net/packet: fix packet receive on L3 devices without visible hard header

In the patchset merged by commit b9fcf0a0d826
("Merge branch 'support-AF_PACKET-for-layer-3-devices'") L3 devices which
did not have header_ops were given one for the purpose of protocol parsing
on af_packet transmit path.

That change made af_packet receive path regard these devices as having a
visible L3 header and therefore aligned incoming skb->data to point to the
skb's mac_header. Some devices, such as ipip, xfrmi, and others, do not
reset their mac_header prior to ingress and therefore their incoming
packets became malformed.

Ideally these devices would reset their mac headers, or af_packet would be
able to rely on dev->hard_header_len being 0 for such cases, but it seems
this is not the case.

Fix by changing af_packet RX ll visibility criteria to include the
existence of a '.create()' header operation, which is used when creating
a device hard header - via dev_hard_header() - by upper layers, and does
not exist in these L3 devices.

As this predicate may be useful in other situations, add it as a common
dev_has_header() helper in netdevice.h.

Fixes: b9fcf0a0d826 ("Merge branch 'support-AF_PACKET-for-layer-3-devices'")
Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
Acked-by: Jason A. Donenfeld <Jason@zx2c4.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20201121062817.3178900-1-eyal.birger@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 964b494..fa275a0 100644 (file)
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3137,6 +3137,11 @@ static inline bool dev_validate_header(const struct net_device *dev,
        return false;
 }
 
+static inline bool dev_has_header(const struct net_device *dev)
+{
+       return dev->header_ops && dev->header_ops->create;
+}
+
 typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr,
                           int len, int size);
 int register_gifconf(unsigned int family, gifconf_func_t *gifconf);

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index cefbd50..7a18fff 100644 (file)
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -93,8 +93,8 @@
 
 /*
    Assumptions:
-   - If the device has no dev->header_ops, there is no LL header visible
-     above the device. In this case, its hard_header_len should be 0.
+   - If the device has no dev->header_ops->create, there is no LL header
+     visible above the device. In this case, its hard_header_len should be 0.
      The device may prepend its own header internally. In this case, its
      needed_headroom should be set to the space needed for it to add its
      internal header.
@@ -108,26 +108,26 @@
 On receive:
 -----------
 
-Incoming, dev->header_ops != NULL
+Incoming, dev_has_header(dev) == true
    mac_header -> ll header
    data       -> data
 
-Outgoing, dev->header_ops != NULL
+Outgoing, dev_has_header(dev) == true
    mac_header -> ll header
    data       -> ll header
 
-Incoming, dev->header_ops == NULL
+Incoming, dev_has_header(dev) == false
    mac_header -> data
      However drivers often make it point to the ll header.
      This is incorrect because the ll header should be invisible to us.
    data       -> data
 
-Outgoing, dev->header_ops == NULL
+Outgoing, dev_has_header(dev) == false
    mac_header -> data. ll header is invisible to us.
    data       -> data
 
 Resume
-  If dev->header_ops == NULL we are unable to restore the ll header,
+  If dev_has_header(dev) == false we are unable to restore the ll header,
     because it is invisible to us.
 
 
@@ -2069,7 +2069,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 
        skb->dev = dev;
 
-       if (dev->header_ops) {
+       if (dev_has_header(dev)) {
                /* The device has an explicit notion of ll header,
                 * exported to higher levels.
                 *
@@ -2198,7 +2198,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
        if (!net_eq(dev_net(dev), sock_net(sk)))
                goto drop;
 
-       if (dev->header_ops) {
+       if (dev_has_header(dev)) {
                if (sk->sk_type != SOCK_DGRAM)
                        skb_push(skb, skb->data - skb_mac_header(skb));
                else if (skb->pkt_type == PACKET_OUTGOING) {