memcg: add per cgroup writeback pages accounting

Add memcg routines to count writeback pages, later dirty pages will also
be accounted.

After Kame's commit 89c06bd52fb9 ("memcg: use new logic for page stat
accounting"), we can use 'struct page' flag to test page state instead
of per page_cgroup flag.  But memcg has a feature to move a page from a
cgroup to another one and may have race between "move" and "page stat
accounting".  So in order to avoid the race we have designed a new lock:

         mem_cgroup_begin_update_page_stat()
         modify page information        -->(a)
         mem_cgroup_update_page_stat()  -->(b)
         mem_cgroup_end_update_page_stat()

It requires both (a) and (b)(writeback pages accounting) to be pretected
in mem_cgroup_{begin/end}_update_page_stat().  It's full no-op for
!CONFIG_MEMCG, almost no-op if memcg is disabled (but compiled in), rcu
read lock in the most cases (no task is moving), and spin_lock_irqsave
on top in the slow path.

There're two writeback interfaces to modify: test_{clear/set}_page_writeback().
And the lock order is:
	--> memcg->move_lock
	  --> mapping->tree_lock

Signed-off-by: Sha Zhengju <handai.szj@taobao.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Greg Thelen <gthelen@google.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 39 insertions, 7 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f952a07ce7a..60e95872da2 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -42,6 +42,7 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_RSS,		/* # of pages charged as anon rss */
 	MEM_CGROUP_STAT_RSS_HUGE,	/* # of pages charged as anon huge */
 	MEM_CGROUP_STAT_FILE_MAPPED,	/* # of pages charged as file rss */
+	MEM_CGROUP_STAT_WRITEBACK,	/* # of pages under writeback */
 	MEM_CGROUP_STAT_SWAP,		/* # of pages, swapped out */
 	MEM_CGROUP_STAT_NSTATS,
 };
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0093bc36c5f..d5ff3ce1302 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -89,6 +89,7 @@ static const char * const mem_cgroup_stat_names[] = {
 	"rss",
 	"rss_huge",
 	"mapped_file",
+	"writeback",
 	"swap",
 };
 
@@ -3654,6 +3655,20 @@ void mem_cgroup_split_huge_fixup(struct page *head)
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+static inline
+void mem_cgroup_move_account_page_stat(struct mem_cgroup *from,
+					struct mem_cgroup *to,
+					unsigned int nr_pages,
+					enum mem_cgroup_stat_index idx)
+{
+	/* Update stat data for mem_cgroup */
+	preempt_disable();
+	WARN_ON_ONCE(from->stat->count[idx] < nr_pages);
+	__this_cpu_add(from->stat->count[idx], -nr_pages);
+	__this_cpu_add(to->stat->count[idx], nr_pages);
+	preempt_enable();
+}
+
 /**
  * mem_cgroup_move_account - move account of the page
  * @page: the page
@@ -3699,13 +3714,14 @@ static int mem_cgroup_move_account(struct page *page,
 
 	move_lock_mem_cgroup(from, &flags);
 
-	if (!anon && page_mapped(page)) {
-		/* Update mapped_file data for mem_cgroup */
-		preempt_disable();
-		__this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
-		__this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
-		preempt_enable();
-	}
+	if (!anon && page_mapped(page))
+		mem_cgroup_move_account_page_stat(from, to, nr_pages,
+			MEM_CGROUP_STAT_FILE_MAPPED);
+
+	if (PageWriteback(page))
+		mem_cgroup_move_account_page_stat(from, to, nr_pages,
+			MEM_CGROUP_STAT_WRITEBACK);
+
 	mem_cgroup_charge_statistics(from, page, anon, -nr_pages);
 
 	/* caller should have done css_get */
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 6c7b0187be8..f5236f804aa 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2143,11 +2143,17 @@ EXPORT_SYMBOL(account_page_dirtied);
 
 /*
  * Helper function for set_page_writeback family.
+ *
+ * The caller must hold mem_cgroup_begin/end_update_page_stat() lock
+ * while calling this function.
+ * See test_set_page_writeback for example.
+ *
  * NOTE: Unlike account_page_dirtied this does not rely on being atomic
  * wrt interrupts.
  */
 void account_page_writeback(struct page *page)
 {
+	mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
 	inc_zone_page_state(page, NR_WRITEBACK);
 }
 EXPORT_SYMBOL(account_page_writeback);
@@ -2364,7 +2370,10 @@ int test_clear_page_writeback(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
 	int ret;
+	bool locked;
+	unsigned long memcg_flags;
 
+	mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags);
 	if (mapping) {
 		struct backing_dev_info *bdi = mapping->backing_dev_info;
 		unsigned long flags;
@@ -2385,9 +2394,11 @@ int test_clear_page_writeback(struct page *page)
 		ret = TestClearPageWriteback(page);
 	}
 	if (ret) {
+		mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
 		dec_zone_page_state(page, NR_WRITEBACK);
 		inc_zone_page_state(page, NR_WRITTEN);
 	}
+	mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags);
 	return ret;
 }
 
@@ -2395,7 +2406,10 @@ int test_set_page_writeback(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
 	int ret;
+	bool locked;
+	unsigned long memcg_flags;
 
+	mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags);
 	if (mapping) {
 		struct backing_dev_info *bdi = mapping->backing_dev_info;
 		unsigned long flags;
@@ -2422,6 +2436,7 @@ int test_set_page_writeback(struct page *page)
 	}
 	if (!ret)
 		account_page_writeback(page);
+	mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags);
 	return ret;
 
 }