mm/lru: introduce relock_page_lruvec()

Add relock_page_lruvec() to replace repeated same code, no functional
change.

When testing for relock we can avoid the need for RCU locking if we simply
compare the page pgdat and memcg pointers versus those that the lruvec is
holding.  By doing this we can avoid the extra pointer walks and accesses
of the memory cgroup.

In addition we can avoid the checks entirely if lruvec is currently NULL.

[alex.shi@linux.alibaba.com: use page_memcg()]
  Link: https://lkml.kernel.org/r/66d8e79d-7ec6-bfbc-1c82-bf32db3ae5b7@linux.alibaba.com

Link: https://lkml.kernel.org/r/1604566549-62481-19-git-send-email-alex.shi@linux.alibaba.com
Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.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>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Tejun Heo <tj@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Chen, Rong A" <rong.a.chen@intel.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.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: Michal Hocko <mhocko@kernel.org>
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: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/memcontrol.h

@@ -485,6 +485,22 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
 
 struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
 
+static inline bool lruvec_holds_page_lru_lock(struct page *page,
+					      struct lruvec *lruvec)
+{
+	pg_data_t *pgdat = page_pgdat(page);
+	const struct mem_cgroup *memcg;
+	struct mem_cgroup_per_node *mz;
+
+	if (mem_cgroup_disabled())
+		return lruvec == &pgdat->__lruvec;
+
+	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+	memcg = page_memcg(page) ? : root_mem_cgroup;
+
+	return lruvec->pgdat == pgdat && mz->memcg == memcg;
+}
+
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 
 struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
@@ -984,6 +1000,14 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
 	return &pgdat->__lruvec;
 }
 
+static inline bool lruvec_holds_page_lru_lock(struct page *page,
+					      struct lruvec *lruvec)
+{
+	pg_data_t *pgdat = page_pgdat(page);
+
+	return lruvec == &pgdat->__lruvec;
+}
+
 static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 {
 	return NULL;
@@ -1354,6 +1378,34 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec,
 	spin_unlock_irqrestore(&lruvec->lru_lock, flags);
 }
 
+/* Don't lock again iff page's lruvec locked */
+static inline struct lruvec *relock_page_lruvec_irq(struct page *page,
+		struct lruvec *locked_lruvec)
+{
+	if (locked_lruvec) {
+		if (lruvec_holds_page_lru_lock(page, locked_lruvec))
+			return locked_lruvec;
+
+		unlock_page_lruvec_irq(locked_lruvec);
+	}
+
+	return lock_page_lruvec_irq(page);
+}
+
+/* Don't lock again iff page's lruvec locked */
+static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page,
+		struct lruvec *locked_lruvec, unsigned long *flags)
+{
+	if (locked_lruvec) {
+		if (lruvec_holds_page_lru_lock(page, locked_lruvec))
+			return locked_lruvec;
+
+		unlock_page_lruvec_irqrestore(locked_lruvec, *flags);
+	}
+
+	return lock_page_lruvec_irqsave(page, flags);
+}
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb);

mm/mlock.c

@@ -277,16 +277,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 			 * so we can spare the get_page() here.
 			 */
 			if (TestClearPageLRU(page)) {
-				struct lruvec *new_lruvec;
-
-				new_lruvec = mem_cgroup_page_lruvec(page,
-						page_pgdat(page));
-				if (new_lruvec != lruvec) {
-					if (lruvec)
-						unlock_page_lruvec_irq(lruvec);
-					lruvec = lock_page_lruvec_irq(page);
-				}
-
+				lruvec = relock_page_lruvec_irq(page, lruvec);
 				del_page_from_lru_list(page, lruvec,
 							page_lru(page));
 				continue;

mm/swap.c

@@ -210,19 +210,12 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
-		struct lruvec *new_lruvec;
 
 		/* block memcg migration during page moving between lru */
 		if (!TestClearPageLRU(page))
 			continue;
 
-		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 = relock_page_lruvec_irqsave(page, lruvec, &flags);
 		(*move_fn)(page, lruvec);
 
 		SetPageLRU(page);
@@ -918,17 +911,12 @@ void release_pages(struct page **pages, int nr)
 		}
 
 		if (PageLRU(page)) {
-			struct lruvec *new_lruvec;
-
-			new_lruvec = mem_cgroup_page_lruvec(page,
-							page_pgdat(page));
-			if (new_lruvec != lruvec) {
-				if (lruvec)
-					unlock_page_lruvec_irqrestore(lruvec,
-									flags);
+			struct lruvec *prev_lruvec = lruvec;
+
+			lruvec = relock_page_lruvec_irqsave(page, lruvec,
+									&flags);
+			if (prev_lruvec != lruvec)
 				lock_batch = 0;
-				lruvec = lock_page_lruvec_irqsave(page, &flags);
-			}
 
 			VM_BUG_ON_PAGE(!PageLRU(page), page);
 			__ClearPageLRU(page);
@@ -1033,15 +1021,8 @@ void __pagevec_lru_add(struct pagevec *pvec)
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
-		struct lruvec *new_lruvec;
-
-		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 = relock_page_lruvec_irqsave(page, lruvec, &flags);
 		__pagevec_lru_add_fn(page, lruvec);
 	}
 	if (lruvec)

mm/vmscan.c

@@ -1883,8 +1883,7 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 		 * All pages were isolated from the same lruvec (and isolation
 		 * inhibits memcg migration).
 		 */
-		VM_BUG_ON_PAGE(mem_cgroup_page_lruvec(page, page_pgdat(page))
-							!= lruvec, page);
+		VM_BUG_ON_PAGE(!lruvec_holds_page_lru_lock(page, lruvec), page);
 		lru = page_lru(page);
 		nr_pages = thp_nr_pages(page);
 
@@ -4273,7 +4272,6 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 	for (i = 0; i < pvec->nr; i++) {
 		struct page *page = pvec->pages[i];
 		int nr_pages;
-		struct lruvec *new_lruvec;
 
 		if (PageTransTail(page))
 			continue;
@@ -4285,13 +4283,7 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 		if (!TestClearPageLRU(page))
 			continue;
 
-		new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
-		if (lruvec != new_lruvec) {
-			if (lruvec)
-				unlock_page_lruvec_irq(lruvec);
-			lruvec = lock_page_lruvec_irq(page);
-		}
-
+		lruvec = relock_page_lruvec_irq(page, lruvec);
 		if (page_evictable(page) && PageUnevictable(page)) {
 			enum lru_list lru = page_lru_base_type(page);