mm + fs: store shadow entries in page cache

Reclaim will be leaving shadow entries in the page cache radix tree upon
evicting the real page.  As those pages are found from the LRU, an
iput() can lead to the inode being freed concurrently.  At this point,
reclaim must no longer install shadow pages because the inode freeing
code needs to ensure the page tree is really empty.

Add an address_space flag, AS_EXITING, that the inode freeing code sets
under the tree lock before doing the final truncate.  Reclaim will check
for this flag before installing shadow pages.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 80 insertions, 9 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index efc63876477f..05c44aa44188 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -107,12 +107,33 @@
  *   ->tasklist_lock            (memory_failure, collect_procs_ao)
  */
 
+static void page_cache_tree_delete(struct address_space *mapping,
+				   struct page *page, void *shadow)
+{
+	if (shadow) {
+		void **slot;
+
+		slot = radix_tree_lookup_slot(&mapping->page_tree, page->index);
+		radix_tree_replace_slot(slot, shadow);
+		mapping->nrshadows++;
+		/*
+		 * Make sure the nrshadows update is committed before
+		 * the nrpages update so that final truncate racing
+		 * with reclaim does not see both counters 0 at the
+		 * same time and miss a shadow entry.
+		 */
+		smp_wmb();
+	} else
+		radix_tree_delete(&mapping->page_tree, page->index);
+	mapping->nrpages--;
+}
+
 /*
  * Delete a page from the page cache and free it. Caller has to make
  * sure the page is locked and that nobody else uses it - or that usage
  * is safe.  The caller must hold the mapping's tree_lock.
  */
-void __delete_from_page_cache(struct page *page)
+void __delete_from_page_cache(struct page *page, void *shadow)
 {
 	struct address_space *mapping = page->mapping;
 
@@ -127,10 +148,11 @@ void __delete_from_page_cache(struct page *page)
 	else
 		cleancache_invalidate_page(mapping, page);
 
-	radix_tree_delete(&mapping->page_tree, page->index);
+	page_cache_tree_delete(mapping, page, shadow);
+
 	page->mapping = NULL;
 	/* Leave page->index set: truncation lookup relies upon it */
-	mapping->nrpages--;
+
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	if (PageSwapBacked(page))
 		__dec_zone_page_state(page, NR_SHMEM);
@@ -166,7 +188,7 @@ void delete_from_page_cache(struct page *page)
 
 	freepage = mapping->a_ops->freepage;
 	spin_lock_irq(&mapping->tree_lock);
-	__delete_from_page_cache(page);
+	__delete_from_page_cache(page, NULL);
 	spin_unlock_irq(&mapping->tree_lock);
 	mem_cgroup_uncharge_cache_page(page);
 
@@ -426,7 +448,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 		new->index = offset;
 
 		spin_lock_irq(&mapping->tree_lock);
-		__delete_from_page_cache(old);
+		__delete_from_page_cache(old, NULL);
 		error = radix_tree_insert(&mapping->page_tree, offset, new);
 		BUG_ON(error);
 		mapping->nrpages++;
@@ -460,6 +482,7 @@ static int page_cache_tree_insert(struct address_space *mapping,
 		if (!radix_tree_exceptional_entry(p))
 			return -EEXIST;
 		radix_tree_replace_slot(slot, page);
+		mapping->nrshadows--;
 		mapping->nrpages++;
 		return 0;
 	}
diff --git a/mm/truncate.c b/mm/truncate.c
index 2e84fe59190b..0db9258319f0 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -35,7 +35,8 @@ static void clear_exceptional_entry(struct address_space *mapping,
 	 * without the tree itself locked.  These unlocked entries
 	 * need verification under the tree lock.
 	 */
-	radix_tree_delete_item(&mapping->page_tree, index, entry);
+	if (radix_tree_delete_item(&mapping->page_tree, index, entry) == entry)
+		mapping->nrshadows--;
 	spin_unlock_irq(&mapping->tree_lock);
 }
 
@@ -229,7 +230,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	int		i;
 
 	cleancache_invalidate_inode(mapping);
-	if (mapping->nrpages == 0)
+	if (mapping->nrpages == 0 && mapping->nrshadows == 0)
 		return;
 
 	/* Offsets within partial pages */
@@ -392,6 +393,53 @@ void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
 EXPORT_SYMBOL(truncate_inode_pages);
 
 /**
+ * truncate_inode_pages_final - truncate *all* pages before inode dies
+ * @mapping: mapping to truncate
+ *
+ * Called under (and serialized by) inode->i_mutex.
+ *
+ * Filesystems have to use this in the .evict_inode path to inform the
+ * VM that this is the final truncate and the inode is going away.
+ */
+void truncate_inode_pages_final(struct address_space *mapping)
+{
+	unsigned long nrshadows;
+	unsigned long nrpages;
+
+	/*
+	 * Page reclaim can not participate in regular inode lifetime
+	 * management (can't call iput()) and thus can race with the
+	 * inode teardown.  Tell it when the address space is exiting,
+	 * so that it does not install eviction information after the
+	 * final truncate has begun.
+	 */
+	mapping_set_exiting(mapping);
+
+	/*
+	 * When reclaim installs eviction entries, it increases
+	 * nrshadows first, then decreases nrpages.  Make sure we see
+	 * this in the right order or we might miss an entry.
+	 */
+	nrpages = mapping->nrpages;
+	smp_rmb();
+	nrshadows = mapping->nrshadows;
+
+	if (nrpages || nrshadows) {
+		/*
+		 * As truncation uses a lockless tree lookup, cycle
+		 * the tree lock to make sure any ongoing tree
+		 * modification that does not see AS_EXITING is
+		 * completed before starting the final truncate.
+		 */
+		spin_lock_irq(&mapping->tree_lock);
+		spin_unlock_irq(&mapping->tree_lock);
+
+		truncate_inode_pages(mapping, 0);
+	}
+}
+EXPORT_SYMBOL(truncate_inode_pages_final);
+
+/**
  * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
  * @mapping: the address_space which holds the pages to invalidate
  * @start: the offset 'from' which to invalidate
@@ -484,7 +532,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 		goto failed;
 
 	BUG_ON(page_has_private(page));
-	__delete_from_page_cache(page);
+	__delete_from_page_cache(page, NULL);
 	spin_unlock_irq(&mapping->tree_lock);
 	mem_cgroup_uncharge_cache_page(page);
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c53d1a54964c..2a0bb8fdb259 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -572,7 +572,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page)
 
 		freepage = mapping->a_ops->freepage;
 
-		__delete_from_page_cache(page);
+		__delete_from_page_cache(page, NULL);
 		spin_unlock_irq(&mapping->tree_lock);
 		mem_cgroup_uncharge_cache_page(page);