Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "191 patches.

  Subsystems affected by this patch series: kthread, ia64, scripts,
  ntfs, squashfs, ocfs2, kernel/watchdog, and mm (gup, pagealloc, slab,
  slub, kmemleak, dax, debug, pagecache, gup, swap, memcg, pagemap,
  mprotect, bootmem, dma, tracing, vmalloc, kasan, initialization,
  pagealloc, and memory-failure)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (191 commits)
  mm,hwpoison: make get_hwpoison_page() call get_any_page()
  mm,hwpoison: send SIGBUS with error virutal address
  mm/page_alloc: split pcp->high across all online CPUs for cpuless nodes
  mm/page_alloc: allow high-order pages to be stored on the per-cpu lists
  mm: replace CONFIG_FLAT_NODE_MEM_MAP with CONFIG_FLATMEM
  mm: replace CONFIG_NEED_MULTIPLE_NODES with CONFIG_NUMA
  docs: remove description of DISCONTIGMEM
  arch, mm: remove stale mentions of DISCONIGMEM
  mm: remove CONFIG_DISCONTIGMEM
  m68k: remove support for DISCONTIGMEM
  arc: remove support for DISCONTIGMEM
  arc: update comment about HIGHMEM implementation
  alpha: remove DISCONTIGMEM and NUMA
  mm/page_alloc: move free_the_page
  mm/page_alloc: fix counting of managed_pages
  mm/page_alloc: improve memmap_pages dbg msg
  mm: drop SECTION_SHIFT in code comments
  mm/page_alloc: introduce vm.percpu_pagelist_high_fraction
  mm/page_alloc: limit the number of pages on PCP lists when reclaim is active
  mm/page_alloc: scale the number of pages that are batch freed
  ...

1 files changed, 64 insertions, 2 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 576220acd686..271f2ca862c8 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -371,12 +371,16 @@ static void wb_exit(struct bdi_writeback *wb)
 #include <linux/memcontrol.h>
 
 /*
- * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, and memcg->cgwb_list.
- * bdi->cgwb_tree is also RCU protected.
+ * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, offline_cgwbs and
+ * memcg->cgwb_list.  bdi->cgwb_tree is also RCU protected.
  */
 static DEFINE_SPINLOCK(cgwb_lock);
 static struct workqueue_struct *cgwb_release_wq;
 
+static LIST_HEAD(offline_cgwbs);
+static void cleanup_offline_cgwbs_workfn(struct work_struct *work);
+static DECLARE_WORK(cleanup_offline_cgwbs_work, cleanup_offline_cgwbs_workfn);
+
 static void cgwb_release_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
@@ -395,7 +399,13 @@ static void cgwb_release_workfn(struct work_struct *work)
 
 	fprop_local_destroy_percpu(&wb->memcg_completions);
 	percpu_ref_exit(&wb->refcnt);
+
+	spin_lock_irq(&cgwb_lock);
+	list_del(&wb->offline_node);
+	spin_unlock_irq(&cgwb_lock);
+
 	wb_exit(wb);
+	WARN_ON_ONCE(!list_empty(&wb->b_attached));
 	kfree_rcu(wb, rcu);
 }
 
@@ -413,6 +423,7 @@ static void cgwb_kill(struct bdi_writeback *wb)
 	WARN_ON(!radix_tree_delete(&wb->bdi->cgwb_tree, wb->memcg_css->id));
 	list_del(&wb->memcg_node);
 	list_del(&wb->blkcg_node);
+	list_add(&wb->offline_node, &offline_cgwbs);
 	percpu_ref_kill(&wb->refcnt);
 }
 
@@ -472,6 +483,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
 
 	wb->memcg_css = memcg_css;
 	wb->blkcg_css = blkcg_css;
+	INIT_LIST_HEAD(&wb->b_attached);
 	INIT_WORK(&wb->release_work, cgwb_release_workfn);
 	set_bit(WB_registered, &wb->state);
 
@@ -633,6 +645,54 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi)
 	mutex_unlock(&bdi->cgwb_release_mutex);
 }
 
+/*
+ * cleanup_offline_cgwbs_workfn - try to release dying cgwbs
+ *
+ * Try to release dying cgwbs by switching attached inodes to the nearest
+ * living ancestor's writeback. Processed wbs are placed at the end
+ * of the list to guarantee the forward progress.
+ */
+static void cleanup_offline_cgwbs_workfn(struct work_struct *work)
+{
+	struct bdi_writeback *wb;
+	LIST_HEAD(processed);
+
+	spin_lock_irq(&cgwb_lock);
+
+	while (!list_empty(&offline_cgwbs)) {
+		wb = list_first_entry(&offline_cgwbs, struct bdi_writeback,
+				      offline_node);
+		list_move(&wb->offline_node, &processed);
+
+		/*
+		 * If wb is dirty, cleaning up the writeback by switching
+		 * attached inodes will result in an effective removal of any
+		 * bandwidth restrictions, which isn't the goal.  Instead,
+		 * it can be postponed until the next time, when all io
+		 * will be likely completed.  If in the meantime some inodes
+		 * will get re-dirtied, they should be eventually switched to
+		 * a new cgwb.
+		 */
+		if (wb_has_dirty_io(wb))
+			continue;
+
+		if (!wb_tryget(wb))
+			continue;
+
+		spin_unlock_irq(&cgwb_lock);
+		while (cleanup_offline_cgwb(wb))
+			cond_resched();
+		spin_lock_irq(&cgwb_lock);
+
+		wb_put(wb);
+	}
+
+	if (!list_empty(&processed))
+		list_splice_tail(&processed, &offline_cgwbs);
+
+	spin_unlock_irq(&cgwb_lock);
+}
+
 /**
  * wb_memcg_offline - kill all wb's associated with a memcg being offlined
  * @memcg: memcg being offlined
@@ -649,6 +709,8 @@ void wb_memcg_offline(struct mem_cgroup *memcg)
 		cgwb_kill(wb);
 	memcg_cgwb_list->next = NULL;	/* prevent new wb's */
 	spin_unlock_irq(&cgwb_lock);
+
+	queue_work(system_unbound_wq, &cleanup_offline_cgwbs_work);
 }
 
 /**