Commit 6126891c authored by Vasily Averin's avatar Vasily Averin Committed by David S. Miller
Browse files

memcg: enable accounting for IP address and routing-related objects 



An netadmin inside container can use 'ip a a' and 'ip r a'
to assign a large number of ipv4/ipv6 addresses and routing entries
and force kernel to allocate megabytes of unaccounted memory
for long-lived per-netdevice related kernel objects:
'struct in_ifaddr', 'struct inet6_ifaddr', 'struct fib6_node',
'struct rt6_info', 'struct fib_rules' and ip_fib caches.

These objects can be manually removed, though usually they lives
in memory till destroy of its net namespace.

It makes sense to account for them to restrict the host's memory
consumption from inside the memcg-limited container.

One of such objects is the 'struct fib6_node' mostly allocated in
net/ipv6/route.c::__ip6_ins_rt() inside the lock_bh()/unlock_bh() section:

 write_lock_bh(&table->tb6_lock);
 err = fib6_add(&table->tb6_root, rt, info, mxc);
 write_unlock_bh(&table->tb6_lock);

In this case it is not enough to simply add SLAB_ACCOUNT to corresponding
kmem cache. The proper memory cgroup still cannot be found due to the
incorrect 'in_interrupt()' check used in memcg_kmem_bypass().

Obsoleted in_interrupt() does not describe real execution context properly.
>From include/linux/preempt.h:

 The following macros are deprecated and should not be used in new code:
 in_interrupt()	- We're in NMI,IRQ,SoftIRQ context or have BH disabled

To verify the current execution context new macro should be used instead:
 in_task()	- We're in task context

Signed-off-by: default avatarVasily Averin <vvs@virtuozzo.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent c948f51c

mm/memcontrol.c

+1 −1
Original line number Diff line number Diff line
@@ -968,7 +968,7 @@ static __always_inline bool memcg_kmem_bypass(void) 
		return false;



	/* Memcg to charge can't be determined. */

	if (in_interrupt() || !current->mm || (current->flags & PF_KTHREAD))

	if (!in_task() || !current->mm || (current->flags & PF_KTHREAD))

		return true;



	return false;

net/core/fib_rules.c

+2 −2
Original line number Diff line number Diff line
@@ -57,7 +57,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, 
{

	struct fib_rule *r;



	r = kzalloc(ops->rule_size, GFP_KERNEL);

	r = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT);

	if (r == NULL)

		return -ENOMEM;
@@ -541,7 +541,7 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, 
			goto errout;

	}



	nlrule = kzalloc(ops->rule_size, GFP_KERNEL);

	nlrule = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT);

	if (!nlrule) {

		err = -ENOMEM;

		goto errout;

net/ipv4/devinet.c

+1 −1
Original line number Diff line number Diff line
@@ -215,7 +215,7 @@ static void devinet_sysctl_unregister(struct in_device *idev) 


static struct in_ifaddr *inet_alloc_ifa(void)

{

	return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL);

	return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL_ACCOUNT);

}



static void inet_rcu_free_ifa(struct rcu_head *head)

net/ipv4/fib_trie.c

+2 −2
Original line number Diff line number Diff line
@@ -2380,11 +2380,11 @@ void __init fib_trie_init(void) 
{

	fn_alias_kmem = kmem_cache_create("ip_fib_alias",

					  sizeof(struct fib_alias),

					  0, SLAB_PANIC, NULL);

					  0, SLAB_PANIC | SLAB_ACCOUNT, NULL);



	trie_leaf_kmem = kmem_cache_create("ip_fib_trie",

					   LEAF_SIZE,

					   0, SLAB_PANIC, NULL);

					   0, SLAB_PANIC | SLAB_ACCOUNT, NULL);

}



struct fib_table *fib_trie_table(u32 id, struct fib_table *alias)

net/ipv6/addrconf.c

+1 −1
Original line number Diff line number Diff line
@@ -1080,7 +1080,7 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, 
			goto out;

	}



	ifa = kzalloc(sizeof(*ifa), gfp_flags);

	ifa = kzalloc(sizeof(*ifa), gfp_flags | __GFP_ACCOUNT);

	if (!ifa) {

		err = -ENOBUFS;

		goto out;