Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
223 lines
5.9 KiB
C
223 lines
5.9 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);
|
|
|
|
extern void prep_compound_page(struct page *page, unsigned long order);
|
|
|
|
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);
|
|
}
|
|
|
|
/*
|
|
* 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);
|
|
|
|
/*
|
|
* 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)
|
|
{
|
|
VM_BUG_ON(!PageBuddy(page));
|
|
return page_private(page);
|
|
}
|
|
|
|
extern int mlock_vma_pages_range(struct vm_area_struct *vma,
|
|
unsigned long start, unsigned long end);
|
|
extern void munlock_vma_pages_all(struct vm_area_struct *vma);
|
|
|
|
#ifdef CONFIG_UNEVICTABLE_LRU
|
|
/*
|
|
* unevictable_migrate_page() called only from migrate_page_copy() to
|
|
* migrate unevictable flag to new page.
|
|
* Note that the old page has been isolated from the LRU lists at this
|
|
* point so we don't need to worry about LRU statistics.
|
|
*/
|
|
static inline void unevictable_migrate_page(struct page *new, struct page *old)
|
|
{
|
|
if (TestClearPageUnevictable(old))
|
|
SetPageUnevictable(new);
|
|
}
|
|
#else
|
|
static inline void unevictable_migrate_page(struct page *new, struct page *old)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_UNEVICTABLE_LRU
|
|
/*
|
|
* 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;
|
|
|
|
SetPageMlocked(page);
|
|
return 1;
|
|
}
|
|
|
|
/*
|
|
* must be called with vma's mmap_sem held for read, and page locked.
|
|
*/
|
|
extern void mlock_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
|
|
*/
|
|
static inline void mlock_migrate_page(struct page *newpage, struct page *page)
|
|
{
|
|
if (TestClearPageMlocked(page))
|
|
SetPageMlocked(newpage);
|
|
}
|
|
|
|
|
|
#else /* CONFIG_UNEVICTABLE_LRU */
|
|
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_UNEVICTABLE_LRU */
|
|
|
|
/*
|
|
* 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 */
|
|
|
|
#define GUP_FLAGS_WRITE 0x1
|
|
#define GUP_FLAGS_FORCE 0x2
|
|
#define GUP_FLAGS_IGNORE_VMA_PERMISSIONS 0x4
|
|
|
|
int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
|
|
unsigned long start, int len, int flags,
|
|
struct page **pages, struct vm_area_struct **vmas);
|
|
|
|
#endif
|