mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
ac79f78dab
This reverts commit a8282608c8
.
The commit references the original intended semantic for MADV_HUGEPAGE
which has subsequently taken on three unique purposes:
- enables or disables thp for a range of memory depending on the system's
config (is thp "enabled" set to "always" or "madvise"),
- determines the synchronous compaction behavior for thp allocations at
fault (is thp "defrag" set to "always", "defer+madvise", or "madvise"),
and
- reverts a previous MADV_NOHUGEPAGE (there is no madvise mode to only
clear previous hugepage advice).
These are the three purposes that currently exist in 5.2 and over the
past several years that userspace has been written around. Adding a
NUMA locality preference adds a fourth dimension to an already conflated
advice mode.
Based on the semantic that MADV_HUGEPAGE has provided over the past
several years, there exist workloads that use the tunable based on these
principles: specifically that the allocation should attempt to
defragment a local node before falling back. It is agreed that remote
hugepages typically (but not always) have a better access latency than
remote native pages, although on Naples this is at parity for
intersocket.
The revert commit that this patch reverts allows hugepage allocation to
immediately allocate remotely when local memory is fragmented. This is
contrary to the semantic of MADV_HUGEPAGE over the past several years:
that is, memory compaction should be attempted locally before falling
back.
The performance degradation of remote hugepages over local hugepages on
Rome, for example, is 53.5% increased access latency. For this reason,
the goal is to revert back to the 5.2 and previous behavior that would
attempt local defragmentation before falling back. With the patch that
is reverted by this patch, we see performance degradations at the tail
because the allocator happily allocates the remote hugepage rather than
even attempting to make a local hugepage available.
zone_reclaim_mode is not a solution to this problem since it does not
only impact hugepage allocations but rather changes the memory
allocation strategy for *all* page allocations.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Stefan Priebe - Profihost AG <s.priebe@profihost.ag>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
313 lines
7.4 KiB
C
313 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/mmzone.h>
|
|
#include <linux/dax.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 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_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_nodemask_intersects(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 */
|
|
static inline bool vma_migratable(struct vm_area_struct *vma)
|
|
{
|
|
if (vma->vm_flags & (VM_IO | VM_PFNMAP))
|
|
return false;
|
|
|
|
/*
|
|
* DAX device mappings require predictable access latency, so avoid
|
|
* incurring periodic faults.
|
|
*/
|
|
if (vma_is_dax(vma))
|
|
return false;
|
|
|
|
#ifndef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
|
|
if (vma->vm_flags & VM_HUGETLB)
|
|
return false;
|
|
#endif
|
|
|
|
/*
|
|
* 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 false;
|
|
return true;
|
|
}
|
|
|
|
extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long);
|
|
extern void mpol_put_task_policy(struct task_struct *);
|
|
|
|
#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)
|
|
{
|
|
}
|
|
#endif /* CONFIG_NUMA */
|
|
#endif
|