linux/include/linux/mempolicy.h
Hugh Dickins ddc1a5cbc0 mempolicy: alloc_pages_mpol() for NUMA policy without vma
Shrink shmem's stack usage by eliminating the pseudo-vma from its folio
allocation.  alloc_pages_mpol(gfp, order, pol, ilx, nid) becomes the
principal actor for passing mempolicy choice down to __alloc_pages(),
rather than vma_alloc_folio(gfp, order, vma, addr, hugepage).

vma_alloc_folio() and alloc_pages() remain, but as wrappers around
alloc_pages_mpol().  alloc_pages_bulk_*() untouched, except to provide the
additional args to policy_nodemask(), which subsumes policy_node(). 
Cleanup throughout, cutting out some unhelpful "helpers".

It would all be much simpler without MPOL_INTERLEAVE, but that adds a
dynamic to the constant mpol: complicated by v3.6 commit 09c231cb8b
("tmpfs: distribute interleave better across nodes"), which added ino bias
to the interleave, hidden from mm/mempolicy.c until this commit.

Hence "ilx" throughout, the "interleave index".  Originally I thought it
could be done just with nid, but that's wrong: the nodemask may come from
the shared policy layer below a shmem vma, or it may come from the task
layer above a shmem vma; and without the final nodemask then nodeid cannot
be decided.  And how ilx is applied depends also on page order.

The interleave index is almost always irrelevant unless MPOL_INTERLEAVE:
with one exception in alloc_pages_mpol(), where the NO_INTERLEAVE_INDEX
passed down from vma-less alloc_pages() is also used as hint not to use
THP-style hugepage allocation - to avoid the overhead of a hugepage arg
(though I don't understand why we never just added a GFP bit for THP - if
it actually needs a different allocation strategy from other pages of the
same order).  vma_alloc_folio() still carries its hugepage arg here, but
it is not used, and should be removed when agreed.

get_vma_policy() no longer allows a NULL vma: over time I believe we've
eradicated all the places which used to need it e.g.  swapoff and madvise
used to pass NULL vma to read_swap_cache_async(), but now know the vma.

[hughd@google.com: handle NULL mpol being passed to __read_swap_cache_async()]
  Link: https://lkml.kernel.org/r/ea419956-4751-0102-21f7-9c93cb957892@google.com
Link: https://lkml.kernel.org/r/74e34633-6060-f5e3-aee-7040d43f2e93@google.com
Link: https://lkml.kernel.org/r/1738368e-bac0-fd11-ed7f-b87142a939fe@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Nhat Pham <nphamcs@gmail.com>
Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Tejun heo <tj@kernel.org>
Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Cc: Domenico Cerasuolo <mimmocerasuolo@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-10-25 16:47:16 -07:00

302 lines
7.2 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;
#define NO_INTERLEAVE_INDEX (-1UL) /* use task il_prev for interleaving */
#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;
}
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.
*/
struct shared_policy {
struct rb_root root;
rwlock_t lock;
};
struct sp_node {
struct rb_node nd;
pgoff_t start, end;
struct mempolicy *policy;
};
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 *sp,
struct vm_area_struct *vma, struct mempolicy *mpol);
void mpol_free_shared_policy(struct shared_policy *sp);
struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
pgoff_t idx);
struct mempolicy *get_task_policy(struct task_struct *p);
struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
unsigned long addr, pgoff_t *ilx);
struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
unsigned long addr, int order, pgoff_t *ilx);
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 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);
int mpol_misplaced(struct folio *, 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);
}
extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone);
#else
struct mempolicy {};
static inline struct mempolicy *get_task_policy(struct task_struct *p)
{
return NULL;
}
static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
return true;
}
static inline void mpol_put(struct mempolicy *pol)
{
}
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 *sp)
{
}
static inline struct mempolicy *
mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx)
{
return NULL;
}
static inline struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
unsigned long addr, int order, pgoff_t *ilx)
{
*ilx = 0;
return 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 folio *folio,
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 bool mpol_is_preferred_many(struct mempolicy *pol)
{
return false;
}
#endif /* CONFIG_NUMA */
#endif