netfilter: nf_tables: implement set transaction support

Set elements are the last object type not supporting transaction support.
Implement similar to the existing rule transactions:

The global transaction counter keeps track of two generations, current
and next. Each element contains a bitmask specifying in which generations
it is inactive.

New elements start out as inactive in the current generation and active
in the next. On commit, the previous next generation becomes the current
generation and the element becomes active. The bitmask is then cleared
to indicate that the element is active in all future generations. If the
transaction is aborted, the element is removed from the set before it
becomes active.

When removing an element, it gets marked as inactive in the next generation.
On commit the next generation becomes active and the therefor the element
inactive. It is then taken out of then set and released. On abort, the
element is marked as active for the next generation again.

Lookups ignore elements not active in the current generation.

The current set types (hash/rbtree) both use a field in the extension area
to store the generation mask. This (currently) does not require any
additional memory since we have some free space in there.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

1 files changed, 20 insertions, 13 deletions

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 66fa5e9..5604c2d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2690,6 +2690,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 		goto err2;
 
 	INIT_LIST_HEAD(&set->bindings);
+	write_pnet(&set->pnet, net);
 	set->ops   = ops;
 	set->ktype = ktype;
 	set->klen  = desc.klen;
@@ -3221,10 +3222,6 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (d1.type != NFT_DATA_VALUE || d1.len != set->klen)
 		goto err2;
 
-	err = -EEXIST;
-	if (set->ops->get(set, &elem) == 0)
-		goto err2;
-
 	nft_set_ext_add(&tmpl, NFT_SET_EXT_KEY);
 
 	if (nla[NFTA_SET_ELEM_DATA] != NULL) {
@@ -3266,6 +3263,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (trans == NULL)
 		goto err4;
 
+	ext->genmask = nft_genmask_cur(ctx->net);
 	err = set->ops->insert(set, &elem);
 	if (err < 0)
 		goto err5;
@@ -3353,19 +3351,24 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 	if (desc.type != NFT_DATA_VALUE || desc.len != set->klen)
 		goto err2;
 
-	err = set->ops->get(set, &elem);
-	if (err < 0)
-		goto err2;
-
 	trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set);
 	if (trans == NULL) {
 		err = -ENOMEM;
 		goto err2;
 	}
 
+	elem.priv = set->ops->deactivate(set, &elem);
+	if (elem.priv == NULL) {
+		err = -ENOENT;
+		goto err3;
+	}
+
 	nft_trans_elem(trans) = elem;
 	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 	return 0;
+
+err3:
+	kfree(trans);
 err2:
 	nft_data_uninit(&elem.key, desc.type);
 err1:
@@ -3692,9 +3695,11 @@ static int nf_tables_commit(struct sk_buff *skb)
 					     NFT_MSG_DELSET, GFP_KERNEL);
 			break;
 		case NFT_MSG_NEWSETELEM:
-			nf_tables_setelem_notify(&trans->ctx,
-						 nft_trans_elem_set(trans),
-						 &nft_trans_elem(trans),
+			te = (struct nft_trans_elem *)trans->data;
+
+			te->set->ops->activate(te->set, &te->elem);
+			nf_tables_setelem_notify(&trans->ctx, te->set,
+						 &te->elem,
 						 NFT_MSG_NEWSETELEM, 0);
 			nft_trans_destroy(trans);
 			break;
@@ -3704,7 +3709,6 @@ static int nf_tables_commit(struct sk_buff *skb)
 			nf_tables_setelem_notify(&trans->ctx, te->set,
 						 &te->elem,
 						 NFT_MSG_DELSETELEM, 0);
-			te->set->ops->get(te->set, &te->elem);
 			te->set->ops->remove(te->set, &te->elem);
 			break;
 		}
@@ -3812,11 +3816,14 @@ static int nf_tables_abort(struct sk_buff *skb)
 			nft_trans_elem_set(trans)->nelems--;
 			te = (struct nft_trans_elem *)trans->data;
 
-			te->set->ops->get(te->set, &te->elem);
 			te->set->ops->remove(te->set, &te->elem);
 			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);
+
 			nft_trans_destroy(trans);
 			break;
 		}