netfilter: nf_tables: prepare set element accounting for async updates

Use atomic operations for the element count to avoid races with async
updates.

To properly handle the transactional semantics during netlink updates,
deleted but not yet committed elements are accounted for seperately and
are treated as being already removed. This means for the duration of
a netlink transaction, the limit might be exceeded by the amount of
elements deleted. Set implementations must be prepared to handle this.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This commit is contained in:
Patrick McHardy 2015-04-05 14:41:06 +02:00 committed by Pablo Neira Ayuso
parent 4a8678efbe
commit 3dd0673ac3
3 changed files with 18 additions and 12 deletions

View File

@ -258,6 +258,7 @@ void nft_unregister_set(struct nft_set_ops *ops);
* @dtype: data type (verdict or numeric type defined by userspace)
* @size: maximum set size
* @nelems: number of elements
* @ndeact: number of deactivated elements queued for removal
* @timeout: default timeout value in msecs
* @gc_int: garbage collection interval in msecs
* @policy: set parameterization (see enum nft_set_policies)
@ -275,7 +276,8 @@ struct nft_set {
u32 ktype;
u32 dtype;
u32 size;
u32 nelems;
atomic_t nelems;
u32 ndeact;
u64 timeout;
u32 gc_int;
u16 policy;

View File

@ -3238,9 +3238,6 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
u32 flags;
int err;
if (set->size && set->nelems == set->size)
return -ENFILE;
err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr,
nft_set_elem_policy);
if (err < 0)
@ -3391,11 +3388,15 @@ static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb,
return -EBUSY;
nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
err = nft_add_set_elem(&ctx, set, attr);
if (err < 0)
break;
if (set->size &&
!atomic_add_unless(&set->nelems, 1, set->size + set->ndeact))
return -ENFILE;
set->nelems++;
err = nft_add_set_elem(&ctx, set, attr);
if (err < 0) {
atomic_dec(&set->nelems);
break;
}
}
return err;
}
@ -3477,7 +3478,7 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb,
if (err < 0)
break;
set->nelems--;
set->ndeact++;
}
return err;
}
@ -3810,6 +3811,8 @@ static int nf_tables_commit(struct sk_buff *skb)
&te->elem,
NFT_MSG_DELSETELEM, 0);
te->set->ops->remove(te->set, &te->elem);
atomic_dec(&te->set->nelems);
te->set->ndeact--;
break;
}
}
@ -3913,16 +3916,16 @@ static int nf_tables_abort(struct sk_buff *skb)
nft_trans_destroy(trans);
break;
case NFT_MSG_NEWSETELEM:
nft_trans_elem_set(trans)->nelems--;
te = (struct nft_trans_elem *)trans->data;
te->set->ops->remove(te->set, &te->elem);
atomic_dec(&te->set->nelems);
break;
case NFT_MSG_DELSETELEM:
te = (struct nft_trans_elem *)trans->data;
nft_trans_elem_set(trans)->nelems++;
te->set->ops->activate(te->set, &te->elem);
te->set->ndeact--;
nft_trans_destroy(trans);
break;

View File

@ -203,7 +203,7 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
static void nft_hash_gc(struct work_struct *work)
{
const struct nft_set *set;
struct nft_set *set;
struct nft_hash_elem *he;
struct nft_hash *priv;
struct nft_set_gc_batch *gcb = NULL;
@ -237,6 +237,7 @@ static void nft_hash_gc(struct work_struct *work)
if (gcb == NULL)
goto out;
rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params);
atomic_dec(&set->nelems);
nft_set_gc_batch_add(gcb, he);
}
out: