Linux-libre 4.6.2-gnu

1 files changed, 264 insertions, 63 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 29fb26970..f8e925eb4 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -7,6 +7,7 @@
  *
  * Copyright IBM Corp. 2007-2010 Mel Gorman <mel@csn.ul.ie>
  */
+#include <linux/cpu.h>
 #include <linux/swap.h>
 #include <linux/migrate.h>
 #include <linux/compaction.h>
@@ -17,6 +18,8 @@
 #include <linux/balloon_compaction.h>
 #include <linux/page-isolation.h>
 #include <linux/kasan.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
 #include "internal.h"
 
 #ifdef CONFIG_COMPACTION
@@ -71,49 +74,6 @@ static inline bool migrate_async_suitable(int migratetype)
 	return is_migrate_cma(migratetype) || migratetype == MIGRATE_MOVABLE;
 }
 
-/*
- * Check that the whole (or subset of) a pageblock given by the interval of
- * [start_pfn, end_pfn) is valid and within the same zone, before scanning it
- * with the migration of free compaction scanner. The scanners then need to
- * use only pfn_valid_within() check for arches that allow holes within
- * pageblocks.
- *
- * Return struct page pointer of start_pfn, or NULL if checks were not passed.
- *
- * It's possible on some configurations to have a setup like node0 node1 node0
- * i.e. it's possible that all pages within a zones range of pages do not
- * belong to a single zone. We assume that a border between node0 and node1
- * can occur within a single pageblock, but not a node0 node1 node0
- * interleaving within a single pageblock. It is therefore sufficient to check
- * the first and last page of a pageblock and avoid checking each individual
- * page in a pageblock.
- */
-static struct page *pageblock_pfn_to_page(unsigned long start_pfn,
-				unsigned long end_pfn, struct zone *zone)
-{
-	struct page *start_page;
-	struct page *end_page;
-
-	/* end_pfn is one past the range we are checking */
-	end_pfn--;
-
-	if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn))
-		return NULL;
-
-	start_page = pfn_to_page(start_pfn);
-
-	if (page_zone(start_page) != zone)
-		return NULL;
-
-	end_page = pfn_to_page(end_pfn);
-
-	/* This gives a shorter code than deriving page_zone(end_page) */
-	if (page_zone_id(start_page) != page_zone_id(end_page))
-		return NULL;
-
-	return start_page;
-}
-
 #ifdef CONFIG_COMPACTION
 
 /* Do not skip compaction more than 64 times */
@@ -200,7 +160,8 @@ static void reset_cached_positions(struct zone *zone)
 {
 	zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn;
 	zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn;
-	zone->compact_cached_free_pfn = zone_end_pfn(zone);
+	zone->compact_cached_free_pfn =
+			round_down(zone_end_pfn(zone) - 1, pageblock_nr_pages);
 }
 
 /*
@@ -554,13 +515,17 @@ unsigned long
 isolate_freepages_range(struct compact_control *cc,
 			unsigned long start_pfn, unsigned long end_pfn)
 {
-	unsigned long isolated, pfn, block_end_pfn;
+	unsigned long isolated, pfn, block_start_pfn, block_end_pfn;
 	LIST_HEAD(freelist);
 
 	pfn = start_pfn;
+	block_start_pfn = pfn & ~(pageblock_nr_pages - 1);
+	if (block_start_pfn < cc->zone->zone_start_pfn)
+		block_start_pfn = cc->zone->zone_start_pfn;
 	block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 
 	for (; pfn < end_pfn; pfn += isolated,
+				block_start_pfn = block_end_pfn,
 				block_end_pfn += pageblock_nr_pages) {
 		/* Protect pfn from changing by isolate_freepages_block */
 		unsigned long isolate_start_pfn = pfn;
@@ -573,11 +538,13 @@ isolate_freepages_range(struct compact_control *cc,
 		 * scanning range to right one.
 		 */
 		if (pfn >= block_end_pfn) {
+			block_start_pfn = pfn & ~(pageblock_nr_pages - 1);
 			block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 			block_end_pfn = min(block_end_pfn, end_pfn);
 		}
 
-		if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone))
+		if (!pageblock_pfn_to_page(block_start_pfn,
+					block_end_pfn, cc->zone))
 			break;
 
 		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
@@ -863,18 +830,23 @@ unsigned long
 isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 							unsigned long end_pfn)
 {
-	unsigned long pfn, block_end_pfn;
+	unsigned long pfn, block_start_pfn, block_end_pfn;
 
 	/* Scan block by block. First and last block may be incomplete */
 	pfn = start_pfn;
+	block_start_pfn = pfn & ~(pageblock_nr_pages - 1);
+	if (block_start_pfn < cc->zone->zone_start_pfn)
+		block_start_pfn = cc->zone->zone_start_pfn;
 	block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 
 	for (; pfn < end_pfn; pfn = block_end_pfn,
+				block_start_pfn = block_end_pfn,
 				block_end_pfn += pageblock_nr_pages) {
 
 		block_end_pfn = min(block_end_pfn, end_pfn);
 
-		if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone))
+		if (!pageblock_pfn_to_page(block_start_pfn,
+					block_end_pfn, cc->zone))
 			continue;
 
 		pfn = isolate_migratepages_block(cc, pfn, block_end_pfn,
@@ -1095,7 +1067,9 @@ int sysctl_compact_unevictable_allowed __read_mostly = 1;
 static isolate_migrate_t isolate_migratepages(struct zone *zone,
 					struct compact_control *cc)
 {
-	unsigned long low_pfn, end_pfn;
+	unsigned long block_start_pfn;
+	unsigned long block_end_pfn;
+	unsigned long low_pfn;
 	unsigned long isolate_start_pfn;
 	struct page *page;
 	const isolate_mode_t isolate_mode =
@@ -1107,16 +1081,21 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	 * initialized by compact_zone()
 	 */
 	low_pfn = cc->migrate_pfn;
+	block_start_pfn = cc->migrate_pfn & ~(pageblock_nr_pages - 1);
+	if (block_start_pfn < zone->zone_start_pfn)
+		block_start_pfn = zone->zone_start_pfn;
 
 	/* Only scan within a pageblock boundary */
-	end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages);
+	block_end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages);
 
 	/*
 	 * Iterate over whole pageblocks until we find the first suitable.
 	 * Do not cross the free scanner.
 	 */
-	for (; end_pfn <= cc->free_pfn;
-			low_pfn = end_pfn, end_pfn += pageblock_nr_pages) {
+	for (; block_end_pfn <= cc->free_pfn;
+			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
@@ -1127,7 +1106,8 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 						&& compact_should_abort(cc))
 			break;
 
-		page = pageblock_pfn_to_page(low_pfn, end_pfn, zone);
+		page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn,
+									zone);
 		if (!page)
 			continue;
 
@@ -1146,8 +1126,8 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 
 		/* Perform the isolation */
 		isolate_start_pfn = low_pfn;
-		low_pfn = isolate_migratepages_block(cc, low_pfn, end_pfn,
-								isolate_mode);
+		low_pfn = isolate_migratepages_block(cc, low_pfn,
+						block_end_pfn, isolate_mode);
 
 		if (!low_pfn || cc->contended) {
 			acct_isolated(zone, cc);
@@ -1203,11 +1183,11 @@ static int __compact_finished(struct zone *zone, struct compact_control *cc,
 
 		/*
 		 * Mark that the PG_migrate_skip information should be cleared
-		 * by kswapd when it goes to sleep. kswapd does not set the
+		 * by kswapd when it goes to sleep. kcompactd does not set the
 		 * flag itself as the decision to be clear should be directly
 		 * based on an allocation request.
 		 */
-		if (!current_is_kswapd())
+		if (cc->direct_compaction)
 			zone->compact_blockskip_flush = true;
 
 		return COMPACT_COMPLETE;
@@ -1350,10 +1330,9 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 
 	/*
 	 * Clear pageblock skip if there were failures recently and compaction
-	 * is about to be retried after being deferred. kswapd does not do
-	 * this reset as it'll reset the cached information when going to sleep.
+	 * is about to be retried after being deferred.
 	 */
-	if (compaction_restarting(zone, cc->order) && !current_is_kswapd())
+	if (compaction_restarting(zone, cc->order))
 		__reset_isolation_suitable(zone);
 
 	/*
@@ -1363,11 +1342,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	 */
 	cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync];
 	cc->free_pfn = zone->compact_cached_free_pfn;
-	if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) {
-		cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1);
+	if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) {
+		cc->free_pfn = round_down(end_pfn - 1, pageblock_nr_pages);
 		zone->compact_cached_free_pfn = cc->free_pfn;
 	}
-	if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_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;
@@ -1489,6 +1468,7 @@ static unsigned long compact_zone_order(struct zone *zone, int order,
 		.mode = mode,
 		.alloc_flags = alloc_flags,
 		.classzone_idx = classzone_idx,
+		.direct_compaction = true,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -1751,4 +1731,225 @@ void compaction_unregister_node(struct node *node)
 }
 #endif /* CONFIG_SYSFS && CONFIG_NUMA */
 
+static inline bool kcompactd_work_requested(pg_data_t *pgdat)
+{
+	return pgdat->kcompactd_max_order > 0 || kthread_should_stop();
+}
+
+static bool kcompactd_node_suitable(pg_data_t *pgdat)
+{
+	int zoneid;
+	struct zone *zone;
+	enum zone_type classzone_idx = pgdat->kcompactd_classzone_idx;
+
+	for (zoneid = 0; zoneid <= classzone_idx; zoneid++) {
+		zone = &pgdat->node_zones[zoneid];
+
+		if (!populated_zone(zone))
+			continue;
+
+		if (compaction_suitable(zone, pgdat->kcompactd_max_order, 0,
+					classzone_idx) == COMPACT_CONTINUE)
+			return true;
+	}
+
+	return false;
+}
+
+static void kcompactd_do_work(pg_data_t *pgdat)
+{
+	/*
+	 * With no special task, compact all zones so that a page of requested
+	 * order is allocatable.
+	 */
+	int zoneid;
+	struct zone *zone;
+	struct compact_control cc = {
+		.order = pgdat->kcompactd_max_order,
+		.classzone_idx = pgdat->kcompactd_classzone_idx,
+		.mode = MIGRATE_SYNC_LIGHT,
+		.ignore_skip_hint = true,
+
+	};
+	bool success = false;
+
+	trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order,
+							cc.classzone_idx);
+	count_vm_event(KCOMPACTD_WAKE);
+
+	for (zoneid = 0; zoneid <= cc.classzone_idx; zoneid++) {
+		int status;
+
+		zone = &pgdat->node_zones[zoneid];
+		if (!populated_zone(zone))
+			continue;
+
+		if (compaction_deferred(zone, cc.order))
+			continue;
+
+		if (compaction_suitable(zone, cc.order, 0, zoneid) !=
+							COMPACT_CONTINUE)
+			continue;
+
+		cc.nr_freepages = 0;
+		cc.nr_migratepages = 0;
+		cc.zone = zone;
+		INIT_LIST_HEAD(&cc.freepages);
+		INIT_LIST_HEAD(&cc.migratepages);
+
+		if (kthread_should_stop())
+			return;
+		status = compact_zone(zone, &cc);
+
+		if (zone_watermark_ok(zone, cc.order, low_wmark_pages(zone),
+						cc.classzone_idx, 0)) {
+			success = true;
+			compaction_defer_reset(zone, cc.order, false);
+		} else if (status == COMPACT_COMPLETE) {
+			/*
+			 * We use sync migration mode here, so we defer like
+			 * sync direct compaction does.
+			 */
+			defer_compaction(zone, cc.order);
+		}
+
+		VM_BUG_ON(!list_empty(&cc.freepages));
+		VM_BUG_ON(!list_empty(&cc.migratepages));
+	}
+
+	/*
+	 * Regardless of success, we are done until woken up next. But remember
+	 * the requested order/classzone_idx in case it was higher/tighter than
+	 * our current ones
+	 */
+	if (pgdat->kcompactd_max_order <= cc.order)
+		pgdat->kcompactd_max_order = 0;
+	if (pgdat->kcompactd_classzone_idx >= cc.classzone_idx)
+		pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1;
+}
+
+void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx)
+{
+	if (!order)
+		return;
+
+	if (pgdat->kcompactd_max_order < order)
+		pgdat->kcompactd_max_order = order;
+
+	if (pgdat->kcompactd_classzone_idx > classzone_idx)
+		pgdat->kcompactd_classzone_idx = classzone_idx;
+
+	if (!waitqueue_active(&pgdat->kcompactd_wait))
+		return;
+
+	if (!kcompactd_node_suitable(pgdat))
+		return;
+
+	trace_mm_compaction_wakeup_kcompactd(pgdat->node_id, order,
+							classzone_idx);
+	wake_up_interruptible(&pgdat->kcompactd_wait);
+}
+
+/*
+ * The background compaction daemon, started as a kernel thread
+ * from the init process.
+ */
+static int kcompactd(void *p)
+{
+	pg_data_t *pgdat = (pg_data_t*)p;
+	struct task_struct *tsk = current;
+
+	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
+
+	if (!cpumask_empty(cpumask))
+		set_cpus_allowed_ptr(tsk, cpumask);
+
+	set_freezable();
+
+	pgdat->kcompactd_max_order = 0;
+	pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1;
+
+	while (!kthread_should_stop()) {
+		trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
+		wait_event_freezable(pgdat->kcompactd_wait,
+				kcompactd_work_requested(pgdat));
+
+		kcompactd_do_work(pgdat);
+	}
+
+	return 0;
+}
+
+/*
+ * This kcompactd start function will be called by init and node-hot-add.
+ * On node-hot-add, kcompactd will moved to proper cpus if cpus are hot-added.
+ */
+int kcompactd_run(int nid)
+{
+	pg_data_t *pgdat = NODE_DATA(nid);
+	int ret = 0;
+
+	if (pgdat->kcompactd)
+		return 0;
+
+	pgdat->kcompactd = kthread_run(kcompactd, pgdat, "kcompactd%d", nid);
+	if (IS_ERR(pgdat->kcompactd)) {
+		pr_err("Failed to start kcompactd on node %d\n", nid);
+		ret = PTR_ERR(pgdat->kcompactd);
+		pgdat->kcompactd = NULL;
+	}
+	return ret;
+}
+
+/*
+ * Called by memory hotplug when all memory in a node is offlined. Caller must
+ * hold mem_hotplug_begin/end().
+ */
+void kcompactd_stop(int nid)
+{
+	struct task_struct *kcompactd = NODE_DATA(nid)->kcompactd;
+
+	if (kcompactd) {
+		kthread_stop(kcompactd);
+		NODE_DATA(nid)->kcompactd = NULL;
+	}
+}
+
+/*
+ * It's optimal to keep kcompactd on the same CPUs as their memory, but
+ * not required for correctness. So if the last cpu in a node goes
+ * 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)
+{
+	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;
+
+			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);
+		}
+	}
+	return NOTIFY_OK;
+}
+
+static int __init kcompactd_init(void)
+{
+	int nid;
+
+	for_each_node_state(nid, N_MEMORY)
+		kcompactd_run(nid);
+	hotcpu_notifier(cpu_callback, 0);
+	return 0;
+}
+subsys_initcall(kcompactd_init)
+
 #endif /* CONFIG_COMPACTION */