* [PATCH 6.12.y 1/2] netfilter: nft_ct: expectation timeouts are passed in milliseconds
2026-11-17 23:46 [PATCH 6.12.y 0/2] netfilter: nft_ct: move custom expectation support to helper Mark Bundschuh
@ 2026-11-17 23:46 ` Mark Bundschuh
2026-11-17 23:46 ` [PATCH 6.12.y 2/2] netfilter: nft_ct: move custom expectation support to helper Mark Bundschuh
1 sibling, 0 replies; 3+ messages in thread
From: Mark Bundschuh @ 2026-11-17 23:46 UTC (permalink / raw)
To: stable; +Cc: Florian Westphal, Pablo Neira Ayuso, Mark Bundschuh
From: Florian Westphal <fw@strlen.de>
[ Upstream commit 6fb421bd07f156cdf0cdede062d31f1c21def326 ]
Userspace passes '5000' in case user asks for 5 seconds.
Allowing for sub-second expectation lifetimes makes sense to me. so
fix up the kernel side instead of munging nft to send a value rounded
up to next second.
Also note that this violates nft convention of passing integers in
network byte order, but we can't change this anymore.
Fixes: 857b46027d6f ("netfilter: nft_ct: add ct expectations support")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Stable-dep-of: 3679da4ad8be ("netfilter: nft_ct: move custom expectation support to helper")
Signed-off-by: Mark Bundschuh <mkbund@amazon.com>
---
net/netfilter/nft_ct.c | 21 ++++++++++++++++++---
1 file changed, 18 insertions(+), 3 deletions(-)
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 07a879f66fab..206cfa2734c6 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -1198,11 +1198,23 @@ struct nft_ct_expect_obj {
u32 timeout;
};
+static int nft_ct_expect_timeout_get(const struct nlattr *attr, u32 *val)
+{
+ unsigned long jiffies_val = msecs_to_jiffies(nla_get_u32(attr));
+
+ if (jiffies_val > UINT_MAX)
+ return -ERANGE;
+
+ *val = jiffies_val;
+ return 0;
+}
+
static int nft_ct_expect_obj_init(const struct nft_ctx *ctx,
const struct nlattr * const tb[],
struct nft_object *obj)
{
struct nft_ct_expect_obj *priv = nft_obj_data(obj);
+ int err;
if (!tb[NFTA_CT_EXPECT_L4PROTO] ||
!tb[NFTA_CT_EXPECT_DPORT] ||
@@ -1238,8 +1250,11 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx,
return -EOPNOTSUPP;
}
+ err = nft_ct_expect_timeout_get(tb[NFTA_CT_EXPECT_TIMEOUT], &priv->timeout);
+ if (err)
+ return err;
+
priv->dport = nla_get_be16(tb[NFTA_CT_EXPECT_DPORT]);
- priv->timeout = nla_get_u32(tb[NFTA_CT_EXPECT_TIMEOUT]);
priv->size = nla_get_u8(tb[NFTA_CT_EXPECT_SIZE]);
return nf_ct_netns_get(ctx->net, ctx->family);
@@ -1259,7 +1274,7 @@ static int nft_ct_expect_obj_dump(struct sk_buff *skb,
if (nla_put_be16(skb, NFTA_CT_EXPECT_L3PROTO, htons(priv->l3num)) ||
nla_put_u8(skb, NFTA_CT_EXPECT_L4PROTO, priv->l4proto) ||
nla_put_be16(skb, NFTA_CT_EXPECT_DPORT, priv->dport) ||
- nla_put_u32(skb, NFTA_CT_EXPECT_TIMEOUT, priv->timeout) ||
+ nla_put_u32(skb, NFTA_CT_EXPECT_TIMEOUT, jiffies_to_msecs(priv->timeout)) ||
nla_put_u8(skb, NFTA_CT_EXPECT_SIZE, priv->size))
return -1;
@@ -1309,7 +1324,7 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj,
&ct->tuplehash[!dir].tuple.src.u3,
&ct->tuplehash[!dir].tuple.dst.u3,
priv->l4proto, NULL, &priv->dport);
- exp->timeout += priv->timeout * HZ;
+ exp->timeout += priv->timeout;
if (nf_ct_expect_related(exp, 0) != 0)
regs->verdict.code = NF_DROP;
base-commit: b869a5313cbfe7102873d3de318ddb68675146d0
--
2.50.1
^ permalink raw reply related [flat|nested] 3+ messages in thread* [PATCH 6.12.y 2/2] netfilter: nft_ct: move custom expectation support to helper
2026-11-17 23:46 [PATCH 6.12.y 0/2] netfilter: nft_ct: move custom expectation support to helper Mark Bundschuh
2026-11-17 23:46 ` [PATCH 6.12.y 1/2] netfilter: nft_ct: expectation timeouts are passed in milliseconds Mark Bundschuh
@ 2026-11-17 23:46 ` Mark Bundschuh
1 sibling, 0 replies; 3+ messages in thread
From: Mark Bundschuh @ 2026-11-17 23:46 UTC (permalink / raw)
To: stable; +Cc: Pablo Neira Ayuso, Jaeyeong Lee, Mark Bundschuh
From: Pablo Neira Ayuso <pablo@netfilter.org>
[ Upstream commit 3679da4ad8be84cddaf40bc307fef1fe13e051ff ]
Originally, the ct expectation support called nf_ct_helper_ext_add() for
confirmed conntracks, which is invalid, triggering a splat. This was
fixed by commit 1710eb913bdc ("netfilter: nft_ct: skip expectations for
confirmed conntrack") which restricted it to unconfirmed conntracks.
However, early insertion of expectations into the expectations list when
the conntrack is unconfirmed leads to stale entries pointing to the
wrong hlist_head through .pprev due to ct extension reallocation.
Commit 7c9664351980 ("netfilter: move nat hlist_head to nf_conn") moved
the nat hlist_head to nf_conn for this reason:
1. ...
2. When reallocation of extension area occurs we need to fixup the
bysource hash head via hlist_replace_rcu.
I'd rather not increase the size of the struct nf_conn for this feature
has very limited scope: only one expectation can be created at a time
given expect_clash() will make nf_ct_expect_related() reports EBUSY.
For this reason, relax nf_ct_expect_related() not to drop packets in
case expectation creation fails, therefore, expectation creation becomes
best effort.
To address this issue, add an internal ct helper and attach it to the
conntrack entry to streamline the custom ct expectation support with
existing ct helpers.
Expose a new nf_conntrack_helper_release() function to release the
internal helper that is allocated and attached to the conntrack entry to
create the custom expectations. The nft_ct module removal always waits
for rcu grace period, then the NULL helper callback is observed after
this.
This patch also restricts the creation of expectations to different
helpers other than this custom helper that is created for this type of
expectations.
Fixes: 857b46027d6f ("netfilter: nft_ct: add ct expectations support")
Reported-by: Jaeyeong Lee <iostreampy@proton.me>
Link: https://patch.msgid.link/20260715144755.00ea7dfcd9f@proton.me
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
[ - ac46f3f35b6e ("netfilter: nf_conntrack_helper: add refcounting from
datapath") is not backported because it reworks helper lifetime
around a datapath ct_refcnt in 9 files, so one static nft_ct_expect
helper is unhelped at nft_ct module exit.
- d4beefc90a66 ("netfilter: nft_ct: support expectation creation for
natted flows") is not backported because it adds expectation support
for NATed flows, so the moved expectation code has no NAT
follow-master part.
- Context differs due to commit: 6031487d4e27 ]
Signed-off-by: Mark Bundschuh <mkbund@amazon.com>
---
include/net/netfilter/nf_conntrack_helper.h | 1 +
net/netfilter/nf_conntrack_helper.c | 20 ++--
net/netfilter/nft_ct.c | 100 +++++++++++++++-----
3 files changed, 89 insertions(+), 32 deletions(-)
diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index 24cf3d2d9745..5b76fa57fd76 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -105,6 +105,7 @@ void nf_ct_helper_init(struct nf_conntrack_helper *helper,
int nf_conntrack_helper_register(struct nf_conntrack_helper *);
void nf_conntrack_helper_unregister(struct nf_conntrack_helper *);
+void nf_conntrack_helper_release(struct nf_conntrack_helper *);
int nf_conntrack_helpers_register(struct nf_conntrack_helper *, unsigned int);
void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *,
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 2cef826e20fb..17538e3382dd 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -425,6 +425,18 @@ static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data)
return this == me;
}
+void nf_conntrack_helper_release(struct nf_conntrack_helper *me)
+{
+ nf_ct_expect_iterate_destroy(expect_iter_me, me);
+ nf_ct_iterate_destroy(unhelp, me);
+
+ /* nf_ct_iterate_destroy() does an unconditional synchronize_rcu() as
+ * last step, this ensures rcu readers of exp->helper are done.
+ * No need for another synchronize_rcu() here.
+ */
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_helper_release);
+
void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
{
mutex_lock(&nf_ct_helper_mutex);
@@ -437,13 +449,7 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
*/
synchronize_rcu();
- nf_ct_expect_iterate_destroy(expect_iter_me, me);
- nf_ct_iterate_destroy(unhelp, me);
-
- /* nf_ct_iterate_destroy() does an unconditional synchronize_rcu() as
- * last step, this ensures rcu readers of exp->helper are done.
- * No need for another synchronize_rcu() here.
- */
+ nf_conntrack_helper_release(me);
}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 206cfa2734c6..60f15bd3b6d1 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -1209,6 +1209,65 @@ static int nft_ct_expect_timeout_get(const struct nlattr *attr, u32 *val)
return 0;
}
+struct nft_ct_expect_data {
+ struct nft_ct_expect_obj obj;
+ enum ip_conntrack_dir dir;
+};
+
+static int ct_expect_help(struct sk_buff *skb, unsigned int protoff,
+ struct nf_conn *ct, enum ip_conntrack_info ctinfo)
+{
+ enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+ struct nft_ct_expect_data *expect_data;
+ struct nf_conntrack_expect *exp;
+ int ret = NF_ACCEPT;
+ u16 l3num;
+
+ if (nf_ct_is_confirmed(ct))
+ return NF_ACCEPT;
+
+ expect_data = nfct_help_data(ct);
+ if (!expect_data)
+ return NF_ACCEPT;
+
+ if (expect_data->dir != dir)
+ return NF_ACCEPT;
+
+ exp = nf_ct_expect_alloc(ct);
+ if (!exp)
+ return NF_DROP;
+
+ if (expect_data->obj.l3num == NFPROTO_INET)
+ l3num = nf_ct_l3num(ct);
+ else
+ l3num = expect_data->obj.l3num;
+
+ nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, l3num,
+ &ct->tuplehash[!dir].tuple.src.u3,
+ &ct->tuplehash[!dir].tuple.dst.u3,
+ expect_data->obj.l4proto, NULL, &expect_data->obj.dport);
+ exp->timeout += expect_data->obj.timeout;
+
+ if (nf_ct_expect_related(exp, 0) != 0)
+ ret = NF_ACCEPT;
+
+ nf_ct_expect_put(exp);
+
+ return ret;
+}
+
+static const struct nf_conntrack_expect_policy nft_ct_expect_helper_policy = {
+ .max_expected = NF_CT_EXPECT_MAX_CNT,
+};
+
+/* No need to register this helper, this is internal. */
+static struct nf_conntrack_helper nft_ct_expect_helper = {
+ .name = "nft_ct_expect",
+ .me = THIS_MODULE,
+ .expect_policy = &nft_ct_expect_helper_policy,
+ .help = ct_expect_help,
+};
+
static int nft_ct_expect_obj_init(const struct nft_ctx *ctx,
const struct nlattr * const tb[],
struct nft_object *obj)
@@ -1216,6 +1275,8 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx,
struct nft_ct_expect_obj *priv = nft_obj_data(obj);
int err;
+ NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nft_ct_expect_data));
+
if (!tb[NFTA_CT_EXPECT_L4PROTO] ||
!tb[NFTA_CT_EXPECT_DPORT] ||
!tb[NFTA_CT_EXPECT_TIMEOUT] ||
@@ -1261,7 +1322,7 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx,
}
static void nft_ct_expect_obj_destroy(const struct nft_ctx *ctx,
- struct nft_object *obj)
+ struct nft_object *obj)
{
nf_ct_netns_put(ctx->net, ctx->family);
}
@@ -1286,11 +1347,9 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj,
const struct nft_pktinfo *pkt)
{
const struct nft_ct_expect_obj *priv = nft_obj_data(obj);
- struct nf_conntrack_expect *exp;
+ struct nft_ct_expect_data *expect_data;
enum ip_conntrack_info ctinfo;
struct nf_conn_help *help;
- enum ip_conntrack_dir dir;
- u16 l3num = priv->l3num;
struct nf_conn *ct;
ct = nf_ct_get(pkt->skb, &ctinfo);
@@ -1298,38 +1357,28 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj,
regs->verdict.code = NFT_BREAK;
return;
}
- dir = CTINFO2DIR(ctinfo);
help = nfct_help(ct);
- if (!help)
- help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
- if (!help) {
- regs->verdict.code = NF_DROP;
- return;
- }
-
- if (help->expecting[NF_CT_EXPECT_CLASS_DEFAULT] >= priv->size) {
+ if (help) {
regs->verdict.code = NFT_BREAK;
return;
}
- if (l3num == NFPROTO_INET)
- l3num = nf_ct_l3num(ct);
- exp = nf_ct_expect_alloc(ct);
- if (exp == NULL) {
+ help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
+ if (!help) {
regs->verdict.code = NF_DROP;
return;
}
- nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, l3num,
- &ct->tuplehash[!dir].tuple.src.u3,
- &ct->tuplehash[!dir].tuple.dst.u3,
- priv->l4proto, NULL, &priv->dport);
- exp->timeout += priv->timeout;
- if (nf_ct_expect_related(exp, 0) != 0)
- regs->verdict.code = NF_DROP;
+ expect_data = nfct_help_data(ct);
+ if (!expect_data) {
+ regs->verdict.code = NFT_BREAK;
+ return;
+ }
+ expect_data->obj = *priv;
+ expect_data->dir = CTINFO2DIR(ctinfo);
- nf_ct_expect_put(exp);
+ rcu_assign_pointer(help->helper, &nft_ct_expect_helper);
}
static const struct nla_policy nft_ct_expect_policy[NFTA_CT_EXPECT_MAX + 1] = {
@@ -1409,6 +1458,7 @@ static void __exit nft_ct_module_exit(void)
nft_unregister_obj(&nft_ct_helper_obj_type);
nft_unregister_expr(&nft_notrack_type);
nft_unregister_expr(&nft_ct_type);
+ nf_conntrack_helper_release(&nft_ct_expect_helper);
}
module_init(nft_ct_module_init);
--
2.50.1
^ permalink raw reply related [flat|nested] 3+ messages in thread