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.

[[email protected]: use page_memcg()]
  Link: https://lkml.kernel.org/r/[email protected]

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Alexander Duyck <[email protected]>
Signed-off-by: Alex Shi <[email protected]>
Acked-by: Hugh Dickins <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Andrey Ryabinin <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Konstantin Khlebnikov <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: "Chen, Rong A" <[email protected]>
Cc: Daniel Jordan <[email protected]>
Cc: "Huang, Ying" <[email protected]>
Cc: Jann Horn <[email protected]>
Cc: Joonsoo Kim <[email protected]>
Cc: Kirill A. Shutemov <[email protected]>
Cc: Kirill A. Shutemov <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Mika Penttilä <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Shakeel Butt <[email protected]>
Cc: Vladimir Davydov <[email protected]>
Cc: Wei Yang <[email protected]>
Cc: Yang Shi <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

1 files changed, 52 insertions, 0 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index aa5d559853c2..ff02f831e7e1 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -485,6 +485,22 @@ out:
 
 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);