mm: kmem: scoped objcg protection

Switch to a scope-based protection of the objcg pointer on slab/kmem
allocation paths.  Instead of using the get_() semantics in the
pre-allocation hook and put the reference afterwards, let's rely on the
fact that objcg is pinned by the scope.

It's possible because:
1) if the objcg is received from the current task struct, the task is
   keeping a reference to the objcg.
2) if the objcg is received from an active memcg (remote charging),
   the memcg is pinned by the scope and has a reference to the
   corresponding objcg.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Roman Gushchin (Cruise) <[email protected]>
Tested-by: Naresh Kamboju <[email protected]>
Acked-by: Shakeel Butt <[email protected]>
Reviewed-by: Vlastimil Babka <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Dennis Zhou <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Muchun Song <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

Author: rgushchin

include/linux/memcontrol.h

@@ -1796,6 +1796,15 @@ bool mem_cgroup_kmem_disabled(void);
 int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order);
 void __memcg_kmem_uncharge_page(struct page *page, int order);
 
+/*
+ * The returned objcg pointer is safe to use without additional
+ * protection within a scope. The scope is defined either by
+ * the current task (similar to the "current" global variable)
+ * or by set_active_memcg() pair.
+ * Please, use obj_cgroup_get() to get a reference if the pointer
+ * needs to be used outside of the local scope.
+ */
+struct obj_cgroup *current_obj_cgroup(void);
 struct obj_cgroup *get_obj_cgroup_from_current(void);
 struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio);
 

include/linux/sched/mm.h

@@ -403,6 +403,10 @@ DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg);
  * __GFP_ACCOUNT allocations till the end of the scope will be charged to the
  * given memcg.
  *
+ * Please, make sure that caller has a reference to the passed memcg structure,
+ * so its lifetime is guaranteed to exceed the scope between two
+ * set_active_memcg() calls.
+ *
  * NOTE: This function can nest. Users must save the return value and
  * reset the previous value after their own charging scope is over.
  */

mm/memcontrol.c

@@ -3170,6 +3170,49 @@ __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
 	return objcg;
 }
 
+__always_inline struct obj_cgroup *current_obj_cgroup(void)
+{
+	struct mem_cgroup *memcg;
+	struct obj_cgroup *objcg;
+
+	if (in_task()) {
+		memcg = current->active_memcg;
+		if (unlikely(memcg))
+			goto from_memcg;
+
+		objcg = READ_ONCE(current->objcg);
+		if (unlikely((unsigned long)objcg & CURRENT_OBJCG_UPDATE_FLAG))
+			objcg = current_objcg_update();
+		/*
+		 * Objcg reference is kept by the task, so it's safe
+		 * to use the objcg by the current task.
+		 */
+		return objcg;
+	}
+
+	memcg = this_cpu_read(int_active_memcg);
+	if (unlikely(memcg))
+		goto from_memcg;
+
+	return NULL;
+
+from_memcg:
+	for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) {
+		/*
+		 * Memcg pointer is protected by scope (see set_active_memcg())
+		 * and is pinning the corresponding objcg, so objcg can't go
+		 * away and can be used within the scope without any additional
+		 * protection.
+		 */
+		objcg = rcu_dereference_check(memcg->objcg, 1);
+		if (likely(objcg))
+			break;
+		objcg = NULL;
+	}
+
+	return objcg;
+}
+
 struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio)
 {
 	struct obj_cgroup *objcg;
@@ -3264,15 +3307,15 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
 	struct obj_cgroup *objcg;
 	int ret = 0;
 
-	objcg = get_obj_cgroup_from_current();
+	objcg = current_obj_cgroup();
 	if (objcg) {
 		ret = obj_cgroup_charge_pages(objcg, gfp, 1 << order);
 		if (!ret) {
+			obj_cgroup_get(objcg);
 			page->memcg_data = (unsigned long)objcg |
 				MEMCG_DATA_KMEM;
 			return 0;
 		}
-		obj_cgroup_put(objcg);
 	}
 	return ret;
 }

mm/slab.h

@@ -484,7 +484,12 @@ static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
 	if (!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT))
 		return true;
 
-	objcg = get_obj_cgroup_from_current();
+	/*
+	 * The obtained objcg pointer is safe to use within the current scope,
+	 * defined by current task or set_active_memcg() pair.
+	 * obj_cgroup_get() is used to get a permanent reference.
+	 */
+	objcg = current_obj_cgroup();
 	if (!objcg)
 		return true;
 
@@ -497,17 +502,14 @@ static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
 		css_put(&memcg->css);
 
 		if (ret)
-			goto out;
+			return false;
 	}
 
 	if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s)))
-		goto out;
+		return false;
 
 	*objcgp = objcg;
 	return true;
-out:
-	obj_cgroup_put(objcg);
-	return false;
 }
 
 static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
@@ -542,7 +544,6 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 			obj_cgroup_uncharge(objcg, obj_full_size(s));
 		}
 	}
-	obj_cgroup_put(objcg);
 }
 
 static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,