[NET]: Added GSO header verification

When GSO packets come from an untrusted source (e.g., a Xen guest domain),
we need to verify the header integrity before passing it to the hardware.

Since the first step in GSO is to verify the header, we can reuse that
code by adding a new bit to gso_type: SKB_GSO_DODGY.  Packets with this
bit set can only be fed directly to devices with the corresponding bit
NETIF_F_GSO_ROBUST.  If the device doesn't have that bit, then the skb
is fed to the GSO engine which will allow the packet to be sent to the
hardware if it passes the header check.

This patch changes the sg flag to a full features flag.  The same method
can be used to implement TSO ECN support.  We simply have to mark packets
with CWR set with SKB_GSO_ECN so that only hardware with a corresponding
NETIF_F_TSO_ECN can accept them.  The GSO engine can either fully segment
the packet, or segment the first MTU and pass the rest to the hardware for
further segmentation.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 59 insertions, 27 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 03cd7551a7a1..84b0f0d16fcb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -315,6 +315,7 @@ struct net_device
 #define NETIF_F_GSO_SHIFT       16
 #define NETIF_F_TSO             (SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT)
 #define NETIF_F_UFO             (SKB_GSO_UDPV4 << NETIF_F_GSO_SHIFT)
+#define NETIF_F_GSO_ROBUST      (SKB_GSO_DODGY << NETIF_F_GSO_SHIFT)
 
 #define NETIF_F_GEN_CSUM        (NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)
 #define NETIF_F_ALL_CSUM        (NETIF_F_IP_CSUM | NETIF_F_GEN_CSUM)
@@ -543,7 +544,8 @@ struct packet_type {
                                          struct net_device *,
                                          struct packet_type *,
                                          struct net_device *);
-        struct sk_buff          *(*gso_segment)(struct sk_buff *skb, int sg);
+        struct sk_buff          *(*gso_segment)(struct sk_buff *skb,
+                                                int features);
         void                    *af_packet_priv;
         struct list_head        list;
 };
@@ -968,7 +970,7 @@ extern int		netdev_max_backlog;
 extern int              weight_p;
 extern int              netdev_set_master(struct net_device *dev, struct net_device *master);
 extern int skb_checksum_help(struct sk_buff *skb, int inward);
-extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg);
+extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features);
 #ifdef CONFIG_BUG
 extern void netdev_rx_csum_fault(struct net_device *dev);
 #else
@@ -988,11 +990,16 @@ extern void dev_seq_stop(struct seq_file *seq, void *v);
 
 extern void linkwatch_run_queue(void);
 
+static inline int skb_gso_ok(struct sk_buff *skb, int features)
+{
+        int feature = skb_shinfo(skb)->gso_size ?
+                      skb_shinfo(skb)->gso_type << NETIF_F_GSO_SHIFT : 0;
+        return (features & feature) != feature;
+}
+
 static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb)
 {
-        int feature = skb_shinfo(skb)->gso_type << NETIF_F_GSO_SHIFT;
-        return skb_shinfo(skb)->gso_size &&
-               (dev->features & feature) != feature;
+        return skb_gso_ok(skb, dev->features);
 }
 
 #endif /* __KERNEL__ */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 16eef03ce0eb..5fb72da7da03 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -172,6 +172,9 @@ enum {
 enum {
         SKB_GSO_TCPV4 = 1 << 0,
         SKB_GSO_UDPV4 = 1 << 1,
+
+        /* This indicates the skb is from an untrusted source. */
+        SKB_GSO_DODGY = 1 << 2,
 };
 
 /** 
@@ -1299,7 +1302,7 @@ extern void	       skb_split(struct sk_buff *skb,
                                  struct sk_buff *skb1, const u32 len);
 
 extern void            skb_release_data(struct sk_buff *skb);
-extern struct sk_buff *skb_segment(struct sk_buff *skb, int sg);
+extern struct sk_buff *skb_segment(struct sk_buff *skb, int features);
 
 static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
                                        int len, void *buffer)
diff --git a/include/net/protocol.h b/include/net/protocol.h
index 3b6dc15c68a5..40b6b9c9973f 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -36,7 +36,8 @@
 struct net_protocol {
         int                     (*handler)(struct sk_buff *skb);
         void                    (*err_handler)(struct sk_buff *skb, u32 info);
-        struct sk_buff         *(*gso_segment)(struct sk_buff *skb, int sg);
+        struct sk_buff         *(*gso_segment)(struct sk_buff *skb,
+                                               int features);
         int                     no_policy;
 };
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index ca3d38dfc00b..624921e76332 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1086,7 +1086,7 @@ extern struct request_sock_ops tcp_request_sock_ops;
 
 extern int tcp_v4_destroy_sock(struct sock *sk);
 
-extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int sg);
+extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features);
 
 #ifdef CONFIG_PROC_FS
 extern int  tcp4_proc_init(void);
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 2afdc7c0736c..f8dbcee80eba 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -184,6 +184,6 @@ void br_dev_setup(struct net_device *dev)
         dev->set_mac_address = br_set_mac_address;
         dev->priv_flags = IFF_EBRIDGE;
 
-        dev->features = NETIF_F_SG | NETIF_F_FRAGLIST
-                | NETIF_F_HIGHDMA | NETIF_F_TSO | NETIF_F_NO_CSUM;
+        dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
+                        NETIF_F_TSO | NETIF_F_NO_CSUM | NETIF_F_GSO_ROBUST;
 }
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 07956ecf545e..f55ef682ef84 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -392,7 +392,8 @@ void br_features_recompute(struct net_bridge *br)
                 features &= feature;
         }
 
-        br->dev->features = features | checksum | NETIF_F_LLTX;
+        br->dev->features = features | checksum | NETIF_F_LLTX |
+                            NETIF_F_GSO_ROBUST;
 }
 
 /* called with RTNL */
diff --git a/net/core/dev.c b/net/core/dev.c
index f1c52cbd6ef7..4f2014994a84 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1190,11 +1190,14 @@ out:
 /**
  *      skb_gso_segment - Perform segmentation on skb.
  *      @skb: buffer to segment
- *      @sg: whether scatter-gather is supported on the target.
+ *      @features: features for the output path (see dev->features)
  *
  *      This function segments the given skb and returns a list of segments.
+ *
+ *      It may return NULL if the skb requires no segmentation.  This is
+ *      only possible when GSO is used for verifying header integrity.
  */
-struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg)
+struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features)
 {
         struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
         struct packet_type *ptype;
@@ -1210,12 +1213,14 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg)
         rcu_read_lock();
         list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & 15], list) {
                 if (ptype->type == type && !ptype->dev && ptype->gso_segment) {
-                        segs = ptype->gso_segment(skb, sg);
+                        segs = ptype->gso_segment(skb, features);
                         break;
                 }
         }
         rcu_read_unlock();
 
+        __skb_push(skb, skb->data - skb->mac.raw);
+
         return segs;
 }
 
@@ -1291,9 +1296,15 @@ static int dev_gso_segment(struct sk_buff *skb)
 {
         struct net_device *dev = skb->dev;
         struct sk_buff *segs;
+        int features = dev->features & ~(illegal_highdma(dev, skb) ?
+                                         NETIF_F_SG : 0);
+
+        segs = skb_gso_segment(skb, features);
+
+        /* Verifying header integrity only. */
+        if (!segs)
+                return 0;
 
-        segs = skb_gso_segment(skb, dev->features & NETIF_F_SG &&
-                                    !illegal_highdma(dev, skb));
         if (unlikely(IS_ERR(segs)))
                 return PTR_ERR(segs);
 
@@ -1310,13 +1321,17 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
                 if (netdev_nit)
                         dev_queue_xmit_nit(skb, dev);
 
-                if (!netif_needs_gso(dev, skb))
-                        return dev->hard_start_xmit(skb, dev);
+                if (netif_needs_gso(dev, skb)) {
+                        if (unlikely(dev_gso_segment(skb)))
+                                goto out_kfree_skb;
+                        if (skb->next)
+                                goto gso;
+                }
 
-                if (unlikely(dev_gso_segment(skb)))
-                        goto out_kfree_skb;
+                return dev->hard_start_xmit(skb, dev);
         }
 
+gso:
         do {
                 struct sk_buff *nskb = skb->next;
                 int rc;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6edbb90cbcec..dfef9eece83e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1848,13 +1848,13 @@ EXPORT_SYMBOL_GPL(skb_pull_rcsum);
 /**
  *      skb_segment - Perform protocol segmentation on skb.
  *      @skb: buffer to segment
- *      @sg: whether scatter-gather can be used for generated segments
+ *      @features: features for the output path (see dev->features)
  *
  *      This function performs segmentation on the given skb.  It returns
  *      the segment at the given position.  It returns NULL if there are
  *      no more segments to generate, or when an error is encountered.
  */
-struct sk_buff *skb_segment(struct sk_buff *skb, int sg)
+struct sk_buff *skb_segment(struct sk_buff *skb, int features)
 {
         struct sk_buff *segs = NULL;
         struct sk_buff *tail = NULL;
@@ -1863,6 +1863,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int sg)
         unsigned int offset = doffset;
         unsigned int headroom;
         unsigned int len;
+        int sg = features & NETIF_F_SG;
         int nfrags = skb_shinfo(skb)->nr_frags;
         int err = -ENOMEM;
         int i = 0;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 461216b47948..8d157157bf8e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1097,7 +1097,7 @@ int inet_sk_rebuild_header(struct sock *sk)
 
 EXPORT_SYMBOL(inet_sk_rebuild_header);
 
-static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int sg)
+static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features)
 {
         struct sk_buff *segs = ERR_PTR(-EINVAL);
         struct iphdr *iph;
@@ -1126,10 +1126,10 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int sg)
         rcu_read_lock();
         ops = rcu_dereference(inet_protos[proto]);
         if (ops && ops->gso_segment)
-                segs = ops->gso_segment(skb, sg);
+                segs = ops->gso_segment(skb, features);
         rcu_read_unlock();
 
-        if (IS_ERR(segs))
+        if (!segs || unlikely(IS_ERR(segs)))
                 goto out;
 
         skb = segs;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c04176be7ed1..0336422c88a0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2145,7 +2145,7 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
 EXPORT_SYMBOL(compat_tcp_getsockopt);
 #endif
 
-struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int sg)
+struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features)
 {
         struct sk_buff *segs = ERR_PTR(-EINVAL);
         struct tcphdr *th;
@@ -2166,10 +2166,14 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int sg)
         if (!pskb_may_pull(skb, thlen))
                 goto out;
 
+        segs = NULL;
+        if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST))
+                goto out;
+
         oldlen = (u16)~skb->len;
         __skb_pull(skb, thlen);
 
-        segs = skb_segment(skb, sg);
+        segs = skb_segment(skb, features);
         if (IS_ERR(segs))
                 goto out;