From 88c22088bf235f50b09a10bd9f022b0472bcb6b5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 24 May 2011 17:12:13 -0700 Subject: 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 Reviewed-by: KAMEZAWA Hiroyuki Cc: Benjamin Herrenschmidt Cc: David Miller Cc: Martin Schwidefsky Cc: Russell King Cc: Paul Mundt Cc: Jeff Dike Cc: Richard Weinberger Cc: Tony Luck Cc: Hugh Dickins Cc: Mel Gorman Cc: KOSAKI Motohiro Cc: Nick Piggin Cc: Namhyung Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/rmap.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 82 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/rmap.c b/mm/rmap.c index ce29d405d093..3a39b518a653 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -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 @@ out: 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); } /* -- cgit v1.2.3