linux_dsm_epyc7002/include/linux/mempolicy.h
Nathan Zimmer 4a8c7bb59a mm/mempolicy.c: convert the shared_policy lock to a rwlock
When running the SPECint_rate gcc on some very large boxes it was
noticed that the system was spending lots of time in
mpol_shared_policy_lookup().  The gamess benchmark can also show it and
is what I mostly used to chase down the issue since the setup for that I
found to be easier.

To be clear the binaries were on tmpfs because of disk I/O requirements.
We then used text replication to avoid icache misses and having all the
copies banging on the memory where the instruction code resides.  This
results in us hitting a bottleneck in mpol_shared_policy_lookup() since
lookup is serialised by the shared_policy lock.

I have only reproduced this on very large (3k+ cores) boxes.  The
problem starts showing up at just a few hundred ranks getting worse
until it threatens to livelock once it gets large enough.  For example
on the gamess benchmark at 128 ranks this area consumes only ~1% of
time, at 512 ranks it consumes nearly 13%, and at 2k ranks it is over
90%.

To alleviate the contention in this area I converted the spinlock to an
rwlock.  This allows a large number of lookups to happen simultaneously.
The results were quite good reducing this consumtion at max ranks to
around 2%.

[akpm@linux-foundation.org: tidy up code comments]
Signed-off-by: Nathan Zimmer <nzimmer@sgi.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Nadia Yvette Chambers <nyc@holomorphy.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 16:00:49 -08:00

296 lines
7.1 KiB
C

/*
* 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/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,
enum mpol_rebind_step step);
extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);
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 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 int vma_migratable(struct vm_area_struct *vma)
{
if (vma->vm_flags & (VM_IO | VM_PFNMAP))
return 0;
#ifndef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
if (vma->vm_flags & VM_HUGETLB)
return 0;
#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 0;
return 1;
}
extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long);
#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)
{
}
#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,
enum mpol_rebind_step step)
{
}
static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
{
}
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,
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 */
}
#endif /* CONFIG_NUMA */
#endif