mm: memcontrol: fix missed end-writeback page accounting

Commit 0a31bc97c80c ("mm: memcontrol: rewrite uncharge API") changed
page migration to uncharge the old page right away.  The page is locked,
unmapped, truncated, and off the LRU, but it could race with writeback
ending, which then doesn't unaccount the page properly:

test_clear_page_writeback()              migration
                                           wait_on_page_writeback()
  TestClearPageWriteback()
                                           mem_cgroup_migrate()
                                             clear PCG_USED
  mem_cgroup_update_page_stat()
    if (PageCgroupUsed(pc))
      decrease memcg pages under writeback

  release pc->mem_cgroup->move_lock

The per-page statistics interface is heavily optimized to avoid a
function call and a lookup_page_cgroup() in the file unmap fast path,
which means it doesn't verify whether a page is still charged before
clearing PageWriteback() and it has to do it in the stat update later.

Rework it so that it looks up the page's memcg once at the beginning of
the transaction and then uses it throughout.  The charge will be
verified before clearing PageWriteback() and migration can't uncharge
the page as long as that is still set.  The RCU lock will protect the
memcg past uncharge.

As far as losing the optimization goes, the following test results are
from a microbenchmark that maps, faults, and unmaps a 4GB sparse file
three times in a nested fashion, so that there are two negative passes
that don't account but still go through the new transaction overhead.
There is no actual difference:

 old:     33.195102545 seconds time elapsed       ( +-  0.01% )
 new:     33.199231369 seconds time elapsed       ( +-  0.03% )

The time spent in page_remove_rmap()'s callees still adds up to the
same, but the time spent in the function itself seems reduced:

     # Children      Self  Command        Shared Object       Symbol
 old:     0.12%     0.11%  filemapstress  [kernel.kallsyms]   [k] page_remove_rmap
 new:     0.12%     0.08%  filemapstress  [kernel.kallsyms]   [k] page_remove_rmap

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: <stable@vger.kernel.org>	[3.17.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 17 insertions, 41 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 19df5d857411..6b75640ef5ab 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -139,48 +139,23 @@ static inline bool mem_cgroup_disabled(void)
         return false;
 }
 
-void __mem_cgroup_begin_update_page_stat(struct page *page, bool *locked,
-                                         unsigned long *flags);
-
-extern atomic_t memcg_moving;
-
-static inline void mem_cgroup_begin_update_page_stat(struct page *page,
-                                        bool *locked, unsigned long *flags)
-{
-        if (mem_cgroup_disabled())
-                return;
-        rcu_read_lock();
-        *locked = false;
-        if (atomic_read(&memcg_moving))
-                __mem_cgroup_begin_update_page_stat(page, locked, flags);
-}
-
-void __mem_cgroup_end_update_page_stat(struct page *page,
-                                unsigned long *flags);
-static inline void mem_cgroup_end_update_page_stat(struct page *page,
-                                        bool *locked, unsigned long *flags)
-{
-        if (mem_cgroup_disabled())
-                return;
-        if (*locked)
-                __mem_cgroup_end_update_page_stat(page, flags);
-        rcu_read_unlock();
-}
-
-void mem_cgroup_update_page_stat(struct page *page,
-                                 enum mem_cgroup_stat_index idx,
-                                 int val);
-
-static inline void mem_cgroup_inc_page_stat(struct page *page,
+struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, bool *locked,
+                                              unsigned long *flags);
+void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool locked,
+                              unsigned long flags);
+void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
+                                 enum mem_cgroup_stat_index idx, int val);
+
+static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg,
                                             enum mem_cgroup_stat_index idx)
 {
-        mem_cgroup_update_page_stat(page, idx, 1);
+        mem_cgroup_update_page_stat(memcg, idx, 1);
 }
 
-static inline void mem_cgroup_dec_page_stat(struct page *page,
+static inline void mem_cgroup_dec_page_stat(struct mem_cgroup *memcg,
                                             enum mem_cgroup_stat_index idx)
 {
-        mem_cgroup_update_page_stat(page, idx, -1);
+        mem_cgroup_update_page_stat(memcg, idx, -1);
 }
 
 unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
@@ -315,13 +290,14 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 {
 }
 
-static inline void mem_cgroup_begin_update_page_stat(struct page *page,
+static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page,
                                         bool *locked, unsigned long *flags)
 {
+        return NULL;
 }
 
-static inline void mem_cgroup_end_update_page_stat(struct page *page,
-                                        bool *locked, unsigned long *flags)
+static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg,
+                                        bool locked, unsigned long flags)
 {
 }
 
@@ -343,12 +319,12 @@ static inline bool mem_cgroup_oom_synchronize(bool wait)
         return false;
 }
 
-static inline void mem_cgroup_inc_page_stat(struct page *page,
+static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg,
                                             enum mem_cgroup_stat_index idx)
 {
 }
 
-static inline void mem_cgroup_dec_page_stat(struct page *page,
+static inline void mem_cgroup_dec_page_stat(struct mem_cgroup *memcg,
                                             enum mem_cgroup_stat_index idx)
 {
 }