1 files changed, 223 insertions, 132 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index b961db601df4..807b58e6eb68 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -40,9 +40,22 @@ static inline void count_compact_events(enum vm_event_item item, long delta)
 {
 	count_vm_events(item, delta);
 }
+
+/*
+ * order == -1 is expected when compacting proactively via
+ * 1. /proc/sys/vm/compact_memory
+ * 2. /sys/devices/system/node/nodex/compact
+ * 3. /proc/sys/vm/compaction_proactiveness
+ */
+static inline bool is_via_compact_memory(int order)
+{
+	return order == -1;
+}
+
 #else
 #define count_compact_event(item) do { } while (0)
 #define count_compact_events(item, delta) do { } while (0)
+static inline bool is_via_compact_memory(int order) { return false; }
 #endif
 
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
@@ -66,45 +79,56 @@ static inline void count_compact_events(enum vm_event_item item, long delta)
 #define COMPACTION_HPAGE_ORDER	(PMD_SHIFT - PAGE_SHIFT)
 #endif
 
-static unsigned long release_freepages(struct list_head *freelist)
+static void split_map_pages(struct list_head *freepages)
 {
+	unsigned int i, order;
 	struct page *page, *next;
-	unsigned long high_pfn = 0;
+	LIST_HEAD(tmp_list);
 
-	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;
-	}
+	for (order = 0; order < NR_PAGE_ORDERS; order++) {
+		list_for_each_entry_safe(page, next, &freepages[order], lru) {
+			unsigned int nr_pages;
 
-	return high_pfn;
+			list_del(&page->lru);
+
+			nr_pages = 1 << order;
+
+			post_alloc_hook(page, order, __GFP_MOVABLE);
+			if (order)
+				split_page(page, order);
+
+			for (i = 0; i < nr_pages; i++) {
+				list_add(&page->lru, &tmp_list);
+				page++;
+			}
+		}
+		list_splice_init(&tmp_list, &freepages[0]);
+	}
 }
 
-static void split_map_pages(struct list_head *list)
+static unsigned long release_free_list(struct list_head *freepages)
 {
-	unsigned int i, order, nr_pages;
-	struct page *page, *next;
-	LIST_HEAD(tmp_list);
-
-	list_for_each_entry_safe(page, next, list, lru) {
-		list_del(&page->lru);
+	int order;
+	unsigned long high_pfn = 0;
 
-		order = page_private(page);
-		nr_pages = 1 << order;
+	for (order = 0; order < NR_PAGE_ORDERS; order++) {
+		struct page *page, *next;
 
-		post_alloc_hook(page, order, __GFP_MOVABLE);
-		if (order)
-			split_page(page, order);
+		list_for_each_entry_safe(page, next, &freepages[order], lru) {
+			unsigned long pfn = page_to_pfn(page);
 
-		for (i = 0; i < nr_pages; i++) {
-			list_add(&page->lru, &tmp_list);
-			page++;
+			list_del(&page->lru);
+			/*
+			 * Convert free pages into post allocation pages, so
+			 * that we can free them via __free_page.
+			 */
+			post_alloc_hook(page, order, __GFP_MOVABLE);
+			__free_pages(page, order);
+			if (pfn > high_pfn)
+				high_pfn = pfn;
 		}
 	}
-
-	list_splice(&tmp_list, list);
+	return high_pfn;
 }
 
 #ifdef CONFIG_COMPACTION
@@ -657,7 +681,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 		nr_scanned += isolated - 1;
 		total_isolated += isolated;
 		cc->nr_freepages += isolated;
-		list_add_tail(&page->lru, freelist);
+		list_add_tail(&page->lru, &freelist[order]);
 
 		if (!strict && cc->nr_migratepages <= cc->nr_freepages) {
 			blockpfn += isolated;
@@ -722,7 +746,11 @@ isolate_freepages_range(struct compact_control *cc,
 			unsigned long start_pfn, unsigned long end_pfn)
 {
 	unsigned long isolated, pfn, block_start_pfn, block_end_pfn;
-	LIST_HEAD(freelist);
+	int order;
+	struct list_head tmp_freepages[NR_PAGE_ORDERS];
+
+	for (order = 0; order < NR_PAGE_ORDERS; order++)
+		INIT_LIST_HEAD(&tmp_freepages[order]);
 
 	pfn = start_pfn;
 	block_start_pfn = pageblock_start_pfn(pfn);
@@ -753,7 +781,7 @@ isolate_freepages_range(struct compact_control *cc,
 			break;
 
 		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
-					block_end_pfn, &freelist, 0, true);
+					block_end_pfn, tmp_freepages, 0, true);
 
 		/*
 		 * In strict mode, isolate_freepages_block() returns 0 if
@@ -770,15 +798,15 @@ isolate_freepages_range(struct compact_control *cc,
 		 */
 	}
 
-	/* __isolate_free_page() does not map the pages */
-	split_map_pages(&freelist);
-
 	if (pfn < end_pfn) {
 		/* Loop terminated early, cleanup. */
-		release_freepages(&freelist);
+		release_free_list(tmp_freepages);
 		return 0;
 	}
 
+	/* __isolate_free_page() does not map the pages */
+	split_map_pages(tmp_freepages);
+
 	/* We don't use freelists for anything. */
 	return pfn;
 }
@@ -817,6 +845,32 @@ static bool too_many_isolated(struct compact_control *cc)
 }
 
 /**
+ * skip_isolation_on_order() - determine when to skip folio isolation based on
+ *			       folio order and compaction target order
+ * @order:		to-be-isolated folio order
+ * @target_order:	compaction target order
+ *
+ * This avoids unnecessary folio isolations during compaction.
+ */
+static bool skip_isolation_on_order(int order, int target_order)
+{
+	/*
+	 * Unless we are performing global compaction (i.e.,
+	 * is_via_compact_memory), skip any folios that are larger than the
+	 * target order: we wouldn't be here if we'd have a free folio with
+	 * the desired target_order, so migrating this folio would likely fail
+	 * later.
+	 */
+	if (!is_via_compact_memory(target_order) && order >= target_order)
+		return true;
+	/*
+	 * We limit memory compaction to pageblocks and won't try
+	 * creating free blocks of memory that are larger than that.
+	 */
+	return order >= pageblock_order;
+}
+
+/**
  * isolate_migratepages_block() - isolate all migrate-able pages within
  *				  a single pageblock
  * @cc:		Compaction control structure.
@@ -947,7 +1001,22 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			valid_page = page;
 		}
 
-		if (PageHuge(page) && cc->alloc_contig) {
+		if (PageHuge(page)) {
+			/*
+			 * skip hugetlbfs if we are not compacting for pages
+			 * bigger than its order. THPs and other compound pages
+			 * are handled below.
+			 */
+			if (!cc->alloc_contig) {
+				const unsigned int order = compound_order(page);
+
+				if (order <= MAX_PAGE_ORDER) {
+					low_pfn += (1UL << order) - 1;
+					nr_scanned += (1UL << order) - 1;
+				}
+				goto isolate_fail;
+			}
+			/* for alloc_contig case */
 			if (locked) {
 				unlock_page_lruvec_irqrestore(locked, flags);
 				locked = NULL;
@@ -1008,21 +1077,24 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		}
 
 		/*
-		 * Regardless of being on LRU, compound pages such as THP and
-		 * hugetlbfs are not to be compacted unless we are attempting
-		 * an allocation much larger than the huge page size (eg CMA).
-		 * We can potentially save a lot of iterations if we skip them
-		 * at once. The check is racy, but we can consider only valid
-		 * values and the only danger is skipping too much.
+		 * Regardless of being on LRU, compound pages such as THP
+		 * (hugetlbfs is handled above) are not to be compacted unless
+		 * we are attempting an allocation larger than the compound
+		 * page size. We can potentially save a lot of iterations if we
+		 * skip them at once. The check is racy, but we can consider
+		 * only valid values and the only danger is skipping too much.
 		 */
 		if (PageCompound(page) && !cc->alloc_contig) {
 			const unsigned int order = compound_order(page);
 
-			if (likely(order <= MAX_PAGE_ORDER)) {
-				low_pfn += (1UL << order) - 1;
-				nr_scanned += (1UL << order) - 1;
+			/* Skip based on page order and compaction target order. */
+			if (skip_isolation_on_order(order, cc->order)) {
+				if (order <= MAX_PAGE_ORDER) {
+					low_pfn += (1UL << order) - 1;
+					nr_scanned += (1UL << order) - 1;
+				}
+				goto isolate_fail;
 			}
-			goto isolate_fail;
 		}
 
 		/*
@@ -1165,10 +1237,11 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			}
 
 			/*
-			 * folio become large since the non-locked check,
-			 * and it's on LRU.
+			 * Check LRU folio order under the lock
 			 */
-			if (unlikely(folio_test_large(folio) && !cc->alloc_contig)) {
+			if (unlikely(skip_isolation_on_order(folio_order(folio),
+							     cc->order) &&
+				     !cc->alloc_contig)) {
 				low_pfn += folio_nr_pages(folio) - 1;
 				nr_scanned += folio_nr_pages(folio) - 1;
 				folio_set_lru(folio);
@@ -1365,12 +1438,14 @@ static bool suitable_migration_target(struct compact_control *cc,
 {
 	/* If the page is a large free page, then disallow migration */
 	if (PageBuddy(page)) {
+		int order = cc->order > 0 ? cc->order : pageblock_order;
+
 		/*
 		 * We are checking page_order without zone->lock taken. But
 		 * the only small danger is that we skip a potentially suitable
 		 * pageblock, so it's not worth to check order for valid range.
 		 */
-		if (buddy_order_unsafe(page) >= pageblock_order)
+		if (buddy_order_unsafe(page) >= order)
 			return false;
 	}
 
@@ -1458,7 +1533,7 @@ fast_isolate_around(struct compact_control *cc, unsigned long pfn)
 	if (!page)
 		return;
 
-	isolate_freepages_block(cc, &start_pfn, end_pfn, &cc->freepages, 1, false);
+	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 (start_pfn == end_pfn && !cc->no_set_skip_hint)
@@ -1587,7 +1662,7 @@ static void fast_isolate_freepages(struct compact_control *cc)
 				nr_scanned += nr_isolated - 1;
 				total_isolated += nr_isolated;
 				cc->nr_freepages += nr_isolated;
-				list_add_tail(&page->lru, &cc->freepages);
+				list_add_tail(&page->lru, &cc->freepages[order]);
 				count_compact_events(COMPACTISOLATED, nr_isolated);
 			} else {
 				/* If isolation fails, abort the search */
@@ -1664,13 +1739,12 @@ static void isolate_freepages(struct compact_control *cc)
 	unsigned long isolate_start_pfn; /* exact pfn we start at */
 	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 */
 	fast_isolate_freepages(cc);
 	if (cc->nr_freepages)
-		goto splitmap;
+		return;
 
 	/*
 	 * Initialise the free scanner. The starting point is where we last
@@ -1730,7 +1804,7 @@ static void isolate_freepages(struct compact_control *cc)
 
 		/* Found a block suitable for isolating free pages from. */
 		nr_isolated = isolate_freepages_block(cc, &isolate_start_pfn,
-					block_end_pfn, freelist, stride, false);
+					block_end_pfn, cc->freepages, stride, false);
 
 		/* Update the skip hint if the full pageblock was scanned */
 		if (isolate_start_pfn == block_end_pfn)
@@ -1771,10 +1845,6 @@ 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);
 }
 
 /*
@@ -1785,19 +1855,47 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
 {
 	struct compact_control *cc = (struct compact_control *)data;
 	struct folio *dst;
+	int order = folio_order(src);
+	bool has_isolated_pages = false;
+	int start_order;
+	struct page *freepage;
+	unsigned long size;
+
+again:
+	for (start_order = order; start_order < NR_PAGE_ORDERS; start_order++)
+		if (!list_empty(&cc->freepages[start_order]))
+			break;
 
-	if (list_empty(&cc->freepages)) {
-		isolate_freepages(cc);
-
-		if (list_empty(&cc->freepages))
+	/* no free pages in the list */
+	if (start_order == NR_PAGE_ORDERS) {
+		if (has_isolated_pages)
 			return NULL;
+		isolate_freepages(cc);
+		has_isolated_pages = true;
+		goto again;
 	}
 
-	dst = list_entry(cc->freepages.next, struct folio, lru);
-	list_del(&dst->lru);
-	cc->nr_freepages--;
+	freepage = list_first_entry(&cc->freepages[start_order], struct page,
+				lru);
+	size = 1 << start_order;
+
+	list_del(&freepage->lru);
+
+	while (start_order > order) {
+		start_order--;
+		size >>= 1;
+
+		list_add(&freepage[size].lru, &cc->freepages[start_order]);
+		set_page_private(&freepage[size], start_order);
+	}
+	dst = (struct folio *)freepage;
 
-	return dst;
+	post_alloc_hook(&dst->page, order, __GFP_MOVABLE);
+	if (order)
+		prep_compound_page(&dst->page, order);
+	cc->nr_freepages -= 1 << order;
+	cc->nr_migratepages -= 1 << order;
+	return page_rmappable_folio(&dst->page);
 }
 
 /*
@@ -1808,9 +1906,19 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
 static void compaction_free(struct folio *dst, unsigned long data)
 {
 	struct compact_control *cc = (struct compact_control *)data;
+	int order = folio_order(dst);
+	struct page *page = &dst->page;
 
-	list_add(&dst->lru, &cc->freepages);
-	cc->nr_freepages++;
+	if (folio_put_testzero(dst)) {
+		free_pages_prepare(page, order);
+		list_add(&dst->lru, &cc->freepages[order]);
+		cc->nr_freepages += 1 << order;
+	}
+	cc->nr_migratepages += 1 << order;
+	/*
+	 * someone else has referenced the page, we cannot take it back to our
+	 * free list.
+	 */
 }
 
 /* possible outcome of isolate_migratepages */
@@ -2087,17 +2195,6 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc)
 }
 
 /*
- * order == -1 is expected when compacting proactively via
- * 1. /proc/sys/vm/compact_memory
- * 2. /sys/devices/system/node/nodex/compact
- * 3. /proc/sys/vm/compaction_proactiveness
- */
-static inline bool is_via_compact_memory(int order)
-{
-	return order == -1;
-}
-
-/*
  * Determine whether kswapd is (or recently was!) running on this node.
  *
  * pgdat_kswapd_lock() pins pgdat->kswapd, so a concurrent kswapd_stop() can't
@@ -2433,7 +2530,8 @@ compact_zone(struct compact_control *cc, struct capture_control *capc)
 	unsigned long last_migrated_pfn;
 	const bool sync = cc->mode != MIGRATE_ASYNC;
 	bool update_cached;
-	unsigned int nr_succeeded = 0;
+	unsigned int nr_succeeded = 0, nr_migratepages;
+	int order;
 
 	/*
 	 * These counters track activities during zone compaction.  Initialize
@@ -2443,7 +2541,8 @@ compact_zone(struct compact_control *cc, struct capture_control *capc)
 	cc->total_free_scanned = 0;
 	cc->nr_migratepages = 0;
 	cc->nr_freepages = 0;
-	INIT_LIST_HEAD(&cc->freepages);
+	for (order = 0; order < NR_PAGE_ORDERS; order++)
+		INIT_LIST_HEAD(&cc->freepages[order]);
 	INIT_LIST_HEAD(&cc->migratepages);
 
 	cc->migratetype = gfp_migratetype(cc->gfp_mask);
@@ -2551,11 +2650,17 @@ rescan:
 				pageblock_start_pfn(cc->migrate_pfn - 1));
 		}
 
+		/*
+		 * Record the number of pages to migrate since the
+		 * compaction_alloc/free() will update cc->nr_migratepages
+		 * properly.
+		 */
+		nr_migratepages = cc->nr_migratepages;
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
 				compaction_free, (unsigned long)cc, cc->mode,
 				MR_COMPACTION, &nr_succeeded);
 
-		trace_mm_compaction_migratepages(cc, nr_succeeded);
+		trace_mm_compaction_migratepages(nr_migratepages, nr_succeeded);
 
 		/* All pages were either migrated or will be released */
 		cc->nr_migratepages = 0;
@@ -2629,7 +2734,7 @@ out:
 	 * so we don't leave any returned pages behind in the next attempt.
 	 */
 	if (cc->nr_freepages > 0) {
-		unsigned long free_pfn = release_freepages(&cc->freepages);
+		unsigned long free_pfn = release_free_list(cc->freepages);
 
 		cc->nr_freepages = 0;
 		VM_BUG_ON(free_pfn == 0);
@@ -2648,7 +2753,6 @@ out:
 
 	trace_mm_compaction_end(cc, start_pfn, end_pfn, sync, ret);
 
-	VM_BUG_ON(!list_empty(&cc->freepages));
 	VM_BUG_ON(!list_empty(&cc->migratepages));
 
 	return ret;
@@ -2783,25 +2887,27 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 }
 
 /*
- * Compact all zones within a node till each zone's fragmentation score
- * reaches within proactive compaction thresholds (as determined by the
- * proactiveness tunable).
+ * compact_node() - compact all zones within a node
+ * @pgdat: The node page data
+ * @proactive: Whether the compaction is proactive
  *
- * It is possible that the function returns before reaching score targets
- * due to various back-off conditions, such as, contention on per-node or
- * per-zone locks.
+ * For proactive compaction, compact till each zone's fragmentation score
+ * reaches within proactive compaction thresholds (as determined by the
+ * proactiveness tunable), it is possible that the function returns before
+ * reaching score targets due to various back-off conditions, such as,
+ * contention on per-node or per-zone locks.
  */
-static void proactive_compact_node(pg_data_t *pgdat)
+static int compact_node(pg_data_t *pgdat, bool proactive)
 {
 	int zoneid;
 	struct zone *zone;
 	struct compact_control cc = {
 		.order = -1,
-		.mode = MIGRATE_SYNC_LIGHT,
+		.mode = proactive ? MIGRATE_SYNC_LIGHT : MIGRATE_SYNC,
 		.ignore_skip_hint = true,
 		.whole_zone = true,
 		.gfp_mask = GFP_KERNEL,
-		.proactive_compaction = true,
+		.proactive_compaction = proactive,
 	};
 
 	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
@@ -2809,54 +2915,39 @@ static void proactive_compact_node(pg_data_t *pgdat)
 		if (!populated_zone(zone))
 			continue;
 
+		if (fatal_signal_pending(current))
+			return -EINTR;
+
 		cc.zone = zone;
 
 		compact_zone(&cc, NULL);
 
-		count_compact_events(KCOMPACTD_MIGRATE_SCANNED,
-				     cc.total_migrate_scanned);
-		count_compact_events(KCOMPACTD_FREE_SCANNED,
-				     cc.total_free_scanned);
+		if (proactive) {
+			count_compact_events(KCOMPACTD_MIGRATE_SCANNED,
+					     cc.total_migrate_scanned);
+			count_compact_events(KCOMPACTD_FREE_SCANNED,
+					     cc.total_free_scanned);
+		}
 	}
-}
-
-/* Compact all zones within a node */
-static void compact_node(int nid)
-{
-	pg_data_t *pgdat = NODE_DATA(nid);
-	int zoneid;
-	struct zone *zone;
-	struct compact_control cc = {
-		.order = -1,
-		.mode = MIGRATE_SYNC,
-		.ignore_skip_hint = true,
-		.whole_zone = true,
-		.gfp_mask = GFP_KERNEL,
-	};
-
-
-	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
-
-		zone = &pgdat->node_zones[zoneid];
-		if (!populated_zone(zone))
-			continue;
-
-		cc.zone = zone;
 
-		compact_zone(&cc, NULL);
-	}
+	return 0;
 }
 
-/* Compact all nodes in the system */
-static void compact_nodes(void)
+/* Compact all zones of all nodes in the system */
+static int compact_nodes(void)
 {
-	int nid;
+	int ret, nid;
 
 	/* Flush pending updates to the LRU lists */
 	lru_add_drain_all();
 
-	for_each_online_node(nid)
-		compact_node(nid);
+	for_each_online_node(nid) {
+		ret = compact_node(NODE_DATA(nid), false);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 static int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write,
@@ -2902,9 +2993,9 @@ static int sysctl_compaction_handler(struct ctl_table *table, int write,
 		return -EINVAL;
 
 	if (write)
-		compact_nodes();
+		ret = compact_nodes();
 
-	return 0;
+	return ret;
 }
 
 #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
@@ -2918,7 +3009,7 @@ static ssize_t compact_store(struct device *dev,
 		/* Flush pending updates to the LRU lists */
 		lru_add_drain_all();
 
-		compact_node(nid);
+		compact_node(NODE_DATA(nid), false);
 	}
 
 	return count;
@@ -3127,7 +3218,7 @@ static int kcompactd(void *p)
 			unsigned int prev_score, score;
 
 			prev_score = fragmentation_score_node(pgdat);
-			proactive_compact_node(pgdat);
+			compact_node(pgdat, true);
 			score = fragmentation_score_node(pgdat);
 			/*
 			 * Defer proactive compaction if the fragmentation