---

yaml
---
r: 322087
b: refs/heads/master
c: c67fe37
h: refs/heads/master
i:
  322085: 81f5245
  322083: c66e455
  322079: b50968b
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: de74f1cc3b1e9730d9b58580cd11361d30cd182d
+refs/heads/master: c67fe3752abe6ab47639e2f9b836900c3dc3da84

trunk/include/linux/compaction.h

@@ -22,7 +22,7 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
-			bool sync);
+			bool sync, bool *contended);
 extern int compact_pgdat(pg_data_t *pgdat, int order);
 extern unsigned long compaction_suitable(struct zone *zone, int order);
 
@@ -64,7 +64,7 @@ static inline bool compaction_deferred(struct zone *zone, int order)
 #else
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			bool sync)
+			bool sync, bool *contended)
 {
 	return COMPACT_CONTINUE;
 }

trunk/mm/compaction.c

@@ -50,6 +50,47 @@ static inline bool migrate_async_suitable(int migratetype)
 	return is_migrate_cma(migratetype) || migratetype == MIGRATE_MOVABLE;
 }
 
+/*
+ * Compaction requires the taking of some coarse locks that are potentially
+ * very heavily contended. Check if the process needs to be scheduled or
+ * if the lock is contended. For async compaction, back out in the event
+ * if contention is severe. For sync compaction, schedule.
+ *
+ * Returns true if the lock is held.
+ * Returns false if the lock is released and compaction should abort
+ */
+static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
+				      bool locked, struct compact_control *cc)
+{
+	if (need_resched() || spin_is_contended(lock)) {
+		if (locked) {
+			spin_unlock_irqrestore(lock, *flags);
+			locked = false;
+		}
+
+		/* async aborts if taking too long or contended */
+		if (!cc->sync) {
+			if (cc->contended)
+				*cc->contended = true;
+			return false;
+		}
+
+		cond_resched();
+		if (fatal_signal_pending(current))
+			return false;
+	}
+
+	if (!locked)
+		spin_lock_irqsave(lock, *flags);
+	return true;
+}
+
+static inline bool compact_trylock_irqsave(spinlock_t *lock,
+			unsigned long *flags, struct compact_control *cc)
+{
+	return compact_checklock_irqsave(lock, flags, false, cc);
+}
+
 /*
  * Isolate free pages onto a private freelist. Caller must hold zone->lock.
  * If @strict is true, will abort returning 0 on any invalid PFNs or non-free
@@ -173,16 +214,22 @@ isolate_freepages_range(unsigned long start_pfn, unsigned long end_pfn)
 }
 
 /* Update the number of anon and file isolated pages in the zone */
-static void acct_isolated(struct zone *zone, struct compact_control *cc)
+static void acct_isolated(struct zone *zone, bool locked, struct compact_control *cc)
 {
 	struct page *page;
 	unsigned int count[2] = { 0, };
 
 	list_for_each_entry(page, &cc->migratepages, lru)
 		count[!!page_is_file_cache(page)]++;
 
-	__mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
-	__mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
+	/* If locked we can use the interrupt unsafe versions */
+	if (locked) {
+		__mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
+		__mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
+	} else {
+		mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
+		mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
+	}
 }
 
 /* Similar to reclaim, but different enough that they don't share logic */
@@ -228,6 +275,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	struct list_head *migratelist = &cc->migratepages;
 	isolate_mode_t mode = 0;
 	struct lruvec *lruvec;
+	unsigned long flags;
+	bool locked;
 
 	/*
 	 * Ensure that there are not too many pages isolated from the LRU
@@ -247,25 +296,22 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 
 	/* Time to isolate some pages for migration */
 	cond_resched();
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irqsave(&zone->lru_lock, flags);
+	locked = true;
 	for (; low_pfn < end_pfn; low_pfn++) {
 		struct page *page;
-		bool locked = true;
 
 		/* give a chance to irqs before checking need_resched() */
 		if (!((low_pfn+1) % SWAP_CLUSTER_MAX)) {
-			spin_unlock_irq(&zone->lru_lock);
+			spin_unlock_irqrestore(&zone->lru_lock, flags);
 			locked = false;
 		}
-		if (need_resched() || spin_is_contended(&zone->lru_lock)) {
-			if (locked)
-				spin_unlock_irq(&zone->lru_lock);
-			cond_resched();
-			spin_lock_irq(&zone->lru_lock);
-			if (fatal_signal_pending(current))
-				break;
-		} else if (!locked)
-			spin_lock_irq(&zone->lru_lock);
+
+		/* Check if it is ok to still hold the lock */
+		locked = compact_checklock_irqsave(&zone->lru_lock, &flags,
+								locked, cc);
+		if (!locked)
+			break;
 
 		/*
 		 * migrate_pfn does not necessarily start aligned to a
@@ -349,9 +395,10 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 		}
 	}
 
-	acct_isolated(zone, cc);
+	acct_isolated(zone, locked, cc);
 
-	spin_unlock_irq(&zone->lru_lock);
+	if (locked)
+		spin_unlock_irqrestore(&zone->lru_lock, flags);
 
 	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
 
@@ -461,7 +508,16 @@ static void isolate_freepages(struct zone *zone,
 		 * are disabled
 		 */
 		isolated = 0;
-		spin_lock_irqsave(&zone->lock, flags);
+
+		/*
+		 * The zone lock must be held to isolate freepages. This
+		 * unfortunately this is a very coarse lock and can be
+		 * heavily contended if there are parallel allocations
+		 * or parallel compactions. For async compaction do not
+		 * spin on the lock
+		 */
+		if (!compact_trylock_irqsave(&zone->lock, &flags, cc))
+			break;
 		if (suitable_migration_target(page)) {
 			end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn);
 			isolated = isolate_freepages_block(pfn, end_pfn,
@@ -773,7 +829,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 
 static unsigned long compact_zone_order(struct zone *zone,
 				 int order, gfp_t gfp_mask,
-				 bool sync)
+				 bool sync, bool *contended)
 {
 	struct compact_control cc = {
 		.nr_freepages = 0,
@@ -782,6 +838,7 @@ static unsigned long compact_zone_order(struct zone *zone,
 		.migratetype = allocflags_to_migratetype(gfp_mask),
 		.zone = zone,
 		.sync = sync,
+		.contended = contended,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -803,7 +860,7 @@ int sysctl_extfrag_threshold = 500;
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			bool sync)
+			bool sync, bool *contended)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
@@ -827,7 +884,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 								nodemask) {
 		int status;
 
-		status = compact_zone_order(zone, order, gfp_mask, sync);
+		status = compact_zone_order(zone, order, gfp_mask, sync,
+						contended);
 		rc = max(status, rc);
 
 		/* If a normal allocation would succeed, stop compacting */

trunk/mm/internal.h

@@ -130,6 +130,7 @@ struct compact_control {
 	int order;			/* order a direct compactor needs */
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
+	bool *contended;		/* True if a lock was contended */
 };
 
 unsigned long

trunk/mm/page_alloc.c

@@ -2102,7 +2102,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
 	int migratetype, bool sync_migration,
-	bool *deferred_compaction,
+	bool *contended_compaction, bool *deferred_compaction,
 	unsigned long *did_some_progress)
 {
 	struct page *page;
@@ -2117,7 +2117,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 
 	current->flags |= PF_MEMALLOC;
 	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
-						nodemask, sync_migration);
+						nodemask, sync_migration,
+						contended_compaction);
 	current->flags &= ~PF_MEMALLOC;
 	if (*did_some_progress != COMPACT_SKIPPED) {
 
@@ -2163,7 +2164,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
 	int migratetype, bool sync_migration,
-	bool *deferred_compaction,
+	bool *contended_compaction, bool *deferred_compaction,
 	unsigned long *did_some_progress)
 {
 	return NULL;
@@ -2336,6 +2337,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	unsigned long did_some_progress;
 	bool sync_migration = false;
 	bool deferred_compaction = false;
+	bool contended_compaction = false;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -2425,6 +2427,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 					nodemask,
 					alloc_flags, preferred_zone,
 					migratetype, sync_migration,
+					&contended_compaction,
 					&deferred_compaction,
 					&did_some_progress);
 	if (page)
@@ -2434,10 +2437,11 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	/*
 	 * If compaction is deferred for high-order allocations, it is because
 	 * sync compaction recently failed. In this is the case and the caller
-	 * has requested the system not be heavily disrupted, fail the
-	 * allocation now instead of entering direct reclaim
+	 * requested a movable allocation that does not heavily disrupt the
+	 * system then fail the allocation instead of entering direct reclaim.
 	 */
-	if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD))
+	if ((deferred_compaction || contended_compaction) &&
+						(gfp_mask & __GFP_NO_KSWAPD))
 		goto nopage;
 
 	/* Try direct reclaim and then allocating */
@@ -2508,6 +2512,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 					nodemask,
 					alloc_flags, preferred_zone,
 					migratetype, sync_migration,
+					&contended_compaction,
 					&deferred_compaction,
 					&did_some_progress);
 		if (page)