mm/lru: replace pgdat lru_lock with lruvec lock

This patch moves per node lru_lock into lruvec, thus bring a lru_lock for
each of memcg per node.  So on a large machine, each of memcg don't have
to suffer from per node pgdat->lru_lock competition.  They could go fast
with their self lru_lock.

After move memcg charge before lru inserting, page isolation could
serialize page's memcg, then per memcg lruvec lock is stable and could
replace per node lru lock.

In isolate_migratepages_block(), compact_unlock_should_abort and
lock_page_lruvec_irqsave are open coded to work with compact_control.
Also add a debug func in locking which may give some clues if there are
sth out of hands.

Daniel Jordan's testing show 62% improvement on modified readtwice case on
his 2P * 10 core * 2 HT broadwell box.
https://lore.kernel.org/lkml/20200915165807.kpp7uhiw7l3loofu@ca-dmjordan1.us.oracle.com/

Hugh Dickins helped on the patch polish, thanks!

[alex.shi@linux.alibaba.com: fix comment typo]
  Link: https://lkml.kernel.org/r/5b085715-292a-4b43-50b3-d73dc90d1de5@linux.alibaba.com
[alex.shi@linux.alibaba.com: use page_memcg()]
  Link: https://lkml.kernel.org/r/5a4c2b72-7ee8-2478-fc0e-85eb83aafec4@linux.alibaba.com

Link: https://lkml.kernel.org/r/1604566549-62481-18-git-send-email-alex.shi@linux.alibaba.com
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rong Chen <rong.a.chen@intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mika Penttilä <mika.penttila@nextfour.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 58 insertions, 58 deletions

diff --git a/mm/swap.c b/mm/swap.c
index d952af770053..ba9fc21b24ea 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -79,16 +79,14 @@ static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = {
 static void __page_cache_release(struct page *page)
 {
 	if (PageLRU(page)) {
-		pg_data_t *pgdat = page_pgdat(page);
 		struct lruvec *lruvec;
 		unsigned long flags;
 
-		spin_lock_irqsave(&pgdat->lru_lock, flags);
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
+		lruvec = lock_page_lruvec_irqsave(page, &flags);
 		VM_BUG_ON_PAGE(!PageLRU(page), page);
 		__ClearPageLRU(page);
 		del_page_from_lru_list(page, lruvec, page_off_lru(page));
-		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+		unlock_page_lruvec_irqrestore(lruvec, flags);
 	}
 	__ClearPageWaiters(page);
 }
@@ -207,32 +205,30 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
 	void (*move_fn)(struct page *page, struct lruvec *lruvec))
 {
 	int i;
-	struct pglist_data *pgdat = NULL;
-	struct lruvec *lruvec;
+	struct lruvec *lruvec = NULL;
 	unsigned long flags = 0;
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
-		struct pglist_data *pagepgdat = page_pgdat(page);
-
-		if (pagepgdat != pgdat) {
-			if (pgdat)
-				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
-			pgdat = pagepgdat;
-			spin_lock_irqsave(&pgdat->lru_lock, flags);
-		}
+		struct lruvec *new_lruvec;
 
 		/* block memcg migration during page moving between lru */
 		if (!TestClearPageLRU(page))
 			continue;
 
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
+		new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
+		if (lruvec != new_lruvec) {
+			if (lruvec)
+				unlock_page_lruvec_irqrestore(lruvec, flags);
+			lruvec = lock_page_lruvec_irqsave(page, &flags);
+		}
+
 		(*move_fn)(page, lruvec);
 
 		SetPageLRU(page);
 	}
-	if (pgdat)
-		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+	if (lruvec)
+		unlock_page_lruvec_irqrestore(lruvec, flags);
 	release_pages(pvec->pages, pvec->nr);
 	pagevec_reinit(pvec);
 }
@@ -274,9 +270,15 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
 {
 	do {
 		unsigned long lrusize;
-		struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
-		spin_lock_irq(&pgdat->lru_lock);
+		/*
+		 * Hold lruvec->lru_lock is safe here, since
+		 * 1) The pinned lruvec in reclaim, or
+		 * 2) From a pre-LRU page during refault (which also holds the
+		 *    rcu lock, so would be safe even if the page was on the LRU
+		 *    and could move simultaneously to a new lruvec).
+		 */
+		spin_lock_irq(&lruvec->lru_lock);
 		/* Record cost event */
 		if (file)
 			lruvec->file_cost += nr_pages;
@@ -300,7 +302,7 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
 			lruvec->file_cost /= 2;
 			lruvec->anon_cost /= 2;
 		}
-		spin_unlock_irq(&pgdat->lru_lock);
+		spin_unlock_irq(&lruvec->lru_lock);
 	} while ((lruvec = parent_lruvec(lruvec)));
 }
 
@@ -364,13 +366,15 @@ static inline void activate_page_drain(int cpu)
 
 static void activate_page(struct page *page)
 {
-	pg_data_t *pgdat = page_pgdat(page);
+	struct lruvec *lruvec;
 
 	page = compound_head(page);
-	spin_lock_irq(&pgdat->lru_lock);
-	if (PageLRU(page))
-		__activate_page(page, mem_cgroup_page_lruvec(page, pgdat));
-	spin_unlock_irq(&pgdat->lru_lock);
+	if (TestClearPageLRU(page)) {
+		lruvec = lock_page_lruvec_irq(page);
+		__activate_page(page, lruvec);
+		unlock_page_lruvec_irq(lruvec);
+		SetPageLRU(page);
+	}
 }
 #endif
 
@@ -860,8 +864,7 @@ void release_pages(struct page **pages, int nr)
 {
 	int i;
 	LIST_HEAD(pages_to_free);
-	struct pglist_data *locked_pgdat = NULL;
-	struct lruvec *lruvec;
+	struct lruvec *lruvec = NULL;
 	unsigned long flags;
 	unsigned int lock_batch;
 
@@ -871,11 +874,11 @@ void release_pages(struct page **pages, int nr)
 		/*
 		 * Make sure the IRQ-safe lock-holding time does not get
 		 * excessive with a continuous string of pages from the
-		 * same pgdat. The lock is held only if pgdat != NULL.
+		 * same lruvec. The lock is held only if lruvec != NULL.
 		 */
-		if (locked_pgdat && ++lock_batch == SWAP_CLUSTER_MAX) {
-			spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
-			locked_pgdat = NULL;
+		if (lruvec && ++lock_batch == SWAP_CLUSTER_MAX) {
+			unlock_page_lruvec_irqrestore(lruvec, flags);
+			lruvec = NULL;
 		}
 
 		page = compound_head(page);
@@ -883,10 +886,9 @@ void release_pages(struct page **pages, int nr)
 			continue;
 
 		if (is_zone_device_page(page)) {
-			if (locked_pgdat) {
-				spin_unlock_irqrestore(&locked_pgdat->lru_lock,
-						       flags);
-				locked_pgdat = NULL;
+			if (lruvec) {
+				unlock_page_lruvec_irqrestore(lruvec, flags);
+				lruvec = NULL;
 			}
 			/*
 			 * ZONE_DEVICE pages that return 'false' from
@@ -907,27 +909,27 @@ void release_pages(struct page **pages, int nr)
 			continue;
 
 		if (PageCompound(page)) {
-			if (locked_pgdat) {
-				spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
-				locked_pgdat = NULL;
+			if (lruvec) {
+				unlock_page_lruvec_irqrestore(lruvec, flags);
+				lruvec = NULL;
 			}
 			__put_compound_page(page);
 			continue;
 		}
 
 		if (PageLRU(page)) {
-			struct pglist_data *pgdat = page_pgdat(page);
+			struct lruvec *new_lruvec;
 
-			if (pgdat != locked_pgdat) {
-				if (locked_pgdat)
-					spin_unlock_irqrestore(&locked_pgdat->lru_lock,
+			new_lruvec = mem_cgroup_page_lruvec(page,
+							page_pgdat(page));
+			if (new_lruvec != lruvec) {
+				if (lruvec)
+					unlock_page_lruvec_irqrestore(lruvec,
 									flags);
 				lock_batch = 0;
-				locked_pgdat = pgdat;
-				spin_lock_irqsave(&locked_pgdat->lru_lock, flags);
+				lruvec = lock_page_lruvec_irqsave(page, &flags);
 			}
 
-			lruvec = mem_cgroup_page_lruvec(page, locked_pgdat);
 			VM_BUG_ON_PAGE(!PageLRU(page), page);
 			__ClearPageLRU(page);
 			del_page_from_lru_list(page, lruvec, page_off_lru(page));
@@ -937,8 +939,8 @@ void release_pages(struct page **pages, int nr)
 
 		list_add(&page->lru, &pages_to_free);
 	}
-	if (locked_pgdat)
-		spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
+	if (lruvec)
+		unlock_page_lruvec_irqrestore(lruvec, flags);
 
 	mem_cgroup_uncharge_list(&pages_to_free);
 	free_unref_page_list(&pages_to_free);
@@ -1026,26 +1028,24 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
 void __pagevec_lru_add(struct pagevec *pvec)
 {
 	int i;
-	struct pglist_data *pgdat = NULL;
-	struct lruvec *lruvec;
+	struct lruvec *lruvec = NULL;
 	unsigned long flags = 0;
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
-		struct pglist_data *pagepgdat = page_pgdat(page);
+		struct lruvec *new_lruvec;
 
-		if (pagepgdat != pgdat) {
-			if (pgdat)
-				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
-			pgdat = pagepgdat;
-			spin_lock_irqsave(&pgdat->lru_lock, flags);
+		new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
+		if (lruvec != new_lruvec) {
+			if (lruvec)
+				unlock_page_lruvec_irqrestore(lruvec, flags);
+			lruvec = lock_page_lruvec_irqsave(page, &flags);
 		}
 
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 		__pagevec_lru_add_fn(page, lruvec);
 	}
-	if (pgdat)
-		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+	if (lruvec)
+		unlock_page_lruvec_irqrestore(lruvec, flags);
 	release_pages(pvec->pages, pvec->nr);
 	pagevec_reinit(pvec);
 }