1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
|
From 2738d9d963bd1f06d5114c2b4fa5771a95703991 Mon Sep 17 00:00:00 2001
From: Ritaro Takenaka <ritarot634@gmail.com>
Date: Tue, 17 May 2022 12:55:30 +0200
Subject: [PATCH] netfilter: flowtable: move dst_check to packet path
Fixes sporadic IPv6 packet loss when flow offloading is enabled.
IPv6 route GC and flowtable GC are not synchronized.
When dst_cache becomes stale and a packet passes through the flow before
the flowtable GC teardowns it, the packet can be dropped.
So, it is necessary to check dst every time in packet path.
Fixes: 227e1e4d0d6c ("netfilter: nf_flowtable: skip device lookup from interface index")
Signed-off-by: Ritaro Takenaka <ritarot634@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_flow_table_core.c | 23 +----------------------
net/netfilter/nf_flow_table_ip.c | 19 +++++++++++++++++++
2 files changed, 20 insertions(+), 22 deletions(-)
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -436,33 +436,12 @@ nf_flow_table_iterate(struct nf_flowtabl
return err;
}
-static bool flow_offload_stale_dst(struct flow_offload_tuple *tuple)
-{
- struct dst_entry *dst;
-
- if (tuple->xmit_type == FLOW_OFFLOAD_XMIT_NEIGH ||
- tuple->xmit_type == FLOW_OFFLOAD_XMIT_XFRM) {
- dst = tuple->dst_cache;
- if (!dst_check(dst, tuple->dst_cookie))
- return true;
- }
-
- return false;
-}
-
-static bool nf_flow_has_stale_dst(struct flow_offload *flow)
-{
- return flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple) ||
- flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple);
-}
-
static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data)
{
struct nf_flowtable *flow_table = data;
if (nf_flow_has_expired(flow) ||
- nf_ct_is_dying(flow->ct) ||
- nf_flow_has_stale_dst(flow))
+ nf_ct_is_dying(flow->ct))
set_bit(NF_FLOW_TEARDOWN, &flow->flags);
if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) {
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -229,6 +229,15 @@ static bool nf_flow_exceeds_mtu(const st
return true;
}
+static inline bool nf_flow_dst_check(struct flow_offload_tuple *tuple)
+{
+ if (tuple->xmit_type != FLOW_OFFLOAD_XMIT_NEIGH &&
+ tuple->xmit_type != FLOW_OFFLOAD_XMIT_XFRM)
+ return true;
+
+ return dst_check(tuple->dst_cache, tuple->dst_cookie);
+}
+
static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
const struct nf_hook_state *state,
struct dst_entry *dst)
@@ -364,6 +373,11 @@ nf_flow_offload_ip_hook(void *priv, stru
if (nf_flow_state_check(flow, iph->protocol, skb, thoff))
return NF_ACCEPT;
+ if (!nf_flow_dst_check(&tuplehash->tuple)) {
+ flow_offload_teardown(flow);
+ return NF_ACCEPT;
+ }
+
if (skb_try_make_writable(skb, thoff + hdrsize))
return NF_DROP;
@@ -600,6 +614,11 @@ nf_flow_offload_ipv6_hook(void *priv, st
if (nf_flow_state_check(flow, ip6h->nexthdr, skb, thoff))
return NF_ACCEPT;
+ if (!nf_flow_dst_check(&tuplehash->tuple)) {
+ flow_offload_teardown(flow);
+ return NF_ACCEPT;
+ }
+
if (skb_try_make_writable(skb, thoff + hdrsize))
return NF_DROP;
|