mm, vmscan: move lru_lock to the node

Node-based reclaim requires node-based LRUs and locking. This is a preparation patch that just moves the lru_lock to the node so later patches are easier to review. It is a mechanical change but note this patch makes contention worse because the LRU lock is hotter and direct reclaim and kswapd can contend on the same lock even when reclaiming from different zones. Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Mel Gorman <[email protected]> Reviewed-by: Minchan Kim <[email protected]> Acked-by: Johannes Weiner <[email protected]> Acked-by: Vlastimil Babka <[email protected]> Cc: Hillf Danton <[email protected]> Cc: Joonsoo Kim <[email protected]> Cc: Michal Hocko <[email protected]> Cc: Rik van Riel <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
akeromi · Jul 28, 2016 · a52633d · a52633d
1 parent 75ef718
commit a52633d
Show file tree

Hide file tree

Showing 14 changed files with 75 additions and 69 deletions.
diff --git a/Documentation/cgroup-v1/memcg_test.txt b/Documentation/cgroup-v1/memcg_test.txt
@@ -107,9 +107,9 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 
 8. LRU
         Each memcg has its own private LRU. Now, its handling is under global
-	VM's control (means that it's handled under global zone->lru_lock).
+	VM's control (means that it's handled under global zone_lru_lock).
 	Almost all routines around memcg's LRU is called by global LRU's
-	list management functions under zone->lru_lock().
+	list management functions under zone_lru_lock().
 
 	A special function is mem_cgroup_isolate_pages(). This scans
 	memcg's private LRU and call __isolate_lru_page() to extract a page

diff --git a/Documentation/cgroup-v1/memory.txt b/Documentation/cgroup-v1/memory.txt
@@ -267,11 +267,11 @@ When oom event notifier is registered, event will be delivered.
    Other lock order is following:
    PG_locked.
    mm->page_table_lock
-       zone->lru_lock
+       zone_lru_lock
 	  lock_page_cgroup.
   In many cases, just lock_page_cgroup() is called.
   per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by
-  zone->lru_lock, it has no lock of its own.
+  zone_lru_lock, it has no lock of its own.
 
 2.7 Kernel Memory Extension (CONFIG_MEMCG_KMEM)
 

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
@@ -118,7 +118,7 @@ struct page {
 	 */
 	union {
 		struct list_head lru;	/* Pageout list, eg. active_list
-					 * protected by zone->lru_lock !
+					 * protected by zone_lru_lock !
 					 * Can be used as a generic list
 					 * by the page owner.
 					 */

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
@@ -93,7 +93,7 @@ struct free_area {
 struct pglist_data;
 
 /*
- * zone->lock and zone->lru_lock are two of the hottest locks in the kernel.
+ * zone->lock and the zone lru_lock are two of the hottest locks in the kernel.
  * So add a wild amount of padding here to ensure that they fall into separate
  * cachelines.  There are very few zone structures in the machine, so space
  * consumption is not a concern here.
@@ -496,7 +496,6 @@ struct zone {
 	/* Write-intensive fields used by page reclaim */
 
 	/* Fields commonly accessed by the page reclaim scanner */
-	spinlock_t		lru_lock;
 	struct lruvec		lruvec;
 
 	/*
@@ -690,6 +689,9 @@ typedef struct pglist_data {
 	/* Number of pages migrated during the rate limiting time interval */
 	unsigned long numabalancing_migrate_nr_pages;
 #endif
+	/* Write-intensive fields used by page reclaim */
+	ZONE_PADDING(_pad1_)
+	spinlock_t		lru_lock;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 	/*
@@ -721,6 +723,10 @@ typedef struct pglist_data {
 
 #define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
 #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid))
+static inline spinlock_t *zone_lru_lock(struct zone *zone)
+{
+	return &zone->zone_pgdat->lru_lock;
+}
 
 static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
 {

diff --git a/mm/compaction.c b/mm/compaction.c
@@ -752,7 +752,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		 * if contended.
 		 */
 		if (!(low_pfn % SWAP_CLUSTER_MAX)
-		    && compact_unlock_should_abort(&zone->lru_lock, flags,
+		    && compact_unlock_should_abort(zone_lru_lock(zone), flags,
 								&locked, cc))
 			break;
 
@@ -813,7 +813,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			if (unlikely(__PageMovable(page)) &&
 					!PageIsolated(page)) {
 				if (locked) {
-					spin_unlock_irqrestore(&zone->lru_lock,
+					spin_unlock_irqrestore(zone_lru_lock(zone),
 									flags);
 					locked = false;
 				}
@@ -836,7 +836,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 		/* If we already hold the lock, we can skip some rechecking */
 		if (!locked) {
-			locked = compact_trylock_irqsave(&zone->lru_lock,
+			locked = compact_trylock_irqsave(zone_lru_lock(zone),
 								&flags, cc);
 			if (!locked)
 				break;
@@ -899,7 +899,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		 */
 		if (nr_isolated) {
 			if (locked) {
-				spin_unlock_irqrestore(&zone->lru_lock,	flags);
+				spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 				locked = false;
 			}
 			acct_isolated(zone, cc);
@@ -927,7 +927,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		low_pfn = end_pfn;
 
 	if (locked)
-		spin_unlock_irqrestore(&zone->lru_lock, flags);
+		spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 
 	/*
 	 * Update the pageblock-skip information and cached scanner pfn,

diff --git a/mm/filemap.c b/mm/filemap.c
@@ -95,8 +95,8 @@
  *    ->swap_lock		(try_to_unmap_one)
  *    ->private_lock		(try_to_unmap_one)
  *    ->tree_lock		(try_to_unmap_one)
- *    ->zone.lru_lock		(follow_page->mark_page_accessed)
- *    ->zone.lru_lock		(check_pte_range->isolate_lru_page)
+ *    ->zone_lru_lock(zone)	(follow_page->mark_page_accessed)
+ *    ->zone_lru_lock(zone)	(check_pte_range->isolate_lru_page)
  *    ->private_lock		(page_remove_rmap->set_page_dirty)
  *    ->tree_lock		(page_remove_rmap->set_page_dirty)
  *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
@@ -1848,7 +1848,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 		spin_unlock(&head->mapping->tree_lock);
 	}
 
-	spin_unlock_irqrestore(&page_zone(head)->lru_lock, flags);
+	spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
 
 	unfreeze_page(head);
 
@@ -2034,7 +2034,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		lru_add_drain();
 
 	/* prevent PageLRU to go away from under us, and freeze lru stats */
-	spin_lock_irqsave(&page_zone(head)->lru_lock, flags);
+	spin_lock_irqsave(zone_lru_lock(page_zone(head)), flags);
 
 	if (mapping) {
 		void **pslot;
@@ -2077,7 +2077,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		spin_unlock(&pgdata->split_queue_lock);
 fail:		if (mapping)
 			spin_unlock(&mapping->tree_lock);
-		spin_unlock_irqrestore(&page_zone(head)->lru_lock, flags);
+		spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
 		unfreeze_page(head);
 		ret = -EBUSY;
 	}

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
@@ -2065,7 +2065,7 @@ static void lock_page_lru(struct page *page, int *isolated)
 {
 	struct zone *zone = page_zone(page);
 
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 	if (PageLRU(page)) {
 		struct lruvec *lruvec;
 
@@ -2089,7 +2089,7 @@ static void unlock_page_lru(struct page *page, int isolated)
 		SetPageLRU(page);
 		add_page_to_lru_list(page, lruvec, page_lru(page));
 	}
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 }
 
 static void commit_charge(struct page *page, struct mem_cgroup *memcg,
@@ -2389,7 +2389,7 @@ void memcg_kmem_uncharge(struct page *page, int order)
 
 /*
  * Because tail pages are not marked as "used", set it. We're under
- * zone->lru_lock and migration entries setup in all page mappings.
+ * zone_lru_lock and migration entries setup in all page mappings.
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {

diff --git a/mm/mlock.c b/mm/mlock.c
@@ -188,7 +188,7 @@ unsigned int munlock_vma_page(struct page *page)
 	 * might otherwise copy PageMlocked to part of the tail pages before
 	 * we clear it in the head page. It also stabilizes hpage_nr_pages().
 	 */
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 
 	nr_pages = hpage_nr_pages(page);
 	if (!TestClearPageMlocked(page))
@@ -197,14 +197,14 @@ unsigned int munlock_vma_page(struct page *page)
 	__mod_zone_page_state(zone, NR_MLOCK, -nr_pages);
 
 	if (__munlock_isolate_lru_page(page, true)) {
-		spin_unlock_irq(&zone->lru_lock);
+		spin_unlock_irq(zone_lru_lock(zone));
 		__munlock_isolated_page(page);
 		goto out;
 	}
 	__munlock_isolation_failed(page);
 
 unlock_out:
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 
 out:
 	return nr_pages - 1;
@@ -289,7 +289,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 	pagevec_init(&pvec_putback, 0);
 
 	/* Phase 1: page isolation */
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 	for (i = 0; i < nr; i++) {
 		struct page *page = pvec->pages[i];
 
@@ -315,7 +315,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 	}
 	delta_munlocked = -nr + pagevec_count(&pvec_putback);
 	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 
 	/* Now we can release pins of pages that we are not munlocking */
 	pagevec_release(&pvec_putback);

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
@@ -5904,6 +5904,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 	init_waitqueue_head(&pgdat->kcompactd_wait);
 #endif
 	pgdat_page_ext_init(pgdat);
+	spin_lock_init(&pgdat->lru_lock);
 
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
@@ -5958,10 +5959,9 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 		zone->min_slab_pages = (freesize * sysctl_min_slab_ratio) / 100;
 #endif
 		zone->name = zone_names[j];
+		zone->zone_pgdat = pgdat;
 		spin_lock_init(&zone->lock);
-		spin_lock_init(&zone->lru_lock);
 		zone_seqlock_init(zone);
-		zone->zone_pgdat = pgdat;
 		zone_pcp_init(zone);
 
 		/* For bootup, initialized properly in watermark setup */

diff --git a/mm/page_idle.c b/mm/page_idle.c
@@ -41,12 +41,12 @@ static struct page *page_idle_get_page(unsigned long pfn)
 		return NULL;
 
 	zone = page_zone(page);
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 	if (unlikely(!PageLRU(page))) {
 		put_page(page);
 		page = NULL;
 	}
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 	return page;
 }
 

diff --git a/mm/rmap.c b/mm/rmap.c
@@ -27,7 +27,7 @@
  *         mapping->i_mmap_rwsem
  *           anon_vma->rwsem
  *             mm->page_table_lock or pte_lock
- *               zone->lru_lock (in mark_page_accessed, isolate_lru_page)
+ *               zone_lru_lock (in mark_page_accessed, isolate_lru_page)
  *               swap_lock (in swap_duplicate, swap_info_get)
  *                 mmlist_lock (in mmput, drain_mmlist and others)
  *                 mapping->private_lock (in __set_page_dirty_buffers)

diff --git a/mm/swap.c b/mm/swap.c
@@ -62,12 +62,12 @@ static void __page_cache_release(struct page *page)
 		struct lruvec *lruvec;
 		unsigned long flags;
 
-		spin_lock_irqsave(&zone->lru_lock, flags);
+		spin_lock_irqsave(zone_lru_lock(zone), flags);
 		lruvec = mem_cgroup_page_lruvec(page, zone);
 		VM_BUG_ON_PAGE(!PageLRU(page), page);
 		__ClearPageLRU(page);
 		del_page_from_lru_list(page, lruvec, page_off_lru(page));
-		spin_unlock_irqrestore(&zone->lru_lock, flags);
+		spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 	}
 	mem_cgroup_uncharge(page);
 }
@@ -189,16 +189,16 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
 
 		if (pagezone != zone) {
 			if (zone)
-				spin_unlock_irqrestore(&zone->lru_lock, flags);
+				spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 			zone = pagezone;
-			spin_lock_irqsave(&zone->lru_lock, flags);
+			spin_lock_irqsave(zone_lru_lock(zone), flags);
 		}
 
 		lruvec = mem_cgroup_page_lruvec(page, zone);
 		(*move_fn)(page, lruvec, arg);
 	}
 	if (zone)
-		spin_unlock_irqrestore(&zone->lru_lock, flags);
+		spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 	release_pages(pvec->pages, pvec->nr, pvec->cold);
 	pagevec_reinit(pvec);
 }
@@ -318,9 +318,9 @@ void activate_page(struct page *page)
 	struct zone *zone = page_zone(page);
 
 	page = compound_head(page);
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 	__activate_page(page, mem_cgroup_page_lruvec(page, zone), NULL);
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 }
 #endif
 
@@ -448,13 +448,13 @@ void add_page_to_unevictable_list(struct page *page)
 	struct zone *zone = page_zone(page);
 	struct lruvec *lruvec;
 
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 	lruvec = mem_cgroup_page_lruvec(page, zone);
 	ClearPageActive(page);
 	SetPageUnevictable(page);
 	SetPageLRU(page);
 	add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE);
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 }
 
 /**
@@ -744,7 +744,7 @@ void release_pages(struct page **pages, int nr, bool cold)
 		 * same zone. The lock is held only if zone != NULL.
 		 */
 		if (zone && ++lock_batch == SWAP_CLUSTER_MAX) {
-			spin_unlock_irqrestore(&zone->lru_lock, flags);
+			spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 			zone = NULL;
 		}
 
@@ -759,7 +759,7 @@ void release_pages(struct page **pages, int nr, bool cold)
 
 		if (PageCompound(page)) {
 			if (zone) {
-				spin_unlock_irqrestore(&zone->lru_lock, flags);
+				spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 				zone = NULL;
 			}
 			__put_compound_page(page);
@@ -771,11 +771,11 @@ void release_pages(struct page **pages, int nr, bool cold)
 
 			if (pagezone != zone) {
 				if (zone)
-					spin_unlock_irqrestore(&zone->lru_lock,
+					spin_unlock_irqrestore(zone_lru_lock(zone),
 									flags);
 				lock_batch = 0;
 				zone = pagezone;
-				spin_lock_irqsave(&zone->lru_lock, flags);
+				spin_lock_irqsave(zone_lru_lock(zone), flags);
 			}
 
 			lruvec = mem_cgroup_page_lruvec(page, zone);
@@ -790,7 +790,7 @@ void release_pages(struct page **pages, int nr, bool cold)
 		list_add(&page->lru, &pages_to_free);
 	}
 	if (zone)
-		spin_unlock_irqrestore(&zone->lru_lock, flags);
+		spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 
 	mem_cgroup_uncharge_list(&pages_to_free);
 	free_hot_cold_page_list(&pages_to_free, cold);
@@ -826,7 +826,7 @@ void lru_add_page_tail(struct page *page, struct page *page_tail,
 	VM_BUG_ON_PAGE(PageCompound(page_tail), page);
 	VM_BUG_ON_PAGE(PageLRU(page_tail), page);
 	VM_BUG_ON(NR_CPUS != 1 &&
-		  !spin_is_locked(&lruvec_zone(lruvec)->lru_lock));
+		  !spin_is_locked(zone_lru_lock(lruvec_zone(lruvec))));
 
 	if (!list)
 		SetPageLRU(page_tail);