The patch titled
bugfix for memory cgroup controller: migration under memory controller fix
has been removed from the -mm tree. Its filename was
bugfix-for-memory-cgroup-controller-migration-under-memory-controller-fix.patch
This patch was dropped because it was merged into mainline or a subsystem tree
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: bugfix for memory cgroup controller: migration under memory controller fix
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
While using memory control cgroup, page-migration under it works as following.
==
1. uncharge all refs at try to unmap.
2. charge regs again remove_migration_ptes()
==
This is simple but has following problems.
==
The page is uncharged and charged back again if *mapped*.
- This means that cgroup before migration can be different from one after
migration
- If page is not mapped but charged as page cache, charge is just ignored
(because not mapped, it will not be uncharged before migration)
This is memory leak.
==
This patch tries to keep memory cgroup at page migration by increasing
one refcnt during it. 3 functions are added.
mem_cgroup_prepare_migration() --- increase refcnt of page->page_cgroup
mem_cgroup_end_migration() --- decrease refcnt of page->page_cgroup
mem_cgroup_page_migration() --- copy page->page_cgroup from old page to
new page.
During migration
- old page is under PG_locked.
- new page is under PG_locked, too.
- both old page and new page is not on LRU.
These 3 facts guarantee that page_cgroup() migration has no race.
Tested and worked well in x86_64/fake-NUMA box.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Cc: Pavel Emelianov <xemul@xxxxxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
Cc: Nick Piggin <nickpiggin@xxxxxxxxxxxx>
Cc: Kirill Korotaev <dev@xxxxx>
Cc: Herbert Poetzl <herbert@xxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Vaidyanathan Srinivasan <svaidy@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/memcontrol.h | 19 +++++++++++++++
mm/memcontrol.c | 43 +++++++++++++++++++++++++++++++++++
mm/migrate.c | 13 ++++++++--
3 files changed, 72 insertions(+), 3 deletions(-)
diff -puN include/linux/memcontrol.h~bugfix-for-memory-cgroup-controller-migration-under-memory-controller-fix include/linux/memcontrol.h
--- a/include/linux/memcontrol.h~bugfix-for-memory-cgroup-controller-migration-under-memory-controller-fix
+++ a/include/linux/memcontrol.h
@@ -60,6 +60,10 @@ static inline void mem_cgroup_uncharge_p
mem_cgroup_uncharge(page_get_page_cgroup(page));
}
+extern int mem_cgroup_prepare_migration(struct page *page);
+extern void mem_cgroup_end_migration(struct page *page);
+extern void mem_cgroup_page_migration(struct page *page, struct page *newpage);
+
#else /* CONFIG_CGROUP_MEM_CONT */
static inline void mm_init_cgroup(struct mm_struct *mm,
struct task_struct *p)
@@ -117,6 +121,21 @@ static inline int task_in_mem_cgroup(str
return 1;
}
+static inline int mem_cgroup_prepare_migration(struct page *page)
+{
+ return 0;
+}
+
+static inline void mem_cgroup_end_migration(struct page *page)
+{
+}
+
+static inline void
+mem_cgroup_page_migration(struct page *page, struct page *newpage)
+{
+}
+
+
#endif /* CONFIG_CGROUP_MEM_CONT */
#endif /* _LINUX_MEMCONTROL_H */
diff -puN mm/memcontrol.c~bugfix-for-memory-cgroup-controller-migration-under-memory-controller-fix mm/memcontrol.c
--- a/mm/memcontrol.c~bugfix-for-memory-cgroup-controller-migration-under-memory-controller-fix
+++ a/mm/memcontrol.c
@@ -492,6 +492,49 @@ void mem_cgroup_uncharge(struct page_cgr
}
}
}
+/*
+ * Returns non-zero if a page (under migration) has valid page_cgroup member.
+ * Refcnt of page_cgroup is incremented.
+ */
+
+int mem_cgroup_prepare_migration(struct page *page)
+{
+ struct page_cgroup *pc;
+ int ret = 0;
+ lock_page_cgroup(page);
+ pc = page_get_page_cgroup(page);
+ if (pc && atomic_inc_not_zero(&pc->ref_cnt))
+ ret = 1;
+ unlock_page_cgroup(page);
+ return ret;
+}
+
+void mem_cgroup_end_migration(struct page *page)
+{
+ struct page_cgroup *pc = page_get_page_cgroup(page);
+ mem_cgroup_uncharge(pc);
+}
+/*
+ * We know both *page* and *newpage* are now not-on-LRU and Pg_locked.
+ * And no race with uncharge() routines because page_cgroup for *page*
+ * has extra one reference by mem_cgroup_prepare_migration.
+ */
+
+void mem_cgroup_page_migration(struct page *page, struct page *newpage)
+{
+ struct page_cgroup *pc;
+retry:
+ pc = page_get_page_cgroup(page);
+ if (!pc)
+ return;
+ if (clear_page_cgroup(page, pc) != pc)
+ goto retry;
+ pc->page = newpage;
+ lock_page_cgroup(newpage);
+ page_assign_page_cgroup(newpage, pc);
+ unlock_page_cgroup(newpage);
+ return;
+}
int mem_cgroup_write_strategy(char *buf, unsigned long long *tmp)
{
diff -puN mm/migrate.c~bugfix-for-memory-cgroup-controller-migration-under-memory-controller-fix mm/migrate.c
--- a/mm/migrate.c~bugfix-for-memory-cgroup-controller-migration-under-memory-controller-fix
+++ a/mm/migrate.c
@@ -593,9 +593,10 @@ static int move_to_new_page(struct page
else
rc = fallback_migrate_page(mapping, newpage, page);
- if (!rc)
+ if (!rc) {
+ mem_cgroup_page_migration(page, newpage);
remove_migration_ptes(page, newpage);
- else
+ } else
newpage->mapping = NULL;
unlock_page(newpage);
@@ -614,6 +615,7 @@ static int unmap_and_move(new_page_t get
int *result = NULL;
struct page *newpage = get_new_page(page, private, &result);
int rcu_locked = 0;
+ int charge = 0;
if (!newpage)
return -ENOMEM;
@@ -673,14 +675,19 @@ static int unmap_and_move(new_page_t get
goto rcu_unlock;
}
+ charge = mem_cgroup_prepare_migration(page);
/* Establish migration ptes or remove ptes */
try_to_unmap(page, 1);
if (!page_mapped(page))
rc = move_to_new_page(newpage, page);
- if (rc)
+ if (rc) {
remove_migration_ptes(page, page);
+ if (charge)
+ mem_cgroup_end_migration(page);
+ } else if (charge)
+ mem_cgroup_end_migration(newpage);
rcu_unlock:
if (rcu_locked)
rcu_read_unlock();
_
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
origin.patch
enable-hotplug-memory-remove-for-ppc64.patch
add-arch-specific-walk_memory_remove-for-ppc64.patch
memory-hotplug-add-removable-to-sysfs-to-show-memblock-removability.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
