linux-kernel - [PATCH v2 4/5] mm: kmem: scoped objcg protection

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Mon,  9 Oct 2023 17:09:28 -0700
From:   Roman Gushchin <roman.gushchin@...ux.dev>
To:     linux-mm@...ck.org
Cc:     linux-kernel@...r.kernel.org, cgroups@...r.kernel.org,
        Johannes Weiner <hannes@...xchg.org>,
        Michal Hocko <mhocko@...nel.org>,
        Shakeel Butt <shakeelb@...gle.com>,
        Muchun Song <muchun.song@...ux.dev>,
        Dennis Zhou <dennis@...nel.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        David Rientjes <rientjes@...gle.com>,
        Vlastimil Babka <vbabka@...e.cz>,
        Naresh Kamboju <naresh.kamboju@...aro.org>,
        Roman Gushchin <roman.gushchin@...ux.dev>
Subject: [PATCH v2 4/5] 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.

Signed-off-by: Roman Gushchin (Cruise) <roman.gushchin@...ux.dev>
---
 include/linux/memcontrol.h |  6 +++++
 mm/memcontrol.c            | 47 ++++++++++++++++++++++++++++++++++++--
 mm/slab.h                  | 10 +++-----
 3 files changed, 54 insertions(+), 9 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 277690af383d..0e53b890f063 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1769,6 +1769,12 @@ 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, refer to the implementation for the
+ * additional details.
+ */
+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);
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 490c5f67be79..84724fb875ce 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3079,6 +3079,49 @@ __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;
@@ -3173,15 +3216,15 @@ 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;
 }
diff --git a/mm/slab.h b/mm/slab.h
index 799a315695c6..8cd3294fedf5 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -484,7 +484,7 @@ 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();
+	objcg = current_obj_cgroup();
 	if (!objcg)
 		return true;
 
@@ -497,17 +497,14 @@ 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 +539,6 @@ 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,
-- 
2.42.0