mm: speculative page references

If we can be sure that elevating the page_count on a pagecache page will
pin it, we can speculatively run this operation, and subsequently check to
see if we hit the right page rather than relying on holding a lock or
otherwise pinning a reference to the page.

This can be done if get_page/put_page behaves consistently throughout the
whole tree (ie.  if we "get" the page after it has been used for something
else, we must be able to free it with a put_page).

Actually, there is a period where the count behaves differently: when the
page is free or if it is a constituent page of a compound page.  We need
an atomic_inc_not_zero operation to ensure we don't try to grab the page
in either case.

This patch introduces the core locking protocol to the pagecache (ie.
adds page_cache_get_speculative, and tweaks some update-side code to make
it work).

Thanks to Hugh for pointing out an improvement to the algorithm setting
page_count to zero when we have control of all references, in order to
hold off speculative getters.

[kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()]
[hugh@veritas.com: fix add_to_page_cache]
[akpm@linux-foundation.org: repair a comment]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Jeff Garzik <jeff@garzik.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Acked-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 54 insertions, 20 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 26672c6..0075eac 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -391,12 +391,10 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 }
 
 /*
- * Attempt to detach a locked page from its ->mapping.  If it is dirty or if
- * someone else has a ref on the page, abort and return 0.  If it was
- * successfully detached, return 1.  Assumes the caller has a single ref on
- * this page.
+ * Same as remove_mapping, but if the page is removed from the mapping, it
+ * gets returned with a refcount of 0.
  */
-int remove_mapping(struct address_space *mapping, struct page *page)
+static int __remove_mapping(struct address_space *mapping, struct page *page)
 {
 	BUG_ON(!PageLocked(page));
 	BUG_ON(mapping != page_mapping(page));
@@ -427,24 +425,24 @@ int remove_mapping(struct address_space *mapping, struct page *page)
 	 * Note that if SetPageDirty is always performed via set_page_dirty,
 	 * and thus under tree_lock, then this ordering is not required.
 	 */
-	if (unlikely(page_count(page) != 2))
+	if (!page_freeze_refs(page, 2))
 		goto cannot_free;
-	smp_rmb();
-	if (unlikely(PageDirty(page)))
+	/* note: atomic_cmpxchg in page_freeze_refs provides the smp_rmb */
+	if (unlikely(PageDirty(page))) {
+		page_unfreeze_refs(page, 2);
 		goto cannot_free;
+	}
 
 	if (PageSwapCache(page)) {
 		swp_entry_t swap = { .val = page_private(page) };
 		__delete_from_swap_cache(page);
 		write_unlock_irq(&mapping->tree_lock);
 		swap_free(swap);
-		__put_page(page);	/* The pagecache ref */
-		return 1;
+	} else {
+		__remove_from_page_cache(page);
+		write_unlock_irq(&mapping->tree_lock);
 	}
 
-	__remove_from_page_cache(page);
-	write_unlock_irq(&mapping->tree_lock);
-	__put_page(page);
 	return 1;
 
 cannot_free:
@@ -453,6 +451,26 @@ cannot_free:
 }
 
 /*
+ * Attempt to detach a locked page from its ->mapping.  If it is dirty or if
+ * someone else has a ref on the page, abort and return 0.  If it was
+ * successfully detached, return 1.  Assumes the caller has a single ref on
+ * this page.
+ */
+int remove_mapping(struct address_space *mapping, struct page *page)
+{
+	if (__remove_mapping(mapping, page)) {
+		/*
+		 * Unfreezing the refcount with 1 rather than 2 effectively
+		 * drops the pagecache ref for us without requiring another
+		 * atomic operation.
+		 */
+		page_unfreeze_refs(page, 1);
+		return 1;
+	}
+	return 0;
+}
+
+/*
  * shrink_page_list() returns the number of reclaimed pages
  */
 static unsigned long shrink_page_list(struct list_head *page_list,
@@ -598,18 +616,34 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		if (PagePrivate(page)) {
 			if (!try_to_release_page(page, sc->gfp_mask))
 				goto activate_locked;
-			if (!mapping && page_count(page) == 1)
-				goto free_it;
+			if (!mapping && page_count(page) == 1) {
+				unlock_page(page);
+				if (put_page_testzero(page))
+					goto free_it;
+				else {
+					/*
+					 * rare race with speculative reference.
+					 * the speculative reference will free
+					 * this page shortly, so we may
+					 * increment nr_reclaimed here (and
+					 * leave it off the LRU).
+					 */
+					nr_reclaimed++;
+					continue;
+				}
+			}
 		}
 
-		if (!mapping || !remove_mapping(mapping, page))
+		if (!mapping || !__remove_mapping(mapping, page))
 			goto keep_locked;
 
-free_it:
 		unlock_page(page);
+free_it:
 		nr_reclaimed++;
-		if (!pagevec_add(&freed_pvec, page))
-			__pagevec_release_nonlru(&freed_pvec);
+		if (!pagevec_add(&freed_pvec, page)) {
+			__pagevec_free(&freed_pvec);
+			pagevec_reinit(&freed_pvec);
+		}
 		continue;
 
 activate_locked:
@@ -623,7 +657,7 @@ keep:
 	}
 	list_splice(&ret_pages, page_list);
 	if (pagevec_count(&freed_pvec))
-		__pagevec_release_nonlru(&freed_pvec);
+		__pagevec_free(&freed_pvec);
 	count_vm_events(PGACTIVATE, pgactivate);
 	return nr_reclaimed;
 }