2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-24 05:04:00 +08:00
linux-next/include/linux/mempolicy.h
Lee Schermerhorn 06808b0827 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 08:53:12 -08:00

363 lines
9.0 KiB
C

#ifndef _LINUX_MEMPOLICY_H
#define _LINUX_MEMPOLICY_H 1
#include <linux/errno.h>
/*
* NUMA memory policies for Linux.
* Copyright 2003,2004 Andi Kleen SuSE Labs
*/
/*
* Both the MPOL_* mempolicy mode and the MPOL_F_* optional mode flags are
* passed by the user to either set_mempolicy() or mbind() in an 'int' actual.
* The MPOL_MODE_FLAGS macro determines the legal set of optional mode flags.
*/
/* Policies */
enum {
MPOL_DEFAULT,
MPOL_PREFERRED,
MPOL_BIND,
MPOL_INTERLEAVE,
MPOL_MAX, /* always last member of enum */
};
/* Flags for set_mempolicy */
#define MPOL_F_STATIC_NODES (1 << 15)
#define MPOL_F_RELATIVE_NODES (1 << 14)
/*
* MPOL_MODE_FLAGS is the union of all possible optional mode flags passed to
* either set_mempolicy() or mbind().
*/
#define MPOL_MODE_FLAGS (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES)
/* Flags for get_mempolicy */
#define MPOL_F_NODE (1<<0) /* return next IL mode instead of node mask */
#define MPOL_F_ADDR (1<<1) /* look up vma using address */
#define MPOL_F_MEMS_ALLOWED (1<<2) /* return allowed memories */
/* Flags for mbind */
#define MPOL_MF_STRICT (1<<0) /* Verify existing pages in the mapping */
#define MPOL_MF_MOVE (1<<1) /* Move pages owned by this process to conform to mapping */
#define MPOL_MF_MOVE_ALL (1<<2) /* Move every page to conform to mapping */
#define MPOL_MF_INTERNAL (1<<3) /* Internal flags start here */
/*
* Internal flags that share the struct mempolicy flags word with
* "mode flags". These flags are allocated from bit 0 up, as they
* are never OR'ed into the mode in mempolicy API arguments.
*/
#define MPOL_F_SHARED (1 << 0) /* identify shared policies */
#define MPOL_F_LOCAL (1 << 1) /* preferred local allocation */
#ifdef __KERNEL__
#include <linux/mmzone.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/spinlock.h>
#include <linux/nodemask.h>
#include <linux/pagemap.h>
struct mm_struct;
#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
* mmap_sem.
*
* Freeing policy:
* Mempolicy objects are reference counted. A mempolicy will be freed when
* mpol_put() decrements the reference count to zero.
*
* Duplicating policy objects:
* mpol_dup() allocates a new mempolicy and copies the specified mempolicy
* to the new storage. The reference count of the new object is initialized
* to 1, representing the caller of mpol_dup().
*/
struct mempolicy {
atomic_t refcnt;
unsigned short mode; /* See MPOL_* above */
unsigned short flags; /* See set_mempolicy() MPOL_F_* above */
union {
short preferred_node; /* preferred */
nodemask_t nodes; /* interleave/bind */
/* undefined for default */
} v;
union {
nodemask_t cpuset_mems_allowed; /* relative to these nodes */
nodemask_t user_nodemask; /* nodemask passed by user */
} w;
};
/*
* Support for managing mempolicy data objects (clone, copy, destroy)
* The default fast path of a NULL MPOL_DEFAULT policy is always inlined.
*/
extern void __mpol_put(struct mempolicy *pol);
static inline void mpol_put(struct mempolicy *pol)
{
if (pol)
__mpol_put(pol);
}
/*
* 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);
}
extern struct mempolicy *__mpol_cond_copy(struct mempolicy *tompol,
struct mempolicy *frompol);
static inline struct mempolicy *mpol_cond_copy(struct mempolicy *tompol,
struct mempolicy *frompol)
{
if (!frompol)
return frompol;
return __mpol_cond_copy(tompol, frompol);
}
extern struct mempolicy *__mpol_dup(struct mempolicy *pol);
static inline struct mempolicy *mpol_dup(struct mempolicy *pol)
{
if (pol)
pol = __mpol_dup(pol);
return pol;
}
#define vma_policy(vma) ((vma)->vm_policy)
#define vma_set_policy(vma, pol) ((vma)->vm_policy = (pol))
static inline void mpol_get(struct mempolicy *pol)
{
if (pol)
atomic_inc(&pol->refcnt);
}
extern int __mpol_equal(struct mempolicy *a, struct mempolicy *b);
static inline int mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
if (a == b)
return 1;
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;
spinlock_t lock;
};
void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol);
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);
extern void numa_default_policy(void);
extern void numa_policy_init(void);
extern void mpol_rebind_task(struct task_struct *tsk,
const nodemask_t *new);
extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);
extern void mpol_fix_fork_child_flag(struct task_struct *p);
extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
unsigned long addr, gfp_t gfp_flags,
struct mempolicy **mpol, nodemask_t **nodemask);
extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
extern unsigned slab_node(struct mempolicy *policy);
extern enum zone_type policy_zone;
static inline void check_highest_zone(enum zone_type k)
{
if (k > policy_zone && k != ZONE_MOVABLE)
policy_zone = k;
}
int do_migrate_pages(struct mm_struct *mm,
const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags);
#ifdef CONFIG_TMPFS
extern int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context);
extern int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol,
int no_context);
#endif
/* Check if a vma is migratable */
static inline int vma_migratable(struct vm_area_struct *vma)
{
if (vma->vm_flags & (VM_IO|VM_HUGETLB|VM_PFNMAP|VM_RESERVED))
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;
}
#else
struct mempolicy {};
static inline int mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
return 1;
}
static inline void mpol_put(struct mempolicy *p)
{
}
static inline void mpol_cond_put(struct mempolicy *pol)
{
}
static inline struct mempolicy *mpol_cond_copy(struct mempolicy *to,
struct mempolicy *from)
{
return from;
}
static inline void mpol_get(struct mempolicy *pol)
{
}
static inline struct mempolicy *mpol_dup(struct mempolicy *old)
{
return NULL;
}
struct shared_policy {};
static inline int mpol_set_shared_policy(struct shared_policy *info,
struct vm_area_struct *vma,
struct mempolicy *new)
{
return -EINVAL;
}
static inline void mpol_shared_policy_init(struct shared_policy *sp,
struct mempolicy *mpol)
{
}
static inline void mpol_free_shared_policy(struct shared_policy *p)
{
}
static inline struct mempolicy *
mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
{
return NULL;
}
#define vma_policy(vma) NULL
#define vma_set_policy(vma, pol) do {} while(0)
static inline void numa_policy_init(void)
{
}
static inline void numa_default_policy(void)
{
}
static inline void mpol_rebind_task(struct task_struct *tsk,
const nodemask_t *new)
{
}
static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
{
}
static inline void mpol_fix_fork_child_flag(struct task_struct *p)
{
}
static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
unsigned long addr, gfp_t gfp_flags,
struct mempolicy **mpol, nodemask_t **nodemask)
{
*mpol = NULL;
*nodemask = NULL;
return node_zonelist(0, gfp_flags);
}
static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; }
static inline int do_migrate_pages(struct mm_struct *mm,
const nodemask_t *from_nodes,
const nodemask_t *to_nodes, int flags)
{
return 0;
}
static inline void check_highest_zone(int k)
{
}
#ifdef CONFIG_TMPFS
static inline int mpol_parse_str(char *str, struct mempolicy **mpol,
int no_context)
{
return 1; /* error */
}
static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol,
int no_context)
{
return 0;
}
#endif
#endif /* CONFIG_NUMA */
#endif /* __KERNEL__ */
#endif