2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* NUMA memory policies for Linux.
|
|
|
|
|
* Copyright 2003,2004 Andi Kleen SuSE Labs
|
|
|
|
|
*/
|
2012-10-13 17:46:48 +08:00
|
|
|
#ifndef _LINUX_MEMPOLICY_H
|
|
|
|
|
#define _LINUX_MEMPOLICY_H 1
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
#include <linux/mmzone.h>
|
|
|
|
|
#include <linux/slab.h>
|
|
|
|
|
#include <linux/rbtree.h>
|
|
|
|
|
#include <linux/spinlock.h>
|
2005-10-30 09:15:48 +08:00
|
|
|
#include <linux/nodemask.h>
|
2008-07-24 12:28:22 +08:00
|
|
|
#include <linux/pagemap.h>
|
2012-10-13 17:46:48 +08:00
|
|
|
#include <uapi/linux/mempolicy.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-06-08 15:43:41 +08:00
|
|
|
struct mm_struct;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
#ifdef CONFIG_NUMA
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Describe a memory policy.
|
|
|
|
|
*
|
|
|
|
|
* A mempolicy can be either associated with a process or with a VMA.
|
|
|
|
|
* For VMA related allocations the VMA policy is preferred, otherwise
|
|
|
|
|
* the process policy is used. Interrupts ignore the memory policy
|
|
|
|
|
* of the current process.
|
|
|
|
|
*
|
|
|
|
|
* Locking policy for interlave:
|
|
|
|
|
* In process context there is no locking because only the process accesses
|
|
|
|
|
* its own state. All vma manipulation is somewhat protected by a down_read on
|
2005-10-30 09:16:41 +08:00
|
|
|
* mmap_sem.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
|
* Freeing policy:
|
2008-04-28 17:12:18 +08:00
|
|
|
* Mempolicy objects are reference counted. A mempolicy will be freed when
|
2008-04-28 17:13:08 +08:00
|
|
|
* mpol_put() decrements the reference count to zero.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
2008-04-28 17:13:09 +08:00
|
|
|
* Duplicating policy objects:
|
|
|
|
|
* mpol_dup() allocates a new mempolicy and copies the specified mempolicy
|
2008-04-28 17:12:18 +08:00
|
|
|
* to the new storage. The reference count of the new object is initialized
|
2008-04-28 17:13:09 +08:00
|
|
|
* to 1, representing the caller of mpol_dup().
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
struct mempolicy {
|
|
|
|
|
atomic_t refcnt;
|
2008-04-28 17:13:12 +08:00
|
|
|
unsigned short mode; /* See MPOL_* above */
|
2008-04-28 17:12:25 +08:00
|
|
|
unsigned short flags; /* See set_mempolicy() MPOL_F_* above */
|
2005-04-17 06:20:36 +08:00
|
|
|
union {
|
|
|
|
|
short preferred_node; /* preferred */
|
2008-04-28 17:12:18 +08:00
|
|
|
nodemask_t nodes; /* interleave/bind */
|
2005-04-17 06:20:36 +08:00
|
|
|
/* undefined for default */
|
|
|
|
|
} v;
|
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 17:12:27 +08:00
|
|
|
union {
|
|
|
|
|
nodemask_t cpuset_mems_allowed; /* relative to these nodes */
|
|
|
|
|
nodemask_t user_nodemask; /* nodemask passed by user */
|
|
|
|
|
} w;
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Support for managing mempolicy data objects (clone, copy, destroy)
|
|
|
|
|
* The default fast path of a NULL MPOL_DEFAULT policy is always inlined.
|
|
|
|
|
*/
|
|
|
|
|
|
2008-04-28 17:13:08 +08:00
|
|
|
extern void __mpol_put(struct mempolicy *pol);
|
|
|
|
|
static inline void mpol_put(struct mempolicy *pol)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
if (pol)
|
2008-04-28 17:13:08 +08:00
|
|
|
__mpol_put(pol);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
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 17:13:16 +08:00
|
|
|
/*
|
|
|
|
|
* Does mempolicy pol need explicit unref after use?
|
|
|
|
|
* Currently only needed for shared policies.
|
|
|
|
|
*/
|
|
|
|
|
static inline int mpol_needs_cond_ref(struct mempolicy *pol)
|
|
|
|
|
{
|
|
|
|
|
return (pol && (pol->flags & MPOL_F_SHARED));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void mpol_cond_put(struct mempolicy *pol)
|
|
|
|
|
{
|
|
|
|
|
if (mpol_needs_cond_ref(pol))
|
|
|
|
|
__mpol_put(pol);
|
|
|
|
|
}
|
|
|
|
|
|
2008-04-28 17:13:09 +08:00
|
|
|
extern struct mempolicy *__mpol_dup(struct mempolicy *pol);
|
|
|
|
|
static inline struct mempolicy *mpol_dup(struct mempolicy *pol)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
if (pol)
|
2008-04-28 17:13:09 +08:00
|
|
|
pol = __mpol_dup(pol);
|
2005-04-17 06:20:36 +08:00
|
|
|
return pol;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define vma_policy(vma) ((vma)->vm_policy)
|
|
|
|
|
|
|
|
|
|
static inline void mpol_get(struct mempolicy *pol)
|
|
|
|
|
{
|
|
|
|
|
if (pol)
|
|
|
|
|
atomic_inc(&pol->refcnt);
|
|
|
|
|
}
|
|
|
|
|
|
2012-01-11 07:08:21 +08:00
|
|
|
extern bool __mpol_equal(struct mempolicy *a, struct mempolicy *b);
|
|
|
|
|
static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
if (a == b)
|
2012-01-11 07:08:21 +08:00
|
|
|
return true;
|
2005-04-17 06:20:36 +08:00
|
|
|
return __mpol_equal(a, b);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Tree of shared policies for a shared memory region.
|
|
|
|
|
* Maintain the policies in a pseudo mm that contains vmas. The vmas
|
|
|
|
|
* carry the policy. As a special twist the pseudo mm is indexed in pages, not
|
|
|
|
|
* bytes, so that we can work with shared memory segments bigger than
|
|
|
|
|
* unsigned long.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
struct sp_node {
|
|
|
|
|
struct rb_node nd;
|
|
|
|
|
unsigned long start, end;
|
|
|
|
|
struct mempolicy *policy;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct shared_policy {
|
|
|
|
|
struct rb_root root;
|
2012-12-22 07:10:25 +08:00
|
|
|
spinlock_t lock;
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
|
|
|
|
|
2013-09-12 05:20:14 +08:00
|
|
|
int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst);
|
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 17:13:26 +08:00
|
|
|
void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol);
|
2005-04-17 06:20:36 +08:00
|
|
|
int mpol_set_shared_policy(struct shared_policy *info,
|
|
|
|
|
struct vm_area_struct *vma,
|
|
|
|
|
struct mempolicy *new);
|
|
|
|
|
void mpol_free_shared_policy(struct shared_policy *p);
|
|
|
|
|
struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
|
|
|
|
|
unsigned long idx);
|
|
|
|
|
|
2011-05-25 08:12:41 +08:00
|
|
|
struct mempolicy *get_vma_policy(struct task_struct *tsk,
|
|
|
|
|
struct vm_area_struct *vma, unsigned long addr);
|
2013-10-07 18:29:09 +08:00
|
|
|
bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma);
|
2011-05-25 08:12:41 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
extern void numa_default_policy(void);
|
|
|
|
|
extern void numa_policy_init(void);
|
mempolicy: restructure rebinding-mempolicy functions
Nick Piggin reported that the allocator may see an empty nodemask when
changing cpuset's mems[1]. It happens only on the kernel that do not do
atomic nodemask_t stores. (MAX_NUMNODES > BITS_PER_LONG)
But I found that there is also a problem on the kernel that can do atomic
nodemask_t stores. The problem is that the allocator can't find a node to
alloc page when changing cpuset's mems though there is a lot of free
memory. The reason is like this:
(mpol: mempolicy)
task1 task1's mpol task2
alloc page 1
alloc on node0? NO 1
1 change mems from 1 to 0
1 rebind task1's mpol
0-1 set new bits
0 clear disallowed bits
alloc on node1? NO 0
...
can't alloc page
goto oom
I can use the attached program reproduce it by the following step:
# mkdir /dev/cpuset
# mount -t cpuset cpuset /dev/cpuset
# mkdir /dev/cpuset/1
# echo `cat /dev/cpuset/cpus` > /dev/cpuset/1/cpus
# echo `cat /dev/cpuset/mems` > /dev/cpuset/1/mems
# echo $$ > /dev/cpuset/1/tasks
# numactl --membind=`cat /dev/cpuset/mems` ./cpuset_mem_hog <nr_tasks> &
<nr_tasks> = max(nr_cpus - 1, 1)
# killall -s SIGUSR1 cpuset_mem_hog
# ./change_mems.sh
several hours later, oom will happen though there is a lot of free memory.
This patchset fixes this problem by expanding the nodes range first(set
newly allowed bits) and shrink it lazily(clear newly disallowed bits). So
we use a variable to tell the write-side task that read-side task is
reading nodemask, and the write-side task clears newly disallowed nodes
after read-side task ends the current memory allocation.
This patch:
In order to fix no node to alloc memory, when we want to update mempolicy
and mems_allowed, we expand the set of nodes first (set all the newly
nodes) and shrink the set of nodes lazily(clean disallowed nodes), But the
mempolicy's rebind functions may breaks the expanding.
So we restructure the mempolicy's rebind functions and split the rebind
work to two steps, just like the update of cpuset's mems: The 1st step:
expand the set of the mempolicy's nodes. The 2nd step: shrink the set of
the mempolicy's nodes. It is used when there is no real lock to protect
the mempolicy in the read-side. Otherwise we can do rebind work at once.
In order to implement it, we define
enum mpol_rebind_step {
MPOL_REBIND_ONCE,
MPOL_REBIND_STEP1,
MPOL_REBIND_STEP2,
MPOL_REBIND_NSTEP,
};
If the mempolicy needn't be updated by two steps, we can pass
MPOL_REBIND_ONCE to the rebind functions. Or we can pass
MPOL_REBIND_STEP1 to do the first step of the rebind work and pass
MPOL_REBIND_STEP2 to do the second step work.
Besides that, it maybe long time between these two step and we have to
release the lock that protects mempolicy and mems_allowed. If we hold the
lock once again, we must check whether the current mempolicy is under the
rebinding (the first step has been done) or not, because the task may
alloc a new mempolicy when we don't hold the lock. So we defined the
following flag to identify it:
#define MPOL_F_REBINDING (1 << 2)
The new functions will be used in the next patch.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Paul Menage <menage@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ravikiran Thirumalai <kiran@scalex86.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-25 05:32:07 +08:00
|
|
|
extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new,
|
|
|
|
|
enum mpol_rebind_step step);
|
[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 17:01:59 +08:00
|
|
|
extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);
|
2006-03-24 19:16:08 +08:00
|
|
|
extern void mpol_fix_fork_child_flag(struct task_struct *p);
|
[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 17:01:59 +08:00
|
|
|
|
2006-01-06 16:10:46 +08:00
|
|
|
extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
|
2008-04-28 17:12:18 +08:00
|
|
|
unsigned long addr, gfp_t gfp_flags,
|
|
|
|
|
struct mempolicy **mpol, nodemask_t **nodemask);
|
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 09:58:21 +08:00
|
|
|
extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
|
2010-08-10 08:18:52 +08:00
|
|
|
extern bool mempolicy_nodemask_intersects(struct task_struct *tsk,
|
|
|
|
|
const nodemask_t *mask);
|
2012-06-09 17:40:03 +08:00
|
|
|
extern unsigned slab_node(void);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-09-26 14:31:18 +08:00
|
|
|
extern enum zone_type policy_zone;
|
2006-01-06 16:11:17 +08:00
|
|
|
|
2006-09-26 14:31:18 +08:00
|
|
|
static inline void check_highest_zone(enum zone_type k)
|
2006-01-06 16:11:17 +08:00
|
|
|
{
|
2007-08-23 05:02:05 +08:00
|
|
|
if (k > policy_zone && k != ZONE_MOVABLE)
|
2006-01-06 16:11:17 +08:00
|
|
|
policy_zone = k;
|
|
|
|
|
}
|
|
|
|
|
|
2012-05-30 06:06:24 +08:00
|
|
|
int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
|
|
|
|
|
const nodemask_t *to, int flags);
|
2006-01-08 17:00:51 +08:00
|
|
|
|
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 17:13:23 +08:00
|
|
|
|
|
|
|
|
#ifdef CONFIG_TMPFS
|
2013-01-02 18:04:23 +08:00
|
|
|
extern int mpol_parse_str(char *str, struct mempolicy **mpol);
|
2011-05-25 08:12:46 +08:00
|
|
|
#endif
|
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 17:13:23 +08:00
|
|
|
|
2013-11-13 07:07:28 +08:00
|
|
|
extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol);
|
2008-07-24 12:28:22 +08:00
|
|
|
|
|
|
|
|
/* Check if a vma is migratable */
|
|
|
|
|
static inline int vma_migratable(struct vm_area_struct *vma)
|
|
|
|
|
{
|
2013-09-12 05:22:08 +08:00
|
|
|
if (vma->vm_flags & (VM_IO | VM_PFNMAP))
|
2008-07-24 12:28:22 +08:00
|
|
|
return 0;
|
|
|
|
|
/*
|
|
|
|
|
* Migration allocates pages in the highest zone. If we cannot
|
|
|
|
|
* do so then migration (at least from node to node) is not
|
|
|
|
|
* possible.
|
|
|
|
|
*/
|
|
|
|
|
if (vma->vm_file &&
|
|
|
|
|
gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping))
|
|
|
|
|
< policy_zone)
|
|
|
|
|
return 0;
|
|
|
|
|
return 1;
|
|
|
|
|
}
|
|
|
|
|
|
2012-10-25 20:16:30 +08:00
|
|
|
extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long);
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#else
|
|
|
|
|
|
|
|
|
|
struct mempolicy {};
|
|
|
|
|
|
2012-01-11 07:08:21 +08:00
|
|
|
static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2012-01-11 07:08:21 +08:00
|
|
|
return true;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2008-04-28 17:13:08 +08:00
|
|
|
static inline void mpol_put(struct mempolicy *p)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
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 17:13:16 +08:00
|
|
|
static inline void mpol_cond_put(struct mempolicy *pol)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline void mpol_get(struct mempolicy *pol)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
struct shared_policy {};
|
|
|
|
|
|
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 17:13:26 +08:00
|
|
|
static inline void mpol_shared_policy_init(struct shared_policy *sp,
|
|
|
|
|
struct mempolicy *mpol)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void mpol_free_shared_policy(struct shared_policy *p)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define vma_policy(vma) NULL
|
2013-09-12 05:20:14 +08:00
|
|
|
|
|
|
|
|
static inline int
|
|
|
|
|
vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
|
|
|
|
|
{
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
static inline void numa_policy_init(void)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void numa_default_policy(void)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
[PATCH] cpuset: numa_policy_rebind cleanup
Cleanup, reorganize and make more robust the mempolicy.c code to rebind
mempolicies relative to the containing cpuset after a tasks memory placement
changes.
The real motivator for this cleanup patch is to lay more groundwork for the
upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's
after the containing cpuset memory placement changes.
NUMA mempolicies are constrained by the cpuset their task is a member of.
When either (1) a task is moved to a different cpuset, or (2) the 'mems'
mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded
node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to
be recalculated, relative to their new cpuset placement.
The old code used an unreliable method of determining what was the old
mems_allowed constraining the mempolicy. It just looked at the tasks
mems_allowed value. This sort of worked with the present code, that just
rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken,
referring to the old nodes. But in an upcoming patch, the vma mempolicies
will be rebound as well. Then the order in which the various task and vma
mempolicies are updated will no longer be deterministic, and one can no longer
count on the task->mems_allowed holding the old value for as long as needed.
It's not even clear if the current code was guaranteed to work reliably for
task mempolicies.
So I added a mems_allowed field to each mempolicy, stating exactly what
mems_allowed the policy is relative to, and updated synchronously and reliably
anytime that the mempolicy is rebound.
Also removed a useless wrapper routine, numa_policy_rebind(), and had its
caller, cpuset_update_task_memory_state(), call directly to the rewritten
policy_rebind() routine, and made that rebind routine extern instead of
static, and added a "mpol_" prefix to its name, making it
mpol_rebind_policy().
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 17:01:56 +08:00
|
|
|
static inline void mpol_rebind_task(struct task_struct *tsk,
|
mempolicy: restructure rebinding-mempolicy functions
Nick Piggin reported that the allocator may see an empty nodemask when
changing cpuset's mems[1]. It happens only on the kernel that do not do
atomic nodemask_t stores. (MAX_NUMNODES > BITS_PER_LONG)
But I found that there is also a problem on the kernel that can do atomic
nodemask_t stores. The problem is that the allocator can't find a node to
alloc page when changing cpuset's mems though there is a lot of free
memory. The reason is like this:
(mpol: mempolicy)
task1 task1's mpol task2
alloc page 1
alloc on node0? NO 1
1 change mems from 1 to 0
1 rebind task1's mpol
0-1 set new bits
0 clear disallowed bits
alloc on node1? NO 0
...
can't alloc page
goto oom
I can use the attached program reproduce it by the following step:
# mkdir /dev/cpuset
# mount -t cpuset cpuset /dev/cpuset
# mkdir /dev/cpuset/1
# echo `cat /dev/cpuset/cpus` > /dev/cpuset/1/cpus
# echo `cat /dev/cpuset/mems` > /dev/cpuset/1/mems
# echo $$ > /dev/cpuset/1/tasks
# numactl --membind=`cat /dev/cpuset/mems` ./cpuset_mem_hog <nr_tasks> &
<nr_tasks> = max(nr_cpus - 1, 1)
# killall -s SIGUSR1 cpuset_mem_hog
# ./change_mems.sh
several hours later, oom will happen though there is a lot of free memory.
This patchset fixes this problem by expanding the nodes range first(set
newly allowed bits) and shrink it lazily(clear newly disallowed bits). So
we use a variable to tell the write-side task that read-side task is
reading nodemask, and the write-side task clears newly disallowed nodes
after read-side task ends the current memory allocation.
This patch:
In order to fix no node to alloc memory, when we want to update mempolicy
and mems_allowed, we expand the set of nodes first (set all the newly
nodes) and shrink the set of nodes lazily(clean disallowed nodes), But the
mempolicy's rebind functions may breaks the expanding.
So we restructure the mempolicy's rebind functions and split the rebind
work to two steps, just like the update of cpuset's mems: The 1st step:
expand the set of the mempolicy's nodes. The 2nd step: shrink the set of
the mempolicy's nodes. It is used when there is no real lock to protect
the mempolicy in the read-side. Otherwise we can do rebind work at once.
In order to implement it, we define
enum mpol_rebind_step {
MPOL_REBIND_ONCE,
MPOL_REBIND_STEP1,
MPOL_REBIND_STEP2,
MPOL_REBIND_NSTEP,
};
If the mempolicy needn't be updated by two steps, we can pass
MPOL_REBIND_ONCE to the rebind functions. Or we can pass
MPOL_REBIND_STEP1 to do the first step of the rebind work and pass
MPOL_REBIND_STEP2 to do the second step work.
Besides that, it maybe long time between these two step and we have to
release the lock that protects mempolicy and mems_allowed. If we hold the
lock once again, we must check whether the current mempolicy is under the
rebinding (the first step has been done) or not, because the task may
alloc a new mempolicy when we don't hold the lock. So we defined the
following flag to identify it:
#define MPOL_F_REBINDING (1 << 2)
The new functions will be used in the next patch.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Paul Menage <menage@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ravikiran Thirumalai <kiran@scalex86.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-25 05:32:07 +08:00
|
|
|
const nodemask_t *new,
|
|
|
|
|
enum mpol_rebind_step step)
|
[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 07:02:36 +08:00
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
[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 17:01:59 +08:00
|
|
|
static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
2006-01-06 16:10:46 +08:00
|
|
|
static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
|
2008-04-28 17:12:18 +08:00
|
|
|
unsigned long addr, gfp_t gfp_flags,
|
|
|
|
|
struct mempolicy **mpol, nodemask_t **nodemask)
|
2006-01-06 16:10:46 +08:00
|
|
|
{
|
2008-04-28 17:12:18 +08:00
|
|
|
*mpol = NULL;
|
|
|
|
|
*nodemask = NULL;
|
2008-04-28 17:12:14 +08:00
|
|
|
return node_zonelist(0, gfp_flags);
|
2006-01-06 16:10:46 +08:00
|
|
|
}
|
|
|
|
|
|
2010-08-10 08:18:52 +08:00
|
|
|
static inline bool init_nodemask_of_mempolicy(nodemask_t *m)
|
|
|
|
|
{
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
|
2012-05-30 06:06:24 +08:00
|
|
|
static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
|
|
|
|
|
const nodemask_t *to, int flags)
|
[PATCH] cpusets: swap migration interface
Add a boolean "memory_migrate" to each cpuset, represented by a file
containing "0" or "1" in each directory below /dev/cpuset.
It defaults to false (file contains "0"). It can be set true by writing
"1" to the file.
If true, then anytime that a task is attached to the cpuset so marked, the
pages of that task will be moved to that cpuset, preserving, to the extent
practical, the cpuset-relative placement of the pages.
Also anytime that a cpuset so marked has its memory placement changed (by
writing to its "mems" file), the tasks in that cpuset will have their pages
moved to the cpusets new nodes, preserving, to the extent practical, the
cpuset-relative placement of the moved pages.
Signed-off-by: Paul Jackson <pj@sgi.com>
Cc: Christoph Lameter <christoph@lameter.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:56 +08:00
|
|
|
{
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2006-01-06 16:11:17 +08:00
|
|
|
static inline void check_highest_zone(int k)
|
|
|
|
|
{
|
|
|
|
|
}
|
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 17:13:23 +08:00
|
|
|
|
|
|
|
|
#ifdef CONFIG_TMPFS
|
2013-01-02 18:04:23 +08:00
|
|
|
static inline int mpol_parse_str(char *str, struct mempolicy **mpol)
|
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 17:13:23 +08:00
|
|
|
{
|
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 17:13:26 +08:00
|
|
|
return 1; /* error */
|
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 17:13:23 +08:00
|
|
|
}
|
2011-05-25 08:12:46 +08:00
|
|
|
#endif
|
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 17:13:23 +08:00
|
|
|
|
2012-10-25 20:16:30 +08:00
|
|
|
static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma,
|
|
|
|
|
unsigned long address)
|
|
|
|
|
{
|
|
|
|
|
return -1; /* no node preference */
|
|
|
|
|
}
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif /* CONFIG_NUMA */
|
|
|
|
|
#endif
|