1 files changed, 63 insertions, 42 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 0409a4ad6ea1..81e1eaa2a2cf 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -12,6 +12,7 @@
 #include <linux/migrate.h>
 #include <linux/compaction.h>
 #include <linux/mm_inline.h>
+#include <linux/sched/signal.h>
 #include <linux/backing-dev.h>
 #include <linux/sysctl.h>
 #include <linux/sysfs.h>
@@ -548,7 +549,7 @@ isolate_fail:
 	if (blockpfn == end_pfn)
 		update_pageblock_skip(cc, valid_page, total_isolated, false);
 
-	count_compact_events(COMPACTFREE_SCANNED, nr_scanned);
+	cc->total_free_scanned += nr_scanned;
 	if (total_isolated)
 		count_compact_events(COMPACTISOLATED, total_isolated);
 	return total_isolated;
@@ -634,22 +635,6 @@ isolate_freepages_range(struct compact_control *cc,
 	return pfn;
 }
 
-/* Update the number of anon and file isolated pages in the zone */
-static void acct_isolated(struct zone *zone, struct compact_control *cc)
-{
-	struct page *page;
-	unsigned int count[2] = { 0, };
-
-	if (list_empty(&cc->migratepages))
-		return;
-
-	list_for_each_entry(page, &cc->migratepages, lru)
-		count[!!page_is_file_cache(page)]++;
-
-	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, count[0]);
-	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, count[1]);
-}
-
 /* Similar to reclaim, but different enough that they don't share logic */
 static bool too_many_isolated(struct zone *zone)
 {
@@ -818,7 +803,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 					locked = false;
 				}
 
-				if (isolate_movable_page(page, isolate_mode))
+				if (!isolate_movable_page(page, isolate_mode))
 					goto isolate_success;
 			}
 
@@ -834,6 +819,13 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		    page_count(page) > page_mapcount(page))
 			goto isolate_fail;
 
+		/*
+		 * Only allow to migrate anonymous pages in GFP_NOFS context
+		 * because those do not depend on fs locks.
+		 */
+		if (!(cc->gfp_mask & __GFP_FS) && page_mapping(page))
+			goto isolate_fail;
+
 		/* If we already hold the lock, we can skip some rechecking */
 		if (!locked) {
 			locked = compact_trylock_irqsave(zone_lru_lock(zone),
@@ -866,6 +858,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 		/* Successfully isolated */
 		del_page_from_lru_list(page, lruvec, page_lru(page));
+		inc_node_page_state(page,
+				NR_ISOLATED_ANON + page_is_file_cache(page));
 
 isolate_success:
 		list_add(&page->lru, &cc->migratepages);
@@ -902,7 +896,6 @@ isolate_fail:
 				spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 				locked = false;
 			}
-			acct_isolated(zone, cc);
 			putback_movable_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
 			cc->last_migrated_pfn = 0;
@@ -939,7 +932,7 @@ isolate_fail:
 	trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn,
 						nr_scanned, nr_isolated);
 
-	count_compact_events(COMPACTMIGRATE_SCANNED, nr_scanned);
+	cc->total_migrate_scanned += nr_scanned;
 	if (nr_isolated)
 		count_compact_events(COMPACTISOLATED, nr_isolated);
 
@@ -988,7 +981,6 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
 			break;
 	}
-	acct_isolated(cc->zone, cc);
 
 	return pfn;
 }
@@ -1258,10 +1250,8 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 		low_pfn = isolate_migratepages_block(cc, low_pfn,
 						block_end_pfn, isolate_mode);
 
-		if (!low_pfn || cc->contended) {
-			acct_isolated(zone, cc);
+		if (!low_pfn || cc->contended)
 			return ISOLATE_ABORT;
-		}
 
 		/*
 		 * Either we isolated something and proceed with migration. Or
@@ -1271,7 +1261,6 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 		break;
 	}
 
-	acct_isolated(zone, cc);
 	/* Record where migration scanner will be restarted. */
 	cc->migrate_pfn = low_pfn;
 
@@ -1643,6 +1632,9 @@ out:
 			zone->compact_cached_free_pfn = free_pfn;
 	}
 
+	count_compact_events(COMPACTMIGRATE_SCANNED, cc->total_migrate_scanned);
+	count_compact_events(COMPACTFREE_SCANNED, cc->total_free_scanned);
+
 	trace_mm_compaction_end(start_pfn, cc->migrate_pfn,
 				cc->free_pfn, end_pfn, sync, ret);
 
@@ -1657,6 +1649,8 @@ static enum compact_result compact_zone_order(struct zone *zone, int order,
 	struct compact_control cc = {
 		.nr_freepages = 0,
 		.nr_migratepages = 0,
+		.total_migrate_scanned = 0,
+		.total_free_scanned = 0,
 		.order = order,
 		.gfp_mask = gfp_mask,
 		.zone = zone,
@@ -1696,14 +1690,16 @@ 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)
 {
-	int may_enter_fs = gfp_mask & __GFP_FS;
 	int may_perform_io = gfp_mask & __GFP_IO;
 	struct zoneref *z;
 	struct zone *zone;
 	enum compact_result rc = COMPACT_SKIPPED;
 
-	/* Check if the GFP flags allow compaction */
-	if (!may_enter_fs || !may_perform_io)
+	/*
+	 * Check if the GFP flags allow compaction - GFP_NOIO is really
+	 * tricky context because the migration might require IO
+	 */
+	if (!may_perform_io)
 		return COMPACT_SKIPPED;
 
 	trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio);
@@ -1767,9 +1763,12 @@ static void compact_node(int nid)
 	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,
+		.gfp_mask = GFP_KERNEL,
 	};
 
 
@@ -1892,14 +1891,17 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 	struct zone *zone;
 	struct compact_control cc = {
 		.order = pgdat->kcompactd_max_order,
+		.total_migrate_scanned = 0,
+		.total_free_scanned = 0,
 		.classzone_idx = pgdat->kcompactd_classzone_idx,
 		.mode = MIGRATE_SYNC_LIGHT,
 		.ignore_skip_hint = true,
+		.gfp_mask = GFP_KERNEL,
 
 	};
 	trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order,
 							cc.classzone_idx);
-	count_vm_event(KCOMPACTD_WAKE);
+	count_compact_event(KCOMPACTD_WAKE);
 
 	for (zoneid = 0; zoneid <= cc.classzone_idx; zoneid++) {
 		int status;
@@ -1917,6 +1919,8 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 
 		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);
@@ -1935,6 +1939,11 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 			defer_compaction(zone, cc.order);
 		}
 
+		count_compact_events(KCOMPACTD_MIGRATE_SCANNED,
+				     cc.total_migrate_scanned);
+		count_compact_events(KCOMPACTD_FREE_SCANNED,
+				     cc.total_free_scanned);
+
 		VM_BUG_ON(!list_empty(&cc.freepages));
 		VM_BUG_ON(!list_empty(&cc.migratepages));
 	}
@@ -1958,6 +1967,13 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx)
 	if (pgdat->kcompactd_max_order < order)
 		pgdat->kcompactd_max_order = order;
 
+	/*
+	 * Pairs with implicit barrier in wait_event_freezable()
+	 * such that wakeups are not missed in the lockless
+	 * waitqueue_active() call.
+	 */
+	smp_acquire__after_ctrl_dep();
+
 	if (pgdat->kcompactd_classzone_idx > classzone_idx)
 		pgdat->kcompactd_classzone_idx = classzone_idx;
 
@@ -2043,33 +2059,38 @@ void kcompactd_stop(int nid)
  * away, we get changed to run anywhere: as the first one comes back,
  * restore their cpu bindings.
  */
-static int cpu_callback(struct notifier_block *nfb, unsigned long action,
-			void *hcpu)
+static int kcompactd_cpu_online(unsigned int cpu)
 {
 	int nid;
 
-	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
-		for_each_node_state(nid, N_MEMORY) {
-			pg_data_t *pgdat = NODE_DATA(nid);
-			const struct cpumask *mask;
+	for_each_node_state(nid, N_MEMORY) {
+		pg_data_t *pgdat = NODE_DATA(nid);
+		const struct cpumask *mask;
 
-			mask = cpumask_of_node(pgdat->node_id);
+		mask = cpumask_of_node(pgdat->node_id);
 
-			if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
-				/* One of our CPUs online: restore mask */
-				set_cpus_allowed_ptr(pgdat->kcompactd, mask);
-		}
+		if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
+			/* One of our CPUs online: restore mask */
+			set_cpus_allowed_ptr(pgdat->kcompactd, mask);
 	}
-	return NOTIFY_OK;
+	return 0;
 }
 
 static int __init kcompactd_init(void)
 {
 	int nid;
+	int ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"mm/compaction:online",
+					kcompactd_cpu_online, NULL);
+	if (ret < 0) {
+		pr_err("kcompactd: failed to register hotplug callbacks.\n");
+		return ret;
+	}
 
 	for_each_node_state(nid, N_MEMORY)
 		kcompactd_run(nid);
-	hotcpu_notifier(cpu_callback, 0);
 	return 0;
 }
 subsys_initcall(kcompactd_init)