mm: memcontrol: prepare objcg API for non-kmem usage

Pagecache pages are charged at the allocation time and holding a reference
to the original memory cgroup until being reclaimed.  Depending on the
memory pressure, specific patterns of the page sharing between different
cgroups and the cgroup creation and destruction rates, a large number of
dying memory cgroups can be pinned by pagecache pages.  It makes the page
reclaim less efficient and wastes memory.

We can convert LRU pages and most other raw memcg pins to the objcg
direction to fix this problem, and then the page->memcg will always point
to an object cgroup pointer.

Therefore, the infrastructure of objcg no longer only serves
CONFIG_MEMCG_KMEM.  In this patch, we move the infrastructure of the objcg
out of the scope of the CONFIG_MEMCG_KMEM so that the LRU pages can reuse
it to charge pages.

We know that the LRU pages are not accounted at the root level.  But the
page->memcg_data points to the root_mem_cgroup.  So the page->memcg_data
of the LRU pages always points to a valid pointer.  But the
root_mem_cgroup dose not have an object cgroup.  If we use obj_cgroup APIs
to charge the LRU pages, we should set the page->memcg_data to a root
object cgroup.  So we also allocate an object cgroup for the
root_mem_cgroup.

Link: https://lkml.kernel.org/r/20220621125658.64935-4-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Michal Koutný <mkoutny@suse.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Waiman Long <longman@redhat.com>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d0c0da7cafb7ef1ac6faad447ceebac162ee6c48..111eda6ff1ced4a7b2a76a64a40736b460c5f2ba 100644 (file)
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -321,10 +321,10 @@ struct mem_cgroup {
 
 #ifdef CONFIG_MEMCG_KMEM
        int kmemcg_id;
+#endif
        struct obj_cgroup __rcu *objcg;
        /* list of inherited objcgs, protected by objcg_lock */
        struct list_head objcg_list;
-#endif
 
        MEMCG_PADDING(_pad2_);
 

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index fc706d6fc26581726aaed366e7e4a02f95de9a81..3c489651d3124b9e010b7196fb9c325f3247a026 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -252,9 +252,9 @@ struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr)
        return container_of(vmpr, struct mem_cgroup, vmpressure);
 }
 
-#ifdef CONFIG_MEMCG_KMEM
 static DEFINE_SPINLOCK(objcg_lock);
 
+#ifdef CONFIG_MEMCG_KMEM
 bool mem_cgroup_kmem_disabled(void)
 {
        return cgroup_memory_nokmem;
@@ -263,12 +263,10 @@ bool mem_cgroup_kmem_disabled(void)
 static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
                                      unsigned int nr_pages);
 
-static void obj_cgroup_release(struct percpu_ref *ref)
+static void obj_cgroup_release_bytes(struct obj_cgroup *objcg)
 {
-       struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt);
        unsigned int nr_bytes;
        unsigned int nr_pages;
-       unsigned long flags;
 
        /*
         * At this point all allocated objects are freed, and
@@ -282,9 +280,9 @@ static void obj_cgroup_release(struct percpu_ref *ref)
         * 3) CPU1: a process from another memcg is allocating something,
         *          the stock if flushed,
         *          objcg->nr_charged_bytes = PAGE_SIZE - 92
-        * 5) CPU0: we do release this object,
+        * 4) CPU0: we do release this object,
         *          92 bytes are added to stock->nr_bytes
-        * 6) CPU0: stock is flushed,
+        * 5) CPU0: stock is flushed,
         *          92 bytes are added to objcg->nr_charged_bytes
         *
         * In the result, nr_charged_bytes == PAGE_SIZE.
@@ -296,6 +294,19 @@ static void obj_cgroup_release(struct percpu_ref *ref)
 
        if (nr_pages)
                obj_cgroup_uncharge_pages(objcg, nr_pages);
+}
+#else
+static inline void obj_cgroup_release_bytes(struct obj_cgroup *objcg)
+{
+}
+#endif
+
+static void obj_cgroup_release(struct percpu_ref *ref)
+{
+       struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt);
+       unsigned long flags;
+
+       obj_cgroup_release_bytes(objcg);
 
        spin_lock_irqsave(&objcg_lock, flags);
        list_del(&objcg->list);
@@ -324,10 +335,10 @@ static struct obj_cgroup *obj_cgroup_alloc(void)
        return objcg;
 }
 
-static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
-                                 struct mem_cgroup *parent)
+static void memcg_reparent_objcgs(struct mem_cgroup *memcg)
 {
        struct obj_cgroup *objcg, *iter;
+       struct mem_cgroup *parent = parent_mem_cgroup(memcg);
 
        objcg = rcu_replace_pointer(memcg->objcg, NULL, true);
 
@@ -346,6 +357,7 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
        percpu_ref_kill(&objcg->refcnt);
 }
 
+#ifdef CONFIG_MEMCG_KMEM
 /*
  * A lot of the calls to the cache allocation functions are expected to be
  * inlined by the compiler. Since the calls to memcg_slab_pre_alloc_hook() are
@@ -3651,21 +3663,12 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 #ifdef CONFIG_MEMCG_KMEM
 static int memcg_online_kmem(struct mem_cgroup *memcg)
 {
-       struct obj_cgroup *objcg;
-
        if (cgroup_memory_nokmem)
                return 0;
 
        if (unlikely(mem_cgroup_is_root(memcg)))
                return 0;
 
-       objcg = obj_cgroup_alloc();
-       if (!objcg)
-               return -ENOMEM;
-
-       objcg->memcg = memcg;
-       rcu_assign_pointer(memcg->objcg, objcg);
-
        static_branch_enable(&memcg_kmem_enabled_key);
 
        memcg->kmemcg_id = memcg->id.id;
@@ -3675,17 +3678,13 @@ static int memcg_online_kmem(struct mem_cgroup *memcg)
 
 static void memcg_offline_kmem(struct mem_cgroup *memcg)
 {
-       struct mem_cgroup *parent;
-
        if (cgroup_memory_nokmem)
                return;
 
        if (unlikely(mem_cgroup_is_root(memcg)))
                return;
 
-       parent = parent_mem_cgroup(memcg);
-       memcg_reparent_objcgs(memcg, parent);
-       memcg_reparent_list_lrus(memcg, parent);
+       memcg_reparent_list_lrus(memcg, parent_mem_cgroup(memcg));
 }
 #else
 static int memcg_online_kmem(struct mem_cgroup *memcg)
@@ -5190,8 +5189,8 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
        memcg->socket_pressure = jiffies;
 #ifdef CONFIG_MEMCG_KMEM
        memcg->kmemcg_id = -1;
-       INIT_LIST_HEAD(&memcg->objcg_list);
 #endif
+       INIT_LIST_HEAD(&memcg->objcg_list);
 #ifdef CONFIG_CGROUP_WRITEBACK
        INIT_LIST_HEAD(&memcg->cgwb_list);
        for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++)
@@ -5256,6 +5255,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
 {
        struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+       struct obj_cgroup *objcg;
 
        if (memcg_online_kmem(memcg))
                goto remove_id;
@@ -5268,6 +5268,13 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
        if (alloc_shrinker_info(memcg))
                goto offline_kmem;
 
+       objcg = obj_cgroup_alloc();
+       if (!objcg)
+               goto free_shrinker;
+
+       objcg->memcg = memcg;
+       rcu_assign_pointer(memcg->objcg, objcg);
+
        /* Online state pins memcg ID, memcg ID pins CSS */
        refcount_set(&memcg->id.ref, 1);
        css_get(css);
@@ -5276,6 +5283,8 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
                queue_delayed_work(system_unbound_wq, &stats_flush_dwork,
                                   2UL*HZ);
        return 0;
+free_shrinker:
+       free_shrinker_info(memcg);
 offline_kmem:
        memcg_offline_kmem(memcg);
 remove_id:
@@ -5303,6 +5312,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
        page_counter_set_min(&memcg->memory, 0);
        page_counter_set_low(&memcg->memory, 0);
 
+       memcg_reparent_objcgs(memcg);
        memcg_offline_kmem(memcg);
        reparent_shrinker_deferred(memcg);
        wb_memcg_offline(memcg);