1 files changed, 33 insertions, 62 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index ea0b7cb4a8c7..2cf69a5e46e6 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -253,32 +253,6 @@ static void bdi_writeout_fraction(struct backing_dev_info *bdi,
 	}
 }
 
-/*
- * Clip the earned share of dirty pages to that which is actually available.
- * This avoids exceeding the total dirty_limit when the floating averages
- * fluctuate too quickly.
- */
-static void clip_bdi_dirty_limit(struct backing_dev_info *bdi,
-		unsigned long dirty, unsigned long *pbdi_dirty)
-{
-	unsigned long avail_dirty;
-
-	avail_dirty = global_page_state(NR_FILE_DIRTY) +
-		 global_page_state(NR_WRITEBACK) +
-		 global_page_state(NR_UNSTABLE_NFS) +
-		 global_page_state(NR_WRITEBACK_TEMP);
-
-	if (avail_dirty < dirty)
-		avail_dirty = dirty - avail_dirty;
-	else
-		avail_dirty = 0;
-
-	avail_dirty += bdi_stat(bdi, BDI_RECLAIMABLE) +
-		bdi_stat(bdi, BDI_WRITEBACK);
-
-	*pbdi_dirty = min(*pbdi_dirty, avail_dirty);
-}
-
 static inline void task_dirties_fraction(struct task_struct *tsk,
 		long *numerator, long *denominator)
 {
@@ -469,7 +443,6 @@ get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty,
 			bdi_dirty = dirty * bdi->max_ratio / 100;
 
 		*pbdi_dirty = bdi_dirty;
-		clip_bdi_dirty_limit(bdi, dirty, pbdi_dirty);
 		task_dirty_limit(current, pbdi_dirty);
 	}
 }
@@ -491,7 +464,7 @@ static void balance_dirty_pages(struct address_space *mapping,
 	unsigned long bdi_thresh;
 	unsigned long pages_written = 0;
 	unsigned long pause = 1;
-
+	bool dirty_exceeded = false;
 	struct backing_dev_info *bdi = mapping->backing_dev_info;
 
 	for (;;) {
@@ -509,10 +482,35 @@ static void balance_dirty_pages(struct address_space *mapping,
 					global_page_state(NR_UNSTABLE_NFS);
 		nr_writeback = global_page_state(NR_WRITEBACK);
 
-		bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
-		bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
+		/*
+		 * In order to avoid the stacked BDI deadlock we need
+		 * to ensure we accurately count the 'dirty' pages when
+		 * the threshold is low.
+		 *
+		 * Otherwise it would be possible to get thresh+n pages
+		 * reported dirty, even though there are thresh-m pages
+		 * actually dirty; with m+n sitting in the percpu
+		 * deltas.
+		 */
+		if (bdi_thresh < 2*bdi_stat_error(bdi)) {
+			bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
+			bdi_nr_writeback = bdi_stat_sum(bdi, BDI_WRITEBACK);
+		} else {
+			bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
+			bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
+		}
 
-		if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
+		/*
+		 * The bdi thresh is somehow "soft" limit derived from the
+		 * global "hard" limit. The former helps to prevent heavy IO
+		 * bdi or process from holding back light ones; The latter is
+		 * the last resort safeguard.
+		 */
+		dirty_exceeded =
+			(bdi_nr_reclaimable + bdi_nr_writeback >= bdi_thresh)
+			|| (nr_reclaimable + nr_writeback >= dirty_thresh);
+
+		if (!dirty_exceeded)
 			break;
 
 		/*
@@ -540,34 +538,10 @@ static void balance_dirty_pages(struct address_space *mapping,
 		if (bdi_nr_reclaimable > bdi_thresh) {
 			writeback_inodes_wb(&bdi->wb, &wbc);
 			pages_written += write_chunk - wbc.nr_to_write;
-			get_dirty_limits(&background_thresh, &dirty_thresh,
-				       &bdi_thresh, bdi);
 			trace_wbc_balance_dirty_written(&wbc, bdi);
+			if (pages_written >= write_chunk)
+				break;		/* We've done our duty */
 		}
-
-		/*
-		 * In order to avoid the stacked BDI deadlock we need
-		 * to ensure we accurately count the 'dirty' pages when
-		 * the threshold is low.
-		 *
-		 * Otherwise it would be possible to get thresh+n pages
-		 * reported dirty, even though there are thresh-m pages
-		 * actually dirty; with m+n sitting in the percpu
-		 * deltas.
-		 */
-		if (bdi_thresh < 2*bdi_stat_error(bdi)) {
-			bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
-			bdi_nr_writeback = bdi_stat_sum(bdi, BDI_WRITEBACK);
-		} else if (bdi_nr_reclaimable) {
-			bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
-			bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
-		}
-
-		if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
-			break;
-		if (pages_written >= write_chunk)
-			break;		/* We've done our duty */
-
 		trace_wbc_balance_dirty_wait(&wbc, bdi);
 		__set_current_state(TASK_INTERRUPTIBLE);
 		io_schedule_timeout(pause);
@@ -581,8 +555,7 @@ static void balance_dirty_pages(struct address_space *mapping,
 			pause = HZ / 10;
 	}
 
-	if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
-			bdi->dirty_exceeded)
+	if (!dirty_exceeded && bdi->dirty_exceeded)
 		bdi->dirty_exceeded = 0;
 
 	if (writeback_in_progress(bdi))
@@ -597,9 +570,7 @@ static void balance_dirty_pages(struct address_space *mapping,
 	 * background_thresh, to keep the amount of dirty memory low.
 	 */
 	if ((laptop_mode && pages_written) ||
-	    (!laptop_mode && ((global_page_state(NR_FILE_DIRTY)
-			       + global_page_state(NR_UNSTABLE_NFS))
-					  > background_thresh)))
+	    (!laptop_mode && (nr_reclaimable > background_thresh)))
 		bdi_start_background_writeback(bdi);
 }