net: preserve IP control block during GSO segmentation

Skb_gso_segment() uses skb control block during segmentation.
This patch adds 32-bytes room for previous control block which
will be copied into all resulting segments.

This patch fixes kernel crash during fragmenting forwarded packets.
Fragmentation requires valid IP CB in skb for clearing ip options.
Also patch removes custom save/restore in ovs code, now it's redundant.

Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com>
Link: http://lkml.kernel.org/r/CALYGNiP-0MZ-FExV2HutTvE9U-QQtkKSoE--KN=JQE5STYsjAA@mail.gmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 07f9ccd28654b6590edb63b97b0aa42b1d4748cf..11f935c1a090419d6cda938aa925bfa79de3616b 100644 (file)
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3551,7 +3551,8 @@ struct skb_gso_cb {
        int     encap_level;
        __u16   csum_start;
 };
-#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)(skb)->cb)
+#define SKB_SGO_CB_OFFSET      32
+#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)((skb)->cb + SKB_SGO_CB_OFFSET))
 
 static inline int skb_tnl_header_len(const struct sk_buff *inner_skb)
 {

diff --git a/net/core/dev.c b/net/core/dev.c
index 0ca95d5d7af0a397654cc85f44f9e474b7cc3061..cc9e3652cf93a6306e6f614f966e0fe7cf17a10e 100644 (file)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2695,6 +2695,8 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
  *
  *     It may return NULL if the skb requires no segmentation.  This is
  *     only possible when GSO is used for verifying header integrity.
+ *
+ *     Segmentation preserves SKB_SGO_CB_OFFSET bytes of previous skb cb.
  */
 struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
                                  netdev_features_t features, bool tx_path)
@@ -2709,6 +2711,9 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
                        return ERR_PTR(err);
        }
 
+       BUILD_BUG_ON(SKB_SGO_CB_OFFSET +
+                    sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb));
+
        SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb);
        SKB_GSO_CB(skb)->encap_level = 0;
 

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 512a44778cf2f9f9e2b594bdb6c996a43c33645a..64878efa045c132d1ce511c326c2da04fc77a895 100644 (file)
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -239,6 +239,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
         * from host network stack.
         */
        features = netif_skb_features(skb);
+       BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
        segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
        if (IS_ERR_OR_NULL(segs)) {
                kfree_skb(skb);

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 91a8b004dc510272e6ab09c22ccea821cb62ac49..deadfdab1bc384c858642e176d690bcf62a103c0 100644 (file)
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -336,12 +336,10 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
        unsigned short gso_type = skb_shinfo(skb)->gso_type;
        struct sw_flow_key later_key;
        struct sk_buff *segs, *nskb;
-       struct ovs_skb_cb ovs_cb;
        int err;
 
-       ovs_cb = *OVS_CB(skb);
+       BUILD_BUG_ON(sizeof(*OVS_CB(skb)) > SKB_SGO_CB_OFFSET);
        segs = __skb_gso_segment(skb, NETIF_F_SG, false);
-       *OVS_CB(skb) = ovs_cb;
        if (IS_ERR(segs))
                return PTR_ERR(segs);
        if (segs == NULL)
@@ -359,7 +357,6 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
        /* Queue all of the segments. */
        skb = segs;
        do {
-               *OVS_CB(skb) = ovs_cb;
                if (gso_type & SKB_GSO_UDP && skb != segs)
                        key = &later_key;
 

diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index cc3676eb6239707909e41c34841abbd4ea8958dd..ff4a91fcab9fd291b09eb48487690301c4388ae2 100644 (file)
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -167,6 +167,8 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb
 {
        struct sk_buff *segs;
 
+       BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
+       BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET);
        segs = skb_gso_segment(skb, 0);
        kfree_skb(skb);
        if (IS_ERR(segs))