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, 14 insertions, 1 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6e765d28841b..3ca9420f627e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -419,6 +419,7 @@ struct address_space {
 	struct mutex		i_mmap_mutex;	/* protect tree, count, list */
 	/* Protected by tree_lock together with the radix tree */
 	unsigned long		nrpages;	/* number of total pages */
+	unsigned long		nrshadows;	/* number of shadow entries */
 	pgoff_t			writeback_index;/* writeback starts here */
 	const struct address_space_operations *a_ops;	/* methods */
 	unsigned long		flags;		/* error bits/gfp mask */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b1331aff769c..58d6ddba5db3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1834,6 +1834,7 @@ vm_unmapped_area(struct vm_unmapped_area_info *info)
 extern void truncate_inode_pages(struct address_space *, loff_t);
 extern void truncate_inode_pages_range(struct address_space *,
 				       loff_t lstart, loff_t lend);
+extern void truncate_inode_pages_final(struct address_space *);
 
 /* generic vm_area_ops exported for stackable file systems */
 extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 493bfd85214e..ff43253f568a 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -25,6 +25,7 @@ enum mapping_flags {
 	AS_MM_ALL_LOCKS	= __GFP_BITS_SHIFT + 2,	/* under mm_take_all_locks() */
 	AS_UNEVICTABLE	= __GFP_BITS_SHIFT + 3,	/* e.g., ramdisk, SHM_LOCK */
 	AS_BALLOON_MAP  = __GFP_BITS_SHIFT + 4, /* balloon page special map */
+	AS_EXITING	= __GFP_BITS_SHIFT + 5, /* final truncate in progress */
 };
 
 static inline void mapping_set_error(struct address_space *mapping, int error)
@@ -69,6 +70,16 @@ static inline int mapping_balloon(struct address_space *mapping)
 	return mapping && test_bit(AS_BALLOON_MAP, &mapping->flags);
 }
 
+static inline void mapping_set_exiting(struct address_space *mapping)
+{
+	set_bit(AS_EXITING, &mapping->flags);
+}
+
+static inline int mapping_exiting(struct address_space *mapping)
+{
+	return test_bit(AS_EXITING, &mapping->flags);
+}
+
 static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 {
 	return (__force gfp_t)mapping->flags & __GFP_BITS_MASK;
@@ -547,7 +558,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 				pgoff_t index, gfp_t gfp_mask);
 extern void delete_from_page_cache(struct page *page);
-extern void __delete_from_page_cache(struct page *page);
+extern void __delete_from_page_cache(struct page *page, void *shadow);
 int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
 
 /*