net: gro: fix udp bad offset in socket lookup by adding {inner_}network_offset to...

Commits a602456 ("udp: Add GRO functions to UDP socket") and 57c67ff ("udp:
additional GRO support") introduce incorrect usage of {ip,ipv6}_hdr in the
complete phase of gro. The functions always return skb->network_header,
which in the case of encapsulated packets at the gro complete phase, is
always set to the innermost L3 of the packet. That means that calling
{ip,ipv6}_hdr for skbs which completed the GRO receive phase (both in
gro_list and *_gro_complete) when parsing an encapsulated packet's _outer_
L3/L4 may return an unexpected value.

This incorrect usage leads to a bug in GRO's UDP socket lookup.
udp{4,6}_lib_lookup_skb functions use ip_hdr/ipv6_hdr respectively. These
*_hdr functions return network_header which will point to the innermost L3,
resulting in the wrong offset being used in __udp{4,6}_lib_lookup with
encapsulated packets.

This patch adds network_offset and inner_network_offset to napi_gro_cb, and
makes sure both are set correctly.

To fix the issue, network_offsets union is used inside napi_gro_cb, in
which both the outer and the inner network offsets are saved.

Reproduction example:

Endpoint configuration example (fou + local address bind)

    # ip fou add port 6666 ipproto 4
    # ip link add name tun1 type ipip remote 2.2.2.1 local 2.2.2.2 encap fou encap-dport 5555 encap-sport 6666 mode ipip
    # ip link set tun1 up
    # ip a add 1.1.1.2/24 dev tun1

Netperf TCP_STREAM result on net-next before patch is applied:

net-next main, GRO enabled:
    $ netperf -H 1.1.1.2 -t TCP_STREAM -l 5
    Recv   Send    Send
    Socket Socket  Message  Elapsed
    Size   Size    Size     Time     Throughput
    bytes  bytes   bytes    secs.    10^6bits/sec

    131072  16384  16384    5.28        2.37

net-next main, GRO disabled:
    $ netperf -H 1.1.1.2 -t TCP_STREAM -l 5
    Recv   Send    Send
    Socket Socket  Message  Elapsed
    Size   Size    Size     Time     Throughput
    bytes  bytes   bytes    secs.    10^6bits/sec

    131072  16384  16384    5.01     2745.06

patch applied, GRO enabled:
    $ netperf -H 1.1.1.2 -t TCP_STREAM -l 5
    Recv   Send    Send
    Socket Socket  Message  Elapsed
    Size   Size    Size     Time     Throughput
    bytes  bytes   bytes    secs.    10^6bits/sec

    131072  16384  16384    5.01     2877.38

Fixes: a6024562ffd7 ("udp: Add GRO functions to UDP socket")
Signed-off-by: Richard Gobert <richardbgobert@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/include/net/gro.h b/include/net/gro.h
index 50f1e403dbbb3805277d74ff80b504677e9a7aa0..c1d4ca0463a178736d2416e172784e35e333e126 100644 (file)
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -87,6 +87,15 @@ struct napi_gro_cb {
 
        /* used to support CHECKSUM_COMPLETE for tunneling protocols */
        __wsum  csum;
+
+       /* L3 offsets */
+       union {
+               struct {
+                       u16 network_offset;
+                       u16 inner_network_offset;
+               };
+               u16 network_offsets[2];
+       };
 };
 
 #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)

diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index f001582345052f8c26e008058ae5f721f8bc224d..9404dd551dfd2850117d4edf9b7fd25e3ba84322 100644 (file)
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -478,6 +478,8 @@ static struct sk_buff *vlan_gro_receive(struct list_head *head,
        if (unlikely(!vhdr))
                goto out;
 
+       NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = hlen;
+
        type = vhdr->h_vlan_encapsulated_proto;
 
        ptype = gro_find_receive_by_type(type);

diff --git a/net/core/gro.c b/net/core/gro.c
index 83f35d99a682c21dae11683fec72074a898fbac2..c7901253a1a8fc1e9425add77014e15b363a1623 100644 (file)
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -371,6 +371,7 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff)
        const skb_frag_t *frag0;
        unsigned int headlen;
 
+       NAPI_GRO_CB(skb)->network_offset = 0;
        NAPI_GRO_CB(skb)->data_offset = 0;
        headlen = skb_headlen(skb);
        NAPI_GRO_CB(skb)->frag0 = skb->data;

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 55bd72997b31063b7baad350fdcff40e938aecb8..fafb123f798be346c247dac0f9dc8e498e034349 100644 (file)
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1572,6 +1572,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
        /* The above will be needed by the transport layer if there is one
         * immediately following this IP hdr.
         */
+       NAPI_GRO_CB(skb)->inner_network_offset = off;
 
        /* Note : No need to call skb_gro_postpull_rcsum() here,
         * as we already checked checksum over ipv4 header was 0

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 420905be5f30c944ff360b349ae29d66104e0286..b32cf2eeeb41d1fc0bbe24e4888301f344ec8488 100644 (file)
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -532,7 +532,8 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
 struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
                                 __be16 sport, __be16 dport)
 {
-       const struct iphdr *iph = ip_hdr(skb);
+       const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+       const struct iphdr *iph = (struct iphdr *)(skb->data + offset);
        struct net *net = dev_net(skb->dev);
        int iif, sdif;
 

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 3498dd1d0694dc3ddb984177d2ddffb7b8abd0b9..fd29d21d579c185eb5cb54e05ffd00e703966ed3 100644 (file)
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -718,7 +718,8 @@ EXPORT_SYMBOL(udp_gro_complete);
 
 INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 {
-       const struct iphdr *iph = ip_hdr(skb);
+       const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+       const struct iphdr *iph = (struct iphdr *)(skb->data + offset);
        struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
        /* do fraglist only if there is no outer UDP encap (or we already processed it) */

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index b41e35af69ea2835aa47d6ca01d9b109d4092462..c8b909a9904f321b91c9cfef46da9bb491c18a7d 100644 (file)
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -237,6 +237,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
                goto out;
 
        skb_set_network_header(skb, off);
+       NAPI_GRO_CB(skb)->inner_network_offset = off;
 
        flush += ntohs(iph->payload_len) != skb->len - hlen;
 

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1a4cccdd40c9ca44675cea5f5c2a08724ccb2d75..8f7aa8bac1e7b1eb330e4a6a9086b88e509886be 100644 (file)
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -272,7 +272,8 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
 struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
                                 __be16 sport, __be16 dport)
 {
-       const struct ipv6hdr *iph = ipv6_hdr(skb);
+       const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+       const struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + offset);
        struct net *net = dev_net(skb->dev);
        int iif, sdif;
 

diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index bbd347de00b450bb3ecbbfa41c4dab9d36bb79d9..b41152dd424697a9fc3cef13fbb430de49dcb913 100644 (file)
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -164,7 +164,8 @@ flush:
 
 INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 {
-       const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+       const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+       const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + offset);
        struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
        /* do fraglist only if there is no outer UDP encap (or we already processed it) */