linux-stable/include/linux/mempolicy.h
Aneesh Kumar K.V c6018b4b25 mm/mempolicy: add set_mempolicy_home_node syscall
This syscall can be used to set a home node for the MPOL_BIND and
MPOL_PREFERRED_MANY memory policy.  Users should use this syscall after
setting up a memory policy for the specified range as shown below.

  mbind(p, nr_pages * page_size, MPOL_BIND, new_nodes->maskp,
        new_nodes->size + 1, 0);
  sys_set_mempolicy_home_node((unsigned long)p, nr_pages * page_size,
				home_node, 0);

The syscall allows specifying a home node/preferred node from which
kernel will fulfill memory allocation requests first.

For address range with MPOL_BIND memory policy, if nodemask specifies
more than one node, page allocations will come from the node in the
nodemask with sufficient free memory that is closest to the home
node/preferred node.

For MPOL_PREFERRED_MANY if the nodemask specifies more than one node,
page allocation will come from the node in the nodemask with sufficient
free memory that is closest to the home node/preferred node.  If there
is not enough memory in all the nodes specified in the nodemask, the
allocation will be attempted from the closest numa node to the home node
in the system.

This helps applications to hint at a memory allocation preference node
and fallback to _only_ a set of nodes if the memory is not available on
the preferred node.  Fallback allocation is attempted from the node
which is nearest to the preferred node.

This helps applications to have control on memory allocation numa nodes
and avoids default fallback to slow memory NUMA nodes.  For example a
system with NUMA nodes 1,2 and 3 with DRAM memory and 10, 11 and 12 of
slow memory

 new_nodes = numa_bitmask_alloc(nr_nodes);

 numa_bitmask_setbit(new_nodes, 1);
 numa_bitmask_setbit(new_nodes, 2);
 numa_bitmask_setbit(new_nodes, 3);

 p = mmap(NULL, nr_pages * page_size, protflag, mapflag, -1, 0);
 mbind(p, nr_pages * page_size, MPOL_BIND, new_nodes->maskp,  new_nodes->size + 1, 0);

 sys_set_mempolicy_home_node(p, nr_pages * page_size, 2, 0);

This will allocate from nodes closer to node 2 and will make sure the
kernel will only allocate from nodes 1, 2, and 3.  Memory will not be
allocated from slow memory nodes 10, 11, and 12.  This differs from
default MPOL_BIND behavior in that with default MPOL_BIND the allocation
will be attempted from node closer to the local node.  One of the
reasons to specify a home node is to allow allocations from cpu less
NUMA node and its nearby NUMA nodes.

With MPOL_PREFERRED_MANY on the other hand will first try to allocate
from the closest node to node 2 from the node list 1, 2 and 3.  If those
nodes don't have enough memory, kernel will allocate from slow memory
node 10, 11 and 12 which ever is closer to node 2.

Link: https://lkml.kernel.org/r/20211202123810.267175-3-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Ben Widawsky <ben.widawsky@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: <linux-api@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-15 16:30:30 +02:00

308 lines
7.4 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* NUMA memory policies for Linux.
* Copyright 2003,2004 Andi Kleen SuSE Labs
*/
#ifndef _LINUX_MEMPOLICY_H
#define _LINUX_MEMPOLICY_H 1
#include <linux/sched.h>
#include <linux/mmzone.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/spinlock.h>
#include <linux/nodemask.h>
#include <linux/pagemap.h>
#include <uapi/linux/mempolicy.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 interleave:
* 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_lock.
*
* 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 */
nodemask_t nodes; /* interleave/bind/perfer */
int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */
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_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)
static inline void mpol_get(struct mempolicy *pol)
{
if (pol)
atomic_inc(&pol->refcnt);
}
extern bool __mpol_equal(struct mempolicy *a, struct mempolicy *b);
static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
if (a == b)
return true;
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;
rwlock_t lock;
};
int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst);
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);
struct mempolicy *get_task_policy(struct task_struct *p);
struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
unsigned long addr);
bool vma_policy_mof(struct vm_area_struct *vma);
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 int huge_node(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 bool mempolicy_in_oom_domain(struct task_struct *tsk,
const nodemask_t *mask);
extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy);
static inline nodemask_t *policy_nodemask_current(gfp_t gfp)
{
struct mempolicy *mpol = get_task_policy(current);
return policy_nodemask(gfp, mpol);
}
extern unsigned int mempolicy_slab_node(void);
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,
const nodemask_t *to, int flags);
#ifdef CONFIG_TMPFS
extern int mpol_parse_str(char *str, struct mempolicy **mpol);
#endif
extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol);
/* Check if a vma is migratable */
extern bool vma_migratable(struct vm_area_struct *vma);
extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long);
extern void mpol_put_task_policy(struct task_struct *);
static inline bool mpol_is_preferred_many(struct mempolicy *pol)
{
return (pol->mode == MPOL_PREFERRED_MANY);
}
#else
struct mempolicy {};
static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
return true;
}
static inline void mpol_put(struct mempolicy *p)
{
}
static inline void mpol_cond_put(struct mempolicy *pol)
{
}
static inline void mpol_get(struct mempolicy *pol)
{
}
struct shared_policy {};
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
static inline int
vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
{
return 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 int huge_node(struct vm_area_struct *vma,
unsigned long addr, gfp_t gfp_flags,
struct mempolicy **mpol, nodemask_t **nodemask)
{
*mpol = NULL;
*nodemask = NULL;
return 0;
}
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,
const nodemask_t *to, 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)
{
return 1; /* error */
}
#endif
static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma,
unsigned long address)
{
return -1; /* no node preference */
}
static inline void mpol_put_task_policy(struct task_struct *task)
{
}
static inline nodemask_t *policy_nodemask_current(gfp_t gfp)
{
return NULL;
}
static inline bool mpol_is_preferred_many(struct mempolicy *pol)
{
return false;
}
#endif /* CONFIG_NUMA */
#endif