mm: remove zone_lru_lock() function, access ->lru_lock directly

We have common pattern to access lru_lock from a page pointer:
	zone_lru_lock(page_zone(page))

Which is silly, because it unfolds to this:
	&NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]->zone_pgdat->lru_lock
while we can simply do
	&NODE_DATA(page_to_nid(page))->lru_lock

Remove zone_lru_lock() function, since it's only complicate things.  Use
'page_pgdat(page)->lru_lock' pattern instead.

[aryabinin@virtuozzo.com: a slightly better version of __split_huge_page()]
  Link: http://lkml.kernel.org/r/20190301121651.7741-1-aryabinin@virtuozzo.com
Link: http://lkml.kernel.org/r/20190228083329.31892-2-aryabinin@virtuozzo.com
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

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 pgdat->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 pgdat->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

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
+       pgdat->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.
+  pgdat->lru_lock, it has no lock of its own.
 
 2.7 Kernel Memory Extension (CONFIG_MEMCG_KMEM)
 

include/linux/mm_types.h

@@ -80,7 +80,7 @@ struct page {
 		struct {	/* Page cache and anonymous pages */
 			/**
 			 * @lru: Pageout list, eg. active_list protected by
-			 * zone_lru_lock.  Sometimes used as a generic list
+			 * pgdat->lru_lock.  Sometimes used as a generic list
 			 * by the page owner.
 			 */
 			struct list_head lru;

include/linux/mmzone.h

@@ -730,10 +730,6 @@ 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 struct lruvec *node_lruvec(struct pglist_data *pgdat)
 {

mm/compaction.c

@@ -775,6 +775,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			unsigned long end_pfn, isolate_mode_t isolate_mode)
 {
 	struct zone *zone = cc->zone;
+	pg_data_t *pgdat = zone->zone_pgdat;
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct lruvec *lruvec;
 	unsigned long flags = 0;
@@ -839,8 +840,8 @@ 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(zone), flags,
+		    && compact_unlock_should_abort(&pgdat->lru_lock,
-								&locked, cc))
+					    flags, &locked, cc))
 			break;
 
 		if (!pfn_valid_within(low_pfn))
@@ -910,7 +911,7 @@ 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(zone),
+					spin_unlock_irqrestore(&pgdat->lru_lock,
 									flags);
 					locked = false;
 				}
@@ -940,7 +941,7 @@ 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_lock_irqsave(zone_lru_lock(zone),
+			locked = compact_lock_irqsave(&pgdat->lru_lock,
 								&flags, cc);
 
 			/* Try get exclusive access under lock */
@@ -965,7 +966,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			}
 		}
 
-		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
 		/* Try isolate the page */
 		if (__isolate_lru_page(page, isolate_mode) != 0)
@@ -1007,7 +1008,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		 */
 		if (nr_isolated) {
 			if (locked) {
-				spin_unlock_irqrestore(zone_lru_lock(zone), flags);
+				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
 				locked = false;
 			}
 			putback_movable_pages(&cc->migratepages);
@@ -1034,7 +1035,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 isolate_abort:
 	if (locked)
-		spin_unlock_irqrestore(zone_lru_lock(zone), flags);
+		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
 
 	/*
 	 * Updated the cached scanner pfn once the pageblock has been scanned

mm/filemap.c

@@ -98,8 +98,8 @@
  *    ->swap_lock		(try_to_unmap_one)
  *    ->private_lock		(try_to_unmap_one)
  *    ->i_pages lock		(try_to_unmap_one)
- *    ->zone_lru_lock(zone)	(follow_page->mark_page_accessed)
+ *    ->pgdat->lru_lock		(follow_page->mark_page_accessed)
- *    ->zone_lru_lock(zone)	(check_pte_range->isolate_lru_page)
+ *    ->pgdat->lru_lock		(check_pte_range->isolate_lru_page)
  *    ->private_lock		(page_remove_rmap->set_page_dirty)
  *    ->i_pages lock		(page_remove_rmap->set_page_dirty)
  *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)

mm/huge_memory.c

@@ -2440,11 +2440,11 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 		pgoff_t end, unsigned long flags)
 {
 	struct page *head = compound_head(page);
-	struct zone *zone = page_zone(head);
+	pg_data_t *pgdat = page_pgdat(head);
 	struct lruvec *lruvec;
 	int i;
 
-	lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat);
+	lruvec = mem_cgroup_page_lruvec(head, pgdat);
 
 	/* complete memcg works before add pages to LRU */
 	mem_cgroup_split_huge_fixup(head);
@@ -2475,7 +2475,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 		xa_unlock(&head->mapping->i_pages);
 	}
 
-	spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
+	spin_unlock_irqrestore(&pgdat->lru_lock, flags);
 
 	remap_page(head);
 
@@ -2686,7 +2686,7 @@ 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(zone_lru_lock(page_zone(head)), flags);
+	spin_lock_irqsave(&pgdata->lru_lock, flags);
 
 	if (mapping) {
 		XA_STATE(xas, &mapping->i_pages, page_index(head));
@@ -2731,7 +2731,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		spin_unlock(&pgdata->split_queue_lock);
 fail:		if (mapping)
 			xa_unlock(&mapping->i_pages);
-		spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
+		spin_unlock_irqrestore(&pgdata->lru_lock, flags);
 		remap_page(head);
 		ret = -EBUSY;
 	}

mm/memcontrol.c

@@ -2362,13 +2362,13 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 
 static void lock_page_lru(struct page *page, int *isolated)
 {
-	struct zone *zone = page_zone(page);
+	pg_data_t *pgdat = page_pgdat(page);
 
-	spin_lock_irq(zone_lru_lock(zone));
+	spin_lock_irq(&pgdat->lru_lock);
 	if (PageLRU(page)) {
 		struct lruvec *lruvec;
 
-		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 		ClearPageLRU(page);
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 		*isolated = 1;
@@ -2378,17 +2378,17 @@ static void lock_page_lru(struct page *page, int *isolated)
 
 static void unlock_page_lru(struct page *page, int isolated)
 {
-	struct zone *zone = page_zone(page);
+	pg_data_t *pgdat = page_pgdat(page);
 
 	if (isolated) {
 		struct lruvec *lruvec;
 
-		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 		SetPageLRU(page);
 		add_page_to_lru_list(page, lruvec, page_lru(page));
 	}
-	spin_unlock_irq(zone_lru_lock(zone));
+	spin_unlock_irq(&pgdat->lru_lock);
 }
 
 static void commit_charge(struct page *page, struct mem_cgroup *memcg,
@@ -2674,7 +2674,7 @@ 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.
+ * pgdat->lru_lock and migration entries setup in all page mappings.
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {

mm/mlock.c

@@ -182,7 +182,7 @@ static void __munlock_isolation_failed(struct page *page)
 unsigned int munlock_vma_page(struct page *page)
 {
 	int nr_pages;
-	struct zone *zone = page_zone(page);
+	pg_data_t *pgdat = page_pgdat(page);
 
 	/* For try_to_munlock() and to serialize with page migration */
 	BUG_ON(!PageLocked(page));
@@ -194,7 +194,7 @@ 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(zone));
+	spin_lock_irq(&pgdat->lru_lock);
 
 	if (!TestClearPageMlocked(page)) {
 		/* Potentially, PTE-mapped THP: do not skip the rest PTEs */
@@ -203,17 +203,17 @@ unsigned int munlock_vma_page(struct page *page)
 	}
 
 	nr_pages = hpage_nr_pages(page);
-	__mod_zone_page_state(zone, NR_MLOCK, -nr_pages);
+	__mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
 
 	if (__munlock_isolate_lru_page(page, true)) {
-		spin_unlock_irq(zone_lru_lock(zone));
+		spin_unlock_irq(&pgdat->lru_lock);
 		__munlock_isolated_page(page);
 		goto out;
 	}
 	__munlock_isolation_failed(page);
 
 unlock_out:
-	spin_unlock_irq(zone_lru_lock(zone));
+	spin_unlock_irq(&pgdat->lru_lock);
 
 out:
 	return nr_pages - 1;
@@ -298,7 +298,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 	pagevec_init(&pvec_putback);
 
 	/* Phase 1: page isolation */
-	spin_lock_irq(zone_lru_lock(zone));
+	spin_lock_irq(&zone->zone_pgdat->lru_lock);
 	for (i = 0; i < nr; i++) {
 		struct page *page = pvec->pages[i];
 
@@ -325,7 +325,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 		pvec->pages[i] = NULL;
 	}
 	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
-	spin_unlock_irq(zone_lru_lock(zone));
+	spin_unlock_irq(&zone->zone_pgdat->lru_lock);
 
 	/* Now we can release pins of pages that we are not munlocking */
 	pagevec_release(&pvec_putback);

mm/page_idle.c

@@ -31,7 +31,7 @@
 static struct page *page_idle_get_page(unsigned long pfn)
 {
 	struct page *page;
-	struct zone *zone;
+	pg_data_t *pgdat;
 
 	if (!pfn_valid(pfn))
 		return NULL;
@@ -41,13 +41,13 @@ static struct page *page_idle_get_page(unsigned long pfn)
 	    !get_page_unless_zero(page))
 		return NULL;
 
-	zone = page_zone(page);
+	pgdat = page_pgdat(page);
-	spin_lock_irq(zone_lru_lock(zone));
+	spin_lock_irq(&pgdat->lru_lock);
 	if (unlikely(!PageLRU(page))) {
 		put_page(page);
 		page = NULL;
 	}
-	spin_unlock_irq(zone_lru_lock(zone));
+	spin_unlock_irq(&pgdat->lru_lock);
 	return page;
 }
 

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)
+ *               pgdat->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)

mm/swap.c

@@ -58,16 +58,16 @@ static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs);
 static void __page_cache_release(struct page *page)
 {
 	if (PageLRU(page)) {
-		struct zone *zone = page_zone(page);
+		pg_data_t *pgdat = page_pgdat(page);
 		struct lruvec *lruvec;
 		unsigned long flags;
 
-		spin_lock_irqsave(zone_lru_lock(zone), flags);
+		spin_lock_irqsave(&pgdat->lru_lock, flags);
-		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 		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(zone), flags);
+		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
 	}
 	__ClearPageWaiters(page);
 	mem_cgroup_uncharge(page);
@@ -322,12 +322,12 @@ static inline void activate_page_drain(int cpu)
 
 void activate_page(struct page *page)
 {
-	struct zone *zone = page_zone(page);
+	pg_data_t *pgdat = page_pgdat(page);
 
 	page = compound_head(page);
-	spin_lock_irq(zone_lru_lock(zone));
+	spin_lock_irq(&pgdat->lru_lock);
-	__activate_page(page, mem_cgroup_page_lruvec(page, zone->zone_pgdat), NULL);
+	__activate_page(page, mem_cgroup_page_lruvec(page, pgdat), NULL);
-	spin_unlock_irq(zone_lru_lock(zone));
+	spin_unlock_irq(&pgdat->lru_lock);
 }
 #endif
 

mm/vmscan.c

@@ -1614,8 +1614,8 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec,
 
 }
 
-/*
+/**
- * zone_lru_lock is heavily contended.  Some of the functions that
+ * pgdat->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.
  *
@@ -1750,11 +1750,11 @@ int isolate_lru_page(struct page *page)
 	WARN_RATELIMIT(PageTail(page), "trying to isolate tail page");
 
 	if (PageLRU(page)) {
-		struct zone *zone = page_zone(page);
+		pg_data_t *pgdat = page_pgdat(page);
 		struct lruvec *lruvec;
 
-		spin_lock_irq(zone_lru_lock(zone));
+		spin_lock_irq(&pgdat->lru_lock);
-		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 		if (PageLRU(page)) {
 			int lru = page_lru(page);
 			get_page(page);
@@ -1762,7 +1762,7 @@ int isolate_lru_page(struct page *page)
 			del_page_from_lru_list(page, lruvec, lru);
 			ret = 0;
 		}
-		spin_unlock_irq(zone_lru_lock(zone));
+		spin_unlock_irq(&pgdat->lru_lock);
 	}
 	return ret;
 }
@@ -1990,9 +1990,9 @@ 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 pgdat->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 pgdat->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.