From: Vasily Averin <vvs@openvz.org>
Date: Fri, 3 Jun 2022 04:19:43 +0000 (+0300)
Subject: net: set proper memcg for net_init hooks allocations
X-Git-Tag: v6.1-rc5~688^2~258
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=1d0403d20f6c281cb3d14c5f1db5317caeec48e9;p=platform%2Fkernel%2Flinux-starfive.git

net: set proper memcg for net_init hooks allocations

__register_pernet_operations() executes init hook of registered
pernet_operation structure in all existing net namespaces.

Typically, these hooks are called by a process associated with the
specified net namespace, and all __GFP_ACCOUNT marked allocation are
accounted for corresponding container/memcg.

However __register_pernet_operations() calls the hooks in the same
context, and as a result all marked allocations are accounted to one memcg
for all processed net namespaces.

This patch adjusts active memcg for each net namespace and helps to
account memory allocated inside ops_init() into the proper memcg.

Link: https://lkml.kernel.org/r/f9394752-e272-9bf9-645f-a18c56d1c4ec@openvz.org
Signed-off-by: Vasily Averin <vvs@openvz.org>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Acked-by: Shakeel Butt <shakeelb@google.com>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Linux Kernel Functional Testing <lkft@linaro.org>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Naresh Kamboju <naresh.kamboju@linaro.org>
Cc: Qian Cai <quic_qiancai@quicinc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 3ce96ce..04f2f33 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1756,6 +1756,42 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
 	rcu_read_unlock();
 }
 
+/**
+ * get_mem_cgroup_from_obj - get a memcg associated with passed kernel object.
+ * @p: pointer to object from which memcg should be extracted. It can be NULL.
+ *
+ * Retrieves the memory group into which the memory of the pointed kernel
+ * object is accounted. If memcg is found, its reference is taken.
+ * If a passed kernel object is uncharged, or if proper memcg cannot be found,
+ * as well as if mem_cgroup is disabled, NULL is returned.
+ *
+ * Return: valid memcg pointer with taken reference or NULL.
+ */
+static inline struct mem_cgroup *get_mem_cgroup_from_obj(void *p)
+{
+	struct mem_cgroup *memcg;
+
+	rcu_read_lock();
+	do {
+		memcg = mem_cgroup_from_obj(p);
+	} while (memcg && !css_tryget(&memcg->css));
+	rcu_read_unlock();
+	return memcg;
+}
+
+/**
+ * mem_cgroup_or_root - always returns a pointer to a valid memory cgroup.
+ * @memcg: pointer to a valid memory cgroup or NULL.
+ *
+ * If passed argument is not NULL, returns it without any additional checks
+ * and changes. Otherwise, root_mem_cgroup is returned.
+ *
+ * NOTE: root_mem_cgroup can be NULL during early boot.
+ */
+static inline struct mem_cgroup *mem_cgroup_or_root(struct mem_cgroup *memcg)
+{
+	return memcg ? memcg : root_mem_cgroup;
+}
 #else
 static inline bool mem_cgroup_kmem_disabled(void)
 {
@@ -1799,7 +1835,7 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg)
 
 static inline struct mem_cgroup *mem_cgroup_from_obj(void *p)
 {
-       return NULL;
+	return NULL;
 }
 
 static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p)
@@ -1812,6 +1848,15 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
 {
 }
 
+static inline struct mem_cgroup *get_mem_cgroup_from_obj(void *p)
+{
+	return NULL;
+}
+
+static inline struct mem_cgroup *mem_cgroup_or_root(struct mem_cgroup *memcg)
+{
+	return NULL;
+}
 #endif /* CONFIG_MEMCG_KMEM */
 
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 0ec2f59..6b9f191 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -18,6 +18,7 @@
 #include <linux/user_namespace.h>
 #include <linux/net_namespace.h>
 #include <linux/sched/task.h>
+#include <linux/sched/mm.h>
 #include <linux/uidgid.h>
 #include <linux/cookie.h>
 
@@ -1143,7 +1144,13 @@ static int __register_pernet_operations(struct list_head *list,
 		 * setup_net() and cleanup_net() are not possible.
 		 */
 		for_each_net(net) {
+			struct mem_cgroup *old, *memcg;
+
+			memcg = mem_cgroup_or_root(get_mem_cgroup_from_obj(net));
+			old = set_active_memcg(memcg);
 			error = ops_init(ops, net);
+			set_active_memcg(old);
+			mem_cgroup_put(memcg);
 			if (error)
 				goto out_undo;
 			list_add_tail(&net->exit_list, &net_exit_list);