kernel_optimize_test/include/linux/rmap.h
Nick Piggin 479db0bf40 mm: dirty page tracking race fix
There is a race with dirty page accounting where a page may not properly
be accounted for.

clear_page_dirty_for_io() calls page_mkclean; then TestClearPageDirty.

page_mkclean walks the rmaps for that page, and for each one it cleans and
write protects the pte if it was dirty.  It uses page_check_address to
find the pte.  That function has a shortcut to avoid the ptl if the pte is
not present.  Unfortunately, the pte can be switched to not-present then
back to present by other code while holding the page table lock -- this
should not be a signal for page_mkclean to ignore that pte, because it may
be dirty.

For example, powerpc64's set_pte_at will clear a previously present pte
before setting it to the desired value.  There may also be other code in
core mm or in arch which do similar things.

The consequence of the bug is loss of data integrity due to msync, and
loss of dirty page accounting accuracy.  XIP's __xip_unmap could easily
also be unreliable (depending on the exact XIP locking scheme), which can
lead to data corruption.

Fix this by having an option to always take ptl to check the pte in
page_check_address.

It's possible to retain this optimization for page_referenced and
try_to_unmap.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Jared Hulbert <jaredeh@gmail.com>
Cc: Carsten Otte <cotte@freenet.de>
Cc: Hugh Dickins <hugh@veritas.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-08-20 15:40:32 -07:00

145 lines
4.0 KiB
C

#ifndef _LINUX_RMAP_H
#define _LINUX_RMAP_H
/*
* Declarations for Reverse Mapping functions in mm/rmap.c
*/
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/spinlock.h>
#include <linux/memcontrol.h>
/*
* The anon_vma heads a list of private "related" vmas, to scan if
* an anonymous page pointing to this anon_vma needs to be unmapped:
* the vmas on the list will be related by forking, or by splitting.
*
* Since vmas come and go as they are split and merged (particularly
* in mprotect), the mapping field of an anonymous page cannot point
* directly to a vma: instead it points to an anon_vma, on whose list
* the related vmas can be easily linked or unlinked.
*
* After unlinking the last vma on the list, we must garbage collect
* the anon_vma object itself: we're guaranteed no page can be
* pointing to this anon_vma once its vma list is empty.
*/
struct anon_vma {
spinlock_t lock; /* Serialize access to vma list */
/*
* NOTE: the LSB of the head.next is set by
* mm_take_all_locks() _after_ taking the above lock. So the
* head must only be read/written after taking the above lock
* to be sure to see a valid next pointer. The LSB bit itself
* is serialized by a system wide lock only visible to
* mm_take_all_locks() (mm_all_locks_mutex).
*/
struct list_head head; /* List of private "related" vmas */
};
#ifdef CONFIG_MMU
extern struct kmem_cache *anon_vma_cachep;
static inline struct anon_vma *anon_vma_alloc(void)
{
return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
}
static inline void anon_vma_free(struct anon_vma *anon_vma)
{
kmem_cache_free(anon_vma_cachep, anon_vma);
}
static inline void anon_vma_lock(struct vm_area_struct *vma)
{
struct anon_vma *anon_vma = vma->anon_vma;
if (anon_vma)
spin_lock(&anon_vma->lock);
}
static inline void anon_vma_unlock(struct vm_area_struct *vma)
{
struct anon_vma *anon_vma = vma->anon_vma;
if (anon_vma)
spin_unlock(&anon_vma->lock);
}
/*
* anon_vma helper functions.
*/
void anon_vma_init(void); /* create anon_vma_cachep */
int anon_vma_prepare(struct vm_area_struct *);
void __anon_vma_merge(struct vm_area_struct *, struct vm_area_struct *);
void anon_vma_unlink(struct vm_area_struct *);
void anon_vma_link(struct vm_area_struct *);
void __anon_vma_link(struct vm_area_struct *);
/*
* rmap interfaces called when adding or removing pte of page
*/
void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long);
void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long);
void page_add_file_rmap(struct page *);
void page_remove_rmap(struct page *, struct vm_area_struct *);
#ifdef CONFIG_DEBUG_VM
void page_dup_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address);
#else
static inline void page_dup_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address)
{
atomic_inc(&page->_mapcount);
}
#endif
/*
* Called from mm/vmscan.c to handle paging out
*/
int page_referenced(struct page *, int is_locked, struct mem_cgroup *cnt);
int try_to_unmap(struct page *, int ignore_refs);
/*
* Called from mm/filemap_xip.c to unmap empty zero page
*/
pte_t *page_check_address(struct page *, struct mm_struct *,
unsigned long, spinlock_t **, int);
/*
* Used by swapoff to help locate where page is expected in vma.
*/
unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
/*
* Cleans the PTEs of shared mappings.
* (and since clean PTEs should also be readonly, write protects them too)
*
* returns the number of cleaned PTEs.
*/
int page_mkclean(struct page *);
#else /* !CONFIG_MMU */
#define anon_vma_init() do {} while (0)
#define anon_vma_prepare(vma) (0)
#define anon_vma_link(vma) do {} while (0)
#define page_referenced(page,l,cnt) TestClearPageReferenced(page)
#define try_to_unmap(page, refs) SWAP_FAIL
static inline int page_mkclean(struct page *page)
{
return 0;
}
#endif /* CONFIG_MMU */
/*
* Return values of try_to_unmap
*/
#define SWAP_SUCCESS 0
#define SWAP_AGAIN 1
#define SWAP_FAIL 2
#endif /* _LINUX_RMAP_H */