The patch titled
Subject: memcg: remove PCG_CACHE page_cgroup flag
has been added to the -mm tree. Its filename is
memcg-remove-pcg_cache-page_cgroup-flag.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Subject: 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.
Consdering 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.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxx>
Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Ying Han <yinghan@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/page_cgroup.h | 8 ----
mm/memcontrol.c | 57 +++++++++++++++++++---------------
2 files changed, 33 insertions(+), 32 deletions(-)
diff -puN include/linux/page_cgroup.h~memcg-remove-pcg_cache-page_cgroup-flag include/linux/page_cgroup.h
--- a/include/linux/page_cgroup.h~memcg-remove-pcg_cache-page_cgroup-flag
+++ a/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##unam
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(stru
{
/*
* 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 -puN mm/memcontrol.c~memcg-remove-pcg_cache-page_cgroup-flag mm/memcontrol.c
--- a/mm/memcontrol.c~memcg-remove-pcg_cache-page_cgroup-flag
+++ a/mm/memcontrol.c
@@ -670,15 +670,19 @@ static unsigned long mem_cgroup_read_eve
}
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 */
@@ -2405,6 +2409,8 @@ static void __mem_cgroup_commit_charge(s
struct page_cgroup *pc,
enum charge_type ctype)
{
+ bool anon;
+
lock_page_cgroup(pc);
if (unlikely(PageCgroupUsed(pc))) {
unlock_page_cgroup(pc);
@@ -2424,21 +2430,14 @@ static void __mem_cgroup_commit_charge(s
* 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_MAPPED)
+ anon = true;
+ else
+ anon = false;
+
+ mem_cgroup_charge_statistics(memcg, anon, nr_pages);
unlock_page_cgroup(pc);
WARN_ON_ONCE(PageLRU(page));
/*
@@ -2503,6 +2502,7 @@ static int mem_cgroup_move_account(struc
{
unsigned long flags;
int ret;
+ bool anon = PageAnon(page);
VM_BUG_ON(from == to);
VM_BUG_ON(PageLRU(page));
@@ -2531,14 +2531,14 @@ static int mem_cgroup_move_account(struc
__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
@@ -2884,6 +2884,7 @@ __mem_cgroup_uncharge_common(struct page
struct mem_cgroup *memcg = NULL;
unsigned int nr_pages = 1;
struct page_cgroup *pc;
+ bool anon;
if (mem_cgroup_disabled())
return NULL;
@@ -2915,6 +2916,7 @@ __mem_cgroup_uncharge_common(struct page
/* See mem_cgroup_prepare_migration() */
if (page_mapped(page) || PageCgroupMigration(pc))
goto unlock_out;
+ anon = true;
break;
case MEM_CGROUP_CHARGE_TYPE_SWAPOUT:
if (!PageAnon(page)) { /* Shared memory */
@@ -2922,12 +2924,14 @@ __mem_cgroup_uncharge_common(struct page
goto unlock_out;
} else if (page_mapped(page)) /* Anon */
goto unlock_out;
+ anon = true;
break;
default:
+ anon = false;
break;
}
- mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), -nr_pages);
+ mem_cgroup_charge_statistics(memcg, anon, -nr_pages);
ClearPageCgroupUsed(pc);
/*
@@ -3251,6 +3255,7 @@ void mem_cgroup_end_migration(struct mem
{
struct page *used, *unused;
struct page_cgroup *pc;
+ bool anon;
if (!memcg)
return;
@@ -3272,8 +3277,10 @@ void mem_cgroup_end_migration(struct mem
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
@@ -3283,7 +3290,7 @@ void mem_cgroup_end_migration(struct mem
* 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
@@ -3313,7 +3320,7 @@ void mem_cgroup_replace_page_cache(struc
/* 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);
_
Subject: Subject: memcg: remove PCG_CACHE page_cgroup flag
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
origin.patch
mm-postpone-migrated-page-mapping-reset.patch
linux-next.patch
mm-oom-avoid-looping-when-chosen-thread-detaches-its-mm.patch
mm-oom-fold-oom_kill_task-into-oom_kill_process.patch
mm-oom-do-not-emit-oom-killer-warning-if-chosen-thread-is-already-exiting.patch
mm-add-rss-counters-consistency-check.patch
mm-vmscanc-cleanup-with-s-reclaim_mode-isolate_mode.patch
mm-make-get_mm_counter-static-inline.patch
memcg-replace-mem_cont-by-mem_res_ctlr.patch
memcg-replace-mem-and-mem_cont-stragglers.patch
memcg-lru_size-instead-of-mem_cgroup_zstat.patch
memcg-enum-lru_list-lru.patch
memcg-remove-redundant-returns.patch
memcg-remove-unnecessary-thp-check-in-page-stat-accounting.patch
idr-make-idr_get_next-good-for-rcu_read_lock.patch
cgroup-revert-ss_id_lock-to-spinlock.patch
memcg-let-css_get_next-rely-upon-rcu_read_lock.patch
memcg-remove-pcg_cache-page_cgroup-flag.patch
proc-speedup-proc-stat-handling.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
