[PATCH] memcg: remove PCG_CACHE

[KAMEZAWA Hiroyuki]

We record 'the page is cache' by PCG_CACHE bit to page_cgroup.
Here, "CACHE" means anonymous user pages (and SwapCache). This
doesn't include shmem.

Consdering callers, at charge/uncharge, the caller should know
what  the page is and we don't need to record it by using 1bit
per page.

This patch removes PCG_CACHE bit and make callers of
mem_cgroup_charge_statistics() to specify what the page is.

Changelog since RFC.
 - rebased onto memcg-devel
 - rename 'file' to 'not_rss'
 - some cleanup and added comment.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
---
 include/linux/page_cgroup.h |    8 +-----
 mm/memcontrol.c             |   55 ++++++++++++++++++++++++++----------------
 2 files changed, 35 insertions(+), 28 deletions(-)

diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index a2d1177..1060292 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -4,7 +4,6 @@
 enum {
 	/* flags for mem_cgroup */
 	PCG_LOCK,  /* Lock for pc->mem_cgroup and following bits. */
-	PCG_CACHE, /* charged as cache */
 	PCG_USED, /* this object is in use. */
 	PCG_MIGRATION, /* under page migration */
 	/* flags for mem_cgroup and file and I/O status */
@@ -64,11 +63,6 @@ static inline void ClearPageCgroup##uname(struct page_cgroup *pc)	\
 static inline int TestClearPageCgroup##uname(struct page_cgroup *pc)	\
 	{ return test_and_clear_bit(PCG_##lname, &pc->flags);  }
 
-/* Cache flag is set only once (at allocation) */
-TESTPCGFLAG(Cache, CACHE)
-CLEARPCGFLAG(Cache, CACHE)
-SETPCGFLAG(Cache, CACHE)
-
 TESTPCGFLAG(Used, USED)
 CLEARPCGFLAG(Used, USED)
 SETPCGFLAG(Used, USED)
@@ -85,7 +79,7 @@ static inline void lock_page_cgroup(struct page_cgroup *pc)
 {
 	/*
 	 * Don't take this lock in IRQ context.
-	 * This lock is for pc->mem_cgroup, USED, CACHE, MIGRATION
+	 * This lock is for pc->mem_cgroup, USED, MIGRATION
 	 */
 	bit_spin_lock(PCG_LOCK, &pc->flags);
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index fb2dfc3..de7721d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -606,11 +606,16 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
 }
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
-					 bool file, int nr_pages)
+					 bool not_rss, int nr_pages)
 {
 	preempt_disable();
 
-	if (file)
+	/*
+	 * Here, RSS means 'mapped anon' and anon's SwapCache. Unlike LRU,
+	 * Shmem is not included to Anon. It' counted as 'file cache'
+	 * which tends to be shared between memcgs.
+	 */
+	if (not_rss)
 		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],
 				nr_pages);
 	else
@@ -2343,6 +2348,8 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 				       struct page_cgroup *pc,
 				       enum charge_type ctype)
 {
+	bool not_rss;
+
 	lock_page_cgroup(pc);
 	if (unlikely(PageCgroupUsed(pc))) {
 		unlock_page_cgroup(pc);
@@ -2362,21 +2369,15 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	 * See mem_cgroup_add_lru_list(), etc.
  	 */
 	smp_wmb();
-	switch (ctype) {
-	case MEM_CGROUP_CHARGE_TYPE_CACHE:
-	case MEM_CGROUP_CHARGE_TYPE_SHMEM:
-		SetPageCgroupCache(pc);
-		SetPageCgroupUsed(pc);
-		break;
-	case MEM_CGROUP_CHARGE_TYPE_MAPPED:
-		ClearPageCgroupCache(pc);
-		SetPageCgroupUsed(pc);
-		break;
-	default:
-		break;
-	}
 
-	mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), nr_pages);
+	SetPageCgroupUsed(pc);
+	if ((ctype == MEM_CGROUP_CHARGE_TYPE_CACHE) ||
+	    (ctype == MEM_CGROUP_CHARGE_TYPE_SHMEM))
+		not_rss = true;
+	else
+		not_rss = false;
+
+	mem_cgroup_charge_statistics(memcg, not_rss, nr_pages);
 	unlock_page_cgroup(pc);
 	WARN_ON_ONCE(PageLRU(page));
 	/*
@@ -2441,6 +2442,7 @@ static int mem_cgroup_move_account(struct page *page,
 {
 	unsigned long flags;
 	int ret;
+	bool not_rss = !PageAnon(page);
 
 	VM_BUG_ON(from == to);
 	VM_BUG_ON(PageLRU(page));
@@ -2469,14 +2471,14 @@ static int mem_cgroup_move_account(struct page *page,
 		__this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
 		preempt_enable();
 	}
-	mem_cgroup_charge_statistics(from, PageCgroupCache(pc), -nr_pages);
+	mem_cgroup_charge_statistics(from, not_rss, -nr_pages);
 	if (uncharge)
 		/* This is not "cancel", but cancel_charge does all we need. */
 		__mem_cgroup_cancel_charge(from, nr_pages);
 
 	/* caller should have done css_get */
 	pc->mem_cgroup = to;
-	mem_cgroup_charge_statistics(to, PageCgroupCache(pc), nr_pages);
+	mem_cgroup_charge_statistics(to, not_rss, nr_pages);
 	/*
 	 * We charges against "to" which may not have any tasks. Then, "to"
 	 * can be under rmdir(). But in current implementation, caller of
@@ -2824,6 +2826,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	struct mem_cgroup *memcg = NULL;
 	unsigned int nr_pages = 1;
 	struct page_cgroup *pc;
+	bool not_rss = false;
 
 	if (mem_cgroup_disabled())
 		return NULL;
@@ -2850,6 +2853,10 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 		goto unlock_out;
 
 	switch (ctype) {
+	case MEM_CGROUP_CHARGE_TYPE_CACHE:
+	case MEM_CGROUP_CHARGE_TYPE_SHMEM:
+		not_rss = true;
+		break;
 	case MEM_CGROUP_CHARGE_TYPE_MAPPED:
 	case MEM_CGROUP_CHARGE_TYPE_DROP:
 		/* See mem_cgroup_prepare_migration() */
@@ -2867,7 +2874,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 		break;
 	}
 
-	mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), -nr_pages);
+	mem_cgroup_charge_statistics(memcg, not_rss, -nr_pages);
 
 	ClearPageCgroupUsed(pc);
 	/*
@@ -2908,9 +2915,15 @@ void mem_cgroup_uncharge_page(struct page *page)
 
 void mem_cgroup_uncharge_cache_page(struct page *page)
 {
+	int ctype;
+
 	VM_BUG_ON(page_mapped(page));
 	VM_BUG_ON(page->mapping);
-	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
+	if (page_is_file_cache(page))
+		ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+	else
+		ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
+	__mem_cgroup_uncharge_common(page, ctype);
 }
 
 /*
@@ -3253,7 +3266,7 @@ void mem_cgroup_replace_page_cache(struct page *oldpage,
 	/* fix accounting on old pages */
 	lock_page_cgroup(pc);
 	memcg = pc->mem_cgroup;
-	mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), -1);
+	mem_cgroup_charge_statistics(memcg, true, -1);
 	ClearPageCgroupUsed(pc);
 	unlock_page_cgroup(pc);
 
-- 
1.7.4.1


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/