mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-25 20:25:31 +07:00
a8282608c8
This reverts commit2f0799a0ff
("mm, thp: restore node-local hugepage allocations"). commit2f0799a0ff
was rightfully applied to avoid the risk of a severe regression that was reported by the kernel test robot at the end of the merge window. Now we understood the regression was a false positive and was caused by a significant increase in fairness during a swap trashing benchmark. So it's safe to re-apply the fix and continue improving the code from there. The benchmark that reported the regression is very useful, but it provides a meaningful result only when there is no significant alteration in fairness during the workload. The removal of __GFP_THISNODE increased fairness. __GFP_THISNODE cannot be used in the generic page faults path for new memory allocations under the MPOL_DEFAULT mempolicy, or the allocation behavior significantly deviates from what the MPOL_DEFAULT semantics are supposed to be for THP and 4k allocations alike. Setting THP defrag to "always" or using MADV_HUGEPAGE (with THP defrag set to "madvise") has never meant to provide an implicit MPOL_BIND on the "current" node the task is running on, causing swap storms and providing a much more aggressive behavior than even zone_reclaim_node = 3. Any workload who could have benefited from __GFP_THISNODE has now to enable zone_reclaim_mode=1||2||3. __GFP_THISNODE implicitly provided the zone_reclaim_mode behavior, but it only did so if THP was enabled: if THP was disabled, there would have been no chance to get any 4k page from the current node if the current node was full of pagecache, which further shows how this __GFP_THISNODE was misplaced in MADV_HUGEPAGE. MADV_HUGEPAGE has never been intended to provide any zone_reclaim_mode semantics, in fact the two are orthogonal, zone_reclaim_mode = 1|2|3 must work exactly the same with MADV_HUGEPAGE set or not. The performance characteristic of memory depends on the hardware details. The numbers below are obtained on Naples/EPYC architecture and the N/A projection extends them to show what we should aim for in the future as a good THP NUMA locality default. The benchmark used exercises random memory seeks (note: the cost of the page faults is not part of the measurement). D0 THP | D0 4k | D1 THP | D1 4k | D2 THP | D2 4k | D3 THP | D3 4k | ... 0% | +43% | +45% | +106% | +131% | +224% | N/A | N/A D0 means distance zero (i.e. local memory), D1 means distance one (i.e. intra socket memory), D2 means distance two (i.e. inter socket memory), etc... For the guest physical memory allocated by qemu and for guest mode kernel the performance characteristic of RAM is more complex and an ideal default could be: D0 THP | D1 THP | D0 4k | D2 THP | D1 4k | D3 THP | D2 4k | D3 4k | ... 0% | +58% | +101% | N/A | +222% | N/A | N/A | N/A NOTE: the N/A are projections and haven't been measured yet, the measurement in this case is done on a 1950x with only two NUMA nodes. The THP case here means THP was used both in the host and in the guest. After applying this commit the THP NUMA locality order that we'll get out of MADV_HUGEPAGE is this: D0 THP | D1 THP | D2 THP | D3 THP | ... | D0 4k | D1 4k | D2 4k | D3 4k | ... Before this commit it was: D0 THP | D0 4k | D1 4k | D2 4k | D3 4k | ... Even if we ignore the breakage of large workloads that can't fit in a single node that the __GFP_THISNODE implicit "current node" mbind caused, the THP NUMA locality order provided by __GFP_THISNODE was still not the one we shall aim for in the long term (i.e. the first one at the top). After this commit is applied, we can introduce a new allocator multi order API and to replace those two alloc_pages_vmas calls in the page fault path, with a single multi order call: unsigned int order = (1 << HPAGE_PMD_ORDER) | (1 << 0); page = alloc_pages_multi_order(..., &order); if (!page) goto out; if (!(order & (1 << 0))) { VM_WARN_ON(order != 1 << HPAGE_PMD_ORDER); /* THP fault */ } else { VM_WARN_ON(order != 1 << 0); /* 4k fallback */ } The page allocator logic has to be altered so that when it fails on any zone with order 9, it has to try again with a order 0 before falling back to the next zone in the zonelist. After that we need to do more measurements and evaluate if adding an opt-in feature for guest mode is worth it, to swap "DN 4k | DN+1 THP" with "DN+1 THP | DN 4k" at every NUMA distance crossing. Link: http://lkml.kernel.org/r/20190503223146.2312-3-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: David Rientjes <rientjes@google.com> Cc: Zi Yan <zi.yan@cs.rutgers.edu> Cc: Stefan Priebe - Profihost AG <s.priebe@profihost.ag> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
315 lines
7.5 KiB
C
315 lines
7.5 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);
|
|
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
|