On Fri, Jun 03, 2022 at 07:19:43AM +0300, Vasily Averin wrote:
> __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>
> ---
...
> 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;
> +}
...
> 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
This triggers a few boot warnings like those.
virt_to_phys used for non-linear address: ffffd8efe2d2fe00 (init_net)
WARNING: CPU: 87 PID: 3170 at arch/arm64/mm/physaddr.c:12 __virt_to_phys
CPU: 87 PID: 3170 Comm: modprobe Tainted: G B W 5.19.0-rc1-next-20220606 #138
pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : __virt_to_phys
lr : __virt_to_phys
sp : ffff800051cc76b0
x29: ffff800051cc76b0 x28: ffffd8efb5ba6ab8 x27: ffffd8efb5ba6b2c
x26: ffffd8efb1bccb20 x25: ffffd8efbaaf8200 x24: ffff800051cc77f0
x23: ffffd8efb744a000 x22: ffffd8efbb1bc000 x21: 0000600000000000
x20: 0000d8efe2d2fe00 x19: ffffd8efe2d2fe00 x18: 0000000000000443
x17: 0000000000000000 x16: 0000000000000002 x15: ffffd8efb9db2000
x14: 0000000000000001 x13: 0000000000000000 x12: ffff6806c88f8986
x11: 1fffe806c88f8985 x10: ffff6806c88f8985 x9 : dfff800000000000
x8 : ffff4036447c4c2b x7 : 0000000000000001 x6 : ffff6806c88f8985
x5 : ffff4036447c4c28 x4 : ffff6806c88f8986 x3 : ffffd8efb34b3850
x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff400335f99a80
Call trace:
__virt_to_phys
mem_cgroup_from_obj
__register_pernet_operations
register_pernet_operations
register_pernet_subsys
nfnetlink_init [nfnetlink]
load_module
__do_sys_finit_module
__arm64_sys_finit_module
invoke_syscall
el0_svc_common.constprop.0
do_el0_svc
el0_svc
el0t_64_sync_handler
el0t_64_sync
irq event stamp: 0
hardirqs last enabled at (0): 0x0
hardirqs last disabled at (0): copy_process
softirqs last enabled at (0): copy_process
softirqs last disabled at (0): 0x0
virt_to_phys used for non-linear address: ffffd8efe2d2fe00 (init_net)
WARNING: CPU: 156 PID: 3176 at arch/arm64/mm/physaddr.c:12 __virt_to_phys
CPU: 156 PID: 3176 Comm: modprobe Tainted: G B W 5.19.0-rc1-next-20220606 #138
pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : __virt_to_phys
lr : __virt_to_phys
sp : ffff800051b376e0
x29: ffff800051b376e0 x28: ffffd8efb5ba6ab8 x27: ffffd8efb5ba6b2c
x26: ffffd8efb286e910 x25: ffffd8efbaaf8200 x24: ffff800051b37820
x23: ffffd8efb744a000 x22: ffffd8efbb1bc000 x21: 0000600000000000
x20: 0000d8efe2d2fe00 x19: ffffd8efe2d2fe00 x18: 00000000000001cb
x17: 0000000000000000 x16: 0000000000000002 x15: ffffd8efb9db2000
x14: 0000000000000001 x13: 0000000000000000 x12: ffff6806c8a03f86
x8 : ffff40364501fc2b x7 : 0000000000000001 x6 : ffff6806c8a03f85
x5 : ffff40364501fc28 x4 : ffff6806c8a03f86 x3 : ffffd8efb34b3850
x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff40033376b4c0
Call trace:
__virt_to_phys
mem_cgroup_from_obj
__register_pernet_operations
register_pernet_operations
register_pernet_subsys
nf_tables_module_init [nf_tables]
do_one_initcall
do_init_module
load_module
__do_sys_finit_module
__arm64_sys_finit_module
invoke_syscall
el0_svc_common.constprop.0
do_el0_svc
el0_svc
el0t_64_sync_handler
el0t_64_sync
irq event stamp: 0
hardirqs last enabled at (0): 0x0
hardirqs last disabled at (0): copy_process
softirqs last enabled at (0): copy_process
softirqs last disabled at (0): 0x0
