@@ -130,7 +130,8 @@ extern void mem_cgroup_print_oom_info(st
 
 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
 						  gfp_t gfp_mask, bool noswap,
-						  struct memcg_scanrecord *rec);
+						  struct memcg_scanrecord *rec,
+						  unsigned long nr_pages);
 extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 						gfp_t gfp_mask, bool noswap,
 						struct zone *zone,

@@ -1729,12 +1729,15 @@ static void mem_cgroup_record_scanstat(s
  * (other groups can be removed while we're walking....)
  *
  * If shrink==true, for avoiding to free too much, this returns immedieately.
+ * Given nr_pages tells how many pages are we over the soft limit or how many
+ * pages do we want to reclaim in the direct reclaim mode.
  */
 static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
 						struct zone *zone,
 						gfp_t gfp_mask,
 						unsigned long reclaim_options,
-						unsigned long *total_scanned)
+						unsigned long *total_scanned,
+						unsigned long nr_pages)
 {
 	struct mem_cgroup *victim;
 	int ret, total = 0;

@@ -1743,11 +1746,8 @@ static int mem_cgroup_hierarchical_recla
 	bool shrink = reclaim_options & MEM_CGROUP_RECLAIM_SHRINK;
 	bool check_soft = reclaim_options & MEM_CGROUP_RECLAIM_SOFT;
 	struct memcg_scanrecord rec;
-	unsigned long excess;
 	unsigned long scanned;
 
-	excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT;
-
 	/* If memsw_is_minimum==1, swap-out is of-no-use. */
 	if (!check_soft && !shrink && root_mem->memsw_is_minimum)
 		noswap = true;

@@ -1785,11 +1785,11 @@ static int mem_cgroup_hierarchical_recla
 				}
 				/*
 				 * We want to do more targeted reclaim.
-				 * excess >> 2 is not to excessive so as to
+				 * nr_pages >> 2 is not to excessive so as to
 				 * reclaim too much, nor too less that we keep
 				 * coming back to reclaim from this cgroup
 				 */
-				if (total >= (excess >> 2) ||
+				if (total >= (nr_pages >> 2) ||
 					(loop > MEM_CGROUP_MAX_RECLAIM_LOOPS)) {
 					css_put(&victim->css);
 					break;

@@ -1816,7 +1816,7 @@ static int mem_cgroup_hierarchical_recla
 			*total_scanned += scanned;
 		} else
 			ret = try_to_free_mem_cgroup_pages(victim, gfp_mask,
-						noswap, &rec);
+						noswap, &rec, nr_pages);
 		mem_cgroup_record_scanstat(&rec);
 		css_put(&victim->css);
 		/*

@@ -2331,8 +2331,14 @@ static int mem_cgroup_do_charge(struct m
 	if (!(gfp_mask & __GFP_WAIT))
 		return CHARGE_WOULDBLOCK;
 
+	/*
+	 * We are lying about nr_pages because we do not want to
+	 * reclaim too much for THP pages which should rather fallback
+	 * to small pages.
+	 */
 	ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, NULL,
-					      gfp_mask, flags, NULL);
+					      gfp_mask, flags, NULL,
+					      1);
 	if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
 		return CHARGE_RETRY;
 	/*

@@ -3567,7 +3573,8 @@ static int mem_cgroup_resize_limit(struc
 
 		mem_cgroup_hierarchical_reclaim(memcg, NULL, GFP_KERNEL,
 						MEM_CGROUP_RECLAIM_SHRINK,
-						NULL);
+						NULL,
+						(val-memlimit) >> PAGE_SHIFT);
 		curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
 		/* Usage is reduced ? */
   		if (curusage >= oldusage)

@@ -3628,7 +3635,8 @@ static int mem_cgroup_resize_memsw_limit
 		mem_cgroup_hierarchical_reclaim(memcg, NULL, GFP_KERNEL,
 						MEM_CGROUP_RECLAIM_NOSWAP |
 						MEM_CGROUP_RECLAIM_SHRINK,
-						NULL);
+						NULL,
+						(val-memswlimit) >> PAGE_SHIFT);
 		curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
 		/* Usage is reduced ? */
 		if (curusage >= oldusage)

@@ -3671,10 +3679,12 @@ unsigned long mem_cgroup_soft_limit_recl
 			break;
 
 		nr_scanned = 0;
+		excess = res_counter_soft_limit_excess(&mz->mem->res);
 		reclaimed = mem_cgroup_hierarchical_reclaim(mz->mem, zone,
 						gfp_mask,
 						MEM_CGROUP_RECLAIM_SOFT,
-						&nr_scanned);
+						&nr_scanned,
+						excess >> PAGE_SHIFT);
 		nr_reclaimed += reclaimed;
 		*total_scanned += nr_scanned;
 		spin_lock(&mctz->lock);

@@ -3871,7 +3881,8 @@ try_to_free:
 		rec.mem = mem;
 		rec.root = mem;
 		progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL,
-						false, &rec);
+						false, &rec,
+						mem->res.usage >> PAGE_SHIFT);
 		if (!progress) {
 			nr_retries--;
 			/* maybe some writeback is necessary */

@@ -2340,7 +2340,8 @@ unsigned long mem_cgroup_shrink_node_zon
 unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 					   gfp_t gfp_mask,
 					   bool noswap,
-					   struct memcg_scanrecord *rec)
+					   struct memcg_scanrecord *rec,
+					   unsigned long nr_pages)
 {
 	struct zonelist *zonelist;
 	unsigned long nr_reclaimed;

@@ -2350,7 +2351,7 @@ unsigned long try_to_free_mem_cgroup_pag
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
 		.may_swap = !noswap,
-		.nr_to_reclaim = SWAP_CLUSTER_MAX,
+		.nr_to_reclaim = max_t(unsigned long, nr_pages, SWAP_CLUSTER_MAX),
 		.order = 0,
 		.mem_cgroup = mem_cont,
 		.memcg_record = rec,