Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "A few small subsystems and some of MM.

  172 patches.

  Subsystems affected by this patch series: hexagon, scripts, ntfs,
  ocfs2, vfs, and mm (slab-generic, slab, slub, debug, pagecache, swap,
  memcg, pagemap, mprotect, mremap, page-reporting, vmalloc, kasan,
  pagealloc, memory-failure, hugetlb, vmscan, z3fold, compaction,
  mempolicy, oom-kill, hugetlbfs, and migration)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (172 commits)
  mm/migrate: remove unneeded semicolons
  hugetlbfs: remove unneeded return value of hugetlb_vmtruncate()
  hugetlbfs: fix some comment typos
  hugetlbfs: correct some obsolete comments about inode i_mutex
  hugetlbfs: make hugepage size conversion more readable
  hugetlbfs: remove meaningless variable avoid_reserve
  hugetlbfs: correct obsolete function name in hugetlbfs_read_iter()
  hugetlbfs: use helper macro default_hstate in init_hugetlbfs_fs
  hugetlbfs: remove useless BUG_ON(!inode) in hugetlbfs_setattr()
  hugetlbfs: remove special hugetlbfs_set_page_dirty()
  mm/hugetlb: change hugetlb_reserve_pages() to type bool
  mm, oom: fix a comment in dump_task()
  mm/mempolicy: use helper range_in_vma() in queue_pages_test_walk()
  numa balancing: migrate on fault among multiple bound nodes
  mm, compaction: make fast_isolate_freepages() stay within zone
  mm/compaction: fix misbehaviors of fast_find_migrateblock()
  mm/compaction: correct deferral logic for proactive compaction
  mm/compaction: remove duplicated VM_BUG_ON_PAGE !PageLocked
  mm/compaction: remove rcu_read_lock during page compaction
  z3fold: simplify the zhdr initialization code in init_z3fold_page()
  ...

1 files changed, 40 insertions, 33 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 190ccdaa6c19..e04f4476e68e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -137,7 +137,6 @@ EXPORT_SYMBOL(__SetPageMovable);
 
 void __ClearPageMovable(struct page *page)
 {
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(!PageMovable(page), page);
 	/*
 	 * Clear registered address_space val with keeping PAGE_MAPPING_MOVABLE
@@ -988,14 +987,13 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (unlikely(!get_page_unless_zero(page)))
 			goto isolate_fail;
 
-		if (__isolate_lru_page_prepare(page, isolate_mode) != 0)
+		if (!__isolate_lru_page_prepare(page, isolate_mode))
 			goto isolate_fail_put;
 
 		/* Try isolate the page */
 		if (!TestClearPageLRU(page))
 			goto isolate_fail_put;
 
-		rcu_read_lock();
 		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
 		/* If we already hold the lock, we can skip some rechecking */
@@ -1005,7 +1003,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 			compact_lock_irqsave(&lruvec->lru_lock, &flags, cc);
 			locked = lruvec;
-			rcu_read_unlock();
 
 			lruvec_memcg_debug(lruvec, page);
 
@@ -1026,15 +1023,14 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 				SetPageLRU(page);
 				goto isolate_fail_put;
 			}
-		} else
-			rcu_read_unlock();
+		}
 
 		/* The whole page is taken off the LRU; skip the tail pages. */
 		if (PageCompound(page))
 			low_pfn += compound_nr(page) - 1;
 
 		/* Successfully isolated */
-		del_page_from_lru_list(page, lruvec, page_lru(page));
+		del_page_from_lru_list(page, lruvec);
 		mod_node_page_state(page_pgdat(page),
 				NR_ISOLATED_ANON + page_is_file_lru(page),
 				thp_nr_pages(page));
@@ -1288,7 +1284,7 @@ static void
 fast_isolate_around(struct compact_control *cc, unsigned long pfn, unsigned long nr_isolated)
 {
 	unsigned long start_pfn, end_pfn;
-	struct page *page = pfn_to_page(pfn);
+	struct page *page;
 
 	/* Do not search around if there are enough pages already */
 	if (cc->nr_freepages >= cc->nr_migratepages)
@@ -1299,8 +1295,12 @@ fast_isolate_around(struct compact_control *cc, unsigned long pfn, unsigned long
 		return;
 
 	/* Pageblock boundaries */
-	start_pfn = pageblock_start_pfn(pfn);
-	end_pfn = min(pageblock_end_pfn(pfn), zone_end_pfn(cc->zone)) - 1;
+	start_pfn = max(pageblock_start_pfn(pfn), cc->zone->zone_start_pfn);
+	end_pfn = min(pageblock_end_pfn(pfn), zone_end_pfn(cc->zone));
+
+	page = pageblock_pfn_to_page(start_pfn, end_pfn, cc->zone);
+	if (!page)
+		return;
 
 	/* Scan before */
 	if (start_pfn != pfn) {
@@ -1402,7 +1402,8 @@ fast_isolate_freepages(struct compact_control *cc)
 			pfn = page_to_pfn(freepage);
 
 			if (pfn >= highest)
-				highest = pageblock_start_pfn(pfn);
+				highest = max(pageblock_start_pfn(pfn),
+					      cc->zone->zone_start_pfn);
 
 			if (pfn >= low_pfn) {
 				cc->fast_search_fail = 0;
@@ -1472,7 +1473,8 @@ fast_isolate_freepages(struct compact_control *cc)
 			} else {
 				if (cc->direct_compaction && pfn_valid(min_pfn)) {
 					page = pageblock_pfn_to_page(min_pfn,
-						pageblock_end_pfn(min_pfn),
+						min(pageblock_end_pfn(min_pfn),
+						    zone_end_pfn(cc->zone)),
 						cc->zone);
 					cc->free_pfn = min_pfn;
 				}
@@ -1702,6 +1704,7 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 	unsigned long pfn = cc->migrate_pfn;
 	unsigned long high_pfn;
 	int order;
+	bool found_block = false;
 
 	/* Skip hints are relied on to avoid repeats on the fast search */
 	if (cc->ignore_skip_hint)
@@ -1744,7 +1747,7 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 	high_pfn = pageblock_start_pfn(cc->migrate_pfn + distance);
 
 	for (order = cc->order - 1;
-	     order >= PAGE_ALLOC_COSTLY_ORDER && pfn == cc->migrate_pfn && nr_scanned < limit;
+	     order >= PAGE_ALLOC_COSTLY_ORDER && !found_block && nr_scanned < limit;
 	     order--) {
 		struct free_area *area = &cc->zone->free_area[order];
 		struct list_head *freelist;
@@ -1759,7 +1762,11 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 		list_for_each_entry(freepage, freelist, lru) {
 			unsigned long free_pfn;
 
-			nr_scanned++;
+			if (nr_scanned++ >= limit) {
+				move_freelist_tail(freelist, freepage);
+				break;
+			}
+
 			free_pfn = page_to_pfn(freepage);
 			if (free_pfn < high_pfn) {
 				/*
@@ -1768,12 +1775,8 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 				 * the list assumes an entry is deleted, not
 				 * reordered.
 				 */
-				if (get_pageblock_skip(freepage)) {
-					if (list_is_last(freelist, &freepage->lru))
-						break;
-
+				if (get_pageblock_skip(freepage))
 					continue;
-				}
 
 				/* Reorder to so a future search skips recent pages */
 				move_freelist_tail(freelist, freepage);
@@ -1781,15 +1784,10 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 				update_fast_start_pfn(cc, free_pfn);
 				pfn = pageblock_start_pfn(free_pfn);
 				cc->fast_search_fail = 0;
+				found_block = true;
 				set_pageblock_skip(freepage);
 				break;
 			}
-
-			if (nr_scanned >= limit) {
-				cc->fast_search_fail++;
-				move_freelist_tail(freelist, freepage);
-				break;
-			}
 		}
 		spin_unlock_irqrestore(&cc->zone->lock, flags);
 	}
@@ -1800,9 +1798,10 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 	 * If fast scanning failed then use a cached entry for a page block
 	 * that had free pages as the basis for starting a linear scan.
 	 */
-	if (pfn == cc->migrate_pfn)
+	if (!found_block) {
+		cc->fast_search_fail++;
 		pfn = reinit_migrate_pfn(cc);
-
+	}
 	return pfn;
 }
 
@@ -1926,20 +1925,28 @@ static bool kswapd_is_running(pg_data_t *pgdat)
 
 /*
  * A zone's fragmentation score is the external fragmentation wrt to the
- * COMPACTION_HPAGE_ORDER scaled by the zone's size. It returns a value
- * in the range [0, 100].
+ * COMPACTION_HPAGE_ORDER. It returns a value in the range [0, 100].
+ */
+static unsigned int fragmentation_score_zone(struct zone *zone)
+{
+	return extfrag_for_order(zone, COMPACTION_HPAGE_ORDER);
+}
+
+/*
+ * A weighted zone's fragmentation score is the external fragmentation
+ * wrt to the COMPACTION_HPAGE_ORDER scaled by the zone's size. It
+ * returns a value in the range [0, 100].
  *
  * The scaling factor ensures that proactive compaction focuses on larger
  * zones like ZONE_NORMAL, rather than smaller, specialized zones like
  * ZONE_DMA32. For smaller zones, the score value remains close to zero,
  * and thus never exceeds the high threshold for proactive compaction.
  */
-static unsigned int fragmentation_score_zone(struct zone *zone)
+static unsigned int fragmentation_score_zone_weighted(struct zone *zone)
 {
 	unsigned long score;
 
-	score = zone->present_pages *
-			extfrag_for_order(zone, COMPACTION_HPAGE_ORDER);
+	score = zone->present_pages * fragmentation_score_zone(zone);
 	return div64_ul(score, zone->zone_pgdat->node_present_pages + 1);
 }
 
@@ -1959,7 +1966,7 @@ static unsigned int fragmentation_score_node(pg_data_t *pgdat)
 		struct zone *zone;
 
 		zone = &pgdat->node_zones[zoneid];
-		score += fragmentation_score_zone(zone);
+		score += fragmentation_score_zone_weighted(zone);
 	}
 
 	return score;