1 files changed, 181 insertions, 8 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 86375605faa9..176dcded298e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -50,6 +50,24 @@ static inline void count_compact_events(enum vm_event_item item, long delta)
 #define pageblock_start_pfn(pfn)	block_start_pfn(pfn, pageblock_order)
 #define pageblock_end_pfn(pfn)		block_end_pfn(pfn, pageblock_order)
 
+/*
+ * Fragmentation score check interval for proactive compaction purposes.
+ */
+static const unsigned int HPAGE_FRAG_CHECK_INTERVAL_MSEC = 500;
+
+/*
+ * Page order with-respect-to which proactive compaction
+ * calculates external fragmentation, which is used as
+ * the "fragmentation score" of a node/zone.
+ */
+#if defined CONFIG_TRANSPARENT_HUGEPAGE
+#define COMPACTION_HPAGE_ORDER	HPAGE_PMD_ORDER
+#elif defined CONFIG_HUGETLBFS
+#define COMPACTION_HPAGE_ORDER	HUGETLB_PAGE_ORDER
+#else
+#define COMPACTION_HPAGE_ORDER	(PMD_SHIFT - PAGE_SHIFT)
+#endif
+
 static unsigned long release_freepages(struct list_head *freelist)
 {
 	struct page *page, *next;
@@ -136,7 +154,7 @@ EXPORT_SYMBOL(__ClearPageMovable);
 
 /*
  * Compaction is deferred when compaction fails to result in a page
- * allocation success. 1 << compact_defer_limit compactions are skipped up
+ * allocation success. 1 << compact_defer_shift, compactions are skipped up
  * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
  */
 void defer_compaction(struct zone *zone, int order)
@@ -991,7 +1009,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 		mod_node_page_state(page_pgdat(page),
 				NR_ISOLATED_ANON + page_is_file_lru(page),
-				hpage_nr_pages(page));
+				thp_nr_pages(page));
 
 isolate_success:
 		list_add(&page->lru, &cc->migratepages);
@@ -1459,7 +1477,7 @@ static void isolate_freepages(struct compact_control *cc)
 	 * this pfn aligned down to the pageblock boundary, because we do
 	 * block_start_pfn -= pageblock_nr_pages in the for loop.
 	 * For ending point, take care when isolating in last pageblock of a
-	 * a zone which ends in the middle of a pageblock.
+	 * zone which ends in the middle of a pageblock.
 	 * The low boundary is the end of the pageblock the migration scanner
 	 * is using.
 	 */
@@ -1857,6 +1875,76 @@ static inline bool is_via_compact_memory(int order)
 	return order == -1;
 }
 
+static bool kswapd_is_running(pg_data_t *pgdat)
+{
+	return pgdat->kswapd && (pgdat->kswapd->state == TASK_RUNNING);
+}
+
+/*
+ * A zone's fragmentation score is the external fragmentation wrt to the
+ * COMPACTION_HPAGE_ORDER scaled by the zone's size. It returns a value
+ * in the range [0, 100].
+ *
+ * The scaling factor ensures that proactive compaction focuses on larger
+ * zones like ZONE_NORMAL, rather than smaller, specialized zones like
+ * ZONE_DMA32. For smaller zones, the score value remains close to zero,
+ * and thus never exceeds the high threshold for proactive compaction.
+ */
+static unsigned int fragmentation_score_zone(struct zone *zone)
+{
+	unsigned long score;
+
+	score = zone->present_pages *
+			extfrag_for_order(zone, COMPACTION_HPAGE_ORDER);
+	return div64_ul(score, zone->zone_pgdat->node_present_pages + 1);
+}
+
+/*
+ * The per-node proactive (background) compaction process is started by its
+ * corresponding kcompactd thread when the node's fragmentation score
+ * exceeds the high threshold. The compaction process remains active till
+ * the node's score falls below the low threshold, or one of the back-off
+ * conditions is met.
+ */
+static unsigned int fragmentation_score_node(pg_data_t *pgdat)
+{
+	unsigned int score = 0;
+	int zoneid;
+
+	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
+		struct zone *zone;
+
+		zone = &pgdat->node_zones[zoneid];
+		score += fragmentation_score_zone(zone);
+	}
+
+	return score;
+}
+
+static unsigned int fragmentation_score_wmark(pg_data_t *pgdat, bool low)
+{
+	unsigned int wmark_low;
+
+	/*
+	 * Cap the low watermak to avoid excessive compaction
+	 * activity in case a user sets the proactivess tunable
+	 * close to 100 (maximum).
+	 */
+	wmark_low = max(100U - sysctl_compaction_proactiveness, 5U);
+	return low ? wmark_low : min(wmark_low + 10, 100U);
+}
+
+static bool should_proactive_compact_node(pg_data_t *pgdat)
+{
+	int wmark_high;
+
+	if (!sysctl_compaction_proactiveness || kswapd_is_running(pgdat))
+		return false;
+
+	wmark_high = fragmentation_score_wmark(pgdat, false);
+	return fragmentation_score_node(pgdat) > wmark_high;
+}
+
 static enum compact_result __compact_finished(struct compact_control *cc)
 {
 	unsigned int order;
@@ -1883,6 +1971,25 @@ static enum compact_result __compact_finished(struct compact_control *cc)
 			return COMPACT_PARTIAL_SKIPPED;
 	}
 
+	if (cc->proactive_compaction) {
+		int score, wmark_low;
+		pg_data_t *pgdat;
+
+		pgdat = cc->zone->zone_pgdat;
+		if (kswapd_is_running(pgdat))
+			return COMPACT_PARTIAL_SKIPPED;
+
+		score = fragmentation_score_zone(cc->zone);
+		wmark_low = fragmentation_score_wmark(pgdat, true);
+
+		if (score > wmark_low)
+			ret = COMPACT_CONTINUE;
+		else
+			ret = COMPACT_SUCCESS;
+
+		goto out;
+	}
+
 	if (is_via_compact_memory(cc->order))
 		return COMPACT_CONTINUE;
 
@@ -1941,6 +2048,7 @@ static enum compact_result __compact_finished(struct compact_control *cc)
 		}
 	}
 
+out:
 	if (cc->contended || fatal_signal_pending(current))
 		ret = COMPACT_CONTENDED;
 
@@ -2421,6 +2529,41 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 	return rc;
 }
 
+/*
+ * Compact all zones within a node 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)
+{
+	int zoneid;
+	struct zone *zone;
+	struct compact_control cc = {
+		.order = -1,
+		.mode = MIGRATE_SYNC_LIGHT,
+		.ignore_skip_hint = true,
+		.whole_zone = true,
+		.gfp_mask = GFP_KERNEL,
+		.proactive_compaction = true,
+	};
+
+	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);
+
+		VM_BUG_ON(!list_empty(&cc.freepages));
+		VM_BUG_ON(!list_empty(&cc.migratepages));
+	}
+}
 
 /* Compact all zones within a node */
 static void compact_node(int nid)
@@ -2468,6 +2611,13 @@ static void compact_nodes(void)
 int sysctl_compact_memory;
 
 /*
+ * Tunable for proactive compaction. It determines how
+ * aggressively the kernel should compact memory in the
+ * background. It takes values in the range [0, 100].
+ */
+unsigned int __read_mostly sysctl_compaction_proactiveness = 20;
+
+/*
  * This is the entry point for compacting all nodes via
  * /proc/sys/vm/compact_memory
  */
@@ -2646,6 +2796,7 @@ static int kcompactd(void *p)
 {
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
+	unsigned int proactive_defer = 0;
 
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
@@ -2661,12 +2812,34 @@ static int kcompactd(void *p)
 		unsigned long pflags;
 
 		trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
-		wait_event_freezable(pgdat->kcompactd_wait,
-				kcompactd_work_requested(pgdat));
+		if (wait_event_freezable_timeout(pgdat->kcompactd_wait,
+			kcompactd_work_requested(pgdat),
+			msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC))) {
+
+			psi_memstall_enter(&pflags);
+			kcompactd_do_work(pgdat);
+			psi_memstall_leave(&pflags);
+			continue;
+		}
 
-		psi_memstall_enter(&pflags);
-		kcompactd_do_work(pgdat);
-		psi_memstall_leave(&pflags);
+		/* kcompactd wait timeout */
+		if (should_proactive_compact_node(pgdat)) {
+			unsigned int prev_score, score;
+
+			if (proactive_defer) {
+				proactive_defer--;
+				continue;
+			}
+			prev_score = fragmentation_score_node(pgdat);
+			proactive_compact_node(pgdat);
+			score = fragmentation_score_node(pgdat);
+			/*
+			 * Defer proactive compaction if the fragmentation
+			 * score did not go down i.e. no progress made.
+			 */
+			proactive_defer = score < prev_score ?
+					0 : 1 << COMPACT_MAX_DEFER_SHIFT;
+		}
 	}
 
 	return 0;