Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few MM hotfixes

 - kthread, tools, scripts, ntfs and ocfs2

 - some of MM

Subsystems affected by this patch series: kthread, tools, scripts, ntfs,
ocfs2 and mm (hofixes, pagealloc, slab-generic, slab, slub, kcsan,
debug, pagecache, gup, swap, shmem, memcg, pagemap, mremap, mincore,
sparsemem, vmalloc, kasan, pagealloc, hugetlb and vmscan).

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (162 commits)
  mm: vmscan: consistent update to pgrefill
  mm/vmscan.c: fix typo
  khugepaged: khugepaged_test_exit() check mmget_still_valid()
  khugepaged: retract_page_tables() remember to test exit
  khugepaged: collapse_pte_mapped_thp() protect the pmd lock
  khugepaged: collapse_pte_mapped_thp() flush the right range
  mm/hugetlb: fix calculation of adjust_range_if_pmd_sharing_possible
  mm: thp: replace HTTP links with HTTPS ones
  mm/page_alloc: fix memalloc_nocma_{save/restore} APIs
  mm/page_alloc.c: skip setting nodemask when we are in interrupt
  mm/page_alloc: fallbacks at most has 3 elements
  mm/page_alloc: silence a KASAN false positive
  mm/page_alloc.c: remove unnecessary end_bitidx for [set|get]_pfnblock_flags_mask()
  mm/page_alloc.c: simplify pageblock bitmap access
  mm/page_alloc.c: extract the common part in pfn_to_bitidx()
  mm/page_alloc.c: replace the definition of NR_MIGRATETYPE_BITS with PB_migratetype_bits
  mm/shuffle: remove dynamic reconfiguration
  mm/memory_hotplug: document why shuffle_zone() is relevant
  mm/page_alloc: remove nr_free_pagecache_pages()
  mm: remove vm_total_pages
  ...

1 files changed, 11 insertions, 28 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 749d239c62b2..72da290b171b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -170,11 +170,6 @@ struct scan_control {
  * From 0 .. 200.  Higher means more swappy.
  */
 int vm_swappiness = 60;
-/*
- * The total number of pages which are beyond the high watermark within all
- * zones.
- */
-unsigned long vm_total_pages;
 
 static void set_task_reclaim_state(struct task_struct *task,
 				   struct reclaim_state *rs)
@@ -915,7 +910,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		 * order to detect refaults, thus thrashing, later on.
 		 *
 		 * But don't store shadows in an address space that is
-		 * already exiting.  This is not just an optizimation,
+		 * already exiting.  This is not just an optimization,
 		 * inode reclaim needs to empty out the radix tree or
 		 * the nodes are lost.  Don't plant shadows behind its
 		 * back.
@@ -2035,7 +2030,8 @@ static void shrink_active_list(unsigned long nr_to_scan,
 
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
 
-	__count_vm_events(PGREFILL, nr_scanned);
+	if (!cgroup_reclaim(sc))
+		__count_vm_events(PGREFILL, nr_scanned);
 	__count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);
 
 	spin_unlock_irq(&pgdat->lru_lock);
@@ -2331,7 +2327,8 @@ out:
 		unsigned long protection;
 
 		lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
-		protection = mem_cgroup_protection(memcg,
+		protection = mem_cgroup_protection(sc->target_mem_cgroup,
+						   memcg,
 						   sc->memcg_low_reclaim);
 
 		if (protection) {
@@ -2619,14 +2616,15 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 		unsigned long reclaimed;
 		unsigned long scanned;
 
-		switch (mem_cgroup_protected(target_memcg, memcg)) {
-		case MEMCG_PROT_MIN:
+		mem_cgroup_calculate_protection(target_memcg, memcg);
+
+		if (mem_cgroup_below_min(memcg)) {
 			/*
 			 * Hard protection.
 			 * If there is no reclaimable memory, OOM.
 			 */
 			continue;
-		case MEMCG_PROT_LOW:
+		} else if (mem_cgroup_below_low(memcg)) {
 			/*
 			 * Soft protection.
 			 * Respect the protection only as long as
@@ -2638,16 +2636,6 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 				continue;
 			}
 			memcg_memory_event(memcg, MEMCG_LOW);
-			break;
-		case MEMCG_PROT_NONE:
-			/*
-			 * All protection thresholds breached. We may
-			 * still choose to vary the scan pressure
-			 * applied based on by how much the cgroup in
-			 * question has exceeded its protection
-			 * thresholds (see get_scan_count).
-			 */
-			break;
 		}
 
 		reclaimed = sc->nr_reclaimed;
@@ -3318,7 +3306,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 					   bool may_swap)
 {
 	unsigned long nr_reclaimed;
-	unsigned long pflags;
 	unsigned int noreclaim_flag;
 	struct scan_control sc = {
 		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
@@ -3339,17 +3326,12 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 	struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
 
 	set_task_reclaim_state(current, &sc.reclaim_state);
-
 	trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask);
-
-	psi_memstall_enter(&pflags);
 	noreclaim_flag = memalloc_noreclaim_save();
 
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
 	memalloc_noreclaim_restore(noreclaim_flag);
-	psi_memstall_leave(&pflags);
-
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
 	set_task_reclaim_state(current, NULL);
 
@@ -4222,7 +4204,8 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
 	 * unmapped file backed pages.
 	 */
 	if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages &&
-	    node_page_state(pgdat, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
+	    node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <=
+	    pgdat->min_slab_pages)
 		return NODE_RECLAIM_FULL;
 
 	/*