diff --git a/mm/compaction.c b/mm/compaction.c
index faca45e..672d3c7 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -22,6 +22,7 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/page_owner.h>
+#include <linux/psi.h>
 #include "internal.h"
 
 #ifdef CONFIG_COMPACTION
@@ -65,7 +66,7 @@
 	return high_pfn;
 }
 
-static void map_pages(struct list_head *list)
+static void split_map_pages(struct list_head *list)
 {
 	unsigned int i, order, nr_pages;
 	struct page *page, *next;
@@ -236,6 +237,78 @@
 	return false;
 }
 
+static bool
+__reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
+							bool check_target)
+{
+	struct page *page = pfn_to_online_page(pfn);
+	struct page *block_page;
+	struct page *end_page;
+	unsigned long block_pfn;
+
+	if (!page)
+		return false;
+	if (zone != page_zone(page))
+		return false;
+	if (pageblock_skip_persistent(page))
+		return false;
+
+	/*
+	 * If skip is already cleared do no further checking once the
+	 * restart points have been set.
+	 */
+	if (check_source && check_target && !get_pageblock_skip(page))
+		return true;
+
+	/*
+	 * If clearing skip for the target scanner, do not select a
+	 * non-movable pageblock as the starting point.
+	 */
+	if (!check_source && check_target &&
+	    get_pageblock_migratetype(page) != MIGRATE_MOVABLE)
+		return false;
+
+	/* Ensure the start of the pageblock or zone is online and valid */
+	block_pfn = pageblock_start_pfn(pfn);
+	block_pfn = max(block_pfn, zone->zone_start_pfn);
+	block_page = pfn_to_online_page(block_pfn);
+	if (block_page) {
+		page = block_page;
+		pfn = block_pfn;
+	}
+
+	/* Ensure the end of the pageblock or zone is online and valid */
+	block_pfn = pageblock_end_pfn(pfn) - 1;
+	block_pfn = min(block_pfn, zone_end_pfn(zone) - 1);
+	end_page = pfn_to_online_page(block_pfn);
+	if (!end_page)
+		return false;
+
+	/*
+	 * Only clear the hint if a sample indicates there is either a
+	 * free page or an LRU page in the block. One or other condition
+	 * is necessary for the block to be a migration source/target.
+	 */
+	do {
+		if (pfn_valid_within(pfn)) {
+			if (check_source && PageLRU(page)) {
+				clear_pageblock_skip(page);
+				return true;
+			}
+
+			if (check_target && PageBuddy(page)) {
+				clear_pageblock_skip(page);
+				return true;
+			}
+		}
+
+		page += (1 << PAGE_ALLOC_COSTLY_ORDER);
+		pfn += (1 << PAGE_ALLOC_COSTLY_ORDER);
+	} while (page <= end_page);
+
+	return false;
+}
+
 /*
  * This function is called to clear all cached information on pageblocks that
  * should be skipped for page isolation when the migrate and free page scanner
@@ -243,30 +316,54 @@
  */
 static void __reset_isolation_suitable(struct zone *zone)
 {
-	unsigned long start_pfn = zone->zone_start_pfn;
-	unsigned long end_pfn = zone_end_pfn(zone);
-	unsigned long pfn;
+	unsigned long migrate_pfn = zone->zone_start_pfn;
+	unsigned long free_pfn = zone_end_pfn(zone) - 1;
+	unsigned long reset_migrate = free_pfn;
+	unsigned long reset_free = migrate_pfn;
+	bool source_set = false;
+	bool free_set = false;
+
+	if (!zone->compact_blockskip_flush)
+		return;
 
 	zone->compact_blockskip_flush = false;
 
-	/* Walk the zone and mark every pageblock as suitable for isolation */
-	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
-		struct page *page;
-
+	/*
+	 * Walk the zone and update pageblock skip information. Source looks
+	 * for PageLRU while target looks for PageBuddy. When the scanner
+	 * is found, both PageBuddy and PageLRU are checked as the pageblock
+	 * is suitable as both source and target.
+	 */
+	for (; migrate_pfn < free_pfn; migrate_pfn += pageblock_nr_pages,
+					free_pfn -= pageblock_nr_pages) {
 		cond_resched();
 
-		page = pfn_to_online_page(pfn);
-		if (!page)
-			continue;
-		if (zone != page_zone(page))
-			continue;
-		if (pageblock_skip_persistent(page))
-			continue;
+		/* Update the migrate PFN */
+		if (__reset_isolation_pfn(zone, migrate_pfn, true, source_set) &&
+		    migrate_pfn < reset_migrate) {
+			source_set = true;
+			reset_migrate = migrate_pfn;
+			zone->compact_init_migrate_pfn = reset_migrate;
+			zone->compact_cached_migrate_pfn[0] = reset_migrate;
+			zone->compact_cached_migrate_pfn[1] = reset_migrate;
+		}
 
-		clear_pageblock_skip(page);
+		/* Update the free PFN */
+		if (__reset_isolation_pfn(zone, free_pfn, free_set, true) &&
+		    free_pfn > reset_free) {
+			free_set = true;
+			reset_free = free_pfn;
+			zone->compact_init_free_pfn = reset_free;
+			zone->compact_cached_free_pfn = reset_free;
+		}
 	}
 
-	reset_cached_positions(zone);
+	/* Leave no distance if no suitable block was reset */
+	if (reset_migrate >= reset_free) {
+		zone->compact_cached_migrate_pfn[0] = migrate_pfn;
+		zone->compact_cached_migrate_pfn[1] = migrate_pfn;
+		zone->compact_cached_free_pfn = free_pfn;
+	}
 }
 
 void reset_isolation_suitable(pg_data_t *pgdat)
@@ -285,15 +382,53 @@
 }
 
 /*
+ * Sets the pageblock skip bit if it was clear. Note that this is a hint as
+ * locks are not required for read/writers. Returns true if it was already set.
+ */
+static bool test_and_set_skip(struct compact_control *cc, struct page *page,
+							unsigned long pfn)
+{
+	bool skip;
+
+	/* Do no update if skip hint is being ignored */
+	if (cc->ignore_skip_hint)
+		return false;
+
+	if (!IS_ALIGNED(pfn, pageblock_nr_pages))
+		return false;
+
+	skip = get_pageblock_skip(page);
+	if (!skip && !cc->no_set_skip_hint)
+		set_pageblock_skip(page);
+
+	return skip;
+}
+
+static void update_cached_migrate(struct compact_control *cc, unsigned long pfn)
+{
+	struct zone *zone = cc->zone;
+
+	pfn = pageblock_end_pfn(pfn);
+
+	/* Set for isolation rather than compaction */
+	if (cc->no_set_skip_hint)
+		return;
+
+	if (pfn > zone->compact_cached_migrate_pfn[0])
+		zone->compact_cached_migrate_pfn[0] = pfn;
+	if (cc->mode != MIGRATE_ASYNC &&
+	    pfn > zone->compact_cached_migrate_pfn[1])
+		zone->compact_cached_migrate_pfn[1] = pfn;
+}
+
+/*
  * If no pages were isolated then mark this pageblock to be skipped in the
  * future. The information is later cleared by __reset_isolation_suitable().
  */
 static void update_pageblock_skip(struct compact_control *cc,
-			struct page *page, unsigned long nr_isolated,
-			bool migrate_scanner)
+			struct page *page, unsigned long pfn)
 {
 	struct zone *zone = cc->zone;
-	unsigned long pfn;
 
 	if (cc->no_set_skip_hint)
 		return;
@@ -301,24 +436,11 @@
 	if (!page)
 		return;
 
-	if (nr_isolated)
-		return;
-
 	set_pageblock_skip(page);
 
-	pfn = page_to_pfn(page);
-
 	/* Update where async and sync compaction should restart */
-	if (migrate_scanner) {
-		if (pfn > zone->compact_cached_migrate_pfn[0])
-			zone->compact_cached_migrate_pfn[0] = pfn;
-		if (cc->mode != MIGRATE_ASYNC &&
-		    pfn > zone->compact_cached_migrate_pfn[1])
-			zone->compact_cached_migrate_pfn[1] = pfn;
-	} else {
-		if (pfn < zone->compact_cached_free_pfn)
-			zone->compact_cached_free_pfn = pfn;
-	}
+	if (pfn < zone->compact_cached_free_pfn)
+		zone->compact_cached_free_pfn = pfn;
 }
 #else
 static inline bool isolation_suitable(struct compact_control *cc,
@@ -333,32 +455,42 @@
 }
 
 static inline void update_pageblock_skip(struct compact_control *cc,
-			struct page *page, unsigned long nr_isolated,
-			bool migrate_scanner)
+			struct page *page, unsigned long pfn)
 {
 }
+
+static void update_cached_migrate(struct compact_control *cc, unsigned long pfn)
+{
+}
+
+static bool test_and_set_skip(struct compact_control *cc, struct page *page,
+							unsigned long pfn)
+{
+	return false;
+}
 #endif /* CONFIG_COMPACTION */
 
 /*
  * Compaction requires the taking of some coarse locks that are potentially
- * very heavily contended. For async compaction, back out if the lock cannot
- * be taken immediately. For sync compaction, spin on the lock if needed.
+ * very heavily contended. For async compaction, trylock and record if the
+ * lock is contended. The lock will still be acquired but compaction will
+ * abort when the current block is finished regardless of success rate.
+ * Sync compaction acquires the lock.
  *
- * Returns true if the lock is held
- * Returns false if the lock is not held and compaction should abort
+ * Always returns true which makes it easier to track lock state in callers.
  */
-static bool compact_trylock_irqsave(spinlock_t *lock, unsigned long *flags,
+static bool compact_lock_irqsave(spinlock_t *lock, unsigned long *flags,
 						struct compact_control *cc)
 {
-	if (cc->mode == MIGRATE_ASYNC) {
-		if (!spin_trylock_irqsave(lock, *flags)) {
-			cc->contended = true;
-			return false;
-		}
-	} else {
-		spin_lock_irqsave(lock, *flags);
+	/* Track if the lock is contended in async mode */
+	if (cc->mode == MIGRATE_ASYNC && !cc->contended) {
+		if (spin_trylock_irqsave(lock, *flags))
+			return true;
+
+		cc->contended = true;
 	}
 
+	spin_lock_irqsave(lock, *flags);
 	return true;
 }
 
@@ -390,37 +522,7 @@
 		return true;
 	}
 
-	if (need_resched()) {
-		if (cc->mode == MIGRATE_ASYNC) {
-			cc->contended = true;
-			return true;
-		}
-		cond_resched();
-	}
-
-	return false;
-}
-
-/*
- * Aside from avoiding lock contention, compaction also periodically checks
- * need_resched() and either schedules in sync compaction or aborts async
- * compaction. This is similar to what compact_unlock_should_abort() does, but
- * is used where no lock is concerned.
- *
- * Returns false when no scheduling was needed, or sync compaction scheduled.
- * Returns true when async compaction should abort.
- */
-static inline bool compact_should_abort(struct compact_control *cc)
-{
-	/* async compaction aborts if contended */
-	if (need_resched()) {
-		if (cc->mode == MIGRATE_ASYNC) {
-			cc->contended = true;
-			return true;
-		}
-
-		cond_resched();
-	}
+	cond_resched();
 
 	return false;
 }
@@ -434,19 +536,24 @@
 				unsigned long *start_pfn,
 				unsigned long end_pfn,
 				struct list_head *freelist,
+				unsigned int stride,
 				bool strict)
 {
 	int nr_scanned = 0, total_isolated = 0;
-	struct page *cursor, *valid_page = NULL;
+	struct page *cursor;
 	unsigned long flags = 0;
 	bool locked = false;
 	unsigned long blockpfn = *start_pfn;
 	unsigned int order;
 
+	/* Strict mode is for isolation, speed is secondary */
+	if (strict)
+		stride = 1;
+
 	cursor = pfn_to_page(blockpfn);
 
 	/* Isolate free pages. */
-	for (; blockpfn < end_pfn; blockpfn++, cursor++) {
+	for (; blockpfn < end_pfn; blockpfn += stride, cursor += stride) {
 		int isolated;
 		struct page *page = cursor;
 
@@ -464,9 +571,6 @@
 		if (!pfn_valid_within(blockpfn))
 			goto isolate_fail;
 
-		if (!valid_page)
-			valid_page = page;
-
 		/*
 		 * For compound pages such as THP and hugetlbfs, we can save
 		 * potentially a lot of iterations if we skip them at once.
@@ -494,18 +598,8 @@
 		 * recheck as well.
 		 */
 		if (!locked) {
-			/*
-			 * The zone lock must be held to isolate freepages.
-			 * Unfortunately this is a very coarse lock and can be
-			 * heavily contended if there are parallel allocations
-			 * or parallel compactions. For async compaction do not
-			 * spin on the lock and we acquire the lock as late as
-			 * possible.
-			 */
-			locked = compact_trylock_irqsave(&cc->zone->lock,
+			locked = compact_lock_irqsave(&cc->zone->lock,
 								&flags, cc);
-			if (!locked)
-				break;
 
 			/* Recheck this is a buddy page under lock */
 			if (!PageBuddy(page))
@@ -564,10 +658,6 @@
 	if (strict && blockpfn < end_pfn)
 		total_isolated = 0;
 
-	/* Update the pageblock-skip if the whole pageblock was scanned */
-	if (blockpfn == end_pfn)
-		update_pageblock_skip(cc, valid_page, total_isolated, false);
-
 	cc->total_free_scanned += nr_scanned;
 	if (total_isolated)
 		count_compact_events(COMPACTISOLATED, total_isolated);
@@ -625,7 +715,7 @@
 			break;
 
 		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
-						block_end_pfn, &freelist, true);
+					block_end_pfn, &freelist, 0, true);
 
 		/*
 		 * In strict mode, isolate_freepages_block() returns 0 if
@@ -643,7 +733,7 @@
 	}
 
 	/* __isolate_free_page() does not map the pages */
-	map_pages(&freelist);
+	split_map_pages(&freelist);
 
 	if (pfn < end_pfn) {
 		/* Loop terminated early, cleanup. */
@@ -656,16 +746,16 @@
 }
 
 /* Similar to reclaim, but different enough that they don't share logic */
-static bool too_many_isolated(struct zone *zone)
+static bool too_many_isolated(pg_data_t *pgdat)
 {
 	unsigned long active, inactive, isolated;
 
-	inactive = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE) +
-			node_page_state(zone->zone_pgdat, NR_INACTIVE_ANON);
-	active = node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE) +
-			node_page_state(zone->zone_pgdat, NR_ACTIVE_ANON);
-	isolated = node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE) +
-			node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON);
+	inactive = node_page_state(pgdat, NR_INACTIVE_FILE) +
+			node_page_state(pgdat, NR_INACTIVE_ANON);
+	active = node_page_state(pgdat, NR_ACTIVE_FILE) +
+			node_page_state(pgdat, NR_ACTIVE_ANON);
+	isolated = node_page_state(pgdat, NR_ISOLATED_FILE) +
+			node_page_state(pgdat, NR_ISOLATED_ANON);
 
 	return isolated > (inactive + active) / 2;
 }
@@ -692,7 +782,7 @@
 isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			unsigned long end_pfn, isolate_mode_t isolate_mode)
 {
-	struct zone *zone = cc->zone;
+	pg_data_t *pgdat = cc->zone->zone_pgdat;
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct lruvec *lruvec;
 	unsigned long flags = 0;
@@ -701,13 +791,14 @@
 	unsigned long start_pfn = low_pfn;
 	bool skip_on_failure = false;
 	unsigned long next_skip_pfn = 0;
+	bool skip_updated = false;
 
 	/*
 	 * Ensure that there are not too many pages isolated from the LRU
 	 * list by either parallel reclaimers or compaction. If there are,
 	 * delay for some time until fewer pages are isolated
 	 */
-	while (unlikely(too_many_isolated(zone))) {
+	while (unlikely(too_many_isolated(pgdat))) {
 		/* async migration should just abort */
 		if (cc->mode == MIGRATE_ASYNC)
 			return 0;
@@ -718,8 +809,7 @@
 			return 0;
 	}
 
-	if (compact_should_abort(cc))
-		return 0;
+	cond_resched();
 
 	if (cc->direct_compaction && (cc->mode == MIGRATE_ASYNC)) {
 		skip_on_failure = true;
@@ -753,13 +843,15 @@
 
 		/*
 		 * Periodically drop the lock (if held) regardless of its
-		 * contention, to give chance to IRQs. Abort async compaction
-		 * if contended.
+		 * contention, to give chance to IRQs. Abort completely if
+		 * a fatal signal is pending.
 		 */
 		if (!(low_pfn % SWAP_CLUSTER_MAX)
-		    && compact_unlock_should_abort(zone_lru_lock(zone), flags,
-								&locked, cc))
-			break;
+		    && compact_unlock_should_abort(&pgdat->lru_lock,
+					    flags, &locked, cc)) {
+			low_pfn = 0;
+			goto fatal_pending;
+		}
 
 		if (!pfn_valid_within(low_pfn))
 			goto isolate_fail;
@@ -767,8 +859,19 @@
 
 		page = pfn_to_page(low_pfn);
 
-		if (!valid_page)
+		/*
+		 * Check if the pageblock has already been marked skipped.
+		 * Only the aligned PFN is checked as the caller isolates
+		 * COMPACT_CLUSTER_MAX at a time so the second call must
+		 * not falsely conclude that the block should be skipped.
+		 */
+		if (!valid_page && IS_ALIGNED(low_pfn, pageblock_nr_pages)) {
+			if (!cc->ignore_skip_hint && get_pageblock_skip(page)) {
+				low_pfn = end_pfn;
+				goto isolate_abort;
+			}
 			valid_page = page;
+		}
 
 		/*
 		 * Skip if free. We read page order here without zone lock
@@ -817,7 +920,7 @@
 			if (unlikely(__PageMovable(page)) &&
 					!PageIsolated(page)) {
 				if (locked) {
-					spin_unlock_irqrestore(zone_lru_lock(zone),
+					spin_unlock_irqrestore(&pgdat->lru_lock,
 									flags);
 					locked = false;
 				}
@@ -847,10 +950,15 @@
 
 		/* If we already hold the lock, we can skip some rechecking */
 		if (!locked) {
-			locked = compact_trylock_irqsave(zone_lru_lock(zone),
+			locked = compact_lock_irqsave(&pgdat->lru_lock,
 								&flags, cc);
-			if (!locked)
-				break;
+
+			/* Try get exclusive access under lock */
+			if (!skip_updated) {
+				skip_updated = true;
+				if (test_and_set_skip(cc, page, low_pfn))
+					goto isolate_abort;
+			}
 
 			/* Recheck PageLRU and PageCompound under lock */
 			if (!PageLRU(page))
@@ -862,12 +970,12 @@
 			 * is safe to read and it's 0 for tail pages.
 			 */
 			if (unlikely(PageCompound(page))) {
-				low_pfn += (1UL << compound_order(page)) - 1;
+				low_pfn += compound_nr(page) - 1;
 				goto isolate_fail;
 			}
 		}
 
-		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
 		/* Try isolate the page */
 		if (__isolate_lru_page(page, isolate_mode) != 0)
@@ -886,16 +994,13 @@
 		nr_isolated++;
 
 		/*
-		 * Record where we could have freed pages by migration and not
-		 * yet flushed them to buddy allocator.
-		 * - this is the lowest page that was isolated and likely be
-		 * then freed by migration.
+		 * Avoid isolating too much unless this block is being
+		 * rescanned (e.g. dirty/writeback pages, parallel allocation)
+		 * or a lock is contended. For contention, isolate quickly to
+		 * potentially remove one source of contention.
 		 */
-		if (!cc->last_migrated_pfn)
-			cc->last_migrated_pfn = low_pfn;
-
-		/* Avoid isolating too much */
-		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
+		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX &&
+		    !cc->rescan && !cc->contended) {
 			++low_pfn;
 			break;
 		}
@@ -912,12 +1017,11 @@
 		 */
 		if (nr_isolated) {
 			if (locked) {
-				spin_unlock_irqrestore(zone_lru_lock(zone), flags);
+				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
 				locked = false;
 			}
 			putback_movable_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
-			cc->last_migrated_pfn = 0;
 			nr_isolated = 0;
 		}
 
@@ -938,19 +1042,28 @@
 	if (unlikely(low_pfn > end_pfn))
 		low_pfn = end_pfn;
 
+isolate_abort:
 	if (locked)
-		spin_unlock_irqrestore(zone_lru_lock(zone), flags);
+		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
 
 	/*
-	 * Update the pageblock-skip information and cached scanner pfn,
-	 * if the whole pageblock was scanned without isolating any page.
+	 * Updated the cached scanner pfn once the pageblock has been scanned
+	 * Pages will either be migrated in which case there is no point
+	 * scanning in the near future or migration failed in which case the
+	 * failure reason may persist. The block is marked for skipping if
+	 * there were no pages isolated in the block or if the block is
+	 * rescanned twice in a row.
 	 */
-	if (low_pfn == end_pfn)
-		update_pageblock_skip(cc, valid_page, nr_isolated, true);
+	if (low_pfn == end_pfn && (!nr_isolated || cc->rescan)) {
+		if (valid_page && !skip_updated)
+			set_pageblock_skip(valid_page);
+		update_cached_migrate(cc, low_pfn);
+	}
 
 	trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn,
 						nr_scanned, nr_isolated);
 
+fatal_pending:
 	cc->total_migrate_scanned += nr_scanned;
 	if (nr_isolated)
 		count_compact_events(COMPACTISOLATED, nr_isolated);
@@ -1012,6 +1125,9 @@
 {
 	int block_mt;
 
+	if (pageblock_skip_persistent(page))
+		return false;
+
 	if ((cc->mode != MIGRATE_ASYNC) || !cc->direct_compaction)
 		return true;
 
@@ -1049,6 +1165,14 @@
 	return false;
 }
 
+static inline unsigned int
+freelist_scan_limit(struct compact_control *cc)
+{
+	unsigned short shift = BITS_PER_LONG - 1;
+
+	return (COMPACT_CLUSTER_MAX >> min(shift, cc->fast_search_fail)) + 1;
+}
+
 /*
  * Test whether the free scanner has reached the same or lower pageblock than
  * the migration scanner, and compaction should thus terminate.
@@ -1060,6 +1184,248 @@
 }
 
 /*
+ * Used when scanning for a suitable migration target which scans freelists
+ * in reverse. Reorders the list such as the unscanned pages are scanned
+ * first on the next iteration of the free scanner
+ */
+static void
+move_freelist_head(struct list_head *freelist, struct page *freepage)
+{
+	LIST_HEAD(sublist);
+
+	if (!list_is_last(freelist, &freepage->lru)) {
+		list_cut_before(&sublist, freelist, &freepage->lru);
+		if (!list_empty(&sublist))
+			list_splice_tail(&sublist, freelist);
+	}
+}
+
+/*
+ * Similar to move_freelist_head except used by the migration scanner
+ * when scanning forward. It's possible for these list operations to
+ * move against each other if they search the free list exactly in
+ * lockstep.
+ */
+static void
+move_freelist_tail(struct list_head *freelist, struct page *freepage)
+{
+	LIST_HEAD(sublist);
+
+	if (!list_is_first(freelist, &freepage->lru)) {
+		list_cut_position(&sublist, freelist, &freepage->lru);
+		if (!list_empty(&sublist))
+			list_splice_tail(&sublist, freelist);
+	}
+}
+
+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);
+
+	/* Do not search around if there are enough pages already */
+	if (cc->nr_freepages >= cc->nr_migratepages)
+		return;
+
+	/* Minimise scanning during async compaction */
+	if (cc->direct_compaction && cc->mode == MIGRATE_ASYNC)
+		return;
+
+	/* Pageblock boundaries */
+	start_pfn = pageblock_start_pfn(pfn);
+	end_pfn = min(pageblock_end_pfn(pfn), zone_end_pfn(cc->zone)) - 1;
+
+	/* Scan before */
+	if (start_pfn != pfn) {
+		isolate_freepages_block(cc, &start_pfn, pfn, &cc->freepages, 1, false);
+		if (cc->nr_freepages >= cc->nr_migratepages)
+			return;
+	}
+
+	/* Scan after */
+	start_pfn = pfn + nr_isolated;
+	if (start_pfn < end_pfn)
+		isolate_freepages_block(cc, &start_pfn, end_pfn, &cc->freepages, 1, false);
+
+	/* Skip this pageblock in the future as it's full or nearly full */
+	if (cc->nr_freepages < cc->nr_migratepages)
+		set_pageblock_skip(page);
+}
+
+/* Search orders in round-robin fashion */
+static int next_search_order(struct compact_control *cc, int order)
+{
+	order--;
+	if (order < 0)
+		order = cc->order - 1;
+
+	/* Search wrapped around? */
+	if (order == cc->search_order) {
+		cc->search_order--;
+		if (cc->search_order < 0)
+			cc->search_order = cc->order - 1;
+		return -1;
+	}
+
+	return order;
+}
+
+static unsigned long
+fast_isolate_freepages(struct compact_control *cc)
+{
+	unsigned int limit = min(1U, freelist_scan_limit(cc) >> 1);
+	unsigned int nr_scanned = 0;
+	unsigned long low_pfn, min_pfn, high_pfn = 0, highest = 0;
+	unsigned long nr_isolated = 0;
+	unsigned long distance;
+	struct page *page = NULL;
+	bool scan_start = false;
+	int order;
+
+	/* Full compaction passes in a negative order */
+	if (cc->order <= 0)
+		return cc->free_pfn;
+
+	/*
+	 * If starting the scan, use a deeper search and use the highest
+	 * PFN found if a suitable one is not found.
+	 */
+	if (cc->free_pfn >= cc->zone->compact_init_free_pfn) {
+		limit = pageblock_nr_pages >> 1;
+		scan_start = true;
+	}
+
+	/*
+	 * Preferred point is in the top quarter of the scan space but take
+	 * a pfn from the top half if the search is problematic.
+	 */
+	distance = (cc->free_pfn - cc->migrate_pfn);
+	low_pfn = pageblock_start_pfn(cc->free_pfn - (distance >> 2));
+	min_pfn = pageblock_start_pfn(cc->free_pfn - (distance >> 1));
+
+	if (WARN_ON_ONCE(min_pfn > low_pfn))
+		low_pfn = min_pfn;
+
+	/*
+	 * Search starts from the last successful isolation order or the next
+	 * order to search after a previous failure
+	 */
+	cc->search_order = min_t(unsigned int, cc->order - 1, cc->search_order);
+
+	for (order = cc->search_order;
+	     !page && order >= 0;
+	     order = next_search_order(cc, order)) {
+		struct free_area *area = &cc->zone->free_area[order];
+		struct list_head *freelist;
+		struct page *freepage;
+		unsigned long flags;
+		unsigned int order_scanned = 0;
+
+		if (!area->nr_free)
+			continue;
+
+		spin_lock_irqsave(&cc->zone->lock, flags);
+		freelist = &area->free_list[MIGRATE_MOVABLE];
+		list_for_each_entry_reverse(freepage, freelist, lru) {
+			unsigned long pfn;
+
+			order_scanned++;
+			nr_scanned++;
+			pfn = page_to_pfn(freepage);
+
+			if (pfn >= highest)
+				highest = pageblock_start_pfn(pfn);
+
+			if (pfn >= low_pfn) {
+				cc->fast_search_fail = 0;
+				cc->search_order = order;
+				page = freepage;
+				break;
+			}
+
+			if (pfn >= min_pfn && pfn > high_pfn) {
+				high_pfn = pfn;
+
+				/* Shorten the scan if a candidate is found */
+				limit >>= 1;
+			}
+
+			if (order_scanned >= limit)
+				break;
+		}
+
+		/* Use a minimum pfn if a preferred one was not found */
+		if (!page && high_pfn) {
+			page = pfn_to_page(high_pfn);
+
+			/* Update freepage for the list reorder below */
+			freepage = page;
+		}
+
+		/* Reorder to so a future search skips recent pages */
+		move_freelist_head(freelist, freepage);
+
+		/* Isolate the page if available */
+		if (page) {
+			if (__isolate_free_page(page, order)) {
+				set_page_private(page, order);
+				nr_isolated = 1 << order;
+				cc->nr_freepages += nr_isolated;
+				list_add_tail(&page->lru, &cc->freepages);
+				count_compact_events(COMPACTISOLATED, nr_isolated);
+			} else {
+				/* If isolation fails, abort the search */
+				order = cc->search_order + 1;
+				page = NULL;
+			}
+		}
+
+		spin_unlock_irqrestore(&cc->zone->lock, flags);
+
+		/*
+		 * Smaller scan on next order so the total scan ig related
+		 * to freelist_scan_limit.
+		 */
+		if (order_scanned >= limit)
+			limit = min(1U, limit >> 1);
+	}
+
+	if (!page) {
+		cc->fast_search_fail++;
+		if (scan_start) {
+			/*
+			 * Use the highest PFN found above min. If one was
+			 * not found, be pessemistic for direct compaction
+			 * and use the min mark.
+			 */
+			if (highest) {
+				page = pfn_to_page(highest);
+				cc->free_pfn = highest;
+			} else {
+				if (cc->direct_compaction && pfn_valid(min_pfn)) {
+					page = pfn_to_page(min_pfn);
+					cc->free_pfn = min_pfn;
+				}
+			}
+		}
+	}
+
+	if (highest && highest >= cc->zone->compact_cached_free_pfn) {
+		highest -= pageblock_nr_pages;
+		cc->zone->compact_cached_free_pfn = highest;
+	}
+
+	cc->total_free_scanned += nr_scanned;
+	if (!page)
+		return cc->free_pfn;
+
+	low_pfn = page_to_pfn(page);
+	fast_isolate_around(cc, low_pfn, nr_isolated);
+	return low_pfn;
+}
+
+/*
  * Based on information in the current compact_control, find blocks
  * suitable for isolating free pages from and then isolate them.
  */
@@ -1072,6 +1438,12 @@
 	unsigned long block_end_pfn;	/* end of current pageblock */
 	unsigned long low_pfn;	     /* lowest pfn scanner is able to scan */
 	struct list_head *freelist = &cc->freepages;
+	unsigned int stride;
+
+	/* Try a small search of the free lists for a candidate */
+	isolate_start_pfn = fast_isolate_freepages(cc);
+	if (cc->nr_freepages)
+		goto splitmap;
 
 	/*
 	 * Initialise the free scanner. The starting point is where we last
@@ -1085,10 +1457,11 @@
 	 * is using.
 	 */
 	isolate_start_pfn = cc->free_pfn;
-	block_start_pfn = pageblock_start_pfn(cc->free_pfn);
+	block_start_pfn = pageblock_start_pfn(isolate_start_pfn);
 	block_end_pfn = min(block_start_pfn + pageblock_nr_pages,
 						zone_end_pfn(zone));
 	low_pfn = pageblock_end_pfn(cc->migrate_pfn);
+	stride = cc->mode == MIGRATE_ASYNC ? COMPACT_CLUSTER_MAX : 1;
 
 	/*
 	 * Isolate free pages until enough are available to migrate the
@@ -1099,14 +1472,14 @@
 				block_end_pfn = block_start_pfn,
 				block_start_pfn -= pageblock_nr_pages,
 				isolate_start_pfn = block_start_pfn) {
+		unsigned long nr_isolated;
+
 		/*
 		 * This can iterate a massively long zone without finding any
-		 * suitable migration targets, so periodically check if we need
-		 * to schedule, or even abort async compaction.
+		 * suitable migration targets, so periodically check resched.
 		 */
-		if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))
-						&& compact_should_abort(cc))
-			break;
+		if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages)))
+			cond_resched();
 
 		page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn,
 									zone);
@@ -1122,15 +1495,15 @@
 			continue;
 
 		/* Found a block suitable for isolating free pages from. */
-		isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn,
-					freelist, false);
+		nr_isolated = isolate_freepages_block(cc, &isolate_start_pfn,
+					block_end_pfn, freelist, stride, false);
 
-		/*
-		 * If we isolated enough freepages, or aborted due to lock
-		 * contention, terminate.
-		 */
-		if ((cc->nr_freepages >= cc->nr_migratepages)
-							|| cc->contended) {
+		/* Update the skip hint if the full pageblock was scanned */
+		if (isolate_start_pfn == block_end_pfn)
+			update_pageblock_skip(cc, page, block_start_pfn);
+
+		/* Are enough freepages isolated? */
+		if (cc->nr_freepages >= cc->nr_migratepages) {
 			if (isolate_start_pfn >= block_end_pfn) {
 				/*
 				 * Restart at previous pageblock if more
@@ -1147,10 +1520,14 @@
 			 */
 			break;
 		}
-	}
 
-	/* __isolate_free_page() does not map the pages */
-	map_pages(freelist);
+		/* Adjust stride depending on isolation */
+		if (nr_isolated) {
+			stride = 1;
+			continue;
+		}
+		stride = min_t(unsigned int, COMPACT_CLUSTER_MAX, stride << 1);
+	}
 
 	/*
 	 * Record where the free scanner will restart next time. Either we
@@ -1159,6 +1536,10 @@
 	 * and the loop terminated due to isolate_start_pfn < low_pfn
 	 */
 	cc->free_pfn = isolate_start_pfn;
+
+splitmap:
+	/* __isolate_free_page() does not map the pages */
+	split_map_pages(freelist);
 }
 
 /*
@@ -1171,13 +1552,8 @@
 	struct compact_control *cc = (struct compact_control *)data;
 	struct page *freepage;
 
-	/*
-	 * Isolate free pages if necessary, and if we are not aborting due to
-	 * contention.
-	 */
 	if (list_empty(&cc->freepages)) {
-		if (!cc->contended)
-			isolate_freepages(cc);
+		isolate_freepages(cc);
 
 		if (list_empty(&cc->freepages))
 			return NULL;
@@ -1216,13 +1592,153 @@
  */
 int sysctl_compact_unevictable_allowed __read_mostly = 1;
 
+static inline void
+update_fast_start_pfn(struct compact_control *cc, unsigned long pfn)
+{
+	if (cc->fast_start_pfn == ULONG_MAX)
+		return;
+
+	if (!cc->fast_start_pfn)
+		cc->fast_start_pfn = pfn;
+
+	cc->fast_start_pfn = min(cc->fast_start_pfn, pfn);
+}
+
+static inline unsigned long
+reinit_migrate_pfn(struct compact_control *cc)
+{
+	if (!cc->fast_start_pfn || cc->fast_start_pfn == ULONG_MAX)
+		return cc->migrate_pfn;
+
+	cc->migrate_pfn = cc->fast_start_pfn;
+	cc->fast_start_pfn = ULONG_MAX;
+
+	return cc->migrate_pfn;
+}
+
+/*
+ * Briefly search the free lists for a migration source that already has
+ * some free pages to reduce the number of pages that need migration
+ * before a pageblock is free.
+ */
+static unsigned long fast_find_migrateblock(struct compact_control *cc)
+{
+	unsigned int limit = freelist_scan_limit(cc);
+	unsigned int nr_scanned = 0;
+	unsigned long distance;
+	unsigned long pfn = cc->migrate_pfn;
+	unsigned long high_pfn;
+	int order;
+
+	/* Skip hints are relied on to avoid repeats on the fast search */
+	if (cc->ignore_skip_hint)
+		return pfn;
+
+	/*
+	 * If the migrate_pfn is not at the start of a zone or the start
+	 * of a pageblock then assume this is a continuation of a previous
+	 * scan restarted due to COMPACT_CLUSTER_MAX.
+	 */
+	if (pfn != cc->zone->zone_start_pfn && pfn != pageblock_start_pfn(pfn))
+		return pfn;
+
+	/*
+	 * For smaller orders, just linearly scan as the number of pages
+	 * to migrate should be relatively small and does not necessarily
+	 * justify freeing up a large block for a small allocation.
+	 */
+	if (cc->order <= PAGE_ALLOC_COSTLY_ORDER)
+		return pfn;
+
+	/*
+	 * Only allow kcompactd and direct requests for movable pages to
+	 * quickly clear out a MOVABLE pageblock for allocation. This
+	 * reduces the risk that a large movable pageblock is freed for
+	 * an unmovable/reclaimable small allocation.
+	 */
+	if (cc->direct_compaction && cc->migratetype != MIGRATE_MOVABLE)
+		return pfn;
+
+	/*
+	 * When starting the migration scanner, pick any pageblock within the
+	 * first half of the search space. Otherwise try and pick a pageblock
+	 * within the first eighth to reduce the chances that a migration
+	 * target later becomes a source.
+	 */
+	distance = (cc->free_pfn - cc->migrate_pfn) >> 1;
+	if (cc->migrate_pfn != cc->zone->zone_start_pfn)
+		distance >>= 2;
+	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--) {
+		struct free_area *area = &cc->zone->free_area[order];
+		struct list_head *freelist;
+		unsigned long flags;
+		struct page *freepage;
+
+		if (!area->nr_free)
+			continue;
+
+		spin_lock_irqsave(&cc->zone->lock, flags);
+		freelist = &area->free_list[MIGRATE_MOVABLE];
+		list_for_each_entry(freepage, freelist, lru) {
+			unsigned long free_pfn;
+
+			nr_scanned++;
+			free_pfn = page_to_pfn(freepage);
+			if (free_pfn < high_pfn) {
+				/*
+				 * Avoid if skipped recently. Ideally it would
+				 * move to the tail but even safe iteration of
+				 * the list assumes an entry is deleted, not
+				 * reordered.
+				 */
+				if (get_pageblock_skip(freepage)) {
+					if (list_is_last(freelist, &freepage->lru))
+						break;
+
+					continue;
+				}
+
+				/* Reorder to so a future search skips recent pages */
+				move_freelist_tail(freelist, freepage);
+
+				update_fast_start_pfn(cc, free_pfn);
+				pfn = pageblock_start_pfn(free_pfn);
+				cc->fast_search_fail = 0;
+				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);
+	}
+
+	cc->total_migrate_scanned += nr_scanned;
+
+	/*
+	 * 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)
+		pfn = reinit_migrate_pfn(cc);
+
+	return pfn;
+}
+
 /*
  * Isolate all pages that can be migrated from the first suitable block,
  * starting at the block pointed to by the migrate scanner pfn within
  * compact_control.
  */
-static isolate_migrate_t isolate_migratepages(struct zone *zone,
-					struct compact_control *cc)
+static isolate_migrate_t isolate_migratepages(struct compact_control *cc)
 {
 	unsigned long block_start_pfn;
 	unsigned long block_end_pfn;
@@ -1231,15 +1747,24 @@
 	const isolate_mode_t isolate_mode =
 		(sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) |
 		(cc->mode != MIGRATE_SYNC ? ISOLATE_ASYNC_MIGRATE : 0);
+	bool fast_find_block;
 
 	/*
 	 * Start at where we last stopped, or beginning of the zone as
-	 * initialized by compact_zone()
+	 * initialized by compact_zone(). The first failure will use
+	 * the lowest PFN as the starting point for linear scanning.
 	 */
-	low_pfn = cc->migrate_pfn;
+	low_pfn = fast_find_migrateblock(cc);
 	block_start_pfn = pageblock_start_pfn(low_pfn);
-	if (block_start_pfn < zone->zone_start_pfn)
-		block_start_pfn = zone->zone_start_pfn;
+	if (block_start_pfn < cc->zone->zone_start_pfn)
+		block_start_pfn = cc->zone->zone_start_pfn;
+
+	/*
+	 * fast_find_migrateblock marks a pageblock skipped so to avoid
+	 * the isolation_suitable check below, check whether the fast
+	 * search was successful.
+	 */
+	fast_find_block = low_pfn != cc->migrate_pfn && !cc->fast_search_fail;
 
 	/* Only scan within a pageblock boundary */
 	block_end_pfn = pageblock_end_pfn(low_pfn);
@@ -1249,6 +1774,7 @@
 	 * Do not cross the free scanner.
 	 */
 	for (; block_end_pfn <= cc->free_pfn;
+			fast_find_block = false,
 			low_pfn = block_end_pfn,
 			block_start_pfn = block_end_pfn,
 			block_end_pfn += pageblock_nr_pages) {
@@ -1256,34 +1782,45 @@
 		/*
 		 * This can potentially iterate a massively long zone with
 		 * many pageblocks unsuitable, so periodically check if we
-		 * need to schedule, or even abort async compaction.
+		 * need to schedule.
 		 */
-		if (!(low_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))
-						&& compact_should_abort(cc))
-			break;
+		if (!(low_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages)))
+			cond_resched();
 
-		page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn,
-									zone);
+		page = pageblock_pfn_to_page(block_start_pfn,
+						block_end_pfn, cc->zone);
 		if (!page)
 			continue;
 
-		/* If isolation recently failed, do not retry */
-		if (!isolation_suitable(cc, page))
+		/*
+		 * If isolation recently failed, do not retry. Only check the
+		 * pageblock once. COMPACT_CLUSTER_MAX causes a pageblock
+		 * to be visited multiple times. Assume skip was checked
+		 * before making it "skip" so other compaction instances do
+		 * not scan the same block.
+		 */
+		if (IS_ALIGNED(low_pfn, pageblock_nr_pages) &&
+		    !fast_find_block && !isolation_suitable(cc, page))
 			continue;
 
 		/*
-		 * For async compaction, also only scan in MOVABLE blocks.
-		 * Async compaction is optimistic to see if the minimum amount
-		 * of work satisfies the allocation.
+		 * For async compaction, also only scan in MOVABLE blocks
+		 * without huge pages. Async compaction is optimistic to see
+		 * if the minimum amount of work satisfies the allocation.
+		 * The cached PFN is updated as it's possible that all
+		 * remaining blocks between source and target are unsuitable
+		 * and the compaction scanners fail to meet.
 		 */
-		if (!suitable_migration_source(cc, page))
+		if (!suitable_migration_source(cc, page)) {
+			update_cached_migrate(cc, block_end_pfn);
 			continue;
+		}
 
 		/* Perform the isolation */
 		low_pfn = isolate_migratepages_block(cc, low_pfn,
 						block_end_pfn, isolate_mode);
 
-		if (!low_pfn || cc->contended)
+		if (!low_pfn)
 			return ISOLATE_ABORT;
 
 		/*
@@ -1309,19 +1846,16 @@
 	return order == -1;
 }
 
-static enum compact_result __compact_finished(struct zone *zone,
-						struct compact_control *cc)
+static enum compact_result __compact_finished(struct compact_control *cc)
 {
 	unsigned int order;
 	const int migratetype = cc->migratetype;
-
-	if (cc->contended || fatal_signal_pending(current))
-		return COMPACT_CONTENDED;
+	int ret;
 
 	/* Compaction run completes if the migrate and free scanner meet */
 	if (compact_scanners_met(cc)) {
 		/* Let the next compaction start anew. */
-		reset_cached_positions(zone);
+		reset_cached_positions(cc->zone);
 
 		/*
 		 * Mark that the PG_migrate_skip information should be cleared
@@ -1330,7 +1864,7 @@
 		 * based on an allocation request.
 		 */
 		if (cc->direct_compaction)
-			zone->compact_blockskip_flush = true;
+			cc->zone->compact_blockskip_flush = true;
 
 		if (cc->whole_zone)
 			return COMPACT_COMPLETE;
@@ -1341,30 +1875,29 @@
 	if (is_via_compact_memory(cc->order))
 		return COMPACT_CONTINUE;
 
-	if (cc->finishing_block) {
-		/*
-		 * We have finished the pageblock, but better check again that
-		 * we really succeeded.
-		 */
-		if (IS_ALIGNED(cc->migrate_pfn, pageblock_nr_pages))
-			cc->finishing_block = false;
-		else
-			return COMPACT_CONTINUE;
-	}
+	/*
+	 * Always finish scanning a pageblock to reduce the possibility of
+	 * fallbacks in the future. This is particularly important when
+	 * migration source is unmovable/reclaimable but it's not worth
+	 * special casing.
+	 */
+	if (!IS_ALIGNED(cc->migrate_pfn, pageblock_nr_pages))
+		return COMPACT_CONTINUE;
 
 	/* Direct compactor: Is a suitable page free? */
+	ret = COMPACT_NO_SUITABLE_PAGE;
 	for (order = cc->order; order < MAX_ORDER; order++) {
-		struct free_area *area = &zone->free_area[order];
+		struct free_area *area = &cc->zone->free_area[order];
 		bool can_steal;
 
 		/* Job done if page is free of the right migratetype */
-		if (!list_empty(&area->free_list[migratetype]))
+		if (!free_area_empty(area, migratetype))
 			return COMPACT_SUCCESS;
 
 #ifdef CONFIG_CMA
 		/* MIGRATE_MOVABLE can fallback on MIGRATE_CMA */
 		if (migratetype == MIGRATE_MOVABLE &&
-			!list_empty(&area->free_list[MIGRATE_CMA]))
+			!free_area_empty(area, MIGRATE_CMA))
 			return COMPACT_SUCCESS;
 #endif
 		/*
@@ -1392,21 +1925,23 @@
 				return COMPACT_SUCCESS;
 			}
 
-			cc->finishing_block = true;
-			return COMPACT_CONTINUE;
+			ret = COMPACT_CONTINUE;
+			break;
 		}
 	}
 
-	return COMPACT_NO_SUITABLE_PAGE;
+	if (cc->contended || fatal_signal_pending(current))
+		ret = COMPACT_CONTENDED;
+
+	return ret;
 }
 
-static enum compact_result compact_finished(struct zone *zone,
-			struct compact_control *cc)
+static enum compact_result compact_finished(struct compact_control *cc)
 {
 	int ret;
 
-	ret = __compact_finished(zone, cc);
-	trace_mm_compaction_finished(zone, cc->order, ret);
+	ret = __compact_finished(cc);
+	trace_mm_compaction_finished(cc->zone, cc->order, ret);
 	if (ret == COMPACT_NO_SUITABLE_PAGE)
 		ret = COMPACT_CONTINUE;
 
@@ -1430,7 +1965,7 @@
 	if (is_via_compact_memory(order))
 		return COMPACT_CONTINUE;
 
-	watermark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
+	watermark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK);
 	/*
 	 * If watermarks for high-order allocation are already met, there
 	 * should be no need for compaction at all.
@@ -1533,15 +2068,29 @@
 	return false;
 }
 
-static enum compact_result compact_zone(struct zone *zone, struct compact_control *cc)
+static enum compact_result
+compact_zone(struct compact_control *cc, struct capture_control *capc)
 {
 	enum compact_result ret;
-	unsigned long start_pfn = zone->zone_start_pfn;
-	unsigned long end_pfn = zone_end_pfn(zone);
+	unsigned long start_pfn = cc->zone->zone_start_pfn;
+	unsigned long end_pfn = zone_end_pfn(cc->zone);
+	unsigned long last_migrated_pfn;
 	const bool sync = cc->mode != MIGRATE_ASYNC;
+	bool update_cached;
+
+	/*
+	 * These counters track activities during zone compaction.  Initialize
+	 * them before compacting a new zone.
+	 */
+	cc->total_migrate_scanned = 0;
+	cc->total_free_scanned = 0;
+	cc->nr_migratepages = 0;
+	cc->nr_freepages = 0;
+	INIT_LIST_HEAD(&cc->freepages);
+	INIT_LIST_HEAD(&cc->migratepages);
 
 	cc->migratetype = gfpflags_to_migratetype(cc->gfp_mask);
-	ret = compaction_suitable(zone, cc->order, cc->alloc_flags,
+	ret = compaction_suitable(cc->zone, cc->order, cc->alloc_flags,
 							cc->classzone_idx);
 	/* Compaction is likely to fail */
 	if (ret == COMPACT_SUCCESS || ret == COMPACT_SKIPPED)
@@ -1554,8 +2103,8 @@
 	 * Clear pageblock skip if there were failures recently and compaction
 	 * is about to be retried after being deferred.
 	 */
-	if (compaction_restarting(zone, cc->order))
-		__reset_isolation_suitable(zone);
+	if (compaction_restarting(cc->zone, cc->order))
+		__reset_isolation_suitable(cc->zone);
 
 	/*
 	 * Setup to move all movable pages to the end of the zone. Used cached
@@ -1563,43 +2112,76 @@
 	 * want to compact the whole zone), but check that it is initialised
 	 * by ensuring the values are within zone boundaries.
 	 */
+	cc->fast_start_pfn = 0;
 	if (cc->whole_zone) {
 		cc->migrate_pfn = start_pfn;
 		cc->free_pfn = pageblock_start_pfn(end_pfn - 1);
 	} else {
-		cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync];
-		cc->free_pfn = zone->compact_cached_free_pfn;
+		cc->migrate_pfn = cc->zone->compact_cached_migrate_pfn[sync];
+		cc->free_pfn = cc->zone->compact_cached_free_pfn;
 		if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) {
 			cc->free_pfn = pageblock_start_pfn(end_pfn - 1);
-			zone->compact_cached_free_pfn = cc->free_pfn;
+			cc->zone->compact_cached_free_pfn = cc->free_pfn;
 		}
 		if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) {
 			cc->migrate_pfn = start_pfn;
-			zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn;
-			zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
+			cc->zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn;
+			cc->zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
 		}
 
-		if (cc->migrate_pfn == start_pfn)
+		if (cc->migrate_pfn <= cc->zone->compact_init_migrate_pfn)
 			cc->whole_zone = true;
 	}
 
-	cc->last_migrated_pfn = 0;
+	last_migrated_pfn = 0;
+
+	/*
+	 * Migrate has separate cached PFNs for ASYNC and SYNC* migration on
+	 * the basis that some migrations will fail in ASYNC mode. However,
+	 * if the cached PFNs match and pageblocks are skipped due to having
+	 * no isolation candidates, then the sync state does not matter.
+	 * Until a pageblock with isolation candidates is found, keep the
+	 * cached PFNs in sync to avoid revisiting the same blocks.
+	 */
+	update_cached = !sync &&
+		cc->zone->compact_cached_migrate_pfn[0] == cc->zone->compact_cached_migrate_pfn[1];
 
 	trace_mm_compaction_begin(start_pfn, cc->migrate_pfn,
 				cc->free_pfn, end_pfn, sync);
 
 	migrate_prep_local();
 
-	while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
+	while ((ret = compact_finished(cc)) == COMPACT_CONTINUE) {
 		int err;
+		unsigned long start_pfn = cc->migrate_pfn;
 
-		switch (isolate_migratepages(zone, cc)) {
+		/*
+		 * Avoid multiple rescans which can happen if a page cannot be
+		 * isolated (dirty/writeback in async mode) or if the migrated
+		 * pages are being allocated before the pageblock is cleared.
+		 * The first rescan will capture the entire pageblock for
+		 * migration. If it fails, it'll be marked skip and scanning
+		 * will proceed as normal.
+		 */
+		cc->rescan = false;
+		if (pageblock_start_pfn(last_migrated_pfn) ==
+		    pageblock_start_pfn(start_pfn)) {
+			cc->rescan = true;
+		}
+
+		switch (isolate_migratepages(cc)) {
 		case ISOLATE_ABORT:
 			ret = COMPACT_CONTENDED;
 			putback_movable_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
+			last_migrated_pfn = 0;
 			goto out;
 		case ISOLATE_NONE:
+			if (update_cached) {
+				cc->zone->compact_cached_migrate_pfn[1] =
+					cc->zone->compact_cached_migrate_pfn[0];
+			}
+
 			/*
 			 * We haven't isolated and migrated anything, but
 			 * there might still be unflushed migrations from
@@ -1607,6 +2189,8 @@
 			 */
 			goto check_drain;
 		case ISOLATE_SUCCESS:
+			update_cached = false;
+			last_migrated_pfn = start_pfn;
 			;
 		}
 
@@ -1638,8 +2222,7 @@
 				cc->migrate_pfn = block_end_pfn(
 						cc->migrate_pfn - 1, cc->order);
 				/* Draining pcplists is useless in this case */
-				cc->last_migrated_pfn = 0;
-
+				last_migrated_pfn = 0;
 			}
 		}
 
@@ -1651,21 +2234,26 @@
 		 * compact_finished() can detect immediately if allocation
 		 * would succeed.
 		 */
-		if (cc->order > 0 && cc->last_migrated_pfn) {
+		if (cc->order > 0 && last_migrated_pfn) {
 			int cpu;
 			unsigned long current_block_start =
 				block_start_pfn(cc->migrate_pfn, cc->order);
 
-			if (cc->last_migrated_pfn < current_block_start) {
+			if (last_migrated_pfn < current_block_start) {
 				cpu = get_cpu();
 				lru_add_drain_cpu(cpu);
-				drain_local_pages(zone);
+				drain_local_pages(cc->zone);
 				put_cpu();
 				/* No more flushing until we migrate again */
-				cc->last_migrated_pfn = 0;
+				last_migrated_pfn = 0;
 			}
 		}
 
+		/* Stop if a page has been captured */
+		if (capc && capc->page) {
+			ret = COMPACT_SUCCESS;
+			break;
+		}
 	}
 
 out:
@@ -1684,8 +2272,8 @@
 		 * Only go back, not forward. The cached pfn might have been
 		 * already reset to zone end in compact_finished()
 		 */
-		if (free_pfn > zone->compact_cached_free_pfn)
-			zone->compact_cached_free_pfn = free_pfn;
+		if (free_pfn > cc->zone->compact_cached_free_pfn)
+			cc->zone->compact_cached_free_pfn = free_pfn;
 	}
 
 	count_compact_events(COMPACTMIGRATE_SCANNED, cc->total_migrate_scanned);
@@ -1699,15 +2287,13 @@
 
 static enum compact_result compact_zone_order(struct zone *zone, int order,
 		gfp_t gfp_mask, enum compact_priority prio,
-		unsigned int alloc_flags, int classzone_idx)
+		unsigned int alloc_flags, int classzone_idx,
+		struct page **capture)
 {
 	enum compact_result ret;
 	struct compact_control cc = {
-		.nr_freepages = 0,
-		.nr_migratepages = 0,
-		.total_migrate_scanned = 0,
-		.total_free_scanned = 0,
 		.order = order,
+		.search_order = order,
 		.gfp_mask = gfp_mask,
 		.zone = zone,
 		.mode = (prio == COMPACT_PRIO_ASYNC) ?
@@ -1719,14 +2305,22 @@
 		.ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY),
 		.ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY)
 	};
-	INIT_LIST_HEAD(&cc.freepages);
-	INIT_LIST_HEAD(&cc.migratepages);
+	struct capture_control capc = {
+		.cc = &cc,
+		.page = NULL,
+	};
 
-	ret = compact_zone(zone, &cc);
+	if (capture)
+		current->capture_control = &capc;
+
+	ret = compact_zone(&cc, &capc);
 
 	VM_BUG_ON(!list_empty(&cc.freepages));
 	VM_BUG_ON(!list_empty(&cc.migratepages));
 
+	*capture = capc.page;
+	current->capture_control = NULL;
+
 	return ret;
 }
 
@@ -1744,7 +2338,7 @@
  */
 enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 		unsigned int alloc_flags, const struct alloc_context *ac,
-		enum compact_priority prio)
+		enum compact_priority prio, struct page **capture)
 {
 	int may_perform_io = gfp_mask & __GFP_IO;
 	struct zoneref *z;
@@ -1772,7 +2366,7 @@
 		}
 
 		status = compact_zone_order(zone, order, gfp_mask, prio,
-					alloc_flags, ac_classzone_idx(ac));
+				alloc_flags, ac_classzone_idx(ac), capture);
 		rc = max(status, rc);
 
 		/* The allocation should succeed, stop compacting */
@@ -1819,8 +2413,6 @@
 	struct zone *zone;
 	struct compact_control cc = {
 		.order = -1,
-		.total_migrate_scanned = 0,
-		.total_free_scanned = 0,
 		.mode = MIGRATE_SYNC,
 		.ignore_skip_hint = true,
 		.whole_zone = true,
@@ -1834,13 +2426,9 @@
 		if (!populated_zone(zone))
 			continue;
 
-		cc.nr_freepages = 0;
-		cc.nr_migratepages = 0;
 		cc.zone = zone;
-		INIT_LIST_HEAD(&cc.freepages);
-		INIT_LIST_HEAD(&cc.migratepages);
 
-		compact_zone(zone, &cc);
+		compact_zone(&cc, NULL);
 
 		VM_BUG_ON(!list_empty(&cc.freepages));
 		VM_BUG_ON(!list_empty(&cc.migratepages));
@@ -1875,14 +2463,6 @@
 	return 0;
 }
 
-int sysctl_extfrag_handler(struct ctl_table *table, int write,
-			void __user *buffer, size_t *length, loff_t *ppos)
-{
-	proc_dointvec_minmax(table, write, buffer, length, ppos);
-
-	return 0;
-}
-
 #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
 static ssize_t sysfs_compact_node(struct device *dev,
 			struct device_attribute *attr,
@@ -1947,8 +2527,7 @@
 	struct zone *zone;
 	struct compact_control cc = {
 		.order = pgdat->kcompactd_max_order,
-		.total_migrate_scanned = 0,
-		.total_free_scanned = 0,
+		.search_order = pgdat->kcompactd_max_order,
 		.classzone_idx = pgdat->kcompactd_classzone_idx,
 		.mode = MIGRATE_SYNC_LIGHT,
 		.ignore_skip_hint = false,
@@ -1972,17 +2551,11 @@
 							COMPACT_CONTINUE)
 			continue;
 
-		cc.nr_freepages = 0;
-		cc.nr_migratepages = 0;
-		cc.total_migrate_scanned = 0;
-		cc.total_free_scanned = 0;
-		cc.zone = zone;
-		INIT_LIST_HEAD(&cc.freepages);
-		INIT_LIST_HEAD(&cc.migratepages);
-
 		if (kthread_should_stop())
 			return;
-		status = compact_zone(zone, &cc);
+
+		cc.zone = zone;
+		status = compact_zone(&cc, NULL);
 
 		if (status == COMPACT_SUCCESS) {
 			compaction_defer_reset(zone, cc.order, false);
@@ -2068,11 +2641,15 @@
 	pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1;
 
 	while (!kthread_should_stop()) {
+		unsigned long pflags;
+
 		trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
 		wait_event_freezable(pgdat->kcompactd_wait,
 				kcompactd_work_requested(pgdat));
 
+		psi_memstall_enter(&pflags);
 		kcompactd_do_work(pgdat);
+		psi_memstall_leave(&pflags);
 	}
 
 	return 0;