memcg: update threshold and softlimit at commit

Presently, move_task does "batched" precharge.  Because res_counter or
css's refcnt are not-scalable jobs for memcg, try_charge_()..  tend to be
done in batched manner if allowed.

Now, softlimit and threshold check their event counter in try_charge, but
the charge is not a per-page event.  And event counter is not updated at
charge().  Moreover, precharge doesn't pass "page" to try_charge() and
softlimit tree will be never updated until uncharge() causes an event."

So the best place to check the event counter is commit_charge().  This is
per-page event by its nature.  This patch move checks to there.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
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 9c9dfcf..006fe14 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1424,8 +1424,7 @@ static int __cpuinit memcg_stock_cpu_callback(struct notifier_block *nb,
  * oom-killer can be invoked.
  */
 static int __mem_cgroup_try_charge(struct mm_struct *mm,
-                       gfp_t gfp_mask, struct mem_cgroup **memcg,
-                       bool oom, struct page *page)
+                       gfp_t gfp_mask, struct mem_cgroup **memcg, bool oom)
 {
        struct mem_cgroup *mem, *mem_over_limit;
        int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
@@ -1463,7 +1462,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
                unsigned long flags = 0;
 
                if (consume_stock(mem))
-                       goto charged;
+                       goto done;
 
                ret = res_counter_charge(&mem->res, csize, &fail_res);
                if (likely(!ret)) {
@@ -1558,16 +1557,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
        }
        if (csize > PAGE_SIZE)
                refill_stock(mem, csize - PAGE_SIZE);
-charged:
-       /*
-        * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
-        * if they exceeds softlimit.
-        */
-       if (page && mem_cgroup_soft_limit_check(mem))
-               mem_cgroup_update_tree(mem, page);
 done:
-       if (mem_cgroup_threshold_check(mem))
-               mem_cgroup_threshold(mem);
        return 0;
 nomem:
        css_put(&mem->css);
@@ -1691,6 +1681,16 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
        mem_cgroup_charge_statistics(mem, pc, true);
 
        unlock_page_cgroup(pc);
+       /*
+        * "charge_statistics" updated event counter. Then, check it.
+        * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
+        * if they exceeds softlimit.
+        */
+       if (mem_cgroup_soft_limit_check(mem))
+               mem_cgroup_update_tree(mem, pc->page);
+       if (mem_cgroup_threshold_check(mem))
+               mem_cgroup_threshold(mem);
+
 }
 
 /**
@@ -1788,7 +1788,7 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc,
                goto put;
 
        parent = mem_cgroup_from_cont(pcg);
-       ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false, page);
+       ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false);
        if (ret || !parent)
                goto put_back;
 
@@ -1824,7 +1824,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
        prefetchw(pc);
 
        mem = memcg;
-       ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true, page);
+       ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true);
        if (ret || !mem)
                return ret;
 
@@ -1944,14 +1944,14 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
        if (!mem)
                goto charge_cur_mm;
        *ptr = mem;
-       ret = __mem_cgroup_try_charge(NULL, mask, ptr, true, page);
+       ret = __mem_cgroup_try_charge(NULL, mask, ptr, true);
        /* drop extra refcnt from tryget */
        css_put(&mem->css);
        return ret;
 charge_cur_mm:
        if (unlikely(!mm))
                mm = &init_mm;
-       return __mem_cgroup_try_charge(mm, mask, ptr, true, page);
+       return __mem_cgroup_try_charge(mm, mask, ptr, true);
 }
 
 static void
@@ -2340,8 +2340,7 @@ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr)
        unlock_page_cgroup(pc);
 
        if (mem) {
-               ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false,
-                                               page);
+               ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false);
                css_put(&mem->css);
        }
        *ptr = mem;
@@ -3872,8 +3871,7 @@ one_by_one:
                        batch_count = PRECHARGE_COUNT_AT_ONCE;
                        cond_resched();
                }
-               ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem,
-                                                               false, NULL);
+               ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false);
                if (ret || !mem)
                        /* mem_cgroup_clear_mc() will do uncharge later */
                        return -ENOMEM;