writeback: fix dirtied pages accounting on sub-page writes

When dd in 512bytes, generic_perform_write() calls
balance_dirty_pages_ratelimited() 8 times for the same page, but
obviously the page is only dirtied once.

Fix it by accounting tsk->nr_dirtied and bdp_ratelimits at page dirty time.
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>

mm/page-writeback.c

@@ -1258,8 +1258,6 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
 	if (bdi->dirty_exceeded)
 		ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10));
 
-	current->nr_dirtied += nr_pages_dirtied;
-
 	preempt_disable();
 	/*
 	 * This prevents one CPU to accumulate too many dirtied pages without
@@ -1270,13 +1268,10 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
 	p =  &__get_cpu_var(bdp_ratelimits);
 	if (unlikely(current->nr_dirtied >= ratelimit))
 		*p = 0;
-	else {
-		*p += nr_pages_dirtied;
-		if (unlikely(*p >= ratelimit_pages)) {
+	else if (unlikely(*p >= ratelimit_pages)) {
 		*p = 0;
 		ratelimit = 0;
 	}
-	}
 	/*
 	 * Pick up the dirtied pages by the exited tasks. This avoids lots of
 	 * short-lived tasks (eg. gcc invocations in a kernel build) escaping
@@ -1768,6 +1763,8 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 		__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
 		__inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
 		task_io_account_write(PAGE_CACHE_SIZE);
+		current->nr_dirtied++;
+		this_cpu_inc(bdp_ratelimits);
 	}
 }
 EXPORT_SYMBOL(account_page_dirtied);