Merge branch 'next' into for-linus

Prepare first set of updates for 3.10 merge window.

1 files changed, 56 insertions, 12 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 830893b2b3c7..efe68148f621 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -35,6 +35,7 @@
 #include <linux/buffer_head.h> /* __set_page_dirty_buffers */
 #include <linux/pagevec.h>
 #include <linux/timer.h>
+#include <linux/sched/rt.h>
 #include <trace/events/writeback.h>
 
 /*
@@ -201,6 +202,18 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
 		     zone_reclaimable_pages(z) - z->dirty_balance_reserve;
 	}
 	/*
+	 * Unreclaimable memory (kernel memory or anonymous memory
+	 * without swap) can bring down the dirtyable pages below
+	 * the zone's dirty balance reserve and the above calculation
+	 * will underflow.  However we still want to add in nodes
+	 * which are below threshold (negative values) to get a more
+	 * accurate calculation but make sure that the total never
+	 * underflows.
+	 */
+	if ((long)x < 0)
+		x = 0;
+
+	/*
 	 * Make sure that the number of highmem pages is never larger
 	 * than the number of the total dirtyable memory. This can only
 	 * occur in very strange VM situations but we want to make sure
@@ -222,12 +235,15 @@ static unsigned long global_dirtyable_memory(void)
 {
 	unsigned long x;
 
-	x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages() -
-	    dirty_balance_reserve;
+	x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
+	x -= min(x, dirty_balance_reserve);
 
 	if (!vm_highmem_is_dirtyable)
 		x -= highmem_dirtyable_memory(x);
 
+	/* Subtract min_free_kbytes */
+	x -= min_t(unsigned long, x, min_free_kbytes >> (PAGE_SHIFT - 10));
+
 	return x + 1;	/* Ensure that we never return 0 */
 }
 
@@ -290,9 +306,12 @@ static unsigned long zone_dirtyable_memory(struct zone *zone)
 	 * highmem zone can hold its share of dirty pages, so we don't
 	 * care about vm_highmem_is_dirtyable here.
 	 */
-	return zone_page_state(zone, NR_FREE_PAGES) +
-	       zone_reclaimable_pages(zone) -
-	       zone->dirty_balance_reserve;
+	unsigned long nr_pages = zone_page_state(zone, NR_FREE_PAGES) +
+		zone_reclaimable_pages(zone);
+
+	/* don't allow this to underflow */
+	nr_pages -= min(nr_pages, zone->dirty_balance_reserve);
+	return nr_pages;
 }
 
 /**
@@ -677,7 +696,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
 	 *     => fast response on large errors; small oscillation near setpoint
 	 */
 	setpoint = (freerun + limit) / 2;
-	x = div_s64((setpoint - dirty) << RATELIMIT_CALC_SHIFT,
+	x = div_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
 		    limit - setpoint + 1);
 	pos_ratio = x;
 	pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
@@ -1069,7 +1088,7 @@ static void bdi_update_bandwidth(struct backing_dev_info *bdi,
 }
 
 /*
- * After a task dirtied this many pages, balance_dirty_pages_ratelimited_nr()
+ * After a task dirtied this many pages, balance_dirty_pages_ratelimited()
  * will look to see if it needs to start dirty throttling.
  *
  * If dirty_poll_interval is too low, big NUMA machines will call the expensive
@@ -1436,9 +1455,8 @@ static DEFINE_PER_CPU(int, bdp_ratelimits);
 DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
 
 /**
- * balance_dirty_pages_ratelimited_nr - balance dirty memory state
+ * balance_dirty_pages_ratelimited - balance dirty memory state
  * @mapping: address_space which was dirtied
- * @nr_pages_dirtied: number of pages which the caller has just dirtied
  *
  * Processes which are dirtying memory should call in here once for each page
  * which was newly dirtied.  The function will periodically check the system's
@@ -1449,8 +1467,7 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
  * limit we decrease the ratelimiting by a lot, to prevent individual processes
  * from overshooting the limit by (ratelimit_pages) each.
  */
-void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
-					unsigned long nr_pages_dirtied)
+void balance_dirty_pages_ratelimited(struct address_space *mapping)
 {
 	struct backing_dev_info *bdi = mapping->backing_dev_info;
 	int ratelimit;
@@ -1484,6 +1501,7 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
 	 */
 	p = &__get_cpu_var(dirty_throttle_leaks);
 	if (*p > 0 && current->nr_dirtied < ratelimit) {
+		unsigned long nr_pages_dirtied;
 		nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied);
 		*p -= nr_pages_dirtied;
 		current->nr_dirtied += nr_pages_dirtied;
@@ -1493,7 +1511,7 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
 	if (unlikely(current->nr_dirtied >= ratelimit))
 		balance_dirty_pages(mapping, current->nr_dirtied);
 }
-EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
+EXPORT_SYMBOL(balance_dirty_pages_ratelimited);
 
 void throttle_vm_writeout(gfp_t gfp_mask)
 {
@@ -1968,6 +1986,8 @@ int __set_page_dirty_no_writeback(struct page *page)
  */
 void account_page_dirtied(struct page *page, struct address_space *mapping)
 {
+	trace_writeback_dirty_page(page, mapping);
+
 	if (mapping_cap_account_dirty(mapping)) {
 		__inc_zone_page_state(page, NR_FILE_DIRTY);
 		__inc_zone_page_state(page, NR_DIRTIED);
@@ -2275,3 +2295,27 @@ int mapping_tagged(struct address_space *mapping, int tag)
 	return radix_tree_tagged(&mapping->page_tree, tag);
 }
 EXPORT_SYMBOL(mapping_tagged);
+
+/**
+ * wait_for_stable_page() - wait for writeback to finish, if necessary.
+ * @page:	The page to wait on.
+ *
+ * This function determines if the given page is related to a backing device
+ * that requires page contents to be held stable during writeback.  If so, then
+ * it will wait for any pending writeback to complete.
+ */
+void wait_for_stable_page(struct page *page)
+{
+	struct address_space *mapping = page_mapping(page);
+	struct backing_dev_info *bdi = mapping->backing_dev_info;
+
+	if (!bdi_cap_stable_pages_required(bdi))
+		return;
+#ifdef CONFIG_NEED_BOUNCE_POOL
+	if (mapping->host->i_sb->s_flags & MS_SNAP_STABLE)
+		return;
+#endif /* CONFIG_NEED_BOUNCE_POOL */
+
+	wait_on_page_writeback(page);
+}
+EXPORT_SYMBOL_GPL(wait_for_stable_page);