cgroups: use css id in swap cgroup for saving memory v5

Try to use CSS ID for records in swap_cgroup.  By this, on 64bit machine,
size of swap_cgroup goes down to 2 bytes from 8bytes.

This means, when 2GB of swap is equipped, (assume the page size is 4096bytes)

	From size of swap_cgroup = 2G/4k * 8 = 4Mbytes.
	To   size of swap_cgroup = 2G/4k * 2 = 1Mbytes.

Reduction is large.  Of course, there are trade-offs.  This CSS ID will
add overhead to swap-in/swap-out/swap-free.

But in general,
  - swap is a resource which the user tend to avoid use.
  - If swap is never used, swap_cgroup area is not used.
  - Reading traditional manuals, size of swap should be proportional to
    size of memory. Memory size of machine is increasing now.

I think reducing size of swap_cgroup makes sense.

Note:
  - ID->CSS lookup routine has no locks, it's under RCU-Read-Side.
  - memcg can be obsolete at rmdir() but not freed while refcnt from
    swap_cgroup is available.

Changelog v4->v5:
 - reworked on to memcg-charge-swapcache-to-proper-memcg.patch
Changlog ->v4:
 - fixed not configured case.
 - deleted unnecessary comments.
 - fixed NULL pointer bug.
 - fixed message in dmesg.

[nishimura@mxp.nes.nec.co.jp: css_tryget can be called twice in !PageCgroupUsed case]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 62 insertions, 12 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 81b0ae8..55dea59 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -991,10 +991,31 @@ nomem:
 	return -ENOMEM;
 }
 
+
+/*
+ * A helper function to get mem_cgroup from ID. must be called under
+ * rcu_read_lock(). The caller must check css_is_removed() or some if
+ * it's concern. (dropping refcnt from swap can be called against removed
+ * memcg.)
+ */
+static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
+{
+	struct cgroup_subsys_state *css;
+
+	/* ID 0 is unused ID */
+	if (!id)
+		return NULL;
+	css = css_lookup(&mem_cgroup_subsys, id);
+	if (!css)
+		return NULL;
+	return container_of(css, struct mem_cgroup, css);
+}
+
 static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page)
 {
 	struct mem_cgroup *mem;
 	struct page_cgroup *pc;
+	unsigned short id;
 	swp_entry_t ent;
 
 	VM_BUG_ON(!PageLocked(page));
@@ -1006,16 +1027,19 @@ static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page)
 	/*
 	 * Used bit of swapcache is solid under page lock.
 	 */
-	if (PageCgroupUsed(pc))
+	if (PageCgroupUsed(pc)) {
 		mem = pc->mem_cgroup;
-	else {
+		if (mem && !css_tryget(&mem->css))
+			mem = NULL;
+	} else {
 		ent.val = page_private(page);
-		mem = lookup_swap_cgroup(ent);
+		id = lookup_swap_cgroup(ent);
+		rcu_read_lock();
+		mem = mem_cgroup_lookup(id);
+		if (mem && !css_tryget(&mem->css))
+			mem = NULL;
+		rcu_read_unlock();
 	}
-	if (!mem)
-		return NULL;
-	if (!css_tryget(&mem->css))
-		return NULL;
 	return mem;
 }
 
@@ -1276,12 +1300,22 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 
 	if (do_swap_account && !ret && PageSwapCache(page)) {
 		swp_entry_t ent = {.val = page_private(page)};
+		unsigned short id;
 		/* avoid double counting */
-		mem = swap_cgroup_record(ent, NULL);
+		id = swap_cgroup_record(ent, 0);
+		rcu_read_lock();
+		mem = mem_cgroup_lookup(id);
 		if (mem) {
+			/*
+			 * We did swap-in. Then, this entry is doubly counted
+			 * both in mem and memsw. We uncharge it, here.
+			 * Recorded ID can be obsolete. We avoid calling
+			 * css_tryget()
+			 */
 			res_counter_uncharge(&mem->memsw, PAGE_SIZE);
 			mem_cgroup_put(mem);
 		}
+		rcu_read_unlock();
 	}
 	return ret;
 }
@@ -1346,13 +1380,21 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
 	 */
 	if (do_swap_account && PageSwapCache(page)) {
 		swp_entry_t ent = {.val = page_private(page)};
+		unsigned short id;
 		struct mem_cgroup *memcg;
-		memcg = swap_cgroup_record(ent, NULL);
+
+		id = swap_cgroup_record(ent, 0);
+		rcu_read_lock();
+		memcg = mem_cgroup_lookup(id);
 		if (memcg) {
+			/*
+			 * This recorded memcg can be obsolete one. So, avoid
+			 * calling css_tryget
+			 */
 			res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
 			mem_cgroup_put(memcg);
 		}
-
+		rcu_read_unlock();
 	}
 	/* add this page(page_cgroup) to the LRU we want. */
 
@@ -1473,7 +1515,7 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
 					MEM_CGROUP_CHARGE_TYPE_SWAPOUT);
 	/* record memcg information */
 	if (do_swap_account && memcg) {
-		swap_cgroup_record(ent, memcg);
+		swap_cgroup_record(ent, css_id(&memcg->css));
 		mem_cgroup_get(memcg);
 	}
 	if (memcg)
@@ -1488,15 +1530,23 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
 void mem_cgroup_uncharge_swap(swp_entry_t ent)
 {
 	struct mem_cgroup *memcg;
+	unsigned short id;
 
 	if (!do_swap_account)
 		return;
 
-	memcg = swap_cgroup_record(ent, NULL);
+	id = swap_cgroup_record(ent, 0);
+	rcu_read_lock();
+	memcg = mem_cgroup_lookup(id);
 	if (memcg) {
+		/*
+		 * We uncharge this because swap is freed.
+		 * This memcg can be obsolete one. We avoid calling css_tryget
+		 */
 		res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
 		mem_cgroup_put(memcg);
 	}
+	rcu_read_unlock();
 }
 #endif