Merge branch 'for-linus' of git://git.kernel.dk/linux-block

Pull block layer fixes from Jens Axboe:
 "A final set of fixes for 4.3.

  It is (again) bigger than I would have liked, but it's all been
  through the testing mill and has been carefully reviewed by multiple
  parties.  Each fix is either a regression fix for this cycle, or is
  marked stable.  You can scold me at KS.  The pull request contains:

   - Three simple fixes for NVMe, fixing regressions since 4.3.  From
     Arnd, Christoph, and Keith.

   - A single xen-blkfront fix from Cathy, fixing a NULL dereference if
     an error is returned through the staste change callback.

   - Fixup for some bad/sloppy code in nbd that got introduced earlier
     in this cycle.  From Markus Pargmann.

   - A blk-mq tagset use-after-free fix from Junichi.

   - A backing device lifetime fix from Tejun, fixing a crash.

   - And finally, a set of regression/stable fixes for cgroup writeback
     from Tejun"

* 'for-linus' of git://git.kernel.dk/linux-block:
  writeback: remove broken rbtree_postorder_for_each_entry_safe() usage in cgwb_bdi_destroy()
  NVMe: Fix memory leak on retried commands
  block: don't release bdi while request_queue has live references
  nvme: use an integer value to Linux errno values
  blk-mq: fix use-after-free in blk_mq_free_tag_set()
  nvme: fix 32-bit build warning
  writeback: fix incorrect calculation of available memory for memcg domains
  writeback: memcg dirty_throttle_control should be initialized with wb->memcg_completions
  writeback: bdi_writeback iteration must not skip dying ones
  writeback: fix bdi_writeback iteration in wakeup_dirtytime_writeback()
  writeback: laptop_mode_timer_fn() needs rcu_read_lock() around bdi_writeback iteration
  nbd: Add locking for tasks
  xen-blkfront: check for null drvdata in blkback_changed (XenbusStateClosing)

1 files changed, 32 insertions, 22 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0a931cdd4f6b..2c90357c34ea 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -145,9 +145,6 @@ struct dirty_throttle_control {
 	unsigned long		pos_ratio;
 };
 
-#define DTC_INIT_COMMON(__wb)	.wb = (__wb),				\
-				.wb_completions = &(__wb)->completions
-
 /*
  * Length of period for aging writeout fractions of bdis. This is an
  * arbitrarily chosen number. The longer the period, the slower fractions will
@@ -157,12 +154,16 @@ struct dirty_throttle_control {
 
 #ifdef CONFIG_CGROUP_WRITEBACK
 
-#define GDTC_INIT(__wb)		.dom = &global_wb_domain,		\
-				DTC_INIT_COMMON(__wb)
+#define GDTC_INIT(__wb)		.wb = (__wb),				\
+				.dom = &global_wb_domain,		\
+				.wb_completions = &(__wb)->completions
+
 #define GDTC_INIT_NO_WB		.dom = &global_wb_domain
-#define MDTC_INIT(__wb, __gdtc)	.dom = mem_cgroup_wb_domain(__wb),	\
-				.gdtc = __gdtc,				\
-				DTC_INIT_COMMON(__wb)
+
+#define MDTC_INIT(__wb, __gdtc)	.wb = (__wb),				\
+				.dom = mem_cgroup_wb_domain(__wb),	\
+				.wb_completions = &(__wb)->memcg_completions, \
+				.gdtc = __gdtc
 
 static bool mdtc_valid(struct dirty_throttle_control *dtc)
 {
@@ -213,7 +214,8 @@ static void wb_min_max_ratio(struct bdi_writeback *wb,
 
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
-#define GDTC_INIT(__wb)		DTC_INIT_COMMON(__wb)
+#define GDTC_INIT(__wb)		.wb = (__wb),                           \
+				.wb_completions = &(__wb)->completions
 #define GDTC_INIT_NO_WB
 #define MDTC_INIT(__wb, __gdtc)
 
@@ -682,13 +684,19 @@ static unsigned long hard_dirty_limit(struct wb_domain *dom,
 	return max(thresh, dom->dirty_limit);
 }
 
-/* memory available to a memcg domain is capped by system-wide clean memory */
-static void mdtc_cap_avail(struct dirty_throttle_control *mdtc)
+/*
+ * Memory which can be further allocated to a memcg domain is capped by
+ * system-wide clean memory excluding the amount being used in the domain.
+ */
+static void mdtc_calc_avail(struct dirty_throttle_control *mdtc,
+			    unsigned long filepages, unsigned long headroom)
 {
 	struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc);
-	unsigned long clean = gdtc->avail - min(gdtc->avail, gdtc->dirty);
+	unsigned long clean = filepages - min(filepages, mdtc->dirty);
+	unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty);
+	unsigned long other_clean = global_clean - min(global_clean, clean);
 
-	mdtc->avail = min(mdtc->avail, clean);
+	mdtc->avail = filepages + min(headroom, other_clean);
 }
 
 /**
@@ -1562,16 +1570,16 @@ static void balance_dirty_pages(struct address_space *mapping,
 		}
 
 		if (mdtc) {
-			unsigned long writeback;
+			unsigned long filepages, headroom, writeback;
 
 			/*
 			 * If @wb belongs to !root memcg, repeat the same
 			 * basic calculations for the memcg domain.
 			 */
-			mem_cgroup_wb_stats(wb, &mdtc->avail, &mdtc->dirty,
-					    &writeback);
-			mdtc_cap_avail(mdtc);
+			mem_cgroup_wb_stats(wb, &filepages, &headroom,
+					    &mdtc->dirty, &writeback);
 			mdtc->dirty += writeback;
+			mdtc_calc_avail(mdtc, filepages, headroom);
 
 			domain_dirty_limits(mdtc);
 
@@ -1893,10 +1901,11 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb)
 		return true;
 
 	if (mdtc) {
-		unsigned long writeback;
+		unsigned long filepages, headroom, writeback;
 
-		mem_cgroup_wb_stats(wb, &mdtc->avail, &mdtc->dirty, &writeback);
-		mdtc_cap_avail(mdtc);
+		mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty,
+				    &writeback);
+		mdtc_calc_avail(mdtc, filepages, headroom);
 		domain_dirty_limits(mdtc);	/* ditto, ignore writeback */
 
 		if (mdtc->dirty > mdtc->bg_thresh)
@@ -1956,7 +1965,6 @@ void laptop_mode_timer_fn(unsigned long data)
 	int nr_pages = global_page_state(NR_FILE_DIRTY) +
 		global_page_state(NR_UNSTABLE_NFS);
 	struct bdi_writeback *wb;
-	struct wb_iter iter;
 
 	/*
 	 * We want to write everything out, not just down to the dirty
@@ -1965,10 +1973,12 @@ void laptop_mode_timer_fn(unsigned long data)
 	if (!bdi_has_dirty_io(&q->backing_dev_info))
 		return;
 
-	bdi_for_each_wb(wb, &q->backing_dev_info, &iter, 0)
+	rcu_read_lock();
+	list_for_each_entry_rcu(wb, &q->backing_dev_info.wb_list, bdi_node)
 		if (wb_has_dirty_io(wb))
 			wb_start_writeback(wb, nr_pages, true,
 					   WB_REASON_LAPTOP_TIMER);
+	rcu_read_unlock();
 }
 
 /*