mm: list_lru: replace linear array with xarray

If we run 10k containers in the system, the size of the
list_lru_memcg->lrus can be ~96KB per list_lru.  When we decrease the
number containers, the size of the array will not be shrinked.  It is
not scalable.  The xarray is a good choice for this case.  We can save a
lot of memory when there are tens of thousands continers in the system.
If we use xarray, we also can remove the logic code of resizing array,
which can simplify the code.

[akpm@linux-foundation.org: remove unused local]

Link: https://lkml.kernel.org/r/20220228122126.37293-13-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Cc: Alex Shi <alexs@kernel.org>
Cc: Anna Schumaker <Anna.Schumaker@Netapp.com>
Cc: Chao Yu <chao@kernel.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Fam Zheng <fam.zheng@bytedance.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kari Argillander <kari.argillander@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 5 insertions, 72 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c36b0a0dbc195..68eb62d10c488 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -351,42 +351,17 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
  * This will be used as a shrinker list's index.
  * The main reason for not using cgroup id for this:
  *  this works better in sparse environments, where we have a lot of memcgs,
- *  but only a few kmem-limited. Or also, if we have, for instance, 200
- *  memcgs, and none but the 200th is kmem-limited, we'd have to have a
- *  200 entry array for that.
- *
- * The current size of the caches array is stored in memcg_nr_cache_ids. It
- * will double each time we have to increase it.
+ *  but only a few kmem-limited.
  */
 static DEFINE_IDA(memcg_cache_ida);
-int memcg_nr_cache_ids;
-
-/* Protects memcg_nr_cache_ids */
-static DECLARE_RWSEM(memcg_cache_ids_sem);
-
-void memcg_get_cache_ids(void)
-{
-	down_read(&memcg_cache_ids_sem);
-}
-
-void memcg_put_cache_ids(void)
-{
-	up_read(&memcg_cache_ids_sem);
-}
 
 /*
- * MIN_SIZE is different than 1, because we would like to avoid going through
- * the alloc/free process all the time. In a small machine, 4 kmem-limited
- * cgroups is a reasonable guess. In the future, it could be a parameter or
- * tunable, but that is strictly not necessary.
- *
  * MAX_SIZE should be as large as the number of cgrp_ids. Ideally, we could get
  * this constant directly from cgroup, but it is understandable that this is
  * better kept as an internal representation in cgroup.c. In any case, the
  * cgrp_id space is not getting any smaller, and we don't have to necessarily
  * increase ours as well if it increases.
  */
-#define MEMCG_CACHES_MIN_SIZE 4
 #define MEMCG_CACHES_MAX_SIZE MEM_CGROUP_ID_MAX
 
 /*
@@ -2944,49 +2919,6 @@ __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
 	return objcg;
 }
 
-static int memcg_alloc_cache_id(void)
-{
-	int id, size;
-	int err;
-
-	id = ida_simple_get(&memcg_cache_ida,
-			    0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL);
-	if (id < 0)
-		return id;
-
-	if (id < memcg_nr_cache_ids)
-		return id;
-
-	/*
-	 * There's no space for the new id in memcg_caches arrays,
-	 * so we have to grow them.
-	 */
-	down_write(&memcg_cache_ids_sem);
-
-	size = 2 * (id + 1);
-	if (size < MEMCG_CACHES_MIN_SIZE)
-		size = MEMCG_CACHES_MIN_SIZE;
-	else if (size > MEMCG_CACHES_MAX_SIZE)
-		size = MEMCG_CACHES_MAX_SIZE;
-
-	err = memcg_update_all_list_lrus(size);
-	if (!err)
-		memcg_nr_cache_ids = size;
-
-	up_write(&memcg_cache_ids_sem);
-
-	if (err) {
-		ida_simple_remove(&memcg_cache_ida, id);
-		return err;
-	}
-	return id;
-}
-
-static void memcg_free_cache_id(int id)
-{
-	ida_simple_remove(&memcg_cache_ida, id);
-}
-
 static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages)
 {
 	mod_memcg_state(memcg, MEMCG_KMEM, nr_pages);
@@ -3673,13 +3605,14 @@ static int memcg_online_kmem(struct mem_cgroup *memcg)
 	if (unlikely(mem_cgroup_is_root(memcg)))
 		return 0;
 
-	memcg_id = memcg_alloc_cache_id();
+	memcg_id = ida_alloc_max(&memcg_cache_ida, MEMCG_CACHES_MAX_SIZE - 1,
+				 GFP_KERNEL);
 	if (memcg_id < 0)
 		return memcg_id;
 
 	objcg = obj_cgroup_alloc();
 	if (!objcg) {
-		memcg_free_cache_id(memcg_id);
+		ida_free(&memcg_cache_ida, memcg_id);
 		return -ENOMEM;
 	}
 	objcg->memcg = memcg;
@@ -3723,7 +3656,7 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 	 */
 	memcg_reparent_list_lrus(memcg, parent);
 
-	memcg_free_cache_id(kmemcg_id);
+	ida_free(&memcg_cache_ida, kmemcg_id);
 }
 #else
 static int memcg_online_kmem(struct mem_cgroup *memcg)