From ce7dbf611ba9db087abc984ba1807771fb0c3545 Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Fri, 26 May 2017 10:43:25 +0530 Subject: tunnels: Don't apply GRO to multiple layers of encapsulation. [ Upstream commit: fac8e0f579695a3ecbc4d3cac369139d7f819971] When drivers express support for TSO of encapsulated packets, they only mean that they can do it for one layer of encapsulation. Supporting additional levels would mean updating, at a minimum, more IP length fields and they are unaware of this. No encapsulation device expresses support for handling offloaded encapsulated packets, so we won't generate these types of frames in the transmit path. However, GRO doesn't have a check for multiple levels of encapsulation and will attempt to build them. UDP tunnel GRO actually does prevent this situation but it only handles multiple UDP tunnels stacked on top of each other. This generalizes that solution to prevent any kind of tunnel stacking that would cause problems. Change-Id: I072ec2fec752795bee66cf5464af48f17c837a7f Signed-off-by: Jesse Gross Signed-off-by: Akshaya --- include/linux/netdevice.h | 4 ++-- net/core/dev.c | 2 +- net/ipv4/af_inet.c | 15 ++++++++++++++- net/ipv4/gre_offload.c | 5 +++++ net/ipv4/udp_offload.c | 6 +++--- net/ipv6/ip6_offload.c | 15 ++++++++++++++- 6 files changed, 39 insertions(+), 8 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 943a8301..173b250 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1902,8 +1902,8 @@ struct napi_gro_cb { /* Used in ipv6_gro_receive() and foo-over-udp */ u16 proto; - /* Used in udp_gro_receive */ - u8 udp_mark:1; + /* Used in tunnel GRO receive */ + u8 encap_mark:1; /* GRO checksum is valid */ u8 csum_valid:1; diff --git a/net/core/dev.c b/net/core/dev.c index 9d41179..99e2387 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4116,7 +4116,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; - NAPI_GRO_CB(skb)->udp_mark = 0; + NAPI_GRO_CB(skb)->encap_mark = 0; /* Setup for GRO checksum validation */ switch (skb->ip_summed) { diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index b39d5ef..5589a7c 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1420,6 +1420,19 @@ out: return pp; } +static struct sk_buff **ipip_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + if (NAPI_GRO_CB(skb)->encap_mark) { + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } + + NAPI_GRO_CB(skb)->encap_mark = 1; + + return inet_gro_receive(head, skb); +} + int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { if (sk->sk_family == AF_INET) @@ -1678,7 +1691,7 @@ static struct packet_offload ip_packet_offload __read_mostly = { static const struct net_offload ipip_offload = { .callbacks = { .gso_segment = inet_gso_segment, - .gro_receive = inet_gro_receive, + .gro_receive = ipip_gro_receive, .gro_complete = inet_gro_complete, }, }; diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index abc50b4..cc7b082 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -128,6 +128,11 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, struct packet_offload *ptype; __be16 type; + if (NAPI_GRO_CB(skb)->encap_mark) + goto out; + + NAPI_GRO_CB(skb)->encap_mark = 1; + off = skb_gro_offset(skb); hlen = off + sizeof(*greh); greh = skb_gro_header_fast(skb, off); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 6480cea..e6d05ae 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -266,14 +266,14 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, unsigned int off = skb_gro_offset(skb); int flush = 1; - if (NAPI_GRO_CB(skb)->udp_mark || + if (NAPI_GRO_CB(skb)->encap_mark || (skb->ip_summed != CHECKSUM_PARTIAL && NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid)) goto out; - /* mark that this skb passed once through the udp gro layer */ - NAPI_GRO_CB(skb)->udp_mark = 1; + /* mark that this skb passed once through the tunnel gro layer */ + NAPI_GRO_CB(skb)->encap_mark = 1; rcu_read_lock(); uo_priv = rcu_dereference(udp_offload_base); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index dece5c7..dbc528e 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -255,6 +255,19 @@ out: return pp; } +static struct sk_buff **sit_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + if (NAPI_GRO_CB(skb)->encap_mark) { + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } + + NAPI_GRO_CB(skb)->encap_mark = 1; + + return ipv6_gro_receive(head, skb); +} + static int ipv6_gro_complete(struct sk_buff *skb, int nhoff) { const struct net_offload *ops; @@ -289,7 +302,7 @@ static struct packet_offload ipv6_packet_offload __read_mostly = { static const struct net_offload sit_offload = { .callbacks = { .gso_segment = ipv6_gso_segment, - .gro_receive = ipv6_gro_receive, + .gro_receive = sit_gro_receive, .gro_complete = ipv6_gro_complete, }, }; -- 1.9.1