mm: introduce kmem_cache_alloc_lru

We currently allocate scope for every memcg to be able to tracked on
every superblock instantiated in the system, regardless of whether that
superblock is even accessible to that memcg.

These huge memcg counts come from container hosts where memcgs are
confined to just a small subset of the total number of superblocks that
instantiated at any given point in time.

For these systems with huge container counts, list_lru does not need the
capability of tracking every memcg on every superblock.  What it comes
down to is that adding the memcg to the list_lru at the first insert.
So introduce kmem_cache_alloc_lru to allocate objects and its list_lru.
In the later patch, we will convert all inode and dentry allocation from
kmem_cache_alloc to kmem_cache_alloc_lru.

Link: https://lkml.kernel.org/r/20220228122126.37293-3-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>

3 files changed, 21 insertions, 0 deletions

diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 729a27b6ff53..ab912c49334f 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -56,6 +56,8 @@ struct list_lru {
 	struct list_head	list;
 	int			shrinker_id;
 	bool			memcg_aware;
+	/* protects ->mlrus->mlru[i] */
+	spinlock_t		lock;
 	/* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
 	struct list_lru_memcg	__rcu *mlrus;
 #endif
@@ -72,6 +74,8 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware,
 #define list_lru_init_memcg(lru, shrinker)		\
 	__list_lru_init((lru), true, NULL, shrinker)
 
+int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru,
+			 gfp_t gfp);
 int memcg_update_all_list_lrus(int num_memcgs);
 void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg);
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ef4b445392a9..b636732f0c14 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -524,6 +524,20 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
 	return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
 }
 
+static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
+{
+	struct mem_cgroup *memcg;
+
+	rcu_read_lock();
+retry:
+	memcg = obj_cgroup_memcg(objcg);
+	if (unlikely(!css_tryget(&memcg->css)))
+		goto retry;
+	rcu_read_unlock();
+
+	return memcg;
+}
+
 #ifdef CONFIG_MEMCG_KMEM
 /*
  * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set.
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 5b6193fd8bd9..e6addaf91afd 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -135,6 +135,7 @@
 
 #include <linux/kasan.h>
 
+struct list_lru;
 struct mem_cgroup;
 /*
  * struct kmem_cache related prototypes
@@ -416,6 +417,8 @@ static __always_inline unsigned int __kmalloc_index(size_t size,
 
 void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1);
 void *kmem_cache_alloc(struct kmem_cache *s, gfp_t flags) __assume_slab_alignment __malloc;
+void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
+			   gfp_t gfpflags) __assume_slab_alignment __malloc;
 void kmem_cache_free(struct kmem_cache *s, void *objp);
 
 /*