[PATCH nf 1/2] netfilter: nf_flow_table: conntrack picks up expired flows

[PATCH nf 1/2] netfilter: nf_flow_table: conntrack picks up expired flows

[Pablo Neira Ayuso]

Update conntrack entry to pick up expired flows, otherwise the conntrack
entry gets stuck with the internal offload timeout (one day). The TCP
state also needs to be adjusted to ESTABLISHED state and tracking is set
to liberal mode in order to give conntrack a chance to pick up the
expired flow.

Fixes: ac2a66665e23 ("netfilter: add generic flow table infrastructure")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_flow_table_core.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index e3d797252a98..68a24471ffee 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -111,7 +111,7 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
 #define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT	(120 * HZ)
 #define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT	(30 * HZ)
 
-static void flow_offload_fixup_ct_state(struct nf_conn *ct)
+static void flow_offload_fixup_ct(struct nf_conn *ct)
 {
 	const struct nf_conntrack_l4proto *l4proto;
 	unsigned int timeout;
@@ -208,6 +208,11 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
 }
 EXPORT_SYMBOL_GPL(flow_offload_add);
 
+static inline bool nf_flow_has_expired(const struct flow_offload *flow)
+{
+	return (__s32)(flow->timeout - (u32)jiffies) <= 0;
+}
+
 static void flow_offload_del(struct nf_flowtable *flow_table,
 			     struct flow_offload *flow)
 {
@@ -223,6 +228,9 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
 	e = container_of(flow, struct flow_offload_entry, flow);
 	clear_bit(IPS_OFFLOAD_BIT, &e->ct->status);
 
+	if (nf_flow_has_expired(flow))
+		flow_offload_fixup_ct(e->ct);
+
 	flow_offload_free(flow);
 }
 
@@ -233,7 +241,7 @@ void flow_offload_teardown(struct flow_offload *flow)
 	flow->flags |= FLOW_OFFLOAD_TEARDOWN;
 
 	e = container_of(flow, struct flow_offload_entry, flow);
-	flow_offload_fixup_ct_state(e->ct);
+	flow_offload_fixup_ct(e->ct);
 }
 EXPORT_SYMBOL_GPL(flow_offload_teardown);
 
@@ -298,11 +306,6 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table,
 	return err;
 }
 
-static inline bool nf_flow_has_expired(const struct flow_offload *flow)
-{
-	return (__s32)(flow->timeout - (u32)jiffies) <= 0;
-}
-
 static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data)
 {
 	struct nf_flowtable *flow_table = data;
-- 
2.11.0

[PATCH nf 2/2] netfilter: nf_flow_table: teardown flow timeout race

[Pablo Neira Ayuso]

Flows that are in teardown state (due to RST / FIN TCP packet) still
have their offload flag set on. Hence, the conntrack garbage collector
may race to undo the timeout adjustment that the fixup routine performs,
leaving the conntrack entry in place with the internal offload timeout
(one day).

Update teardown flow state to ESTABLISHED and set tracking to liberal,
then once the offload bit is cleared, adjust timeout if it is more than
the default fixup timeout (conntrack might already have set a lower
timeout from the packet path).

Fixes: da5984e51063 ("netfilter: nf_flow_table: add support for sending flows back to the slow path")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_flow_table_core.c | 34 +++++++++++++++++++++++++---------
 1 file changed, 25 insertions(+), 9 deletions(-)

diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 68a24471ffee..80a8f9ae4c93 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -111,15 +111,16 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
 #define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT	(120 * HZ)
 #define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT	(30 * HZ)
 
-static void flow_offload_fixup_ct(struct nf_conn *ct)
+static inline __s32 nf_flow_timeout_delta(unsigned int timeout)
+{
+	return (__s32)(timeout - (u32)jiffies);
+}
+
+static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
 {
 	const struct nf_conntrack_l4proto *l4proto;
+	int l4num = nf_ct_protonum(ct);
 	unsigned int timeout;
-	int l4num;
-
-	l4num = nf_ct_protonum(ct);
-	if (l4num == IPPROTO_TCP)
-		flow_offload_fixup_tcp(&ct->proto.tcp);
 
 	l4proto = nf_ct_l4proto_find(l4num);
 	if (!l4proto)
@@ -132,7 +133,20 @@ static void flow_offload_fixup_ct(struct nf_conn *ct)
 	else
 		return;
 
-	ct->timeout = nfct_time_stamp + timeout;
+	if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout)
+		ct->timeout = nfct_time_stamp + timeout;
+}
+
+static void flow_offload_fixup_ct_state(struct nf_conn *ct)
+{
+	if (nf_ct_protonum(ct) == IPPROTO_TCP)
+		flow_offload_fixup_tcp(&ct->proto.tcp);
+}
+
+static void flow_offload_fixup_ct(struct nf_conn *ct)
+{
+	flow_offload_fixup_ct_state(ct);
+	flow_offload_fixup_ct_timeout(ct);
 }
 
 void flow_offload_free(struct flow_offload *flow)
@@ -210,7 +224,7 @@ EXPORT_SYMBOL_GPL(flow_offload_add);
 
 static inline bool nf_flow_has_expired(const struct flow_offload *flow)
 {
-	return (__s32)(flow->timeout - (u32)jiffies) <= 0;
+	return nf_flow_timeout_delta(flow->timeout) <= 0;
 }
 
 static void flow_offload_del(struct nf_flowtable *flow_table,
@@ -230,6 +244,8 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
 
 	if (nf_flow_has_expired(flow))
 		flow_offload_fixup_ct(e->ct);
+	else if (flow->flags & FLOW_OFFLOAD_TEARDOWN)
+		flow_offload_fixup_ct_timeout(e->ct);
 
 	flow_offload_free(flow);
 }
@@ -241,7 +257,7 @@ void flow_offload_teardown(struct flow_offload *flow)
 	flow->flags |= FLOW_OFFLOAD_TEARDOWN;
 
 	e = container_of(flow, struct flow_offload_entry, flow);
-	flow_offload_fixup_ct(e->ct);
+	flow_offload_fixup_ct_state(e->ct);
 }
 EXPORT_SYMBOL_GPL(flow_offload_teardown);
 
-- 
2.11.0