fb_defio: fix for non-dirty ptes

Fix a problem observed while using fb_defio with a short delay on a
PowerPC platform.

It is possible that page_mkclean() is invoked in the deferred io work
function _before_ a PTE has been marked dirty.  In this case, the page is
removed from the defio pagelist but page_mkclean() does not write-protect
the page again.  The end result is that defio ignores all subsequent
writes to the page and the corresponding portions of the framebuffer never
get updated.

The fix consists in keeping track of the pages with non-dirty PTEs,
re-checking them again on the next deferred io work iteration.  Note that
those pages are not passed to the defio callback as they are not written
by userspace yet.
Signed-off-by: NAlbert Herranz <albert_herranz@yahoo.es>
Acked-by: NJaya Kumar <jayakumar.lkml@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

drivers/video/fb_defio.c

@@ -155,25 +155,41 @@ static void fb_deferred_io_work(struct work_struct *work)
 {
 	struct fb_info *info = container_of(work, struct fb_info,
 						deferred_work.work);
-	struct list_head *node, *next;
-	struct page *cur;
 	struct fb_deferred_io *fbdefio = info->fbdefio;
+	struct page *page, *tmp_page;
+	struct list_head *node, *tmp_node;
+	struct list_head non_dirty;
+
+	INIT_LIST_HEAD(&non_dirty);
 
 	/* here we mkclean the pages, then do all deferred IO */
 	mutex_lock(&fbdefio->lock);
-	list_for_each_entry(cur, &fbdefio->pagelist, lru) {
-		lock_page(cur);
-		page_mkclean(cur);
-		unlock_page(cur);
+	list_for_each_entry_safe(page, tmp_page, &fbdefio->pagelist, lru) {
+		lock_page(page);
+		/*
+		 * The workqueue callback can be triggered after a
+		 * ->page_mkwrite() call but before the PTE has been marked
+		 * dirty. In this case page_mkclean() won't "rearm" the page.
+		 *
+		 * To avoid this, remove those "non-dirty" pages from the
+		 * pagelist before calling the driver's callback, then add
+		 * them back to get processed on the next work iteration.
+		 * At that time, their PTEs will hopefully be dirty for real.
+		 */
+		if (!page_mkclean(page))
+			list_move_tail(&page->lru, &non_dirty);
+		unlock_page(page);
 	}
 
 	/* driver's callback with pagelist */
 	fbdefio->deferred_io(info, &fbdefio->pagelist);
 
-	/* clear the list */
-	list_for_each_safe(node, next, &fbdefio->pagelist) {
+	/* clear the list... */
+	list_for_each_safe(node, tmp_node, &fbdefio->pagelist) {
 		list_del(node);
 	}
+	/* ... and add back the "non-dirty" pages to the list */
+	list_splice_tail(&non_dirty, &fbdefio->pagelist);
 	mutex_unlock(&fbdefio->lock);
 }
 
@@ -202,6 +218,7 @@ EXPORT_SYMBOL_GPL(fb_deferred_io_open);
 void fb_deferred_io_cleanup(struct fb_info *info)
 {
 	struct fb_deferred_io *fbdefio = info->fbdefio;
+	struct list_head *node, *tmp_node;
 	struct page *page;
 	int i;
 
@@ -209,6 +226,13 @@ void fb_deferred_io_cleanup(struct fb_info *info)
 	cancel_delayed_work(&info->deferred_work);
 	flush_scheduled_work();
 
+	/*  the list may have still some non-dirty pages at this point */
+	mutex_lock(&fbdefio->lock);
+	list_for_each_safe(node, tmp_node, &fbdefio->pagelist) {
+		list_del(node);
+	}
+	mutex_unlock(&fbdefio->lock);
+
 	/* clear out the mapping that we setup */
 	for (i = 0 ; i < info->fix.smem_len; i += PAGE_SIZE) {
 		page = fb_deferred_io_page(info, i);