mm: move page->mem_cgroup bad page handling into generic code

Now that the external page_cgroup data structure and its lookup is
gone, let the generic bad_page() check for page->mem_cgroup sanity.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: David S. Miller <davem@davemloft.net>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Tejun Heo <tj@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index c4d080875164624653d223df95809027d62ef00d..6ea9f919e8881dcef92fe52bd664f375707bb402 100644 (file)
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -173,10 +173,6 @@ static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
 void mem_cgroup_split_huge_fixup(struct page *head);
 #endif
 
-#ifdef CONFIG_DEBUG_VM
-bool mem_cgroup_bad_page_check(struct page *page);
-void mem_cgroup_print_bad_page(struct page *page);
-#endif
 #else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
@@ -346,19 +342,6 @@ void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 }
 #endif /* CONFIG_MEMCG */
 
-#if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM)
-static inline bool
-mem_cgroup_bad_page_check(struct page *page)
-{
-       return false;
-}
-
-static inline void
-mem_cgroup_print_bad_page(struct page *page)
-{
-}
-#endif
-
 enum {
        UNDER_LIMIT,
        SOFT_LIMIT,

diff --git a/init/Kconfig b/init/Kconfig
index 46768752130da48d45344ef6051642d3518ad38b..7e9fbd48e2abc2a9ca32ae7b371e7f2525d54891 100644 (file)
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -983,18 +983,6 @@ config MEMCG
          Provides a memory resource controller that manages both anonymous
          memory and page cache. (See Documentation/cgroups/memory.txt)
 
-         Note that setting this option increases fixed memory overhead
-         associated with each page of memory in the system. By this,
-         8(16)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory
-         usage tracking struct at boot. Total amount of this is printed out
-         at boot.
-
-         Only enable when you're ok with these trade offs and really
-         sure you need the memory resource controller. Even when you enable
-         this, you can set "cgroup_disable=memory" at your boot option to
-         disable memory resource controller and you can avoid overheads.
-         (and lose benefits of memory resource controller)
-
 config MEMCG_SWAP
        bool "Memory Resource Controller Swap Extension"
        depends on MEMCG && SWAP

diff --git a/mm/debug.c b/mm/debug.c
index 5ce45c9a29b5229b1b7161e2bf8aa4d6536a6473..0e58f3211f89702e5e1faaf6fd4fa4aa5ba9b729 100644 (file)
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -95,7 +95,10 @@ void dump_page_badflags(struct page *page, const char *reason,
                dump_flags(page->flags & badflags,
                                pageflag_names, ARRAY_SIZE(pageflag_names));
        }
-       mem_cgroup_print_bad_page(page);
+#ifdef CONFIG_MEMCG
+       if (page->mem_cgroup)
+               pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup);
+#endif
 }
 
 void dump_page(struct page *page, const char *reason)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ab270e34ba3ef45f00003ebf5d9bd22033ca5f60..1869cb64d0891983fad4eef55bb17cb331505fc2 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3157,21 +3157,6 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
 }
 #endif
 
-#ifdef CONFIG_DEBUG_VM
-bool mem_cgroup_bad_page_check(struct page *page)
-{
-       if (mem_cgroup_disabled())
-               return false;
-
-       return page->mem_cgroup != NULL;
-}
-
-void mem_cgroup_print_bad_page(struct page *page)
-{
-       pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup);
-}
-#endif
-
 static DEFINE_MUTEX(memcg_limit_mutex);
 
 static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 22cfdeffbf691d9f1a5c5ebb00788ce3e7a8b103..a7198c065999c564f41be65ba7e66899913c375b 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -640,8 +640,10 @@ static inline int free_pages_check(struct page *page)
                bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
                bad_flags = PAGE_FLAGS_CHECK_AT_FREE;
        }
-       if (unlikely(mem_cgroup_bad_page_check(page)))
-               bad_reason = "cgroup check failed";
+#ifdef CONFIG_MEMCG
+       if (unlikely(page->mem_cgroup))
+               bad_reason = "page still charged to cgroup";
+#endif
        if (unlikely(bad_reason)) {
                bad_page(page, bad_reason, bad_flags);
                return 1;
@@ -900,8 +902,10 @@ static inline int check_new_page(struct page *page)
                bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set";
                bad_flags = PAGE_FLAGS_CHECK_AT_PREP;
        }
-       if (unlikely(mem_cgroup_bad_page_check(page)))
-               bad_reason = "cgroup check failed";
+#ifdef CONFIG_MEMCG
+       if (unlikely(page->mem_cgroup))
+               bad_reason = "page still charged to cgroup";
+#endif
        if (unlikely(bad_reason)) {
                bad_page(page, bad_reason, bad_flags);
                return 1;