VM: Remove "clear_page_dirty()" and "test_clear_page_dirty()" functions

They were horribly easy to mis-use because of their tempting naming, and
they also did way more than any users of them generally wanted them to
do.

A dirty page can become clean under two circumstances:

 (a) when we write it out.  We have "clear_page_dirty_for_io()" for
     this, and that function remains unchanged.

     In the "for IO" case it is not sufficient to just clear the dirty
     bit, you also have to mark the page as being under writeback etc.

 (b) when we actually remove a page due to it becoming inaccessible to
     users, notably because it was truncate()'d away or the file (or
     metadata) no longer exists, and we thus want to cancel any
     outstanding dirty state.

For the (b) case, we now introduce "cancel_dirty_page()", which only
touches the page state itself, and verifies that the page is not mapped
(since cancelling writes on a mapped page would be actively wrong as it
is still accessible to users).

Some filesystems need to be fixed up for this: CIFS, FUSE, JFS,
ReiserFS, XFS all use the old confusing functions, and will be fixed
separately in subsequent commits (with some of them just removing the
offending logic, and others using clear_page_dirty_for_io()).

This was confirmed by Martin Michlmayr to fix the apt database
corruption on ARM.

Cc: Martin Michlmayr <tbm@cyrius.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Andrei Popa <andrei.popa@i-neo.ro>
Cc: Andrew Morton <akpm@osdl.org>
Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Cc: Gordon Farquharson <gordonfarquharson@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

4 files changed, 20 insertions, 47 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index ed2c223..4f4cd13 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -176,7 +176,7 @@ static int hugetlbfs_commit_write(struct file *file,
 
 static void truncate_huge_page(struct page *page)
 {
-	clear_page_dirty(page);
+	cancel_dirty_page(page, /* No IO accounting for huge pages? */0);
 	ClearPageUptodate(page);
 	remove_from_page_cache(page);
 	put_page(page);
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 4830a3b..350878a 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -253,15 +253,11 @@ static inline void SetPageUptodate(struct page *page)
 
 struct page;	/* forward declaration */
 
-int test_clear_page_dirty(struct page *page);
+extern void cancel_dirty_page(struct page *page, unsigned int account_size);
+
 int test_clear_page_writeback(struct page *page);
 int test_set_page_writeback(struct page *page);
 
-static inline void clear_page_dirty(struct page *page)
-{
-	test_clear_page_dirty(page);
-}
-
 static inline void set_page_writeback(struct page *page)
 {
 	test_set_page_writeback(page);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 237107c..b3a198c 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -845,38 +845,6 @@ int set_page_dirty_lock(struct page *page)
 EXPORT_SYMBOL(set_page_dirty_lock);
 
 /*
- * Clear a page's dirty flag, while caring for dirty memory accounting. 
- * Returns true if the page was previously dirty.
- */
-int test_clear_page_dirty(struct page *page)
-{
-	struct address_space *mapping = page_mapping(page);
-	unsigned long flags;
-
-	if (!mapping)
-		return TestClearPageDirty(page);
-
-	write_lock_irqsave(&mapping->tree_lock, flags);
-	if (TestClearPageDirty(page)) {
-		radix_tree_tag_clear(&mapping->page_tree,
-				page_index(page), PAGECACHE_TAG_DIRTY);
-		write_unlock_irqrestore(&mapping->tree_lock, flags);
-		/*
-		 * We can continue to use `mapping' here because the
-		 * page is locked, which pins the address_space
-		 */
-		if (mapping_cap_account_dirty(mapping)) {
-			page_mkclean(page);
-			dec_zone_page_state(page, NR_FILE_DIRTY);
-		}
-		return 1;
-	}
-	write_unlock_irqrestore(&mapping->tree_lock, flags);
-	return 0;
-}
-EXPORT_SYMBOL(test_clear_page_dirty);
-
-/*
  * Clear a page's dirty flag, while caring for dirty memory accounting.
  * Returns true if the page was previously dirty.
  *
diff --git a/mm/truncate.c b/mm/truncate.c
index 9bfb8e8..bf9e296 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -51,6 +51,20 @@ static inline void truncate_partial_page(struct page *page, unsigned partial)
 		do_invalidatepage(page, partial);
 }
 
+void cancel_dirty_page(struct page *page, unsigned int account_size)
+{
+	/* If we're cancelling the page, it had better not be mapped any more */
+	if (page_mapped(page)) {
+		static unsigned int warncount;
+
+		WARN_ON(++warncount < 5);
+	}
+		
+	if (TestClearPageDirty(page) && account_size)
+		task_io_account_cancelled_write(account_size);
+}
+
+
 /*
  * If truncate cannot remove the fs-private metadata from the page, the page
  * becomes anonymous.  It will be left on the LRU and may even be mapped into
@@ -70,8 +84,8 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
 	if (PagePrivate(page))
 		do_invalidatepage(page, 0);
 
-	if (test_clear_page_dirty(page))
-		task_io_account_cancelled_write(PAGE_CACHE_SIZE);
+	cancel_dirty_page(page, PAGE_CACHE_SIZE);
+
 	ClearPageUptodate(page);
 	ClearPageMappedToDisk(page);
 	remove_from_page_cache(page);
@@ -350,7 +364,6 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 		for (i = 0; !ret && i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 			pgoff_t page_index;
-			int was_dirty;
 
 			lock_page(page);
 			if (page->mapping != mapping) {
@@ -386,12 +399,8 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 					  PAGE_CACHE_SIZE, 0);
 				}
 			}
-			was_dirty = test_clear_page_dirty(page);
-			if (!invalidate_complete_page2(mapping, page)) {
-				if (was_dirty)
-					set_page_dirty(page);
+			if (!invalidate_complete_page2(mapping, page))
 				ret = -EIO;
-			}
 			unlock_page(page);
 		}
 		pagevec_release(&pvec);