[PATCH] invalidate_inode_pages2(): ignore page refcounts

The recent fix to invalidate_inode_pages() (git commit 016eb4a) managed to
unfix invalidate_inode_pages2().

The problem is that various bits of code in the kernel can take transient refs
on pages: the page scanner will do this when inspecting a batch of pages, and
the lru_cache_add() batching pagevecs also hold a ref.

Net result is transient failures in invalidate_inode_pages2().  This affects
NFS directory invalidation (observed) and presumably also block-backed
direct-io (not yet reported).

Fix it by reverting invalidate_inode_pages2() back to the old version which
ignores the page refcounts.

We may come up with something more clever later, but for now we need a 2.6.18
fix for NFS.

Cc: Chuck Lever <cel@citi.umich.edu>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/mm/truncate.c b/mm/truncate.c
index 8fde6580657ed15c860d2f6e5bffa77c88965240..f4edbc179d14423e1f3acf9555b96bc9795b37bc 100644 (file)
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -287,9 +287,39 @@ unsigned long invalidate_inode_pages(struct address_space *mapping)
 {
        return invalidate_mapping_pages(mapping, 0, ~0UL);
 }
-
 EXPORT_SYMBOL(invalidate_inode_pages);
 
+/*
+ * This is like invalidate_complete_page(), except it ignores the page's
+ * refcount.  We do this because invalidate_inode_pages2() needs stronger
+ * invalidation guarantees, and cannot afford to leave pages behind because
+ * shrink_list() has a temp ref on them, or because they're transiently sitting
+ * in the lru_cache_add() pagevecs.
+ */
+static int
+invalidate_complete_page2(struct address_space *mapping, struct page *page)
+{
+       if (page->mapping != mapping)
+               return 0;
+
+       if (PagePrivate(page) && !try_to_release_page(page, 0))
+               return 0;
+
+       write_lock_irq(&mapping->tree_lock);
+       if (PageDirty(page))
+               goto failed;
+
+       BUG_ON(PagePrivate(page));
+       __remove_from_page_cache(page);
+       write_unlock_irq(&mapping->tree_lock);
+       ClearPageUptodate(page);
+       page_cache_release(page);       /* pagecache ref */
+       return 1;
+failed:
+       write_unlock_irq(&mapping->tree_lock);
+       return 0;
+}
+
 /**
  * invalidate_inode_pages2_range - remove range of pages from an address_space
  * @mapping: the address_space
@@ -356,7 +386,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
                                }
                        }
                        was_dirty = test_clear_page_dirty(page);
-                       if (!invalidate_complete_page(mapping, page)) {
+                       if (!invalidate_complete_page2(mapping, page)) {
                                if (was_dirty)
                                        set_page_dirty(page);
                                ret = -EIO;