writeback: fix dirtied pages accounting on redirty

De-account the accumulative dirty counters on page redirty.

Page redirties (very common in ext4) will introduce mismatch between
counters (a) and (b)

a) NR_DIRTIED, BDI_DIRTIED, tsk->nr_dirtied
b) NR_WRITTEN, BDI_WRITTEN

This will introduce systematic errors in balanced_rate and result in
dirty page position errors (ie. the dirty pages are no longer balanced
around the global/bdi setpoints).

Acked-by: Jan Kara <jack@suse.cz>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>

2 files changed, 21 insertions, 0 deletions

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 05eaf5e3aad7..b30419cd425e 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -197,6 +197,8 @@ void writeback_set_ratelimit(void);
 void tag_pages_for_writeback(struct address_space *mapping,
 			     pgoff_t start, pgoff_t end);
 
+void account_page_redirty(struct page *page);
+
 /* pdflush.c */
 extern int nr_pdflush_threads;	/* Global so it can be exported to sysctl
 				   read-only. */
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 5d1ef5d8613a..96b3e7aa705c 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1825,6 +1825,24 @@ int __set_page_dirty_nobuffers(struct page *page)
 EXPORT_SYMBOL(__set_page_dirty_nobuffers);
 
 /*
+ * Call this whenever redirtying a page, to de-account the dirty counters
+ * (NR_DIRTIED, BDI_DIRTIED, tsk->nr_dirtied), so that they match the written
+ * counters (NR_WRITTEN, BDI_WRITTEN) in long term. The mismatches will lead to
+ * systematic errors in balanced_dirty_ratelimit and the dirty pages position
+ * control.
+ */
+void account_page_redirty(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	if (mapping && mapping_cap_account_dirty(mapping)) {
+		current->nr_dirtied--;
+		dec_zone_page_state(page, NR_DIRTIED);
+		dec_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
+	}
+}
+EXPORT_SYMBOL(account_page_redirty);
+
+/*
  * When a writepage implementation decides that it doesn't want to write this
  * page for some reason, it should redirty the locked page via
  * redirty_page_for_writepage() and it should then unlock the page and return 0
@@ -1832,6 +1850,7 @@ EXPORT_SYMBOL(__set_page_dirty_nobuffers);
 int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
 {
 	wbc->pages_skipped++;
+	account_page_redirty(page);
 	return __set_page_dirty_nobuffers(page);
 }
 EXPORT_SYMBOL(redirty_page_for_writepage);