fs: introduce some page/buffer invariants

It is a bug to set a page dirty if it is not uptodate unless it has
buffers.  If the page has buffers, then the page may be dirty (some buffers
dirty) but not uptodate (some buffers not uptodate).  The exception to this
rule is if the set_page_dirty caller is racing with truncate or invalidate.

A buffer can not be set dirty if it is not uptodate.

If either of these situations occurs, it indicates there could be some data
loss problem.  Some of these warnings could be a harmless one where the
page or buffer is set uptodate immediately after it is dirtied, however we
should fix those up, and enforce this ordering.

Bring the order of operations for truncate into line with those of
invalidate.  This will prevent a page from being able to go !uptodate while
we're holding the tree_lock, which is probably a good thing anyway.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 39 insertions, 18 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index d654a3b6209e..0f9006714230 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -676,6 +676,39 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode)
 EXPORT_SYMBOL(mark_buffer_dirty_inode);
 
 /*
+ * Mark the page dirty, and set it dirty in the radix tree, and mark the inode
+ * dirty.
+ *
+ * If warn is true, then emit a warning if the page is not uptodate and has
+ * not been truncated.
+ */
+static int __set_page_dirty(struct page *page,
+		struct address_space *mapping, int warn)
+{
+	if (unlikely(!mapping))
+		return !TestSetPageDirty(page);
+
+	if (TestSetPageDirty(page))
+		return 0;
+
+	write_lock_irq(&mapping->tree_lock);
+	if (page->mapping) {	/* Race with truncate? */
+		WARN_ON_ONCE(warn && !PageUptodate(page));
+
+		if (mapping_cap_account_dirty(mapping)) {
+			__inc_zone_page_state(page, NR_FILE_DIRTY);
+			task_io_account_write(PAGE_CACHE_SIZE);
+		}
+		radix_tree_tag_set(&mapping->page_tree,
+				page_index(page), PAGECACHE_TAG_DIRTY);
+	}
+	write_unlock_irq(&mapping->tree_lock);
+	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+
+	return 1;
+}
+
+/*
  * Add a page to the dirty page list.
  *
  * It is a sad fact of life that this function is called from several places
@@ -702,7 +735,7 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
  */
 int __set_page_dirty_buffers(struct page *page)
 {
-	struct address_space * const mapping = page_mapping(page);
+	struct address_space *mapping = page_mapping(page);
 
 	if (unlikely(!mapping))
 		return !TestSetPageDirty(page);
@@ -719,21 +752,7 @@ int __set_page_dirty_buffers(struct page *page)
 	}
 	spin_unlock(&mapping->private_lock);
 
-	if (TestSetPageDirty(page))
-		return 0;
-
-	write_lock_irq(&mapping->tree_lock);
-	if (page->mapping) {	/* Race with truncate? */
-		if (mapping_cap_account_dirty(mapping)) {
-			__inc_zone_page_state(page, NR_FILE_DIRTY);
-			task_io_account_write(PAGE_CACHE_SIZE);
-		}
-		radix_tree_tag_set(&mapping->page_tree,
-				page_index(page), PAGECACHE_TAG_DIRTY);
-	}
-	write_unlock_irq(&mapping->tree_lock);
-	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
-	return 1;
+	return __set_page_dirty(page, mapping, 1);
 }
 EXPORT_SYMBOL(__set_page_dirty_buffers);
 
@@ -1132,8 +1151,9 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size)
  */
 void fastcall mark_buffer_dirty(struct buffer_head *bh)
 {
+	WARN_ON_ONCE(!buffer_uptodate(bh));
 	if (!buffer_dirty(bh) && !test_set_buffer_dirty(bh))
-		__set_page_dirty_nobuffers(bh->b_page);
+		__set_page_dirty(bh->b_page, page_mapping(bh->b_page), 0);
 }
 
 /*
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index ea9da3bed3e9..886ea0d5a136 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -824,6 +824,7 @@ int __set_page_dirty_nobuffers(struct page *page)
 		mapping2 = page_mapping(page);
 		if (mapping2) { /* Race with truncate? */
 			BUG_ON(mapping2 != mapping);
+			WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
 			if (mapping_cap_account_dirty(mapping)) {
 				__inc_zone_page_state(page, NR_FILE_DIRTY);
 				task_io_account_write(PAGE_CACHE_SIZE);
diff --git a/mm/truncate.c b/mm/truncate.c
index 7c994f2d6145..f47e46d1be3b 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -100,9 +100,9 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
 	if (PagePrivate(page))
 		do_invalidatepage(page, 0);
 
+	remove_from_page_cache(page);
 	ClearPageUptodate(page);
 	ClearPageMappedToDisk(page);
-	remove_from_page_cache(page);
 	page_cache_release(page);	/* pagecache ref */
 }