Increase success rates and reduce latency of compaction v1

index 536bc2a839b9..5564841fce36 100644
@@ -185,8 +185,8 @@ struct compact_control {
 	struct list_head freepages;	/* List of free pages to migrate to */
 	struct list_head migratepages;	/* List of pages being migrated */
 	struct zone *zone;
-	unsigned long nr_freepages;	/* Number of isolated free pages */
-	unsigned long nr_migratepages;	/* Number of pages to migrate */
+	unsigned int nr_freepages;	/* Number of isolated free pages */
+	unsigned int nr_migratepages;	/* Number of pages to migrate */
 	unsigned long total_migrate_scanned;
 	unsigned long total_free_scanned;
 	unsigned long free_pfn;		/* isolate_freepages search base */

index 5564841fce36..867af5425432 100644
@@ -184,14 +184,14 @@ extern int user_min_free_kbytes;
 struct compact_control {
 	struct list_head freepages;	/* List of free pages to migrate to */
 	struct list_head migratepages;	/* List of pages being migrated */
-	struct zone *zone;
 	unsigned int nr_freepages;	/* Number of isolated free pages */
 	unsigned int nr_migratepages;	/* Number of pages to migrate */
-	unsigned long total_migrate_scanned;
-	unsigned long total_free_scanned;
 	unsigned long free_pfn;		/* isolate_freepages search base */
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
 	unsigned long last_migrated_pfn;/* Not yet flushed page being freed */
+	struct zone *zone;
+	unsigned long total_migrate_scanned;
+	unsigned long total_free_scanned;
 	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
 	int order;			/* order a direct compactor needs */
 	int migratetype;		/* migratetype of direct compactor */

index ef29490b0f46..fb4d9f52ed56 100644
@@ -886,15 +886,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		cc->nr_migratepages++;
 		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.
-		 */
-		if (!cc->last_migrated_pfn)
-			cc->last_migrated_pfn = low_pfn;
-
 		/* Avoid isolating too much */
 		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
 			++low_pfn;

@@ -918,7 +909,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			}
 			putback_movable_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
-			cc->last_migrated_pfn = 0;
 			nr_isolated = 0;
 		}
 

@@ -1539,6 +1529,7 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 	enum compact_result ret;
 	unsigned long start_pfn = zone->zone_start_pfn;
 	unsigned long end_pfn = zone_end_pfn(zone);
+	unsigned long last_migrated_pfn;
 	const bool sync = cc->mode != MIGRATE_ASYNC;
 
 	cc->migratetype = gfpflags_to_migratetype(cc->gfp_mask);

@@ -1584,7 +1575,7 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 			cc->whole_zone = true;
 	}
 
-	cc->last_migrated_pfn = 0;
+	last_migrated_pfn = 0;
 
 	trace_mm_compaction_begin(start_pfn, cc->migrate_pfn,
 				cc->free_pfn, end_pfn, sync);

@@ -1593,12 +1584,14 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 
 	while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
 		int err;
+		unsigned long start_pfn = cc->migrate_pfn;
 
 		switch (isolate_migratepages(zone, 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:
 			/*

@@ -1608,6 +1601,7 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 			 */
 			goto check_drain;
 		case ISOLATE_SUCCESS:
+			last_migrated_pfn = start_pfn;
 			;
 		}
 

@@ -1639,8 +1633,7 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 				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;
 			}
 		}
 

@@ -1652,18 +1645,18 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 		 * 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);
 				put_cpu();
 				/* No more flushing until we migrate again */
-				cc->last_migrated_pfn = 0;
+				last_migrated_pfn = 0;
 			}
 		}
 

index 867af5425432..f40d06d70683 100644
@@ -188,7 +188,6 @@ struct compact_control {
 	unsigned int nr_migratepages;	/* Number of pages to migrate */
 	unsigned long free_pfn;		/* isolate_freepages search base */
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
-	unsigned long last_migrated_pfn;/* Not yet flushed page being freed */
 	struct zone *zone;
 	unsigned long total_migrate_scanned;
 	unsigned long total_free_scanned;

index fb4d9f52ed56..3afa4e9188b6 100644
@@ -66,7 +66,7 @@ static unsigned long release_freepages(struct list_head *freelist)
 	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;

@@ -644,7 +644,7 @@ isolate_freepages_range(struct compact_control *cc,
 	}
 
 	/* __isolate_free_page() does not map the pages */
-	map_pages(&freelist);
+	split_map_pages(&freelist);
 
 	if (pfn < end_pfn) {
 		/* Loop terminated early, cleanup. */

@@ -1141,7 +1141,7 @@ static void isolate_freepages(struct compact_control *cc)
 	}
 
 	/* __isolate_free_page() does not map the pages */
-	map_pages(freelist);
+	split_map_pages(freelist);
 
 	/*
 	 * Record where the free scanner will restart next time. Either we

@@ -1300,8 +1300,7 @@ static inline bool is_via_compact_memory(int order)
 	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;

@@ -1312,7 +1311,7 @@ static enum compact_result __compact_finished(struct zone *zone,
 	/* 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

@@ -1321,7 +1320,7 @@ static enum compact_result __compact_finished(struct zone *zone,
 		 * 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;

@@ -1345,7 +1344,7 @@ static enum compact_result __compact_finished(struct zone *zone,
 
 	/* Direct compactor: Is a suitable page free? */
 	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 */

@@ -1391,13 +1390,12 @@ static enum compact_result __compact_finished(struct zone *zone,
 	return COMPACT_NO_SUITABLE_PAGE;
 }
 
-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;
 

@@ -1524,16 +1522,16 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
 	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)
 {
 	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;
 
 	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)

@@ -1546,8 +1544,8 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 	 * 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

@@ -1559,16 +1557,16 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 		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)

@@ -1582,11 +1580,11 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 
 	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)) {
+		switch (isolate_migratepages(cc->zone, cc)) {
 		case ISOLATE_ABORT:
 			ret = COMPACT_CONTENDED;
 			putback_movable_pages(&cc->migratepages);

@@ -1653,7 +1651,7 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 			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 */
 				last_migrated_pfn = 0;

@@ -1678,8 +1676,8 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 		 * 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);

@@ -1716,7 +1714,7 @@ static enum compact_result compact_zone_order(struct zone *zone, int order,
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
 
-	ret = compact_zone(zone, &cc);
+	ret = compact_zone(&cc);
 
 	VM_BUG_ON(!list_empty(&cc.freepages));
 	VM_BUG_ON(!list_empty(&cc.migratepages));

@@ -1834,7 +1832,7 @@ static void compact_node(int nid)
 		INIT_LIST_HEAD(&cc.freepages);
 		INIT_LIST_HEAD(&cc.migratepages);
 
-		compact_zone(zone, &cc);
+		compact_zone(&cc);
 
 		VM_BUG_ON(!list_empty(&cc.freepages));
 		VM_BUG_ON(!list_empty(&cc.migratepages));

@@ -1976,7 +1974,7 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 
 		if (kthread_should_stop())
 			return;
-		status = compact_zone(zone, &cc);
+		status = compact_zone(&cc);
 
 		if (status == COMPACT_SUCCESS) {
 			compaction_defer_reset(zone, cc.order, false);

index 3afa4e9188b6..8134dba47584 100644
@@ -827,6 +827,13 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 					goto isolate_success;
 			}
 
+			/*
+			 * A reserved page is never freed and tend to be
+			 * clustered in the same pageblocks. Skip the block.
+			 */
+			if (PageReserved(page))
+				low_pfn = end_pfn;
+
 			goto isolate_fail;
 		}
 

index df17a710e2c7..0e27a10429e2 100644
@@ -885,7 +885,7 @@ static int fallback_migrate_page(struct address_space *mapping,
 	 */
 	if (page_has_private(page) &&
 	    !try_to_release_page(page, GFP_KERNEL))
-		return -EAGAIN;
+		return mode == MIGRATE_SYNC ? -EAGAIN : -EBUSY;
 
 	return migrate_page(mapping, newpage, page, mode);
 }

index 8134dba47584..4f51435c645a 100644
@@ -1338,16 +1338,14 @@ static enum compact_result __compact_finished(struct compact_control *cc)
 	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? */
 	for (order = cc->order; order < MAX_ORDER; order++) {

@@ -1389,7 +1387,6 @@ static enum compact_result __compact_finished(struct compact_control *cc)
 				return COMPACT_SUCCESS;
 			}
 
-			cc->finishing_block = true;
 			return COMPACT_CONTINUE;
 		}
 	}

index f40d06d70683..9b32f4cab0ae 100644
@@ -203,7 +203,6 @@ struct compact_control {
 	bool direct_compaction;		/* False from kcompactd or /proc/... */
 	bool whole_zone;		/* Whole zone should/has been scanned */
 	bool contended;			/* Signal lock or sched contention */
-	bool finishing_block;		/* Finishing current pageblock */
 };
 
 unsigned long

index 0705164f928c..ed9a95b63374 100644
@@ -543,7 +543,12 @@ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
 extern void __free_pages(struct page *page, unsigned int order);
 extern void free_pages(unsigned long addr, unsigned int order);
 extern void free_unref_page(struct page *page);
-extern void free_unref_page_list(struct list_head *list);
+extern void __free_page_list(struct list_head *list, bool dropref, unsigned long *highest_pfn);
+
+static inline void free_unref_page_list(struct list_head *list)
+{
+	return __free_page_list(list, false, NULL);
+}
 
 struct page_frag_cache;
 extern void __page_frag_cache_drain(struct page *page, unsigned int count);

index 4f51435c645a..8ba9b3b479e3 100644
@@ -52,16 +52,10 @@ static inline void count_compact_events(enum vm_event_item item, long delta)
 
 static unsigned long release_freepages(struct list_head *freelist)
 {
-	struct page *page, *next;
-	unsigned long high_pfn = 0;
+	unsigned long high_pfn;
 
-	list_for_each_entry_safe(page, next, freelist, lru) {
-		unsigned long pfn = page_to_pfn(page);
-		list_del(&page->lru);
-		__free_page(page);
-		if (pfn > high_pfn)
-			high_pfn = pfn;
-	}
+	__free_page_list(freelist, true, &high_pfn);
+	INIT_LIST_HEAD(freelist);
 
 	return high_pfn;
 }

index a6e7bfd18cde..80535cd55a92 100644
@@ -2961,18 +2961,26 @@ void free_unref_page(struct page *page)
 /*
  * Free a list of 0-order pages
  */
-void free_unref_page_list(struct list_head *list)
+void __free_page_list(struct list_head *list, bool dropref,
+				unsigned long *highest_pfn)
 {
 	struct page *page, *next;
 	unsigned long flags, pfn;
 	int batch_count = 0;
 
+	if (highest_pfn)
+		*highest_pfn = 0;
+
 	/* Prepare pages for freeing */
 	list_for_each_entry_safe(page, next, list, lru) {
+		if (dropref)
+			WARN_ON_ONCE(!put_page_testzero(page));
 		pfn = page_to_pfn(page);
 		if (!free_unref_page_prepare(page, pfn))
 			list_del(&page->lru);
 		set_page_private(page, pfn);
+		if (highest_pfn && pfn > *highest_pfn)
+			*highest_pfn = pfn;
 	}
 
 	local_irq_save(flags);

index 80535cd55a92..c7b80e62bfd9 100644
@@ -3043,7 +3043,7 @@ int __isolate_free_page(struct page *page, unsigned int order)
 		 * watermark, because we already know our high-order page
 		 * exists.
 		 */
-		watermark = min_wmark_pages(zone) + (1UL << order);
+		watermark = zone->_watermark[WMARK_MIN] + (1UL << order);
 		if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
 			return 0;
 

index 8ba9b3b479e3..65c7ab1847a0 100644
@@ -1041,6 +1041,12 @@ static bool suitable_migration_target(struct compact_control *cc,
 	return false;
 }
 
+static inline unsigned int
+freelist_scan_limit(struct compact_control *cc)
+{
+	return (COMPACT_CLUSTER_MAX >> 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.

@@ -1051,6 +1057,19 @@ static inline bool compact_scanners_met(struct compact_control *cc)
 		<= (cc->migrate_pfn >> pageblock_order);
 }
 
+/* Reorder the free list to reduce repeated future searches */
+static void
+move_freelist_tail(struct list_head *freelist, struct page *freepage)
+{
+	LIST_HEAD(sublist);
+
+	if (!list_is_last(freelist, &freepage->lru)) {
+		list_cut_position(&sublist, freelist, &freepage->lru);
+		if (!list_empty(&sublist))
+			list_splice_tail(&sublist, freelist);
+	}
+}
+
 /*
  * Based on information in the current compact_control, find blocks
  * suitable for isolating free pages from and then isolate them.

@@ -1208,6 +1227,160 @@ typedef enum {
  */
 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 void
+reinit_migrate_pfn(struct compact_control *cc)
+{
+	if (!cc->fast_start_pfn || cc->fast_start_pfn == ULONG_MAX)
+		return;
+
+	cc->migrate_pfn = cc->fast_start_pfn;
+	cc->fast_start_pfn = ULONG_MAX;
+}
+
+/*
+ * 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 nr_skipped = 0;
+		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) {
+				update_fast_start_pfn(cc, free_pfn);
+
+				/*
+				 * Avoid if skipped recently. Move to the tail
+				 * of the list so it will not be found again
+				 * soon
+				 */
+				if (get_pageblock_skip(freepage)) {
+
+					if (list_is_last(freelist, &freepage->lru))
+						break;
+
+					nr_skipped++;
+					list_del(&freepage->lru);
+					list_add_tail(&freepage->lru, freelist);
+					if (nr_skipped > 2)
+						break;
+					continue;
+				}
+
+				/* Reorder to so a future search skips recent pages */
+				move_freelist_tail(freelist, freepage);
+
+				pfn = pageblock_start_pfn(free_pfn);
+				cc->fast_search_fail = 0;
+				set_pageblock_skip(freepage);
+				break;
+			}
+
+			/*
+			 * If low PFNs are being found and discarded then
+			 * limit the scan as fast searching is finding
+			 * poor candidates.
+			 */
+			if (free_pfn < cc->migrate_pfn)
+				limit >>= 1;
+
+			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)
+		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

@@ -1226,9 +1399,10 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 
 	/*
 	 * 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;

@@ -1551,6 +1725,7 @@ static enum compact_result compact_zone(struct compact_control *cc)
 	 * 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);

index 9b32f4cab0ae..983cb975545f 100644
@@ -188,9 +188,11 @@ struct compact_control {
 	unsigned int nr_migratepages;	/* Number of pages to migrate */
 	unsigned long free_pfn;		/* isolate_freepages search base */
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
+	unsigned long fast_start_pfn;	/* a pfn to start linear scan from */
 	struct zone *zone;
 	unsigned long total_migrate_scanned;
 	unsigned long total_free_scanned;
+	unsigned int fast_search_fail;	/* failures to use free list searches */
 	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
 	int order;			/* order a direct compactor needs */
 	int migratetype;		/* migratetype of direct compactor */

index 65c7ab1847a0..b0309bf409b3 100644
@@ -279,13 +279,51 @@ void reset_isolation_suitable(pg_data_t *pgdat)
 	}
 }
 
+/*
+ * 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 nr_isolated)
 {
 	struct zone *zone = cc->zone;
 	unsigned long pfn;

@@ -304,16 +342,8 @@ static void update_pageblock_skip(struct compact_control *cc,
 	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,

@@ -561,7 +591,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 	/* Update the pageblock-skip if the whole pageblock was scanned */
 	if (blockpfn == end_pfn)
-		update_pageblock_skip(cc, valid_page, total_isolated, false);
+		update_pageblock_skip(cc, valid_page, total_isolated);
 
 	cc->total_free_scanned += nr_scanned;
 	if (total_isolated)

@@ -696,6 +726,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 	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

@@ -762,8 +793,19 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 		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

@@ -851,8 +893,19 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (!locked) {
 			locked = compact_trylock_irqsave(zone_lru_lock(zone),
 								&flags, cc);
-			if (!locked)
+
+			/* Allow future scanning if the lock is contended */
+			if (!locked) {
+				clear_pageblock_skip(page);
 				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))

@@ -930,15 +983,20 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 	if (unlikely(low_pfn > end_pfn))
 		low_pfn = end_pfn;
 
+isolate_abort:
 	if (locked)
 		spin_unlock_irqrestore(zone_lru_lock(zone), 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 if the pageblock was scanned
+	 * without isolating a page. The pageblock may not be marked
+	 * skipped already if there were no LRU pages in the block.
 	 */
-	if (low_pfn == end_pfn)
-		update_pageblock_skip(cc, valid_page, nr_isolated, true);
+	if (low_pfn == end_pfn && !nr_isolated) {
+		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);

@@ -1323,8 +1381,6 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 			nr_scanned++;
 			free_pfn = page_to_pfn(freepage);
 			if (free_pfn < high_pfn) {
-				update_fast_start_pfn(cc, free_pfn);
-
 				/*
 				 * Avoid if skipped recently. Move to the tail
 				 * of the list so it will not be found again

@@ -1346,9 +1402,9 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 				/* 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;
 			}
 

@@ -1418,7 +1474,6 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 			low_pfn = block_end_pfn,
 			block_start_pfn = block_end_pfn,
 			block_end_pfn += pageblock_nr_pages) {
-
 		/*
 		 * This can potentially iterate a massively long zone with
 		 * many pageblocks unsuitable, so periodically check if we

@@ -1433,8 +1488,15 @@ static isolate_migrate_t isolate_migratepages(struct zone *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) &&
+		    !isolation_suitable(cc, page))
 			continue;
 
 		/*

index b0309bf409b3..ba3035dcc548 100644
@@ -1117,7 +1117,7 @@ static inline bool compact_scanners_met(struct compact_control *cc)
 
 /* Reorder the free list to reduce repeated future searches */
 static void
-move_freelist_tail(struct list_head *freelist, struct page *freepage)
+move_freelist_head(struct list_head *freelist, struct page *freepage)
 {
 	LIST_HEAD(sublist);
 

@@ -1128,6 +1128,193 @@ move_freelist_tail(struct list_head *freelist, struct page *freepage)
 	}
 }
 
+static void
+move_freelist_tail(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);
+	}
+}
+
+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(start_pfn + pageblock_nr_pages, zone_end_pfn(cc->zone));
+
+	/* Scan before */
+	if (start_pfn != pfn) {
+		isolate_freepages_block(cc, &start_pfn, pfn, &cc->freepages, 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, 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);
+}
+
+static unsigned long
+fast_isolate_freepages(struct compact_control *cc)
+{
+	unsigned int limit = min(1U, freelist_scan_limit(cc) >> 1);
+	unsigned int order_scanned = 0, 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;
+
+	/*
+	 * 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 == pageblock_start_pfn(zone_end_pfn(cc->zone) - 1)) {
+		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;
+
+	for (order = cc->order - 1;
+	     order >= 0 && !page;
+	     order--) {
+		struct free_area *area = &cc->zone->free_area[order];
+		struct list_head *freelist;
+		struct page *freepage;
+		unsigned long flags;
+
+		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;
+				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 = -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) {
+					page = pfn_to_page(min_pfn);
+					cc->free_pfn = min_pfn;
+				}
+			}
+		}
+	}
+
+	if (highest && highest > cc->zone->compact_cached_free_pfn)
+		cc->zone->compact_cached_free_pfn = highest;
+
+	cc->total_free_scanned += nr_scanned;
+	if (!page)
+		return 0;
+
+	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.

@@ -1142,6 +1329,11 @@ static void isolate_freepages(struct compact_control *cc)
 	unsigned long low_pfn;	     /* lowest pfn scanner is able to scan */
 	struct list_head *freelist = &cc->freepages;
 
+	/* Try a small search of the free lists for a candidate */
+	isolate_start_pfn = fast_isolate_freepages(cc);
+	if (isolate_start_pfn)
+		goto splitmap;
+
 	/*
 	 * Initialise the free scanner. The starting point is where we last
 	 * successfully isolated from, zone-cached value, or the end of the

@@ -1218,9 +1410,6 @@ static void isolate_freepages(struct compact_control *cc)
 		}
 	}
 
-	/* __isolate_free_page() does not map the pages */
-	split_map_pages(freelist);
-
 	/*
 	 * Record where the free scanner will restart next time. Either we
 	 * broke from the loop and set isolate_start_pfn based on the last

@@ -1228,6 +1417,10 @@ static void isolate_freepages(struct compact_control *cc)
 	 * 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);
 }
 
 /*

index 68250a57aace..b0d530cf46d1 100644
@@ -95,7 +95,8 @@ extern int sysctl_compact_unevictable_allowed;
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern 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);
+		const struct alloc_context *ac, enum compact_priority prio,
+		struct page **page);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern enum compact_result compaction_suitable(struct zone *zone, int order,
 		unsigned int alloc_flags, int classzone_idx);

index 8681905589f0..f1758ef4d1e2 100644
@@ -47,6 +47,7 @@ struct pid_namespace;
 struct pipe_inode_info;
 struct rcu_node;
 struct reclaim_state;
+struct capture_control;
 struct robust_list_head;
 struct sched_attr;
 struct sched_param;

@@ -964,6 +965,9 @@ struct task_struct {
 
 	struct io_context		*io_context;
 
+#ifdef CONFIG_COMPACTION
+	struct capture_control		*capture_control;
+#endif
 	/* Ptrace state: */
 	unsigned long			ptrace_message;
 	kernel_siginfo_t		*last_siginfo;

index 5f41fd2e0b6b..cd6d816aa40b 100644
@@ -2177,6 +2177,9 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
 #endif
 
+#ifdef CONFIG_COMPACTION
+	p->capture_control = NULL;
+#endif
 	init_numa_balancing(clone_flags, p);
 }
 

index ba3035dcc548..39d33b6d1172 100644
@@ -1949,7 +1949,8 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
 	return false;
 }
 
-static enum compact_result compact_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 = cc->zone->zone_start_pfn;

@@ -2086,6 +2087,11 @@ static enum compact_result compact_zone(struct compact_control *cc)
 			}
 		}
 
+		/* Stop if a page has been captured */
+		if (capc && capc->page) {
+			ret = COMPACT_SUCCESS;
+			break;
+		}
 	}
 
 out:

@@ -2119,7 +2125,8 @@ static enum compact_result compact_zone(struct compact_control *cc)
 
 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 = {

@@ -2139,14 +2146,24 @@ static enum compact_result compact_zone_order(struct zone *zone, int order,
 		.ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY),
 		.ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY)
 	};
+	struct capture_control capc = {
+		.cc = &cc,
+		.page = NULL,
+	};
+
+	if (capture)
+		current->capture_control = &capc;
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
 
-	ret = compact_zone(&cc);
+	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;
 }
 

@@ -2164,7 +2181,7 @@ int sysctl_extfrag_threshold = 500;
  */
 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;

@@ -2192,7 +2209,7 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 		}
 
 		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 */

@@ -2260,7 +2277,7 @@ static void compact_node(int nid)
 		INIT_LIST_HEAD(&cc.freepages);
 		INIT_LIST_HEAD(&cc.migratepages);
 
-		compact_zone(&cc);
+		compact_zone(&cc, NULL);
 
 		VM_BUG_ON(!list_empty(&cc.freepages));
 		VM_BUG_ON(!list_empty(&cc.migratepages));

@@ -2402,7 +2419,7 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 
 		if (kthread_should_stop())
 			return;
-		status = compact_zone(&cc);
+		status = compact_zone(&cc, NULL);
 
 		if (status == COMPACT_SUCCESS) {
 			compaction_defer_reset(zone, cc.order, false);

index 983cb975545f..08fbb9d157c0 100644
@@ -207,6 +207,15 @@ struct compact_control {
 	bool contended;			/* Signal lock or sched contention */
 };
 
+/*
+ * Used in direct compaction when a page should be taken from the freelists
+ * immediately when one is created during the free path.
+ */
+struct capture_control {
+	struct compact_control *cc;
+	struct page *page;
+};
+
 unsigned long
 isolate_freepages_range(struct compact_control *cc,
 			unsigned long start_pfn, unsigned long end_pfn);

99 lines not on this page · raw message

index 39d33b6d1172..05fecd7227e4 100644
@@ -2208,6 +2208,16 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 			continue;
 		}
 
+		/*
+		 * Do not compact remote memory. It's expensive and high-order
+		 * small allocations are expected to prefer or require local
+		 * memory. Similarly, larger requests such as THP can fallback
+		 * to base pages in preference to remote huge pages if
+		 * __GFP_THISNODE is not specified
+		 */
+		if (zone_to_nid(zone) != zone_to_nid(ac->preferred_zoneref->zone))
+			continue;
+
 		status = compact_zone_order(zone, order, gfp_mask, prio,
 				alloc_flags, ac_classzone_idx(ac), capture);
 		rc = max(status, rc);