netfilter: nf_tables: zero timeout means element never times out

This patch uses zero as timeout marker for those elements that never expire
when the element is created.

If userspace provides no timeout for an element, then the default set
timeout applies. However, if no default set timeout is specified and
timeout flag is set on, then timeout extension is allocated and timeout
is set to zero to allow for future updates.

Use of zero a never timeout marker has been suggested by Phil Sutter.

Note that, in older kernels, it is already possible to define elements
that never expire by declaring a set with the set timeout flag set on
and no global set timeout, in this case, new element with no explicit
timeout never expire do not allocate the timeout extension, hence, they
never expire. This approach makes it complicated to accomodate element
timeout update, because element extensions do not support reallocations.
Therefore, allocate the timeout extension and use the new marker for
this case, but do not expose it to userspace to retain backward
compatibility in the set listing.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

2 files changed, 25 insertions, 17 deletions

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c295d6e6c1fb..ed85b10edb32 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5815,24 +5815,31 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 		goto nla_put_failure;
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) {
-		u64 expires, now = get_jiffies_64();
+		u64 timeout = nft_set_ext_timeout(ext)->timeout;
+		u64 set_timeout = READ_ONCE(set->timeout);
+		__be64 msecs = 0;
+
+		if (set_timeout != timeout) {
+			msecs = nf_jiffies64_to_msecs(timeout);
+			if (nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, msecs,
+					 NFTA_SET_ELEM_PAD))
+				goto nla_put_failure;
+		}
 
-		if (nft_set_ext_timeout(ext)->timeout != READ_ONCE(set->timeout) &&
-		    nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT,
-				 nf_jiffies64_to_msecs(nft_set_ext_timeout(ext)->timeout),
-				 NFTA_SET_ELEM_PAD))
-			goto nla_put_failure;
+		if (timeout > 0) {
+			u64 expires, now = get_jiffies_64();
 
-		expires = READ_ONCE(nft_set_ext_timeout(ext)->expiration);
-		if (time_before64(now, expires))
-			expires -= now;
-		else
-			expires = 0;
+			expires = READ_ONCE(nft_set_ext_timeout(ext)->expiration);
+			if (time_before64(now, expires))
+				expires -= now;
+			else
+				expires = 0;
 
-		if (nla_put_be64(skb, NFTA_SET_ELEM_EXPIRATION,
-				 nf_jiffies64_to_msecs(expires),
-				 NFTA_SET_ELEM_PAD))
-			goto nla_put_failure;
+			if (nla_put_be64(skb, NFTA_SET_ELEM_EXPIRATION,
+					 nf_jiffies64_to_msecs(expires),
+					 NFTA_SET_ELEM_PAD))
+				goto nla_put_failure;
+		}
 	}
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) {
@@ -7015,7 +7022,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			goto err_parse_key_end;
 	}
 
-	if (timeout > 0) {
+	if (set->flags & NFT_SET_TIMEOUT) {
 		err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
 		if (err < 0)
 			goto err_parse_key_end;
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index ed8d692bebe3..6a10305de24b 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -94,7 +94,8 @@ void nft_dynset_eval(const struct nft_expr *expr,
 	if (set->ops->update(set, &regs->data[priv->sreg_key], nft_dynset_new,
 			     expr, regs, &ext)) {
 		if (priv->op == NFT_DYNSET_OP_UPDATE &&
-		    nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) {
+		    nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
+		    nft_set_ext_timeout(ext)->timeout != 0) {
 			timeout = priv->timeout ? : READ_ONCE(set->timeout);
 			WRITE_ONCE(nft_set_ext_timeout(ext)->expiration, get_jiffies_64() + timeout);
 		}