linux/mm/internal.h
Shaohua Li 744ed14427 mm: batch activate_page() to reduce lock contention
The zone->lru_lock is heavily contented in workload where activate_page()
is frequently used.  We could do batch activate_page() to reduce the lock
contention.  The batched pages will be added into zone list when the pool
is full or page reclaim is trying to drain them.

For example, in a 4 socket 64 CPU system, create a sparse file and 64
processes, processes shared map to the file.  Each process read access the
whole file and then exit.  The process exit will do unmap_vmas() and cause
a lot of activate_page() call.  In such workload, we saw about 58% total
time reduction with below patch.  Other workloads with a lot of
activate_page also benefits a lot too.

I tested some microbenchmarks:
case-anon-cow-rand-mt		0.58%
case-anon-cow-rand		-3.30%
case-anon-cow-seq-mt		-0.51%
case-anon-cow-seq		-5.68%
case-anon-r-rand-mt		0.23%
case-anon-r-rand		0.81%
case-anon-r-seq-mt		-0.71%
case-anon-r-seq			-1.99%
case-anon-rx-rand-mt		2.11%
case-anon-rx-seq-mt		3.46%
case-anon-w-rand-mt		-0.03%
case-anon-w-rand		-0.50%
case-anon-w-seq-mt		-1.08%
case-anon-w-seq			-0.12%
case-anon-wx-rand-mt		-5.02%
case-anon-wx-seq-mt		-1.43%
case-fork			1.65%
case-fork-sleep			-0.07%
case-fork-withmem		1.39%
case-hugetlb			-0.59%
case-lru-file-mmap-read-mt	-0.54%
case-lru-file-mmap-read		0.61%
case-lru-file-mmap-read-rand	-2.24%
case-lru-file-readonce		-0.64%
case-lru-file-readtwice		-11.69%
case-lru-memcg			-1.35%
case-mmap-pread-rand-mt		1.88%
case-mmap-pread-rand		-15.26%
case-mmap-pread-seq-mt		0.89%
case-mmap-pread-seq		-69.72%
case-mmap-xread-rand-mt		0.71%
case-mmap-xread-seq-mt		0.38%

The most significent are:
case-lru-file-readtwice		-11.69%
case-mmap-pread-rand		-15.26%
case-mmap-pread-seq		-69.72%

which use activate_page a lot.  others are basically variations because
each run has slightly difference.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-13 17:32:50 -08:00

276 lines
7.5 KiB
C

/* internal.h: mm/ internal definitions
*
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef __MM_INTERNAL_H
#define __MM_INTERNAL_H
#include <linux/mm.h>
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
unsigned long floor, unsigned long ceiling);
static inline void set_page_count(struct page *page, int v)
{
atomic_set(&page->_count, v);
}
/*
* Turn a non-refcounted page (->_count == 0) into refcounted with
* a count of one.
*/
static inline void set_page_refcounted(struct page *page)
{
VM_BUG_ON(PageTail(page));
VM_BUG_ON(atomic_read(&page->_count));
set_page_count(page, 1);
}
static inline void __put_page(struct page *page)
{
atomic_dec(&page->_count);
}
extern unsigned long highest_memmap_pfn;
#ifdef CONFIG_SMP
extern int putback_active_lru_page(struct zone *zone, struct page *page);
#else
static inline int putback_active_lru_page(struct zone *zone, struct page *page)
{
return 0;
}
#endif
/*
* in mm/vmscan.c:
*/
extern int isolate_lru_page(struct page *page);
extern void putback_lru_page(struct page *page);
/*
* in mm/page_alloc.c
*/
extern void __free_pages_bootmem(struct page *page, unsigned int order);
extern void prep_compound_page(struct page *page, unsigned long order);
#ifdef CONFIG_MEMORY_FAILURE
extern bool is_free_buddy_page(struct page *page);
#endif
/*
* function for dealing with page's order in buddy system.
* zone->lock is already acquired when we use these.
* So, we don't need atomic page->flags operations here.
*/
static inline unsigned long page_order(struct page *page)
{
/* PageBuddy() must be checked by the caller */
return page_private(page);
}
#ifdef CONFIG_MMU
extern long mlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
extern void munlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
{
munlock_vma_pages_range(vma, vma->vm_start, vma->vm_end);
}
/*
* Called only in fault path via page_evictable() for a new page
* to determine if it's being mapped into a LOCKED vma.
* If so, mark page as mlocked.
*/
static inline int is_mlocked_vma(struct vm_area_struct *vma, struct page *page)
{
VM_BUG_ON(PageLRU(page));
if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED))
return 0;
if (!TestSetPageMlocked(page)) {
inc_zone_page_state(page, NR_MLOCK);
count_vm_event(UNEVICTABLE_PGMLOCKED);
}
return 1;
}
/*
* must be called with vma's mmap_sem held for read or write, and page locked.
*/
extern void mlock_vma_page(struct page *page);
extern void munlock_vma_page(struct page *page);
/*
* Clear the page's PageMlocked(). This can be useful in a situation where
* we want to unconditionally remove a page from the pagecache -- e.g.,
* on truncation or freeing.
*
* It is legal to call this function for any page, mlocked or not.
* If called for a page that is still mapped by mlocked vmas, all we do
* is revert to lazy LRU behaviour -- semantics are not broken.
*/
extern void __clear_page_mlock(struct page *page);
static inline void clear_page_mlock(struct page *page)
{
if (unlikely(TestClearPageMlocked(page)))
__clear_page_mlock(page);
}
/*
* mlock_migrate_page - called only from migrate_page_copy() to
* migrate the Mlocked page flag; update statistics.
*/
static inline void mlock_migrate_page(struct page *newpage, struct page *page)
{
if (TestClearPageMlocked(page)) {
unsigned long flags;
local_irq_save(flags);
__dec_zone_page_state(page, NR_MLOCK);
SetPageMlocked(newpage);
__inc_zone_page_state(newpage, NR_MLOCK);
local_irq_restore(flags);
}
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern unsigned long vma_address(struct page *page,
struct vm_area_struct *vma);
#endif
#else /* !CONFIG_MMU */
static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
{
return 0;
}
static inline void clear_page_mlock(struct page *page) { }
static inline void mlock_vma_page(struct page *page) { }
static inline void mlock_migrate_page(struct page *new, struct page *old) { }
#endif /* !CONFIG_MMU */
/*
* Return the mem_map entry representing the 'offset' subpage within
* the maximally aligned gigantic page 'base'. Handle any discontiguity
* in the mem_map at MAX_ORDER_NR_PAGES boundaries.
*/
static inline struct page *mem_map_offset(struct page *base, int offset)
{
if (unlikely(offset >= MAX_ORDER_NR_PAGES))
return pfn_to_page(page_to_pfn(base) + offset);
return base + offset;
}
/*
* Iterator over all subpages withing the maximally aligned gigantic
* page 'base'. Handle any discontiguity in the mem_map.
*/
static inline struct page *mem_map_next(struct page *iter,
struct page *base, int offset)
{
if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) {
unsigned long pfn = page_to_pfn(base) + offset;
if (!pfn_valid(pfn))
return NULL;
return pfn_to_page(pfn);
}
return iter + 1;
}
/*
* FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node,
* so all functions starting at paging_init should be marked __init
* in those cases. SPARSEMEM, however, allows for memory hotplug,
* and alloc_bootmem_node is not used.
*/
#ifdef CONFIG_SPARSEMEM
#define __paginginit __meminit
#else
#define __paginginit __init
#endif
/* Memory initialisation debug and verification */
enum mminit_level {
MMINIT_WARNING,
MMINIT_VERIFY,
MMINIT_TRACE
};
#ifdef CONFIG_DEBUG_MEMORY_INIT
extern int mminit_loglevel;
#define mminit_dprintk(level, prefix, fmt, arg...) \
do { \
if (level < mminit_loglevel) { \
printk(level <= MMINIT_WARNING ? KERN_WARNING : KERN_DEBUG); \
printk(KERN_CONT "mminit::" prefix " " fmt, ##arg); \
} \
} while (0)
extern void mminit_verify_pageflags_layout(void);
extern void mminit_verify_page_links(struct page *page,
enum zone_type zone, unsigned long nid, unsigned long pfn);
extern void mminit_verify_zonelist(void);
#else
static inline void mminit_dprintk(enum mminit_level level,
const char *prefix, const char *fmt, ...)
{
}
static inline void mminit_verify_pageflags_layout(void)
{
}
static inline void mminit_verify_page_links(struct page *page,
enum zone_type zone, unsigned long nid, unsigned long pfn)
{
}
static inline void mminit_verify_zonelist(void)
{
}
#endif /* CONFIG_DEBUG_MEMORY_INIT */
/* mminit_validate_memmodel_limits is independent of CONFIG_DEBUG_MEMORY_INIT */
#if defined(CONFIG_SPARSEMEM)
extern void mminit_validate_memmodel_limits(unsigned long *start_pfn,
unsigned long *end_pfn);
#else
static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
unsigned long *end_pfn)
{
}
#endif /* CONFIG_SPARSEMEM */
int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, int len, unsigned int foll_flags,
struct page **pages, struct vm_area_struct **vmas,
int *nonblocking);
#define ZONE_RECLAIM_NOSCAN -2
#define ZONE_RECLAIM_FULL -1
#define ZONE_RECLAIM_SOME 0
#define ZONE_RECLAIM_SUCCESS 1
#endif
extern int hwpoison_filter(struct page *p);
extern u32 hwpoison_filter_dev_major;
extern u32 hwpoison_filter_dev_minor;
extern u64 hwpoison_filter_flags_mask;
extern u64 hwpoison_filter_flags_value;
extern u64 hwpoison_filter_memcg;
extern u32 hwpoison_filter_enable;