These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

1 files changed, 131 insertions, 90 deletions

diff --git a/kernel/mm/compaction.c b/kernel/mm/compaction.c
index 0af17fef6..ba0f146d8 100644
--- a/kernel/mm/compaction.c
+++ b/kernel/mm/compaction.c
@@ -35,17 +35,6 @@ static inline void count_compact_events(enum vm_event_item item, long delta)
 #endif
 
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
-#ifdef CONFIG_TRACEPOINTS
-static const char *const compaction_status_string[] = {
-	"deferred",
-	"skipped",
-	"continue",
-	"partial",
-	"complete",
-	"no_suitable_page",
-	"not_suitable_zone",
-};
-#endif
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/compaction.h>
@@ -207,6 +196,13 @@ static inline bool isolation_suitable(struct compact_control *cc,
 	return !get_pageblock_skip(page);
 }
 
+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);
+}
+
 /*
  * This function is called to clear all cached information on pageblocks that
  * should be skipped for page isolation when the migrate and free page scanner
@@ -218,9 +214,6 @@ static void __reset_isolation_suitable(struct zone *zone)
 	unsigned long end_pfn = zone_end_pfn(zone);
 	unsigned long pfn;
 
-	zone->compact_cached_migrate_pfn[0] = start_pfn;
-	zone->compact_cached_migrate_pfn[1] = start_pfn;
-	zone->compact_cached_free_pfn = end_pfn;
 	zone->compact_blockskip_flush = false;
 
 	/* Walk the zone and mark every pageblock as suitable for isolation */
@@ -238,6 +231,8 @@ static void __reset_isolation_suitable(struct zone *zone)
 
 		clear_pageblock_skip(page);
 	}
+
+	reset_cached_positions(zone);
 }
 
 void reset_isolation_suitable(pg_data_t *pgdat)
@@ -431,6 +426,24 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		if (!valid_page)
 			valid_page = page;
+
+		/*
+		 * For compound pages such as THP and hugetlbfs, we can save
+		 * potentially 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)) {
+			unsigned int comp_order = compound_order(page);
+
+			if (likely(comp_order < MAX_ORDER)) {
+				blockpfn += (1UL << comp_order) - 1;
+				cursor += (1UL << comp_order) - 1;
+			}
+
+			goto isolate_fail;
+		}
+
 		if (!PageBuddy(page))
 			goto isolate_fail;
 
@@ -490,6 +503,13 @@ isolate_fail:
 
 	}
 
+	/*
+	 * There is a tiny chance that we have read bogus compound_order(),
+	 * so be careful to not go outside of the pageblock.
+	 */
+	if (unlikely(blockpfn > end_pfn))
+		blockpfn = end_pfn;
+
 	trace_mm_compaction_isolate_freepages(*start_pfn, blockpfn,
 					nr_scanned, total_isolated);
 
@@ -674,6 +694,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 	/* Time to isolate some pages for migration */
 	for (; low_pfn < end_pfn; low_pfn++) {
+		bool is_lru;
+
 		/*
 		 * Periodically drop the lock (if held) regardless of its
 		 * contention, to give chance to IRQs. Abort async compaction
@@ -717,36 +739,35 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		 * It's possible to migrate LRU pages and balloon pages
 		 * Skip any other type of page
 		 */
-		if (!PageLRU(page)) {
+		is_lru = PageLRU(page);
+		if (!is_lru) {
 			if (unlikely(balloon_page_movable(page))) {
 				if (balloon_page_isolate(page)) {
 					/* Successfully isolated */
 					goto isolate_success;
 				}
 			}
-			continue;
 		}
 
 		/*
-		 * PageLRU is set. lru_lock normally excludes isolation
-		 * splitting and collapsing (collapsing has already happened
-		 * if PageLRU is set) but the lock is not necessarily taken
-		 * here and it is wasteful to take it just to check transhuge.
-		 * Check TransHuge without lock and skip the whole pageblock if
-		 * it's either a transhuge or hugetlbfs page, as calling
-		 * compound_order() without preventing THP from splitting the
-		 * page underneath us may return surprising results.
+		 * Regardless of being on LRU, compound pages such as THP and
+		 * hugetlbfs are not to be compacted. 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 (PageTransHuge(page)) {
-			if (!locked)
-				low_pfn = ALIGN(low_pfn + 1,
-						pageblock_nr_pages) - 1;
-			else
-				low_pfn += (1 << compound_order(page)) - 1;
+		if (PageCompound(page)) {
+			unsigned int comp_order = compound_order(page);
+
+			if (likely(comp_order < MAX_ORDER))
+				low_pfn += (1UL << comp_order) - 1;
 
 			continue;
 		}
 
+		if (!is_lru)
+			continue;
+
 		/*
 		 * Migration will fail if an anonymous page is pinned in memory,
 		 * so avoid taking lru_lock and isolating it unnecessarily in an
@@ -763,11 +784,17 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			if (!locked)
 				break;
 
-			/* Recheck PageLRU and PageTransHuge under lock */
+			/* Recheck PageLRU and PageCompound under lock */
 			if (!PageLRU(page))
 				continue;
-			if (PageTransHuge(page)) {
-				low_pfn += (1 << compound_order(page)) - 1;
+
+			/*
+			 * Page become compound since the non-locked check,
+			 * and it's on LRU. It can only be a THP so the order
+			 * is safe to read and it's 0 for tail pages.
+			 */
+			if (unlikely(PageCompound(page))) {
+				low_pfn += (1UL << compound_order(page)) - 1;
 				continue;
 			}
 		}
@@ -778,7 +805,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (__isolate_lru_page(page, isolate_mode) != 0)
 			continue;
 
-		VM_BUG_ON_PAGE(PageTransCompound(page), page);
+		VM_BUG_ON_PAGE(PageCompound(page), page);
 
 		/* Successfully isolated */
 		del_page_from_lru_list(page, lruvec, page_lru(page));
@@ -898,6 +925,16 @@ static bool suitable_migration_target(struct page *page)
 }
 
 /*
+ * Test whether the free scanner has reached the same or lower pageblock than
+ * the migration scanner, and compaction should thus terminate.
+ */
+static inline bool compact_scanners_met(struct compact_control *cc)
+{
+	return (cc->free_pfn >> pageblock_order)
+		<= (cc->migrate_pfn >> pageblock_order);
+}
+
+/*
  * Based on information in the current compact_control, find blocks
  * suitable for isolating free pages from and then isolate them.
  */
@@ -933,8 +970,7 @@ static void isolate_freepages(struct compact_control *cc)
 	 * pages on cc->migratepages. We stop searching if the migrate
 	 * and free page scanners meet or enough free pages are isolated.
 	 */
-	for (; block_start_pfn >= low_pfn &&
-			cc->nr_migratepages > cc->nr_freepages;
+	for (; block_start_pfn >= low_pfn;
 				block_end_pfn = block_start_pfn,
 				block_start_pfn -= pageblock_nr_pages,
 				isolate_start_pfn = block_start_pfn) {
@@ -966,6 +1002,8 @@ static void isolate_freepages(struct compact_control *cc)
 					block_end_pfn, freelist, false);
 
 		/*
+		 * If we isolated enough freepages, or aborted due to async
+		 * compaction being contended, terminate the loop.
 		 * Remember where the free scanner should restart next time,
 		 * which is where isolate_freepages_block() left off.
 		 * But if it scanned the whole pageblock, isolate_start_pfn
@@ -974,27 +1012,31 @@ static void isolate_freepages(struct compact_control *cc)
 		 * In that case we will however want to restart at the start
 		 * of the previous pageblock.
 		 */
-		cc->free_pfn = (isolate_start_pfn < block_end_pfn) ?
-				isolate_start_pfn :
-				block_start_pfn - pageblock_nr_pages;
-
-		/*
-		 * isolate_freepages_block() might have aborted due to async
-		 * compaction being contended
-		 */
-		if (cc->contended)
+		if ((cc->nr_freepages >= cc->nr_migratepages)
+							|| cc->contended) {
+			if (isolate_start_pfn >= block_end_pfn)
+				isolate_start_pfn =
+					block_start_pfn - pageblock_nr_pages;
 			break;
+		} else {
+			/*
+			 * isolate_freepages_block() should not terminate
+			 * prematurely unless contended, or isolated enough
+			 */
+			VM_BUG_ON(isolate_start_pfn < block_end_pfn);
+		}
 	}
 
 	/* split_free_page does not map the pages */
 	map_pages(freelist);
 
 	/*
-	 * If we crossed the migrate scanner, we want to keep it that way
-	 * so that compact_finished() may detect this
+	 * Record where the free scanner will restart next time. Either we
+	 * broke from the loop and set isolate_start_pfn based on the last
+	 * call to isolate_freepages_block(), or we met the migration scanner
+	 * and the loop terminated due to isolate_start_pfn < low_pfn
 	 */
-	if (block_start_pfn < low_pfn)
-		cc->free_pfn = cc->migrate_pfn;
+	cc->free_pfn = isolate_start_pfn;
 }
 
 /*
@@ -1062,6 +1104,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 					struct compact_control *cc)
 {
 	unsigned long low_pfn, end_pfn;
+	unsigned long isolate_start_pfn;
 	struct page *page;
 	const isolate_mode_t isolate_mode =
 		(sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) |
@@ -1110,6 +1153,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 			continue;
 
 		/* Perform the isolation */
+		isolate_start_pfn = low_pfn;
 		low_pfn = isolate_migratepages_block(cc, low_pfn, end_pfn,
 								isolate_mode);
 
@@ -1119,6 +1163,15 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 		}
 
 		/*
+		 * Record where we could have freed pages by migration and not
+		 * yet flushed them to buddy allocator.
+		 * - this is the lowest page that could have been isolated and
+		 * then freed by migration.
+		 */
+		if (cc->nr_migratepages && !cc->last_migrated_pfn)
+			cc->last_migrated_pfn = isolate_start_pfn;
+
+		/*
 		 * Either we isolated something and proceed with migration. Or
 		 * we failed and compact_zone should decide if we should
 		 * continue or not.
@@ -1127,16 +1180,21 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	}
 
 	acct_isolated(zone, cc);
-	/*
-	 * Record where migration scanner will be restarted. If we end up in
-	 * the same pageblock as the free scanner, make the scanners fully
-	 * meet so that compact_finished() terminates compaction.
-	 */
-	cc->migrate_pfn = (end_pfn <= cc->free_pfn) ? low_pfn : cc->free_pfn;
+	/* Record where migration scanner will be restarted. */
+	cc->migrate_pfn = low_pfn;
 
 	return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
 }
 
+/*
+ * order == -1 is expected when compacting via
+ * /proc/sys/vm/compact_memory
+ */
+static inline bool is_via_compact_memory(int order)
+{
+	return order == -1;
+}
+
 static int __compact_finished(struct zone *zone, struct compact_control *cc,
 			    const int migratetype)
 {
@@ -1144,14 +1202,12 @@ static int __compact_finished(struct zone *zone, struct compact_control *cc,
 	unsigned long watermark;
 
 	if (cc->contended || fatal_signal_pending(current))
-		return COMPACT_PARTIAL;
+		return COMPACT_CONTENDED;
 
 	/* Compaction run completes if the migrate and free scanner meet */
-	if (cc->free_pfn <= cc->migrate_pfn) {
+	if (compact_scanners_met(cc)) {
 		/* Let the next compaction start anew. */
-		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);
+		reset_cached_positions(zone);
 
 		/*
 		 * Mark that the PG_migrate_skip information should be cleared
@@ -1165,11 +1221,7 @@ static int __compact_finished(struct zone *zone, struct compact_control *cc,
 		return COMPACT_COMPLETE;
 	}
 
-	/*
-	 * order == -1 is expected when compacting via
-	 * /proc/sys/vm/compact_memory
-	 */
-	if (cc->order == -1)
+	if (is_via_compact_memory(cc->order))
 		return COMPACT_CONTINUE;
 
 	/* Compaction run is not finished if the watermark is not met */
@@ -1232,11 +1284,7 @@ static unsigned long __compaction_suitable(struct zone *zone, int order,
 	int fragindex;
 	unsigned long watermark;
 
-	/*
-	 * order == -1 is expected when compacting via
-	 * /proc/sys/vm/compact_memory
-	 */
-	if (order == -1)
+	if (is_via_compact_memory(order))
 		return COMPACT_CONTINUE;
 
 	watermark = low_wmark_pages(zone);
@@ -1295,7 +1343,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	unsigned long end_pfn = zone_end_pfn(zone);
 	const int migratetype = gfpflags_to_migratetype(cc->gfp_mask);
 	const bool sync = cc->mode != MIGRATE_ASYNC;
-	unsigned long last_migrated_pfn = 0;
 
 	ret = compaction_suitable(zone, cc->order, cc->alloc_flags,
 							cc->classzone_idx);
@@ -1333,6 +1380,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn;
 		zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
 	}
+	cc->last_migrated_pfn = 0;
 
 	trace_mm_compaction_begin(start_pfn, cc->migrate_pfn,
 				cc->free_pfn, end_pfn, sync);
@@ -1342,11 +1390,10 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	while ((ret = compact_finished(zone, cc, migratetype)) ==
 						COMPACT_CONTINUE) {
 		int err;
-		unsigned long isolate_start_pfn = cc->migrate_pfn;
 
 		switch (isolate_migratepages(zone, cc)) {
 		case ISOLATE_ABORT:
-			ret = COMPACT_PARTIAL;
+			ret = COMPACT_CONTENDED;
 			putback_movable_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
 			goto out;
@@ -1376,22 +1423,12 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 			 * migrate_pages() may return -ENOMEM when scanners meet
 			 * and we want compact_finished() to detect it
 			 */
-			if (err == -ENOMEM && cc->free_pfn > cc->migrate_pfn) {
-				ret = COMPACT_PARTIAL;
+			if (err == -ENOMEM && !compact_scanners_met(cc)) {
+				ret = COMPACT_CONTENDED;
 				goto out;
 			}
 		}
 
-		/*
-		 * Record where we could have freed pages by migration and not
-		 * yet flushed them to buddy allocator. We use the pfn that
-		 * isolate_migratepages() started from in this loop iteration
-		 * - this is the lowest page that could have been isolated and
-		 * then freed by migration.
-		 */
-		if (!last_migrated_pfn)
-			last_migrated_pfn = isolate_start_pfn;
-
 check_drain:
 		/*
 		 * Has the migration scanner moved away from the previous
@@ -1400,12 +1437,12 @@ check_drain:
 		 * compact_finished() can detect immediately if allocation
 		 * would succeed.
 		 */
-		if (cc->order > 0 && last_migrated_pfn) {
+		if (cc->order > 0 && cc->last_migrated_pfn) {
 			int cpu;
 			unsigned long current_block_start =
 				cc->migrate_pfn & ~((1UL << cc->order) - 1);
 
-			if (last_migrated_pfn < current_block_start) {
+			if (cc->last_migrated_pfn < current_block_start) {
 				cpu = get_cpu_light();
 				local_lock_irq(swapvec_lock);
 				lru_add_drain_cpu(cpu);
@@ -1413,7 +1450,7 @@ check_drain:
 				drain_local_pages(zone);
 				put_cpu_light();
 				/* No more flushing until we migrate again */
-				last_migrated_pfn = 0;
+				cc->last_migrated_pfn = 0;
 			}
 		}
 
@@ -1442,6 +1479,9 @@ out:
 	trace_mm_compaction_end(start_pfn, cc->migrate_pfn,
 				cc->free_pfn, end_pfn, sync, ret);
 
+	if (ret == COMPACT_CONTENDED)
+		ret = COMPACT_PARTIAL;
+
 	return ret;
 }
 
@@ -1613,10 +1653,11 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 		 * this makes sure we compact the whole zone regardless of
 		 * cached scanner positions.
 		 */
-		if (cc->order == -1)
+		if (is_via_compact_memory(cc->order))
 			__reset_isolation_suitable(zone);
 
-		if (cc->order == -1 || !compaction_deferred(zone, cc->order))
+		if (is_via_compact_memory(cc->order) ||
+				!compaction_deferred(zone, cc->order))
 			compact_zone(zone, cc);
 
 		if (cc->order > 0) {