linux-stable/include/linux/rmap.h
Andrea Arcangeli 7906d00cd1 mmu-notifiers: add mm_take_all_locks() operation
mm_take_all_locks holds off reclaim from an entire mm_struct.  This allows
mmu notifiers to register into the mm at any time with the guarantee that
no mmu operation is in progress on the mm.

This operation locks against the VM for all pte/vma/mm related operations
that could ever happen on a certain mm.  This includes vmtruncate,
try_to_unmap, and all page faults.

The caller must take the mmap_sem in write mode before calling
mm_take_all_locks().  The caller isn't allowed to release the mmap_sem
until mm_drop_all_locks() returns.

mmap_sem in write mode is required in order to block all operations that
could modify pagetables and free pages without need of altering the vma
layout (for example populate_range() with nonlinear vmas).  It's also
needed in write mode to avoid new anon_vmas to be associated with existing
vmas.

A single task can't take more than one mm_take_all_locks() in a row or it
would deadlock.

mm_take_all_locks() and mm_drop_all_locks are expensive operations that
may have to take thousand of locks.

mm_take_all_locks() can fail if it's interrupted by signals.

When mmu_notifier_register returns, we must be sure that the driver is
notified if some task is in the middle of a vmtruncate for the 'mm' where
the mmu notifier was registered (mmu_notifier_invalidate_range_start/end
is run around the vmtruncation but mmu_notifier_register can run after
mmu_notifier_invalidate_range_start and before
mmu_notifier_invalidate_range_end).  Same problem for rmap paths.  And
we've to remove page pinning to avoid replicating the tlb_gather logic
inside KVM (and GRU doesn't work well with page pinning regardless of
needing tlb_gather), so without mm_take_all_locks when vmtruncate frees
the page, kvm would have no way to notice that it mapped into sptes a page
that is going into the freelist without a chance of any further
mmu_notifier notification.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Andrea Arcangeli <andrea@qumranet.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Jack Steiner <steiner@sgi.com>
Cc: Robin Holt <holt@sgi.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Kanoj Sarcar <kanojsarcar@yahoo.com>
Cc: Roland Dreier <rdreier@cisco.com>
Cc: Steve Wise <swise@opengridcomputing.com>
Cc: Avi Kivity <avi@qumranet.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Anthony Liguori <aliguori@us.ibm.com>
Cc: Chris Wright <chrisw@redhat.com>
Cc: Marcelo Tosatti <marcelo@kvack.org>
Cc: Eric Dumazet <dada1@cosmosbay.com>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Cc: Izik Eidus <izike@qumranet.com>
Cc: Anthony Liguori <aliguori@us.ibm.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>
2008-07-28 16:30:21 -07:00

144 lines
4 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 **);
/*
* 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 */