remarkable-linux/mm/internal.h
Andrea Arcangeli 70b50f94f1 mm: thp: tail page refcounting fix
Michel while working on the working set estimation code, noticed that
calling get_page_unless_zero() on a random pfn_to_page(random_pfn)
wasn't safe, if the pfn ended up being a tail page of a transparent
hugepage under splitting by __split_huge_page_refcount().

He then found the problem could also theoretically materialize with
page_cache_get_speculative() during the speculative radix tree lookups
that uses get_page_unless_zero() in SMP if the radix tree page is freed
and reallocated and get_user_pages is called on it before
page_cache_get_speculative has a chance to call get_page_unless_zero().

So the best way to fix the problem is to keep page_tail->_count zero at
all times.  This will guarantee that get_page_unless_zero() can never
succeed on any tail page.  page_tail->_mapcount is guaranteed zero and
is unused for all tail pages of a compound page, so we can simply
account the tail page references there and transfer them to
tail_page->_count in __split_huge_page_refcount() (in addition to the
head_page->_mapcount).

While debugging this s/_count/_mapcount/ change I also noticed get_page is
called by direct-io.c on pages returned by get_user_pages.  That wasn't
entirely safe because the two atomic_inc in get_page weren't atomic.  As
opposed to other get_user_page users like secondary-MMU page fault to
establish the shadow pagetables would never call any superflous get_page
after get_user_page returns.  It's safer to make get_page universally safe
for tail pages and to use get_page_foll() within follow_page (inside
get_user_pages()).  get_page_foll() is safe to do the refcounting for tail
pages without taking any locks because it is run within PT lock protected
critical sections (PT lock for pte and page_table_lock for
pmd_trans_huge).

The standard get_page() as invoked by direct-io instead will now take
the compound_lock but still only for tail pages.  The direct-io paths
are usually I/O bound and the compound_lock is per THP so very
finegrined, so there's no risk of scalability issues with it.  A simple
direct-io benchmarks with all lockdep prove locking and spinlock
debugging infrastructure enabled shows identical performance and no
overhead.  So it's worth it.  Ideally direct-io should stop calling
get_page() on pages returned by get_user_pages().  The spinlock in
get_page() is already optimized away for no-THP builds but doing
get_page() on tail pages returned by GUP is generally a rare operation
and usually only run in I/O paths.

This new refcounting on page_tail->_mapcount in addition to avoiding new
RCU critical sections will also allow the working set estimation code to
work without any further complexity associated to the tail page
refcounting with THP.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: Michel Lespinasse <walken@google.com>
Reviewed-by: Michel Lespinasse <walken@google.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: <stable@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-02 16:06:57 -07:00

312 lines
8.6 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);
}
static inline void __get_page_tail_foll(struct page *page,
bool get_page_head)
{
/*
* If we're getting a tail page, the elevated page->_count is
* required only in the head page and we will elevate the head
* page->_count and tail page->_mapcount.
*
* We elevate page_tail->_mapcount for tail pages to force
* page_tail->_count to be zero at all times to avoid getting
* false positives from get_page_unless_zero() with
* speculative page access (like in
* page_cache_get_speculative()) on tail pages.
*/
VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0);
VM_BUG_ON(atomic_read(&page->_count) != 0);
VM_BUG_ON(page_mapcount(page) < 0);
if (get_page_head)
atomic_inc(&page->first_page->_count);
atomic_inc(&page->_mapcount);
}
/*
* This is meant to be called as the FOLL_GET operation of
* follow_page() and it must be called while holding the proper PT
* lock while the pte (or pmd_trans_huge) is still mapping the page.
*/
static inline void get_page_foll(struct page *page)
{
if (unlikely(PageTail(page)))
/*
* This is safe only because
* __split_huge_page_refcount() can't run under
* get_page_foll() because we hold the proper PT lock.
*/
__get_page_tail_foll(page, true);
else {
/*
* Getting a normal page or the head of a compound page
* requires to already have an elevated page->_count.
*/
VM_BUG_ON(atomic_read(&page->_count) <= 0);
atomic_inc(&page->_count);
}
}
extern unsigned long highest_memmap_pfn;
/*
* 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);
}
/* mm/util.c */
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
struct vm_area_struct *prev, struct rb_node *rb_parent);
#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 within 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 */
#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;