Steffen reported that the recent change to add oif to dst lookups breaks
the VTI use case. The problem is that with the oif set in the flow struct
the comparison to the nh_oif is triggered. Fix by splitting the
FLOWI_FLAG_VRFSRC into 2 flags -- one that triggers the vrf device cache
bypass (FLOWI_FLAG_VRFSRC) and another telling the lookup to not compare
nh oif (FLOWI_FLAG_SKIP_NH_OIF).
Fixes: 42a7b32b73d6 ("xfrm: Add oif to dst lookups")
Signed-off-by: David Ahern <d...@cumulusnetworks.com>
---
IPv6 does not show this problem for me. So no change is added for IPv6.
If your mileage varies let me know and I'll take another look.
drivers/net/vrf.c | 3 ++-
include/net/flow.h | 1 +
include/net/route.h | 2 +-
net/ipv4/fib_trie.c | 2 +-
net/ipv4/udp.c | 3 ++-
net/ipv4/xfrm4_policy.c | 2 ++
6 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index e7094fbd7568..488c6f50df73 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -193,7 +193,8 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff
*skb,
.flowi4_oif = vrf_dev->ifindex,
.flowi4_iif = LOOPBACK_IFINDEX,
.flowi4_tos = RT_TOS(ip4h->tos),
- .flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_VRFSRC,
+ .flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_VRFSRC |
+ FLOWI_FLAG_SKIP_NH_OIF,
.daddr = ip4h->daddr,
};
diff --git a/include/net/flow.h b/include/net/flow.h
index acd6a096250e..9b85db85f13c 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -35,6 +35,7 @@ struct flowi_common {
#define FLOWI_FLAG_ANYSRC 0x01
#define FLOWI_FLAG_KNOWN_NH 0x02
#define FLOWI_FLAG_VRFSRC 0x04
+#define FLOWI_FLAG_SKIP_NH_OIF 0x08
__u32 flowic_secid;
struct flowi_tunnel flowic_tun_key;
};
diff --git a/include/net/route.h b/include/net/route.h
index cc61cb95f059..f46af256880c 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -255,7 +255,7 @@ static inline void ip_route_connect_init(struct flowi4
*fl4, __be32 dst, __be32
flow_flags |= FLOWI_FLAG_ANYSRC;
if (netif_index_is_vrf(sock_net(sk), oif))
- flow_flags |= FLOWI_FLAG_VRFSRC;
+ flow_flags |= FLOWI_FLAG_VRFSRC | FLOWI_FLAG_SKIP_NH_OIF;
flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
protocol, flow_flags, dst, src, dport, sport);
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 26d6ffb6d23c..6c2af797f2f9 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1426,7 +1426,7 @@ int fib_table_lookup(struct fib_table *tb, const struct
flowi4 *flp,
nh->nh_flags & RTNH_F_LINKDOWN &&
!(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
continue;
- if (!(flp->flowi4_flags & FLOWI_FLAG_VRFSRC)) {
+ if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) {
if (flp->flowi4_oif &&
flp->flowi4_oif != nh->nh_oif)
continue;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c0a15e7f359f..f7d1d5e19e95 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1024,7 +1024,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg,
size_t len)
if (netif_index_is_vrf(net, ipc.oif)) {
flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
- (flow_flags | FLOWI_FLAG_VRFSRC),
+ (flow_flags | FLOWI_FLAG_VRFSRC |
+ FLOWI_FLAG_SKIP_NH_OIF),
faddr, saddr, dport,
inet->inet_sport);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index bb919b28619f..c10a9ee68433 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -33,6 +33,8 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net,
struct flowi4 *fl4,
if (saddr)
fl4->saddr = saddr->a4;
+ fl4->flowi4_flags = FLOWI_FLAG_SKIP_NH_OIF;
+
rt = __ip_route_output_key(net, fl4);
if (!IS_ERR(rt))
return &rt->dst;
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
