1 files changed, 104 insertions, 111 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0c6258bd1ba3..e3bccac1f025 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)
 {
@@ -287,16 +261,24 @@ static inline void task_dirties_fraction(struct task_struct *tsk,
 }
 
 /*
- * scale the dirty limit
+ * task_dirty_limit - scale down dirty throttling threshold for one task
  *
  * task specific dirty limit:
  *
  *   dirty -= (dirty/8) * p_{t}
+ *
+ * To protect light/slow dirtying tasks from heavier/fast ones, we start
+ * throttling individual tasks before reaching the bdi dirty limit.
+ * Relatively low thresholds will be allocated to heavy dirtiers. So when
+ * dirty pages grow large, heavy dirtiers will be throttled first, which will
+ * effectively curb the growth of dirty pages. Light dirtiers with high enough
+ * dirty threshold may never get throttled.
  */
-static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty)
+static unsigned long task_dirty_limit(struct task_struct *tsk,
+				       unsigned long bdi_dirty)
 {
 	long numerator, denominator;
-	unsigned long dirty = *pdirty;
+	unsigned long dirty = bdi_dirty;
 	u64 inv = dirty >> 3;
 
 	task_dirties_fraction(tsk, &numerator, &denominator);
@@ -304,10 +286,8 @@ static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty)
 	do_div(inv, denominator);
 
 	dirty -= inv;
-	if (dirty < *pdirty/2)
-		dirty = *pdirty/2;
 
-	*pdirty = dirty;
+	return max(dirty, bdi_dirty/2);
 }
 
 /*
@@ -417,9 +397,16 @@ unsigned long determine_dirtyable_memory(void)
 	return x + 1;	/* Ensure that we never return 0 */
 }
 
-void
-get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty,
-		 unsigned long *pbdi_dirty, struct backing_dev_info *bdi)
+/*
+ * global_dirty_limits - background-writeback and dirty-throttling thresholds
+ *
+ * Calculate the dirty thresholds based on sysctl parameters
+ * - vm.dirty_background_ratio  or  vm.dirty_background_bytes
+ * - vm.dirty_ratio             or  vm.dirty_bytes
+ * The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and
+ * runtime tasks.
+ */
+void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
 {
 	unsigned long background;
 	unsigned long dirty;
@@ -451,27 +438,37 @@ get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty,
 	}
 	*pbackground = background;
 	*pdirty = dirty;
+}
 
-	if (bdi) {
-		u64 bdi_dirty;
-		long numerator, denominator;
+/*
+ * bdi_dirty_limit - @bdi's share of dirty throttling threshold
+ *
+ * Allocate high/low dirty limits to fast/slow devices, in order to prevent
+ * - starving fast devices
+ * - piling up dirty pages (that will take long time to sync) on slow devices
+ *
+ * The bdi's share of dirty limit will be adapting to its throughput and
+ * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set.
+ */
+unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty)
+{
+	u64 bdi_dirty;
+	long numerator, denominator;
 
-		/*
-		 * Calculate this BDI's share of the dirty ratio.
-		 */
-		bdi_writeout_fraction(bdi, &numerator, &denominator);
-
-		bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100;
-		bdi_dirty *= numerator;
-		do_div(bdi_dirty, denominator);
-		bdi_dirty += (dirty * bdi->min_ratio) / 100;
-		if (bdi_dirty > (dirty * bdi->max_ratio) / 100)
-			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);
-	}
+	/*
+	 * Calculate this BDI's share of the dirty ratio.
+	 */
+	bdi_writeout_fraction(bdi, &numerator, &denominator);
+
+	bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100;
+	bdi_dirty *= numerator;
+	do_div(bdi_dirty, denominator);
+
+	bdi_dirty += (dirty * bdi->min_ratio) / 100;
+	if (bdi_dirty > (dirty * bdi->max_ratio) / 100)
+		bdi_dirty = dirty * bdi->max_ratio / 100;
+
+	return bdi_dirty;
 }
 
 /*
@@ -491,7 +488,7 @@ 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 (;;) {
@@ -502,18 +499,11 @@ static void balance_dirty_pages(struct address_space *mapping,
 			.range_cyclic	= 1,
 		};
 
-		get_dirty_limits(&background_thresh, &dirty_thresh,
-				&bdi_thresh, bdi);
-
 		nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
 					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);
-
-		if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
-			break;
+		global_dirty_limits(&background_thresh, &dirty_thresh);
 
 		/*
 		 * Throttle it only when the background writeback cannot
@@ -524,26 +514,8 @@ static void balance_dirty_pages(struct address_space *mapping,
 				(background_thresh + dirty_thresh) / 2)
 			break;
 
-		if (!bdi->dirty_exceeded)
-			bdi->dirty_exceeded = 1;
-
-		/* Note: nr_reclaimable denotes nr_dirty + nr_unstable.
-		 * Unstable writes are a feature of certain networked
-		 * filesystems (i.e. NFS) in which data may have been
-		 * written to the server's write cache, but has not yet
-		 * been flushed to permanent storage.
-		 * Only move pages to writeback if this bdi is over its
-		 * threshold otherwise wait until the disk writes catch
-		 * up.
-		 */
-		trace_wbc_balance_dirty_start(&wbc, bdi);
-		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);
-		}
+		bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
+		bdi_thresh = task_dirty_limit(current, bdi_thresh);
 
 		/*
 		 * In order to avoid the stacked BDI deadlock we need
@@ -558,16 +530,44 @@ static void balance_dirty_pages(struct address_space *mapping,
 		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) {
+		} 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;
-		if (pages_written >= write_chunk)
-			break;		/* We've done our duty */
 
+		if (!bdi->dirty_exceeded)
+			bdi->dirty_exceeded = 1;
+
+		/* Note: nr_reclaimable denotes nr_dirty + nr_unstable.
+		 * Unstable writes are a feature of certain networked
+		 * filesystems (i.e. NFS) in which data may have been
+		 * written to the server's write cache, but has not yet
+		 * been flushed to permanent storage.
+		 * Only move pages to writeback if this bdi is over its
+		 * threshold otherwise wait until the disk writes catch
+		 * up.
+		 */
+		trace_wbc_balance_dirty_start(&wbc, bdi);
+		if (bdi_nr_reclaimable > bdi_thresh) {
+			writeback_inodes_wb(&bdi->wb, &wbc);
+			pages_written += write_chunk - wbc.nr_to_write;
+			trace_wbc_balance_dirty_written(&wbc, bdi);
+			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 +581,7 @@ 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 +596,7 @@ 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);
 }
 
@@ -663,7 +660,7 @@ void throttle_vm_writeout(gfp_t gfp_mask)
 	unsigned long dirty_thresh;
 
         for ( ; ; ) {
-		get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
+		global_dirty_limits(&background_thresh, &dirty_thresh);
 
                 /*
                  * Boost the allowable dirty threshold a bit for page
@@ -825,10 +822,10 @@ void __init page_writeback_init(void)
 /*
  * We tag pages in batches of WRITEBACK_TAG_BATCH to reduce tree_lock latency.
  */
-#define WRITEBACK_TAG_BATCH 4096
 void tag_pages_for_writeback(struct address_space *mapping,
 			     pgoff_t start, pgoff_t end)
 {
+#define WRITEBACK_TAG_BATCH 4096
 	unsigned long tagged;
 
 	do {
@@ -839,7 +836,8 @@ void tag_pages_for_writeback(struct address_space *mapping,
 		spin_unlock_irq(&mapping->tree_lock);
 		WARN_ON_ONCE(tagged > WRITEBACK_TAG_BATCH);
 		cond_resched();
-	} while (tagged >= WRITEBACK_TAG_BATCH);
+		/* We check 'start' to handle wrapping when end == ~0UL */
+	} while (tagged >= WRITEBACK_TAG_BATCH && start);
 }
 EXPORT_SYMBOL(tag_pages_for_writeback);
 
@@ -987,22 +985,16 @@ continue_unlock:
 				}
 			}
 
-			if (wbc->nr_to_write > 0) {
-				if (--wbc->nr_to_write == 0 &&
-				    wbc->sync_mode == WB_SYNC_NONE) {
-					/*
-					 * We stop writing back only if we are
-					 * not doing integrity sync. In case of
-					 * integrity sync we have to keep going
-					 * because someone may be concurrently
-					 * dirtying pages, and we might have
-					 * synced a lot of newly appeared dirty
-					 * pages, but have not synced all of the
-					 * old dirty pages.
-					 */
-					done = 1;
-					break;
-				}
+			/*
+			 * We stop writing back only if we are not doing
+			 * integrity sync. In case of integrity sync we have to
+			 * keep going until we have written all the pages
+			 * we tagged for writeback prior to entering this loop.
+			 */
+			if (--wbc->nr_to_write <= 0 &&
+			    wbc->sync_mode == WB_SYNC_NONE) {
+				done = 1;
+				break;
 			}
 		}
 		pagevec_release(&pvec);
@@ -1134,6 +1126,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 		task_io_account_write(PAGE_CACHE_SIZE);
 	}
 }
+EXPORT_SYMBOL(account_page_dirtied);
 
 /*
  * For address_spaces which do not use buffers.  Just tag the page as dirty in