memcg: remove PCG_CACHE page_cgroup flag
We record 'the page is cache' with the PCG_CACHE bit in page_cgroup.
Here, "CACHE" means anonymous user pages (and SwapCache). This doesn't
include shmem.
Considering callers, at charge/uncharge, the caller should know what the
page is and we don't need to record it by using one bit per page.
This patch removes PCG_CACHE bit and make callers of
mem_cgroup_charge_statistics() to specify what the page is.
About page migration: Mapping of the used page is not touched during migra
tion (see page_remove_rmap) so we can rely on it and push the correct
charge type down to __mem_cgroup_uncharge_common from end_migration for
unused page. The force flag was misleading was abused for skipping the
needless page_mapped() / PageCgroupMigration() check, as we know the
unused page is no longer mapped and cleared the migration flag just a few
lines up. But doing the checks is no biggie and it's not worth adding
another flag just to skip them.
[akpm@linux-foundation.org: checkpatch fixes]
[hughd@google.com: fix PageAnon uncharging]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ying Han <yinghan@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 69af5d5..88113ee 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -690,15 +690,19 @@
}
static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
- bool file, int nr_pages)
+ bool anon, int nr_pages)
{
preempt_disable();
- if (file)
- __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],
+ /*
+ * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is
+ * counted as CACHE even if it's on ANON LRU.
+ */
+ if (anon)
+ __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS],
nr_pages);
else
- __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS],
+ __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],
nr_pages);
/* pagein of a big page is an event. So, ignore page size */
@@ -2442,6 +2446,7 @@
{
struct zone *uninitialized_var(zone);
bool was_on_lru = false;
+ bool anon;
lock_page_cgroup(pc);
if (unlikely(PageCgroupUsed(pc))) {
@@ -2477,19 +2482,7 @@
* 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;
- }
+ SetPageCgroupUsed(pc);
if (lrucare) {
if (was_on_lru) {
@@ -2500,7 +2493,12 @@
spin_unlock_irq(&zone->lru_lock);
}
- mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), nr_pages);
+ if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
+ anon = true;
+ else
+ anon = false;
+
+ mem_cgroup_charge_statistics(memcg, anon, nr_pages);
unlock_page_cgroup(pc);
/*
@@ -2565,6 +2563,7 @@
{
unsigned long flags;
int ret;
+ bool anon = PageAnon(page);
VM_BUG_ON(from == to);
VM_BUG_ON(PageLRU(page));
@@ -2593,14 +2592,14 @@
__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, anon, -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, anon, nr_pages);
/*
* We charges against "to" which may not have any tasks. Then, "to"
* can be under rmdir(). But in current implementation, caller of
@@ -2921,6 +2920,7 @@
struct mem_cgroup *memcg = NULL;
unsigned int nr_pages = 1;
struct page_cgroup *pc;
+ bool anon;
if (mem_cgroup_disabled())
return NULL;
@@ -2946,8 +2946,12 @@
if (!PageCgroupUsed(pc))
goto unlock_out;
+ anon = PageAnon(page);
+
switch (ctype) {
case MEM_CGROUP_CHARGE_TYPE_MAPPED:
+ anon = true;
+ /* fallthrough */
case MEM_CGROUP_CHARGE_TYPE_DROP:
/* See mem_cgroup_prepare_migration() */
if (page_mapped(page) || PageCgroupMigration(pc))
@@ -2964,7 +2968,7 @@
break;
}
- mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), -nr_pages);
+ mem_cgroup_charge_statistics(memcg, anon, -nr_pages);
ClearPageCgroupUsed(pc);
/*
@@ -3271,6 +3275,7 @@
{
struct page *used, *unused;
struct page_cgroup *pc;
+ bool anon;
if (!memcg)
return;
@@ -3292,8 +3297,10 @@
lock_page_cgroup(pc);
ClearPageCgroupMigration(pc);
unlock_page_cgroup(pc);
-
- __mem_cgroup_uncharge_common(unused, MEM_CGROUP_CHARGE_TYPE_FORCE);
+ anon = PageAnon(used);
+ __mem_cgroup_uncharge_common(unused,
+ anon ? MEM_CGROUP_CHARGE_TYPE_MAPPED
+ : MEM_CGROUP_CHARGE_TYPE_CACHE);
/*
* If a page is a file cache, radix-tree replacement is very atomic
@@ -3303,7 +3310,7 @@
* and USED bit check in mem_cgroup_uncharge_page() will do enough
* check. (see prepare_charge() also)
*/
- if (PageAnon(used))
+ if (anon)
mem_cgroup_uncharge_page(used);
/*
* At migration, we may charge account against cgroup which has no
@@ -3333,7 +3340,7 @@
/* 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, false, -1);
ClearPageCgroupUsed(pc);
unlock_page_cgroup(pc);