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)

3 files changed, 79 insertions, 46 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 2df8ddcb0ca0..619984fc07ec 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -480,6 +480,10 @@ static void cgwb_release_workfn(struct work_struct *work)
 						release_work);
 	struct backing_dev_info *bdi = wb->bdi;
 
+	spin_lock_irq(&cgwb_lock);
+	list_del_rcu(&wb->bdi_node);
+	spin_unlock_irq(&cgwb_lock);
+
 	wb_shutdown(wb);
 
 	css_put(wb->memcg_css);
@@ -575,6 +579,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
 		ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb);
 		if (!ret) {
 			atomic_inc(&bdi->usage_cnt);
+			list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list);
 			list_add(&wb->memcg_node, memcg_cgwb_list);
 			list_add(&wb->blkcg_node, blkcg_cgwb_list);
 			css_get(memcg_css);
@@ -676,7 +681,7 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
 {
 	struct radix_tree_iter iter;
-	struct bdi_writeback_congested *congested, *congested_n;
+	struct rb_node *rbn;
 	void **slot;
 
 	WARN_ON(test_bit(WB_registered, &bdi->wb.state));
@@ -686,9 +691,11 @@ static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
 	radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)
 		cgwb_kill(*slot);
 
-	rbtree_postorder_for_each_entry_safe(congested, congested_n,
-					&bdi->cgwb_congested_tree, rb_node) {
-		rb_erase(&congested->rb_node, &bdi->cgwb_congested_tree);
+	while ((rbn = rb_first(&bdi->cgwb_congested_tree))) {
+		struct bdi_writeback_congested *congested =
+			rb_entry(rbn, struct bdi_writeback_congested, rb_node);
+
+		rb_erase(rbn, &bdi->cgwb_congested_tree);
 		congested->bdi = NULL;	/* mark @congested unlinked */
 	}
 
@@ -764,15 +771,22 @@ static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { }
 
 int bdi_init(struct backing_dev_info *bdi)
 {
+	int ret;
+
 	bdi->dev = NULL;
 
 	bdi->min_ratio = 0;
 	bdi->max_ratio = 100;
 	bdi->max_prop_frac = FPROP_FRAC_BASE;
 	INIT_LIST_HEAD(&bdi->bdi_list);
+	INIT_LIST_HEAD(&bdi->wb_list);
 	init_waitqueue_head(&bdi->wb_waitq);
 
-	return cgwb_bdi_init(bdi);
+	ret = cgwb_bdi_init(bdi);
+
+	list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list);
+
+	return ret;
 }
 EXPORT_SYMBOL(bdi_init);
 
@@ -823,7 +837,7 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi)
 	synchronize_rcu_expedited();
 }
 
-void bdi_destroy(struct backing_dev_info *bdi)
+void bdi_unregister(struct backing_dev_info *bdi)
 {
 	/* make sure nobody finds us on the bdi_list anymore */
 	bdi_remove_from_list(bdi);
@@ -835,9 +849,19 @@ void bdi_destroy(struct backing_dev_info *bdi)
 		device_unregister(bdi->dev);
 		bdi->dev = NULL;
 	}
+}
 
+void bdi_exit(struct backing_dev_info *bdi)
+{
+	WARN_ON_ONCE(bdi->dev);
 	wb_exit(&bdi->wb);
 }
+
+void bdi_destroy(struct backing_dev_info *bdi)
+{
+	bdi_unregister(bdi);
+	bdi_exit(bdi);
+}
 EXPORT_SYMBOL(bdi_destroy);
 
 /*
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d9b5c817dce8..c57c4423c688 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3741,44 +3741,43 @@ struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
 /**
  * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg
  * @wb: bdi_writeback in question
- * @pavail: out parameter for number of available pages
+ * @pfilepages: out parameter for number of file pages
+ * @pheadroom: out parameter for number of allocatable pages according to memcg
  * @pdirty: out parameter for number of dirty pages
  * @pwriteback: out parameter for number of pages under writeback
  *
- * Determine the numbers of available, dirty, and writeback pages in @wb's
- * memcg.  Dirty and writeback are self-explanatory.  Available is a bit
- * more involved.
+ * Determine the numbers of file, headroom, dirty, and writeback pages in
+ * @wb's memcg.  File, dirty and writeback are self-explanatory.  Headroom
+ * is a bit more involved.
  *
- * A memcg's headroom is "min(max, high) - used".  The available memory is
- * calculated as the lowest headroom of itself and the ancestors plus the
- * number of pages already being used for file pages.  Note that this
- * doesn't consider the actual amount of available memory in the system.
- * The caller should further cap *@pavail accordingly.
+ * A memcg's headroom is "min(max, high) - used".  In the hierarchy, the
+ * headroom is calculated as the lowest headroom of itself and the
+ * ancestors.  Note that this doesn't consider the actual amount of
+ * available memory in the system.  The caller should further cap
+ * *@pheadroom accordingly.
  */
-void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pavail,
-			 unsigned long *pdirty, unsigned long *pwriteback)
+void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
+			 unsigned long *pheadroom, unsigned long *pdirty,
+			 unsigned long *pwriteback)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
 	struct mem_cgroup *parent;
-	unsigned long head_room = PAGE_COUNTER_MAX;
-	unsigned long file_pages;
 
 	*pdirty = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_DIRTY);
 
 	/* this should eventually include NR_UNSTABLE_NFS */
 	*pwriteback = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_WRITEBACK);
+	*pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) |
+						     (1 << LRU_ACTIVE_FILE));
+	*pheadroom = PAGE_COUNTER_MAX;
 
-	file_pages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) |
-						    (1 << LRU_ACTIVE_FILE));
 	while ((parent = parent_mem_cgroup(memcg))) {
 		unsigned long ceiling = min(memcg->memory.limit, memcg->high);
 		unsigned long used = page_counter_read(&memcg->memory);
 
-		head_room = min(head_room, ceiling - min(ceiling, used));
+		*pheadroom = min(*pheadroom, ceiling - min(ceiling, used));
 		memcg = parent;
 	}
-
-	*pavail = file_pages + head_room;
 }
 
 #else	/* CONFIG_CGROUP_WRITEBACK */
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();
 }
 
 /*