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>

2 files changed, 60 insertions, 1 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f530d634f055..aa5d559853c2 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -491,6 +491,19 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
 
 struct mem_cgroup *get_mem_cgroup_from_page(struct page *page);
 
+struct lruvec *lock_page_lruvec(struct page *page);
+struct lruvec *lock_page_lruvec_irq(struct page *page);
+struct lruvec *lock_page_lruvec_irqsave(struct page *page,
+						unsigned long *flags);
+
+#ifdef CONFIG_DEBUG_VM
+void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page);
+#else
+static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+{
+}
+#endif
+
 static inline
 struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 	return css ? container_of(css, struct mem_cgroup, css) : NULL;
@@ -996,6 +1009,31 @@ static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 }
 
+static inline struct lruvec *lock_page_lruvec(struct page *page)
+{
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	spin_lock(&pgdat->__lruvec.lru_lock);
+	return &pgdat->__lruvec;
+}
+
+static inline struct lruvec *lock_page_lruvec_irq(struct page *page)
+{
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	spin_lock_irq(&pgdat->__lruvec.lru_lock);
+	return &pgdat->__lruvec;
+}
+
+static inline struct lruvec *lock_page_lruvec_irqsave(struct page *page,
+		unsigned long *flagsp)
+{
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp);
+	return &pgdat->__lruvec;
+}
+
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
 		struct mem_cgroup *prev,
@@ -1215,6 +1253,10 @@ static inline
 void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 {
 }
+
+static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+{
+}
 #endif /* CONFIG_MEMCG */
 
 /* idx can be of type enum memcg_stat_item or node_stat_item */
@@ -1296,6 +1338,22 @@ static inline struct lruvec *parent_lruvec(struct lruvec *lruvec)
 	return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec));
 }
 
+static inline void unlock_page_lruvec(struct lruvec *lruvec)
+{
+	spin_unlock(&lruvec->lru_lock);
+}
+
+static inline void unlock_page_lruvec_irq(struct lruvec *lruvec)
+{
+	spin_unlock_irq(&lruvec->lru_lock);
+}
+
+static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec,
+		unsigned long flags)
+{
+	spin_unlock_irqrestore(&lruvec->lru_lock, flags);
+}
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 98a80c01d150..9da23c019dc5 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -276,6 +276,8 @@ enum lruvec_flags {
 
 struct lruvec {
 	struct list_head		lists[NR_LRU_LISTS];
+	/* per lruvec lru_lock for memcg */
+	spinlock_t			lru_lock;
 	/*
 	 * These track the cost of reclaiming one LRU - file or anon -
 	 * over the other. As the observed cost of reclaiming one LRU
@@ -782,7 +784,6 @@ typedef struct pglist_data {
 
 	/* Write-intensive fields used by page reclaim */
 	ZONE_PADDING(_pad1_)
-	spinlock_t		lru_lock;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 	/*