Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: Mel Gorman <mgorman@techsingularity.net>
To: Andrew Morton <akpm@linux-foundation.org>, Linux-MM <linux-mm@kvack.org>
Cc: Rik van Riel <riel@surriel.com>, Vlastimil Babka <vbabka@suse.cz>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Minchan Kim <minchan@kernel.org>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	LKML <linux-kernel@vger.kernel.org>,
	Mel Gorman <mgorman@techsingularity.net>
Subject: [PATCH 02/34] mm, vmscan: move lru_lock to the node
Date: Fri,  8 Jul 2016 10:34:38 +0100
Message-ID: <1467970510-21195-3-git-send-email-mgorman@techsingularity.net> (raw)
In-Reply-To: <1467970510-21195-1-git-send-email-mgorman@techsingularity.net>

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.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Minchan Kim <minchan@kernel.org>
---
 Documentation/cgroup-v1/memcg_test.txt |  4 +--
 Documentation/cgroup-v1/memory.txt     |  4 +--
 include/linux/mm_types.h               |  2 +-
 include/linux/mmzone.h                 | 10 +++++--
 mm/compaction.c                        | 10 +++----
 mm/filemap.c                           |  4 +--
 mm/huge_memory.c                       |  6 ++---
 mm/memcontrol.c                        |  6 ++---
 mm/mlock.c                             | 10 +++----
 mm/page_alloc.c                        |  4 +--
 mm/page_idle.c                         |  4 +--
 mm/rmap.c                              |  2 +-
 mm/swap.c                              | 30 ++++++++++-----------
 mm/vmscan.c                            | 48 +++++++++++++++++-----------------
 14 files changed, 75 insertions(+), 69 deletions(-)

diff --git a/Documentation/cgroup-v1/memcg_test.txt b/Documentation/cgroup-v1/memcg_test.txt
index 8870b0212150..78a8c2963b38 100644
--- 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
index b14abf217239..946e69103cdd 100644
--- 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
index e093e1d3285b..ca2ed9a6c8d8 100644
--- 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
index 078ecb81e209..cfa870107abe 100644
--- 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
index 0bd53fb05162..7607efb7bee2 100644
--- 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
index e90c1543ec2d..7ec50bd6f88c 100644
--- 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
index 848c16caf8f8..2f997328ae64 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1860,7 +1860,7 @@ 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);
 
@@ -2046,7 +2046,7 @@ 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;
@@ -2089,7 +2089,7 @@ 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
index 40dfca3ef4bb..9b70f9ca8ddf 100644
--- 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
index ef8dc9f395c4..997f63082ff5 100644
--- 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
index 34e46c02a406..48b5414009ac 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5947,6 +5947,7 @@ 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;
@@ -6001,10 +6002,9 @@ 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
index 4ea9c4ef5146..ae11aa914e55 100644
--- 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
index 256e585c67ef..573253efb645 100644
--- 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
index 616df4ddd870..bf37e5cfae81 100644
--- 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);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 21d417ccff69..e7ffcd259cc4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1349,7 +1349,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
 }
 
 /*
- * zone->lru_lock is heavily contended.  Some of the functions that
+ * zone_lru_lock is heavily contended.  Some of the functions that
  * shrink the lists perform better by taking out a batch of pages
  * and working on them outside the LRU lock.
  *
@@ -1444,7 +1444,7 @@ int isolate_lru_page(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);
 		if (PageLRU(page)) {
 			int lru = page_lru(page);
@@ -1453,7 +1453,7 @@ int isolate_lru_page(struct page *page)
 			del_page_from_lru_list(page, lruvec, lru);
 			ret = 0;
 		}
-		spin_unlock_irq(&zone->lru_lock);
+		spin_unlock_irq(zone_lru_lock(zone));
 	}
 	return ret;
 }
@@ -1512,9 +1512,9 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 		list_del(&page->lru);
 		if (unlikely(!page_evictable(page))) {
-			spin_unlock_irq(&zone->lru_lock);
+			spin_unlock_irq(zone_lru_lock(zone));
 			putback_lru_page(page);
-			spin_lock_irq(&zone->lru_lock);
+			spin_lock_irq(zone_lru_lock(zone));
 			continue;
 		}
 
@@ -1535,10 +1535,10 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
 			del_page_from_lru_list(page, lruvec, lru);
 
 			if (unlikely(PageCompound(page))) {
-				spin_unlock_irq(&zone->lru_lock);
+				spin_unlock_irq(zone_lru_lock(zone));
 				mem_cgroup_uncharge(page);
 				(*get_compound_page_dtor(page))(page);
-				spin_lock_irq(&zone->lru_lock);
+				spin_lock_irq(zone_lru_lock(zone));
 			} else
 				list_add(&page->lru, &pages_to_free);
 		}
@@ -1600,7 +1600,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	if (!sc->may_writepage)
 		isolate_mode |= ISOLATE_CLEAN;
 
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 
 	nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list,
 				     &nr_scanned, sc, isolate_mode, lru);
@@ -1616,7 +1616,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		else
 			__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scanned);
 	}
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 
 	if (nr_taken == 0)
 		return 0;
@@ -1626,7 +1626,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 				&nr_writeback, &nr_immediate,
 				false);
 
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 
 	if (global_reclaim(sc)) {
 		if (current_is_kswapd())
@@ -1641,7 +1641,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 	__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
 
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 
 	mem_cgroup_uncharge_list(&page_list);
 	free_hot_cold_page_list(&page_list, true);
@@ -1715,9 +1715,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
  * processes, from rmap.
  *
  * If the pages are mostly unmapped, the processing is fast and it is
- * appropriate to hold zone->lru_lock across the whole operation.  But if
+ * appropriate to hold zone_lru_lock across the whole operation.  But if
  * the pages are mapped, the processing is slow (page_referenced()) so we
- * should drop zone->lru_lock around each page.  It's impossible to balance
+ * should drop zone_lru_lock around each page.  It's impossible to balance
  * this, so instead we remove the pages from the LRU while processing them.
  * It is safe to rely on PG_active against the non-LRU pages in here because
  * nobody will play with that bit on a non-LRU page.
@@ -1754,10 +1754,10 @@ static void move_active_pages_to_lru(struct lruvec *lruvec,
 			del_page_from_lru_list(page, lruvec, lru);
 
 			if (unlikely(PageCompound(page))) {
-				spin_unlock_irq(&zone->lru_lock);
+				spin_unlock_irq(zone_lru_lock(zone));
 				mem_cgroup_uncharge(page);
 				(*get_compound_page_dtor(page))(page);
-				spin_lock_irq(&zone->lru_lock);
+				spin_lock_irq(zone_lru_lock(zone));
 			} else
 				list_add(&page->lru, pages_to_free);
 		}
@@ -1792,7 +1792,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	if (!sc->may_writepage)
 		isolate_mode |= ISOLATE_CLEAN;
 
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 
 	nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
 				     &nr_scanned, sc, isolate_mode, lru);
@@ -1805,7 +1805,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 		__mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned);
 	__count_zone_vm_events(PGREFILL, zone, nr_scanned);
 
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 
 	while (!list_empty(&l_hold)) {
 		cond_resched();
@@ -1850,7 +1850,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	/*
 	 * Move pages back to the lru list.
 	 */
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 	/*
 	 * Count referenced pages from currently used mappings as rotated,
 	 * even though only some of them are actually re-activated.  This
@@ -1862,7 +1862,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru);
 	move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE);
 	__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 
 	mem_cgroup_uncharge_list(&l_hold);
 	free_hot_cold_page_list(&l_hold, true);
@@ -2077,7 +2077,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	file  = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) +
 		lruvec_lru_size(lruvec, LRU_INACTIVE_FILE);
 
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 	if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
 		reclaim_stat->recent_scanned[0] /= 2;
 		reclaim_stat->recent_rotated[0] /= 2;
@@ -2098,7 +2098,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 
 	fp = file_prio * (reclaim_stat->recent_scanned[1] + 1);
 	fp /= reclaim_stat->recent_rotated[1] + 1;
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 
 	fraction[0] = ap;
 	fraction[1] = fp;
@@ -3791,9 +3791,9 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages)
 		pagezone = page_zone(page);
 		if (pagezone != zone) {
 			if (zone)
-				spin_unlock_irq(&zone->lru_lock);
+				spin_unlock_irq(zone_lru_lock(zone));
 			zone = pagezone;
-			spin_lock_irq(&zone->lru_lock);
+			spin_lock_irq(zone_lru_lock(zone));
 		}
 		lruvec = mem_cgroup_page_lruvec(page, zone);
 
@@ -3814,7 +3814,7 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages)
 	if (zone) {
 		__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
 		__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
-		spin_unlock_irq(&zone->lru_lock);
+		spin_unlock_irq(zone_lru_lock(zone));
 	}
 }
 #endif /* CONFIG_SHMEM */
-- 
2.6.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply index

Thread overview: 109+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-07-08  9:34 [PATCH 00/34] Move LRU page reclaim from zones to nodes v9 Mel Gorman
2016-07-08  9:34 ` [PATCH 01/34] mm, vmstat: add infrastructure for per-node vmstats Mel Gorman
2016-08-03 19:13   ` Reza Arbab
2016-07-08  9:34 ` Mel Gorman [this message]
2016-07-12 11:06   ` [PATCH 02/34] mm, vmscan: move lru_lock to the node Balbir Singh
2016-07-12 11:18     ` Mel Gorman
2016-07-13  5:50       ` Balbir Singh
2016-07-13  8:39         ` Vlastimil Babka
2016-07-08  9:34 ` [PATCH 03/34] mm, vmscan: move LRU lists to node Mel Gorman
2016-08-04 20:59   ` James Hogan
2016-08-05  8:41     ` Mel Gorman
2016-08-05 10:52       ` James Hogan
2016-08-05 11:55         ` Mel Gorman
2016-08-05 12:02           ` James Hogan
2016-07-08  9:34 ` [PATCH 04/34] mm, mmzone: clarify the usage of zone padding Mel Gorman
2016-07-12 13:49   ` Johannes Weiner
2016-07-08  9:34 ` [PATCH 05/34] mm, vmscan: begin reclaiming pages on a per-node basis Mel Gorman
2016-07-12 13:54   ` Johannes Weiner
2016-07-14  9:19   ` Vlastimil Babka
2016-07-08  9:34 ` [PATCH 06/34] mm, vmscan: have kswapd only scan based on the highest requested zone Mel Gorman
2016-07-12 14:05   ` Johannes Weiner
2016-07-13  8:37     ` Mel Gorman
2016-07-08  9:34 ` [PATCH 07/34] mm, vmscan: make kswapd reclaim in terms of nodes Mel Gorman
2016-08-29  9:38   ` Srikar Dronamraju
2016-08-30 12:07     ` Mel Gorman
2016-08-30 14:25       ` Srikar Dronamraju
2016-08-30 15:00         ` Mel Gorman
2016-08-31  6:09           ` Srikar Dronamraju
2016-08-31  8:49             ` Mel Gorman
2016-08-31 11:09               ` Michal Hocko
2016-08-31 12:46                 ` Mel Gorman
2016-08-31 17:33               ` Srikar Dronamraju
2016-07-08  9:34 ` [PATCH 08/34] mm, vmscan: remove balance gap Mel Gorman
2016-07-12 14:06   ` Johannes Weiner
2016-07-08  9:34 ` [PATCH 09/34] mm, vmscan: simplify the logic deciding whether kswapd sleeps Mel Gorman
2016-07-08  9:34 ` [PATCH 10/34] mm, vmscan: by default have direct reclaim only shrink once per node Mel Gorman
2016-07-08  9:34 ` [PATCH 11/34] mm, vmscan: remove duplicate logic clearing node congestion and dirty state Mel Gorman
2016-07-12 14:22   ` Johannes Weiner
2016-07-13  8:40     ` Mel Gorman
2016-07-14  9:45   ` Vlastimil Babka
2016-07-08  9:34 ` [PATCH 12/34] mm: vmscan: do not reclaim from kswapd if there is any eligible zone Mel Gorman
2016-07-12 14:29   ` Johannes Weiner
2016-07-13  8:47     ` Mel Gorman
2016-07-13 12:28       ` Johannes Weiner
2016-07-08  9:34 ` [PATCH 13/34] mm, vmscan: make shrink_node decisions more node-centric Mel Gorman
2016-07-12 14:32   ` Johannes Weiner
2016-07-13  8:48     ` Mel Gorman
2016-07-08  9:34 ` [PATCH 14/34] mm, memcg: move memcg limit enforcement from zones to nodes Mel Gorman
2016-07-12 14:38   ` Johannes Weiner
2016-07-08  9:34 ` [PATCH 15/34] mm, workingset: make working set detection node-aware Mel Gorman
2016-07-08  9:34 ` [PATCH 16/34] mm, page_alloc: consider dirtyable memory in terms of nodes Mel Gorman
2016-07-08  9:34 ` [PATCH 17/34] mm: move page mapped accounting to the node Mel Gorman
2016-07-12 14:42   ` Johannes Weiner
2016-07-08  9:34 ` [PATCH 18/34] mm: rename NR_ANON_PAGES to NR_ANON_MAPPED Mel Gorman
2016-07-12 14:58   ` Johannes Weiner
2016-07-13  8:55     ` Mel Gorman
2016-07-13 13:04       ` Johannes Weiner
2016-07-13 13:37         ` Mel Gorman
2016-07-13 21:13           ` Andrew Morton
2016-07-15 10:46             ` Mel Gorman
2016-07-15 22:35               ` Andrew Morton
2016-07-18 13:34                 ` Johannes Weiner
2016-07-14  1:27           ` Minchan Kim
2016-07-08  9:34 ` [PATCH 19/34] mm: move most file-based accounting to the node Mel Gorman
2016-07-12 15:11   ` Johannes Weiner
2016-07-08  9:34 ` [PATCH 20/34] mm: move vmscan writes and file write " Mel Gorman
2016-07-12 15:15   ` Johannes Weiner
2016-07-08  9:34 ` [PATCH 21/34] mm, vmscan: only wakeup kswapd once per node for the requested classzone Mel Gorman
2016-07-12 17:18   ` Johannes Weiner
2016-07-08  9:34 ` [PATCH 22/34] mm, page_alloc: wake kswapd based on the highest eligible zone Mel Gorman
2016-07-12 17:24   ` Johannes Weiner
2016-07-14 10:05   ` Vlastimil Babka
2016-07-08  9:34 ` [PATCH 23/34] mm: convert zone_reclaim to node_reclaim Mel Gorman
2016-07-12 17:28   ` Johannes Weiner
2016-07-08  9:35 ` [PATCH 24/34] mm, vmscan: avoid passing in classzone_idx unnecessarily to shrink_node Mel Gorman
2016-07-12 17:31   ` Johannes Weiner
2016-07-14 10:09   ` Vlastimil Babka
2016-07-08  9:35 ` [PATCH 25/34] mm, vmscan: avoid passing in classzone_idx unnecessarily to compaction_ready Mel Gorman
2016-07-12 18:01   ` Johannes Weiner
2016-07-14 12:12   ` Vlastimil Babka
2016-07-08  9:35 ` [PATCH 26/34] mm, vmscan: avoid passing in remaining unnecessarily to prepare_kswapd_sleep Mel Gorman
2016-07-12 18:06   ` Johannes Weiner
2016-07-14 12:48   ` Vlastimil Babka
2016-07-08  9:35 ` [PATCH 27/34] mm, vmscan: Have kswapd reclaim from all zones if reclaiming and buffer_heads_over_limit Mel Gorman
2016-07-12 18:10   ` Johannes Weiner
2016-07-14 12:54   ` Vlastimil Babka
2016-07-08  9:35 ` [PATCH 28/34] mm, vmscan: add classzone information to tracepoints Mel Gorman
2016-07-12 18:13   ` Johannes Weiner
2016-07-08  9:35 ` [PATCH 29/34] mm, page_alloc: remove fair zone allocation policy Mel Gorman
2016-07-12 18:18   ` Johannes Weiner
2016-07-08  9:35 ` [PATCH 30/34] mm: page_alloc: cache the last node whose dirty limit is reached Mel Gorman
2016-07-12 18:43   ` Johannes Weiner
2016-07-08  9:35 ` [PATCH 31/34] mm: vmstat: replace __count_zone_vm_events with a zone id equivalent Mel Gorman
2016-07-12 19:10   ` Johannes Weiner
2016-07-08  9:35 ` [PATCH 32/34] mm: vmstat: account per-zone stalls and pages skipped during reclaim Mel Gorman
2016-07-12 19:06   ` Johannes Weiner
2016-07-08  9:35 ` [PATCH 33/34] mm, vmstat: print node-based stats in zoneinfo file Mel Gorman
2016-07-12 19:18   ` Johannes Weiner
2016-07-14 12:56   ` Vlastimil Babka
2016-07-08  9:35 ` [PATCH 34/34] mm, vmstat: remove zone and node double accounting by approximating retries Mel Gorman
2016-07-14 13:40   ` Vlastimil Babka
2016-07-15  7:48     ` Mel Gorman
2016-07-15 12:20       ` Vlastimil Babka
2016-08-19 13:12 ` [PATCH 00/34] Move LRU page reclaim from zones to nodes v9 Andrea Arcangeli
2016-08-19 13:23   ` Vlastimil Babka
2016-08-19 13:55     ` Andrea Arcangeli
2016-08-19 14:53   ` Mel Gorman
2016-08-19 15:32     ` Andrea Arcangeli
2016-08-19 15:55       ` Mel Gorman

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1467970510-21195-3-git-send-email-mgorman@techsingularity.net \
    --to=mgorman@techsingularity.net \
    --cc=akpm@linux-foundation.org \
    --cc=hannes@cmpxchg.org \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=minchan@kernel.org \
    --cc=riel@surriel.com \
    --cc=vbabka@suse.cz \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org linux-mm@archiver.kernel.org
	public-inbox-index linux-mm


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/ public-inbox