91 0.31
System: 81.52 0.42 81.64 0.34
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 07:46:47 +02:00
|
|
|
pol = get_vma_policy(priv->task, vma, vma->vm_start);
|
mempolicy: use struct mempolicy pointer in shmem_sb_info
This patch replaces the mempolicy mode, mode_flags, and nodemask in the
shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.
This removes dependency on the details of mempolicy from shmem.c and hugetlbfs
inode.c and simplifies the interfaces.
mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a
pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the
returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context'
argument that causes the input nodemask to be stored in the w.user_nodemask of
the created mempolicy for use when the mempolicy is installed in a tmpfs inode
shared policy tree. At that time, any cpuset contextualization is applied to
the original input nodemask. This preserves the previous behavior where the
input nodemask was stored in the superblock. We can think of the returned
mempolicy as "context free".
Because mpol_parse_str() is now calling mpol_new(), we can remove from
mpol_to_str() the semantic checks that mpol_new() already performs.
Add 'no_context' parameter to mpol_to_str() to specify that it should format
the nodemask in w.user_nodemask for 'bind' and 'interleave' policies.
Change mpol_shared_policy_init() to take a pointer to a "context free" struct
mempolicy and to create a new, "contextualized" mempolicy using the mode,
mode_flags and user_nodemask from the input mempolicy.
Note: we know that the mempolicy passed to mpol_to_str() or
mpol_shared_policy_init() from a tmpfs superblock is "context free". This
is currently the only instance thereof. However, if we found more uses for
this concept, and introduced any ambiguity as to whether a mempolicy was
context free or not, we could add another internal mode flag to identify
context free mempolicies. Then, we could remove the 'no_context' argument
from mpol_to_str().
Added shmem_get_sbmpol() to return a reference counted superblock mempolicy,
if one exists, to pass to mpol_shared_policy_init(). We must add the
reference under the sb stat_lock to prevent races with replacement of the mpol
by remount. This reference is removed in mpol_shared_policy_init().
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: yet another build fix]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:26 +02:00
|
|
|
mpol_to_str(buffer, sizeof(buffer), pol, 0);
|
mempolicy: rework mempolicy Reference Counting [yet again]
After further discussion with Christoph Lameter, it has become clear that my
earlier attempts to clean up the mempolicy reference counting were a bit of
overkill in some areas, resulting in superflous ref/unref in what are usually
fast paths. In other areas, further inspection reveals that I botched the
unref for interleave policies.
A separate patch, suitable for upstream/stable trees, fixes up the known
errors in the previous attempt to fix reference counting.
This patch reworks the memory policy referencing counting and, one hopes,
simplifies the code. Maybe I'll get it right this time.
See the update to the numa_memory_policy.txt document for a discussion of
memory policy reference counting that motivates this patch.
Summary:
Lookup of mempolicy, based on (vma, address) need only add a reference for
shared policy, and we need only unref the policy when finished for shared
policies. So, this patch backs out all of the unneeded extra reference
counting added by my previous attempt. It then unrefs only shared policies
when we're finished with them, using the mpol_cond_put() [conditional put]
helper function introduced by this patch.
Note that shmem_swapin() calls read_swap_cache_async() with a dummy vma
containing just the policy. read_swap_cache_async() can call alloc_page_vma()
multiple times, so we can't let alloc_page_vma() unref the shared policy in
this case. To avoid this, we make a copy of any non-null shared policy and
remove the MPOL_F_SHARED flag from the copy. This copy occurs before reading
a page [or multiple pages] from swap, so the overhead should not be an issue
here.
I introduced a new static inline function "mpol_cond_copy()" to copy the
shared policy to an on-stack policy and remove the flags that would require a
conditional free. The current implementation of mpol_cond_copy() assumes that
the struct mempolicy contains no pointers to dynamically allocated structures
that must be duplicated or reference counted during copy.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:16 +02:00
|
|
|
mpol_cond_put(pol);
|
2006-03-07 00:42:53 +01:00
|
|
|
|
|
|
|
seq_printf(m, "%08lx %s", vma->vm_start, buffer);
|
|
|
|
|
|
|
|
if (file) {
|
|
|
|
seq_printf(m, " file=");
|
2008-02-15 04:38:43 +01:00
|
|
|
seq_path(m, &file->f_path, "\n\t= ");
|
2006-03-07 00:42:53 +01:00
|
|
|
} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
|
|
|
|
seq_printf(m, " heap");
|
|
|
|
} else if (vma->vm_start <= mm->start_stack &&
|
|
|
|
vma->vm_end >= mm->start_stack) {
|
|
|
|
seq_printf(m, " stack");
|
|
|
|
}
|
|
|
|
|
|
|
|
if (is_vm_hugetlb_page(vma)) {
|
|
|
|
check_huge_range(vma, vma->vm_start, vma->vm_end, md);
|
|
|
|
seq_printf(m, " huge");
|
|
|
|
} else {
|
2006-03-02 11:54:37 +01:00
|
|
|
check_pgd_range(vma, vma->vm_start, vma->vm_end,
|
2007-10-16 10:25:35 +02:00
|
|
|
&node_states[N_HIGH_MEMORY], MPOL_MF_STATS, md);
|
2006-03-07 00:42:53 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
if (!md->pages)
|
|
|
|
goto out;
|
2006-01-08 10:01:02 +01:00
|
|
|
|
2006-03-07 00:42:53 +01:00
|
|
|
if (md->anon)
|
|
|
|
seq_printf(m," anon=%lu",md->anon);
|
2006-01-08 10:01:02 +01:00
|
|
|
|
2006-03-07 00:42:53 +01:00
|
|
|
if (md->dirty)
|
|
|
|
seq_printf(m," dirty=%lu",md->dirty);
|
2006-01-08 10:01:02 +01:00
|
|
|
|
2006-03-07 00:42:53 +01:00
|
|
|
if (md->pages != md->anon && md->pages != md->dirty)
|
|
|
|
seq_printf(m, " mapped=%lu", md->pages);
|
2006-01-08 10:01:02 +01:00
|
|
|
|
2006-03-07 00:42:53 +01:00
|
|
|
if (md->mapcount_max > 1)
|
|
|
|
seq_printf(m, " mapmax=%lu", md->mapcount_max);
|
2006-01-08 10:01:02 +01:00
|
|
|
|
2006-03-07 00:42:53 +01:00
|
|
|
if (md->swapcache)
|
|
|
|
seq_printf(m," swapcache=%lu", md->swapcache);
|
|
|
|
|
|
|
|
if (md->active < md->pages && !is_vm_hugetlb_page(vma))
|
|
|
|
seq_printf(m," active=%lu", md->active);
|
|
|
|
|
|
|
|
if (md->writeback)
|
|
|
|
seq_printf(m," writeback=%lu", md->writeback);
|
|
|
|
|
2007-10-16 10:25:35 +02:00
|
|
|
for_each_node_state(n, N_HIGH_MEMORY)
|
2006-03-07 00:42:53 +01:00
|
|
|
if (md->node[n])
|
|
|
|
seq_printf(m, " N%d=%lu", n, md->node[n]);
|
|
|
|
out:
|
|
|
|
seq_putc(m, '\n');
|
2006-01-08 10:01:02 +01:00
|
|
|
kfree(md);
|
|
|
|
|
|
|
|
if (m->count < m->size)
|
2006-06-26 09:25:55 +02:00
|
|
|
m->version = (vma != priv->tail_vma) ? vma->vm_start : 0;
|
2006-01-08 10:01:02 +01:00
|
|
|
return 0;
|
|
|
|
}
|