[RFC PATCH v5 1/4] mm: add page_counter_margin()

From: Johannes Weiner <[email protected]>

mem_cgroup_get_nr_swap_pages() open-codes the remaining capacity across
the memcg swap counter hierarchy.

Add page_counter_margin() to return the minimum usable space from a page
counter to the root, and use it in mem_cgroup_get_nr_swap_pages(). This
is a pure refactoring with no intended behavior change.

Signed-off-by: Johannes Weiner <[email protected]>
Signed-off-by: Xueyuan Chen <[email protected]>
---
 include/linux/page_counter.h |  1 +
 mm/memcontrol.c              |  9 +++------
 mm/page_counter.c            | 20 ++++++++++++++++++++
 3 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
index d649b6bbbc87..07b7cb12249c 100644
--- a/include/linux/page_counter.h
+++ b/include/linux/page_counter.h
@@ -68,6 +68,7 @@ static inline unsigned long page_counter_read(struct page_counter *counter)
 	return atomic_long_read(&counter->usage);
 }
 
+long page_counter_margin(struct page_counter *counter);
 void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages);
 void page_counter_charge(struct page_counter *counter, unsigned long nr_pages);
 bool page_counter_try_charge(struct page_counter *counter,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8319ad8c5c23..109c08be91cf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5670,12 +5670,9 @@ long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
 {
 	long nr_swap_pages = get_nr_swap_pages();
 
-	if (mem_cgroup_disabled() || do_memsw_account())
-		return nr_swap_pages;
-	for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg))
-		nr_swap_pages = min_t(long, nr_swap_pages,
-				      READ_ONCE(memcg->swap.max) -
-				      page_counter_read(&memcg->swap));
+	if (!mem_cgroup_disabled() && !do_memsw_account())
+		nr_swap_pages = min(nr_swap_pages, page_counter_margin(&memcg->swap));
+
 	return nr_swap_pages;
 }
 
diff --git a/mm/page_counter.c b/mm/page_counter.c
index 661e0f2a5127..450543f4b318 100644
--- a/mm/page_counter.c
+++ b/mm/page_counter.c
@@ -46,6 +46,26 @@ static void propagate_protected_usage(struct page_counter *c,
 	}
 }
 
+/**
+ * page_counter_margin - remaining usable space within hierarchical limits
+ * @counter: counter
+ *
+ * Return: The minimum value of max minus usage across @counter and all of
+ * its ancestors. The value may be negative during a concurrent charge.
+ */
+long page_counter_margin(struct page_counter *counter)
+{
+	long margin = PAGE_COUNTER_MAX;
+
+	do {
+		long m = READ_ONCE(counter->max) - page_counter_read(counter);
+
+		margin = min(margin, m);
+	} while ((counter = counter->parent));
+
+	return margin;
+}
+
 /**
  * page_counter_cancel - take pages out of the local counter
  * @counter: counter
-- 
2.47.3