memcg: helper function for relcaim from shmem.

A new call, mem_cgroup_shrink_usage() is added for shmem handling and
relacing non-standard usage of mem_cgroup_charge/uncharge.

Now, shmem calls mem_cgroup_charge() just for reclaim some pages from
mem_cgroup.  In general, shmem is used by some process group and not for
global resource (like file caches).  So, it's reasonable to reclaim pages
from mem_cgroup where shmem is mainly used.

[hugh@veritas.com: shmem_getpage release page sooner]
[hugh@veritas.com: mem_cgroup_shrink_usage css_put]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Cc: Paul Menage <menage@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/memcontrol.h

@@ -37,6 +37,8 @@ extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 extern void mem_cgroup_uncharge_page(struct page *page);
 extern void mem_cgroup_uncharge_cache_page(struct page *page);
 extern void mem_cgroup_move_lists(struct page *page, bool active);
+extern int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask);
+
 extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 					struct list_head *dst,
 					unsigned long *scanned, int order,
@@ -102,6 +104,11 @@ static inline void mem_cgroup_uncharge_cache_page(struct page *page)
 {
 }
 
+static inline int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
+{
+	return 0;
+}
+
 static inline void mem_cgroup_move_lists(struct page *page, bool active)
 {
 }

mm/memcontrol.c

@@ -780,6 +780,32 @@ void mem_cgroup_end_migration(struct page *newpage)
 		mem_cgroup_uncharge_page(newpage);
 }
 
+/*
+ * A call to try to shrink memory usage under specified resource controller.
+ * This is typically used for page reclaiming for shmem for reducing side
+ * effect of page allocation from shmem, which is used by some mem_cgroup.
+ */
+int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
+{
+	struct mem_cgroup *mem;
+	int progress = 0;
+	int retry = MEM_CGROUP_RECLAIM_RETRIES;
+
+	rcu_read_lock();
+	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	css_get(&mem->css);
+	rcu_read_unlock();
+
+	do {
+		progress = try_to_free_mem_cgroup_pages(mem, gfp_mask);
+	} while (!progress && --retry);
+
+	css_put(&mem->css);
+	if (!retry)
+		return -ENOMEM;
+	return 0;
+}
+
 /*
  * This routine traverse page_cgroup in given list and drop them all.
  * *And* this routine doesn't reclaim page itself, just removes page_cgroup.

mm/shmem.c

@@ -1315,17 +1315,14 @@ repeat:
 			shmem_swp_unmap(entry);
 			spin_unlock(&info->lock);
 			unlock_page(swappage);
+			page_cache_release(swappage);
 			if (error == -ENOMEM) {
 				/* allow reclaim from this memory cgroup */
-				error = mem_cgroup_cache_charge(swappage,
+				error = mem_cgroup_shrink_usage(current->mm,
-					current->mm, gfp & ~__GFP_HIGHMEM);
+								gfp);
-				if (error) {
+				if (error)
-					page_cache_release(swappage);
 					goto failed;
 			}
-				mem_cgroup_uncharge_cache_page(swappage);
-			}
-			page_cache_release(swappage);
 			goto repeat;
 		}
 	} else if (sgp == SGP_READ && !filepage) {