mm: optimize page_lock_anon_vma() fast-path

Optimize the page_lock_anon_vma() fast path to be one atomic op, instead
of two.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Miller <davem@davemloft.net>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Namhyung Kim <namhyung@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Peter Zijlstra 2011-05-24 17:12:13 -07:00 committed by Linus Torvalds
parent 2b575eb64f
commit 88c22088bf

View File

@ -86,6 +86,29 @@ static inline struct anon_vma *anon_vma_alloc(void)
static inline void anon_vma_free(struct anon_vma *anon_vma)
{
VM_BUG_ON(atomic_read(&anon_vma->refcount));
/*
* Synchronize against page_lock_anon_vma() such that
* we can safely hold the lock without the anon_vma getting
* freed.
*
* Relies on the full mb implied by the atomic_dec_and_test() from
* put_anon_vma() against the acquire barrier implied by
* mutex_trylock() from page_lock_anon_vma(). This orders:
*
* page_lock_anon_vma() VS put_anon_vma()
* mutex_trylock() atomic_dec_and_test()
* LOCK MB
* atomic_read() mutex_is_locked()
*
* LOCK should suffice since the actual taking of the lock must
* happen _before_ what follows.
*/
if (mutex_is_locked(&anon_vma->root->mutex)) {
anon_vma_lock(anon_vma);
anon_vma_unlock(anon_vma);
}
kmem_cache_free(anon_vma_cachep, anon_vma);
}
@ -372,20 +395,75 @@ struct anon_vma *page_get_anon_vma(struct page *page)
return anon_vma;
}
/*
* Similar to page_get_anon_vma() except it locks the anon_vma.
*
* Its a little more complex as it tries to keep the fast path to a single
* atomic op -- the trylock. If we fail the trylock, we fall back to getting a
* reference like with page_get_anon_vma() and then block on the mutex.
*/
struct anon_vma *page_lock_anon_vma(struct page *page)
{
struct anon_vma *anon_vma = page_get_anon_vma(page);
struct anon_vma *anon_vma = NULL;
unsigned long anon_mapping;
if (anon_vma)
anon_vma_lock(anon_vma);
rcu_read_lock();
anon_mapping = (unsigned long) ACCESS_ONCE(page->mapping);
if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
goto out;
if (!page_mapped(page))
goto out;
anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
if (mutex_trylock(&anon_vma->root->mutex)) {
/*
* If we observe a !0 refcount, then holding the lock ensures
* the anon_vma will not go away, see __put_anon_vma().
*/
if (!atomic_read(&anon_vma->refcount)) {
anon_vma_unlock(anon_vma);
anon_vma = NULL;
}
goto out;
}
/* trylock failed, we got to sleep */
if (!atomic_inc_not_zero(&anon_vma->refcount)) {
anon_vma = NULL;
goto out;
}
if (!page_mapped(page)) {
put_anon_vma(anon_vma);
anon_vma = NULL;
goto out;
}
/* we pinned the anon_vma, its safe to sleep */
rcu_read_unlock();
anon_vma_lock(anon_vma);
if (atomic_dec_and_test(&anon_vma->refcount)) {
/*
* Oops, we held the last refcount, release the lock
* and bail -- can't simply use put_anon_vma() because
* we'll deadlock on the anon_vma_lock() recursion.
*/
anon_vma_unlock(anon_vma);
__put_anon_vma(anon_vma);
anon_vma = NULL;
}
return anon_vma;
out:
rcu_read_unlock();
return anon_vma;
}
void page_unlock_anon_vma(struct anon_vma *anon_vma)
{
anon_vma_unlock(anon_vma);
put_anon_vma(anon_vma);
}
/*