[PATCH memcg v6] net: set proper memcg for net_init hooks allocations

[Vasily Averin]

__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.

Signed-off-by: Vasily Averin <vvs@xxxxxxxxxx>
Acked-by: Roman Gushchin <roman.gushchin@xxxxxxxxx>
Acked-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
---
v6: re-based to current upstream (v5.18-11267-gb00ed48bb0a7)

v5: documented get_mem_cgroup_from_obj() and for mem_cgroup_or_root()
    functions, asked by Shakeel.

v4: get_mem_cgroup_from_kmem() renamed to get_mem_cgroup_from_obj(),
    get_net_memcg() renamed to mem_cgroup_or_root(), suggested by Roman.

v3: put_net_memcg() replaced by an alreay existing mem_cgroup_put()
    It checks memcg before accessing it, this is required for
    __register_pernet_operations() called before memcg initialization.
    Additionally fixed leading whitespaces in non-memcg_kmem version
    of mem_cgroup_from_obj().

v2: introduced get/put_net_memcg(),
    new functions are moved under CONFIG_MEMCG_KMEM
    to fix compilation issues reported by Intel's kernel test robot

v1: introduced get_mem_cgroup_from_kmem(), which takes the refcount
    for the found memcg, suggested by Shakeel
---
 include/linux/memcontrol.h | 47 +++++++++++++++++++++++++++++++++++++-
 net/core/net_namespace.c   |  7 ++++++
 2 files changed, 53 insertions(+), 1 deletion(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 9ecead1042b9..dad16b484cd5 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1755,6 +1755,42 @@ 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)
 {
@@ -1798,7 +1834,7 @@ 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 void count_objcg_event(struct obj_cgroup *objcg,
@@ -1806,6 +1842,15 @@ 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 0ec2f5906a27..6b9f19122ec1 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);
-- 
2.36.1